Active learning in robotics: A review of control principles
Active learning is a decision-making process. In both abstract and physical settings, active learning demands both analysis and action. This is a review of active learning in robotics, focusing on methods amenable to the demands of embodied learning systems. Robots must be able to learn efficiently...
Saved in:
| Published in | Mechatronics (Oxford) Vol. 77; p. 102576 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Ltd
01.08.2021
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Active learning is a decision-making process. In both abstract and physical settings, active learning demands both analysis and action. This is a review of active learning in robotics, focusing on methods amenable to the demands of embodied learning systems. Robots must be able to learn efficiently and flexibly through continuous online deployment. This poses a distinct set of control-oriented challenges—one must choose suitable measures as objectives, synthesize real-time control, and produce analyses that guarantee performance and safety with limited knowledge of the environment or robot itself. In this work, we survey the fundamental components of robotic active learning systems. We discuss classes of learning tasks that robots typically encounter, measures with which they gauge the information content of observations, and algorithms for generating action plans. Moreover, we provide a variety of examples – from environmental mapping to nonparametric shape estimation – that highlight the qualitative differences between learning tasks, information measures, and control techniques. We conclude with a discussion of control-oriented open challenges, including safety-constrained learning and distributed learning. |
|---|---|
| AbstractList | Active learning is a decision-making process. In both abstract and physical settings, active learning demands both analysis and action. This is a review of active learning in robotics, focusing on methods amenable to the demands of embodied learning systems. Robots must be able to learn efficiently and flexibly through continuous online deployment. This poses a distinct set of control-oriented challenges—one must choose suitable measures as objectives, synthesize real-time control, and produce analyses that guarantee performance and safety with limited knowledge of the environment or robot itself. In this work, we survey the fundamental components of robotic active learning systems. We discuss classes of learning tasks that robots typically encounter, measures with which they gauge the information content of observations, and algorithms for generating action plans. Moreover, we provide a variety of examples – from environmental mapping to nonparametric shape estimation – that highlight the qualitative differences between learning tasks, information measures, and control techniques. We conclude with a discussion of control-oriented open challenges, including safety-constrained learning and distributed learning. |
| ArticleNumber | 102576 |
| Author | Murphey, Todd D. Taylor, Annalisa T. Berrueta, Thomas A. |
| Author_xml | – sequence: 1 givenname: Annalisa T. orcidid: 0000-0002-7204-4956 surname: Taylor fullname: Taylor, Annalisa T. email: annalisa.taylor@u.northwestern.edu – sequence: 2 givenname: Thomas A. orcidid: 0000-0002-3781-0934 surname: Berrueta fullname: Berrueta, Thomas A. email: tberrueta@u.northwestern.edu – sequence: 3 givenname: Todd D. orcidid: 0000-0003-2262-8176 surname: Murphey fullname: Murphey, Todd D. email: t-murphey@northwestern.edu |
| BookMark | eNqNkE1LAzEQhoNUsK3-h-B9aya7m6T1YqmfUPCi55DNzmrKNinJUvHfm1IP4qmngRnmmXmfCRn54JGQa2AzYCBuNrMt2k8zxOCdTTPOOOQBr6U4I2NQsiwqxsSIjNm8lkUFtbogk5Q2jIEEkGNyu7SD2yPt0UTv_Ad1nsbQhCHjFnRJI-4dftHQURt8PtPTXXTeul2P6ZKcd6ZPePVbp-T98eFt9VysX59eVst1YUsphqKppQLFKlPnm9xwI1qBHTRgW8yT3DQNSDPnCiqOskJeMc5AGaEUGCPKKbk7cm0MKUXstHWDGdzhIeN6DUwfZOiN_itDH2Too4yMWPxD5BhbE79PW74_LmMOmXVEnaxDb7F1Ee2g2-BOwfwANZ-EBA |
| CitedBy_id | crossref_primary_10_3389_frobt_2024_1281060 crossref_primary_10_1016_j_engappai_2022_105631 crossref_primary_10_1021_acs_chemrev_3c00189 crossref_primary_10_1177_02783649241256044 crossref_primary_10_1109_MWC_014_2100665 crossref_primary_10_1038_s43588_024_00744_y crossref_primary_10_1080_15397734_2022_2096629 crossref_primary_10_1016_j_engappai_2022_105184 crossref_primary_10_1016_j_ejcon_2023_100861 crossref_primary_10_1109_TRO_2022_3228130 crossref_primary_10_1002_rnc_6235 crossref_primary_10_1109_LRA_2024_3444670 crossref_primary_10_1002_aisy_202400458 crossref_primary_10_1109_LRA_2024_3486217 crossref_primary_10_1109_TSP_2024_3450270 crossref_primary_10_1016_j_ifacol_2024_09_013 crossref_primary_10_1016_j_robot_2025_104947 crossref_primary_10_1038_s42256_024_00829_3 crossref_primary_10_1109_LRA_2022_3185786 crossref_primary_10_1177_02783649231184498 crossref_primary_10_1016_j_robot_2024_104727 crossref_primary_10_3389_frai_2023_1212336 crossref_primary_10_1109_TRO_2025_3531816 crossref_primary_10_1016_j_engappai_2023_107329 crossref_primary_10_1109_ACCESS_2024_3390679 crossref_primary_10_1109_LRA_2022_3149299 crossref_primary_10_1038_s41598_023_47188_4 crossref_primary_10_1002_aisy_202300111 crossref_primary_10_1142_S0218001424520049 crossref_primary_10_3389_frai_2024_1308031 crossref_primary_10_1002_aisy_202400344 crossref_primary_10_3390_asi5030047 |
| Cites_doi | 10.1145/3377454 10.1109/IJCNN.2014.6889862 10.1242/jeb.203.9.1409 10.1016/S0921-8890(98)00049-9 10.1109/CVPR.2019.01291 10.1016/S0019-9958(80)90285-5 10.1007/s00359-006-0099-4 10.1109/TRO.2016.2624754 10.1109/IROS.2012.6385653 10.1023/A:1016639210559 10.1145/1349822.1349868 10.1007/s10846-009-9318-x 10.1080/002071700417876 10.3109/09638237.2015.1019048 10.2514/1.G001921 10.1609/icaps.v27i1.13816 10.5040/9798216009511 10.1109/IROS.2017.8206000 10.1145/3054912 10.2514/1.21562 10.1109/TRO.2014.2312812 10.1088/1742-5468/2005/11/P11011 10.1016/j.robot.2006.05.008 10.1016/0020-0190(87)90114-1 10.1109/MRA.2009.932529 10.1109/ICRA.2012.6224748 10.15607/RSS.2020.XVI.067 10.1109/CoASE.2015.7294129 10.1177/02783649922066484 10.1109/TRO.2014.2320795 10.1109/TRO.2019.2923880 10.1038/nature05464 10.1137/16M1062296 10.1126/scirobotics.aau4978 10.1109/ACC.2016.7525371 10.1109/ICRA.2018.8460891 10.1109/CVPR.2017.173 10.1109/TASE.2020.3043636 10.23919/CCC50068.2020.9189276 10.1242/jeb.068007 10.1038/nature14543 10.1126/scirobotics.aav1488 10.1109/TOH.2016.2615924 10.1007/s10994-010-5174-y 10.1109/TRO.2014.2345918 10.1109/37.126844 10.1109/IRDS.2002.1041446 10.1109/TRO.2015.2500441 10.1007/978-3-030-66723-8_27 10.1017/S0140525X0001092X 10.2307/1415413 10.1126/science.1229163 10.3390/e23040418 10.1109/CDC.2012.6426381 10.1109/TRO.2004.837239 10.1371/journal.pone.0150171 10.1016/j.tcs.2009.01.016 10.1016/S0921-8890(02)00271-3 10.1073/pnas.38.8.716 10.1109/TRO.2019.2894039 10.1177/0278364920987859 10.1109/LRA.2018.2800101 10.1109/ACC.2006.1656452 10.1109/CDC.2018.8619820 10.1007/BF00116827 10.1109/ROMOCO.1999.791086 10.1007/978-3-319-32552-1_60 10.1007/s00521-009-0262-2 10.1089/soro.2014.0008 10.1038/s41467-018-07210-0 10.1146/annurev-control-073119-090634 10.1145/322326.322334 10.1613/jair.2674 10.1098/rsif.2019.0162 10.1109/TRO.2013.2257577 10.1038/44831 10.1109/CDC.2009.5399490 10.1109/TPAMI.2004.38 10.1109/ICRA.2014.6907763 10.1126/scirobotics.aaz1012 10.3389/fbioe.2014.00003 10.1109/ICRA.2014.6907452 10.1609/aaai.v33i01.33013387 10.1112/plms/s2-42.1.230 10.1214/18-STS665 10.1145/356914.356918 10.1126/scirobotics.aah3690 10.1016/j.na.2005.10.049 10.1177/027836499101000401 10.1007/s10846-013-9981-9 10.1109/ICRA.2017.7989202 10.1109/IROS.2005.1545070 10.1109/CDC.2014.7039601 10.1109/ROBOSOFT.2018.8404894 10.1016/j.physd.2010.10.010 10.1613/jair.295 10.1016/j.asd.2004.05.009 10.1006/cviu.1998.0736 10.1109/ICRA.2015.7139224 10.1109/2.30720 10.1117/12.719395 10.1109/ICCV.2001.937519 10.1109/LRA.2018.2849588 10.1109/TAC.2014.2299335 10.1038/208059a0 10.3934/jcd.2014.1.391 10.1109/TMECH.2012.2213607 10.1126/scirobotics.aaz9239 10.1002/(SICI)1520-684X(199810)29:11<31::AID-SCJ4>3.0.CO;2-T 10.1109/LRA.2018.2884091 10.2307/1542524 10.1088/1751-8113/42/43/434002 10.1109/MRA.2006.1678135 10.1038/scientificamerican0851-60 10.1109/ROBOT.2000.844072 10.1038/nature16961 10.1089/soro.2015.0019 10.1002/j.1538-7305.1948.tb01338.x 10.1109/MSP.2020.2975749 10.1049/iet-cps.2018.5032 10.1038/s42256-018-0002-3 10.1609/icaps.v22i1.13529 10.1109/IROS.2015.7354071 10.1121/1.405716 10.1109/IROS.2017.8206410 10.1007/s10514-015-9454-z 10.1016/S0019-9958(67)91165-5 10.1109/ICRA.2015.7139863 10.1007/978-1-4615-7572-6_4 10.5244/C.12.78 10.1126/science.153.3731.34 10.1007/978-94-015-9554-4_43 10.1177/0278364912467485 10.1126/scirobotics.abc7104 10.1109/TRO.2018.2872402 10.1163/016918609X12529286896877 10.1177/0278364903022001002 10.1038/s41586-020-03123-5 10.1023/A:1012439023425 10.1177/0278364918755924 10.1038/s42256-021-00330-1 10.1145/293347.293351 10.1007/978-3-662-44845-8_43 10.7554/eLife.52371 10.1177/0278364908100177 10.1109/ICCV.2003.1238372 10.1109/TPAMI.2013.218 10.1080/00207176608921369 10.1016/j.robot.2005.11.006 10.1016/j.robot.2013.09.004 10.1109/TRO.2017.2659727 10.1007/978-3-030-35713-9_16 10.1002/rob.20300 10.1038/433595a 10.1109/34.982896 10.1109/TSMC.1983.6313077 10.1038/ncomms1712 10.1145/76359.76371 10.1038/s42256-021-00321-2 10.1177/0278364911410755 10.1109/TAC.2016.2638961 10.1109/ICRA.2013.6630605 10.1109/ICRA.2016.7487176 10.1007/978-3-030-44051-0_16 10.1007/978-3-030-36808-1_74 10.1016/j.automatica.2012.09.012 10.1126/science.aax4705 10.1145/1968.1972 10.1016/j.robot.2008.10.024 10.1016/j.jfds.2017.05.001 10.1109/TSMCB.2008.2008561 10.1109/ACC.2013.6580484 10.1006/inco.1995.1042 10.1109/TRO.2017.2766265 10.1126/scirobotics.aav6079 10.5194/npg-22-701-2015 10.1007/BF00453370 10.1186/s41074-017-0027-2 10.1177/0278364918770733 10.1093/mind/LIX.236.433 10.1126/scirobotics.abb9138 10.1177/0278364909341659 10.1016/j.arcontrol.2020.06.001 10.1016/j.sigpro.2004.11.004 10.15607/RSS.2019.XV.039 10.1073/pnas.17.5.315 10.1177/0278364919840426 10.1007/s00332-015-9258-5 10.1126/science.aaz7597 10.1007/BF00116828 10.1037/0033-295X.88.2.135 10.1109/ICRA.2012.6225244 10.1109/TCYB.2015.2454334 10.1109/5.5968 10.1109/ICCV.1999.791227 10.1177/0278364914533443 10.23919/ECC.2019.8796030 10.1109/LRA.2017.2654542 10.1016/j.robot.2010.01.001 10.1126/science.1183310 10.1038/ncomms2444 10.1038/nature14539 10.1038/srep10487 10.1088/0957-0233/9/6/003 10.1016/S0005-1098(96)00104-5 10.1109/IROS.2006.282530 10.1017/CBO9781139626514 10.1037/h0074428 10.1126/scirobotics.aav3041 10.1037/h0042519 10.1109/CDC.2017.8263977 10.1177/0278364914547893 10.1126/science.1165893 10.1073/pnas.18.1.70 10.1109/TRO.2018.2808902 |
| ContentType | Journal Article |
| Copyright | 2021 The Authors |
| Copyright_xml | – notice: 2021 The Authors |
| DBID | 6I. AAFTH AAYXX CITATION |
| DOI | 10.1016/j.mechatronics.2021.102576 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1873-4006 |
| ExternalDocumentID | 10_1016_j_mechatronics_2021_102576 S0957415821000659 |
| GrantInformation_xml | – fundername: United States Army Research Office MURI grantid: W911NF-19-1-0233 funderid: http://dx.doi.org/10.13039/100000183 – fundername: United States National Science Foundation grantid: 1837515 funderid: http://dx.doi.org/10.13039/100000001 |
| GroupedDBID | --K --M -~X .~1 0R~ 1B1 1~. 1~5 29M 4.4 457 4G. 5GY 5VS 6I. 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAFTH AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO ABMAC ABXDB ABYKQ ACDAQ ACGFS ACNNM ACRLP ADBBV ADEZE ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HVGLF HZ~ IHE J1W JJJVA KOM LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SCC SDF SDG SDP SES SET SEW SPC SPCBC SST SSZ T5K VOH WUQ XPP ZMT ~G- AATTM AAXKI AAYWO AAYXX ABJNI ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AFXIZ AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH |
| ID | FETCH-LOGICAL-c376t-b5781804a51712a2a6d6ef1b1cde781171ab17a928142e74e2402018a6881aa63 |
| IEDL.DBID | .~1 |
| ISSN | 0957-4158 |
| IngestDate | Thu Apr 24 23:12:57 EDT 2025 Tue Jul 01 03:54:04 EDT 2025 Fri Feb 23 02:47:09 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Learning theory Perception and sensing Active learning Robot control Artificial intelligence Robotics |
| Language | English |
| License | This is an open access article under the CC BY license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c376t-b5781804a51712a2a6d6ef1b1cde781171ab17a928142e74e2402018a6881aa63 |
| ORCID | 0000-0002-7204-4956 0000-0002-3781-0934 0000-0003-2262-8176 |
| OpenAccessLink | https://www.sciencedirect.com/science/article/pii/S0957415821000659 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_mechatronics_2021_102576 crossref_primary_10_1016_j_mechatronics_2021_102576 elsevier_sciencedirect_doi_10_1016_j_mechatronics_2021_102576 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | August 2021 2021-08-00 |
| PublicationDateYYYYMMDD | 2021-08-01 |
| PublicationDate_xml | – month: 08 year: 2021 text: August 2021 |
| PublicationDecade | 2020 |
| PublicationTitle | Mechatronics (Oxford) |
| PublicationYear | 2021 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Shih, Shah, Li, Thuruthel, Park, Iida (b145) 2020; 5 Berthoz, Petit (b295) 2008 Rahimi M, Hansen M, Kaiser W, Sukhatme G, Estrin D. Adaptive sampling for environmental field estimation using robotic sensors. In: IEEE int. conf. on intelligent robots and systems (IROS), 2005. p. 3692–8. Cover, Thomas (b175) 2012 Stanton (b3) 2018; 3 Agharese N, Cloyd T, Blumenschein LH, Raitor M, Hawkes EW, Culbertson H et al. HapWRAP: soft growing wearable haptic device. In: IEEE international conference on robotics and automation (ICRA), 2018. p. 5466–72. Ucinski D, Korbicz J. Path planning for moving sensors in parameter estimation of distributed systems. In: Workshop on robot motion and control (RoMoCo), 1999. p. 273–8. Chui, Maciejowski (b286) 1996; 32 DasGupta, Hespanha, Riehl, Sontag (b148) 2006; 65 Picardi, Hauser, Laschi, Calisti (b224) 2019; 40 Nguyen-Tuong, Seeger, Peters (b117) 2009; 23 Fitzsimons, Acosta, Dewald, Murphey (b24) 2019; 4 Bellman R. On the theory of dynamic programming. In: Proceedings of the national academy. vol. 38.8, 1952. p. 716. Paley, Wolek (b208) 2020; 3 Judah, Fern, Dietterich (b265) 2012 Mamakoukas, Castaño, Tan, Murphey (b138) 2019 Neumann (b180) 1932; 18 Daniel, Kroemer, Viering, Metz, Peters (b264) 2015; 39 Tolley, Shepherd, Mosadegh, Galloway, Wehner, Karpelson (b221) 2014; 1 Kreucher C, Wegrzyn J, Beauvais M, Conti R. Multiplatform information-based sensor management: an inverted UAV demonstration. In: SPIE defense transformation and network-centric systems. Vol. 6578; 2007. p. 65780Y–1–11. Sünderhauf, Brock, Scheirer, Hadsell, Fox, Leitner (b73) 2018; 37 Yin, Müller (b15) 2021 Kearns (b47) 1998; 45 Sim R, Roy N. Global A-optimal robot exploration in SLAM. In: IEEE int. conf. on robotics and automation (ICRA); 2005. p. 661–6. Chen, Pauly, Reis (b16) 2021; 589 Valiant (b43) 1984; 27 Rodríguez-Arévalo, Neira, Castellanos (b239) 2018; 34 Hussein, Gaber, Elyan, Jayne (b255) 2017; 50 Cooper (b52) 2003 Tassa, Mansard, Todorov (b192) 2014 Sumbre, Fiorito, Flash, Hochner (b226) 2005; 433 Basil, Hanlon, Sheikh, Atema (b5) 2000; 203 Best, Cliff, Patten, Mettu, Fitch (b271) 2019; 38 Roy N, Earnest C. Dynamic action spaces for information gain maximization in search and exploration. In: American controls conf. (ACC); 2006. p. 1631–36. Mamakoukas, Abraham, Murphey (b293) 2020 Paull, Saeedi, Seto, Li (b229) 2013; 18 Nocks (b54) 2007 Zhong, Wang, Ling, Dong (b140) 2016; 2 Arbel T, Ferrie F. Viewpoint selection by navigation through entropy maps. In: IEEE int. conf. on computer vision, 1999. p. 248–54. Dressel L, Kochenderfer MJ. Using neural networks to generate information maps for mobile sensors. In: 2018 IEEE conference on decision and control (CDC), 2018. p. 2555–60. Abraham, de la Torre, Murphey (b136) 2017 Bishop (b139) 2006 Mavrommati, Tzorakoleftherakis, Abraham, Murphey (b216) 2018; 34 Schaal S, Atkeson C, Vijayakumar S. Real-time robot learning with locally weighted statistical learning. In: Proceedings of the IEEE international conference on robotics and automation (ICRA). Vol. 1; 2000. p. 288–93. Marsden, Ratiu (b285) 2013 Schwager, Rus, Slotine (b236) 2009; 28 Lusch, Kutz, Brunton (b144) 2018; 9 Bajcsy (b1) 1988; 76 Argall, Chernova, Veloso, Browning (b256) 2009; 57 Ijspeert, Nakanishi, Schaal (b260) 2002; vol. 2 Rosenblatt (b44) 1958; 65 Zhang, Ferrari, Qian (b164) 2009; 56 Choset (b233) 2001; 31 Erichson, Muehlebach, Mahoney (b290) 2019 Tsiamis, Pappas (b83) 2021 Veitch, Render, Aravind (b211) 2019 Osa, Pajarinen, Neumann, Bagnell, Abbeel, Peters (b257) 2018 Peng, Andrychowicz, Zaremba, Abbeel (b77) 2018 de Bruin, Kober, Tuyls, BabuΩ CČska (b143) 2018; 3 Williams G, Wagener N, Goldfain B, Drews P, Rehg JM, Boots B et al. Information theoretic MPC for model-based reinforcement learning. In: International conference on robotics and automation (ICRA). 2017. Abraham, Murphey (b270) 2018; 3 García, Fernández (b80) 2015; 16 Tu, Rowley, Luchtenburg, Brunton, Kutz (b131) 2014; 1 Zhang, Ryan, Hobson, Kieft, Romano, Barone (b105) 2021; 6 Atanasov N, Le Ny J, Daniilidis K, Pappas GJ. Decentralized active information acquisition: Theory and application to multi-robot SLAM. In: 2015 IEEE international conference on robotics and automation (ICRA), 2015. p. 4775–82. Oksanen, Visala (b230) 2009; 26 James S, Wohlhart P, Kalakrishnan M, Kalashnikov D, Irpan A, Ibarz J et al. Sim-to-real via sim-to-sim: Data-efficient robotic grasping via randomized-to-canonical adaptation networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR); 2019. Laschi, Mazzolai, Cianchetti (b34) 2016; 1 Hollinger, Englot, Hover, Mitra, Sukhatme (b165) 2013; 32 Leung, Huang, Kwok, Dissanayake (b86) 2006; 54 Zhang G, Ferrari S. An adaptive artificial potential function approach for geometric sensing. In: IEEE int. conf. on decision and control (CDC); 2009. p. 7903–10. Dima, Hebert (b262) 2005 Grocholsky, Keller, Kumar, Pappas (b162) 2006; 13 Bourgault F, Makarenko AA, Williams S, Grocholsky B, Durrant-Whyte H. Information based adaptive robotic exploration. In: IEEE Int. Conf. on Intelligent Robots and Systems (IROS). Vol. 1; 2002. p. 540–5. Liao, Carin (b166) 2004; 26 Cadena, Carlone, Carrillo, Latif, Scaramuzza, Neira (b179) 2016; 32 Bayes-optimal active learning of Gaussian processes. In: International conference on machine learning; 2014. p. 739–47. Boffi, Tu, Matni, Slotine, Sindhwani (b291) 2020 Tovar B, Murphey TD. Trajectory tracking among landmarks and binary sensor beams. In: IEEE int. conf. on robotics and automation (ICRA), 2012. p. 2121–7. Valencia, Morta, Andrade-Cetto, Porta (b248) 2013; 29 Vázquez, Feixas, Sbert, Heidrich (b156) 2001; vol. 1 Hollinger, Sukhatme (b201) 2014; 33 Elfes (b96) 1989; 22 Deisenroth, Fox, Rasmussen (b128) 2015; 37 Oubbati, Palm (b116) 2010; 19 Singh, Krause, Guestrin, Kaiser (b101) 2009; 34 Fossum, Fragoso, Davies, Ullgren, Mendes, Johnsen (b106) 2019; 4 Ucinski (b169) 2000; 73 Ibarz, Tan, Finn, Kalakrishnan, Pastor, Levine (b72) 2021 Jan GE, Luo C, Hung L, Shih S. A computationally efficient complete area coverage algorithm for intelligent mobile robot navigation. In: 2014 international joint conference on neural networks, (IJCNN), 2014. p. 961–6. Souza J, Marchant R, Ott L, Wolf D, Ramos F. Bayesian optimisation for active perception and smooth navigation. In: IEEE Int. Conf. on Robotics and Automation (ICRA); 2014. p. 4081–87. Brunton, Brunton, Proctor, Kutz (b133) 2016; 11 Englot B, Hover FS. Sampling-based coverage path planning for inspection of complex structures. In: International conference on automated planning and scheduling (ICAPS). 2012. Pfeifer, Gómez (b19) 2009 Kumar, Gupta, Todorov, Levine (b193) 2016 Khan, Sarangi, Bhalla (b8) 2012; 3 Ben-David, Hrubeš, Moran, Shpilka, Yehudayoff (b49) 2019; 1 Carlone, Karaman (b254) 2018; 35 Gu, Holly, Lillicrap, Levine (b70) 2017 Ames, Powell (b275) 2013 Watson (b59) 1913; 20 Yovel, Falk, Moss, Ulanovsky (b6) 2010; 327 Butepage J, Black MJ, Kragic D, Kjellstrom H. Deep representation learning for human motion prediction and classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR); 2017. p. 6158–66. Reinhold, Sanguinetti-Scheck, Hartmann, Brecht (b29) 2019; 365 Turing (b38) 1937; s2-42 Angluin, Smith (b45) 1983; 15 Schmidt, Lipson (b113) 2009; 324 Cooper J, Goodrich M. Towards combining UAV and sensor operator roles in UAV-enabled visual search. In: IEEE int. conf. on human robot interaction (HRI), 2008. p. 351–8. Benet, Blanes, Simó, Pérez (b151) 2002; 40 Miller L, Murphey TD. Optimal planning for target localization and coverage using range sensing. In: IEEE int. conf. on automation science and engineering (CASE), 2015. p. 501–8. Nakajima, Hauser, Li, Pfeifer (b14) 2015; 5 Silver, Bagnell, Stentz (b261) 2012 Bansal S, Chen M, Herbert S, Tomlin CJ. Hamilton-Jacobi reachability: A brief overview and recent advances. In: IEEE 56th annual conference on decision and control, 2017. p. 2242–53. Otto, Rowley (b129) 2021; 4 Devol (b36) 1954 Gehring C, Precup D. Smart exploration in reinforcement learning using absolute temporal difference errors. In: Proceedings of the 2013 international conference on autonomous agents and multi-agent systems; 2013. p. 1037–44. Bekoff (b28) 1976 Sutton, Barto (b67) 2018 Webb, Harrison, Willis (b7) 2004; 33 Sutton, Barto (b62) 1981; 88 Ghosh, Gupta, Levine (b297) 2018 Dressel, Kochenderfer (b206) 2019; 4 Hofmann, Schölkopf, Smola (b121) 2008 Kaiser, Kutz, Brunton (b135) 2017 Chen Z, Xiao L, Wang Q, Wang Z, Sun Z. Coverage control of multi-agent systems for ergodic exploration. In: 2020 39th Chinese control conference (CCC), 2020. p. 4947–52. Nelson, MacIver (b12) 2006; 192 Wong E-M, Bourgault F, Furukawa T. Multi-vehicle Bayesian search for multiple lost targets. In: IEEE int. conf. on robotics and automation (ICRA); 2005. p. 3169–74. Mayne (b190) 1966; 3 Haarnoja T, Zhou A, Abbeel P, Levine S. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of the international conference on machine learning (ICML). Vol. 80; 2018. p. 1861–70. Koopman (b130) 1931; 17 Berrueta, Pervan, Fitzsimons, Murphey (b23) 2019; 4 Lu, Zhang, Ferrari, Fierro, Palunko (b94) 2011 Marchant R, Ramos F. Bayesian optimisation for intelligent environmental monitoring. In: IEEE int. conf. on intelligent robots and systems (IROS); 2012. p. 2242–49. Prabhakar A, Abraham I, Schlafly M, Taylor A, Popovic K, Diniz G et al. Ergodic specifications for flexible swarm control: from user commands to persistent adaptation. In: Robotics: science and systems proceedings, 2020. Bonet, Geffner (b245) 2000 Bender A, Williams SB, Pizarro O. Autonomous exploration of large-scale benthic environments. In: IEEE Int. Conf. on Robotics and Automation (ICRA); 2013. p. 390–6. Sutton, Barto, Williams (b65) 1992; 12 García-Garrido, Mancho, Wiggins, Mendoza (b238) 2015; 22 Mammano, Nobili (b225) 1993; 93 Li, Zhang, Goldman (b33) 2013; 339 Ye, Tsotsos (b187) 1999; 73 Kolter, Manek (b81) 2019 Karapetyan N, Benson K, McKinney C, Taslakian P, Rekleitis I. Efficient DasGupta (10.1016/j.mechatronics.2021.102576_b148) 2006; 65 Oubbati (10.1016/j.mechatronics.2021.102576_b116) 2010; 19 Takeuchi (10.1016/j.mechatronics.2021.102576_b157) 1998; 29 Ansari (10.1016/j.mechatronics.2021.102576_b198) 2017; 32 Chen (10.1016/j.mechatronics.2021.102576_b16) 2021; 589 Tovar (10.1016/j.mechatronics.2021.102576_b177) 2006; 54 Erichson (10.1016/j.mechatronics.2021.102576_b290) 2019 Walter (10.1016/j.mechatronics.2021.102576_b37) 1951; 185 Li (10.1016/j.mechatronics.2021.102576_b267) 2017 Sutton (10.1016/j.mechatronics.2021.102576_b62) 1981; 88 Furutani (10.1016/j.mechatronics.2021.102576_b21) 2021; 23 Leung (10.1016/j.mechatronics.2021.102576_b86) 2006; 54 Blumer (10.1016/j.mechatronics.2021.102576_b51) 1989; 36 Paley (10.1016/j.mechatronics.2021.102576_b208) 2020; 3 Mamakoukas (10.1016/j.mechatronics.2021.102576_b293) 2020 Feder (10.1016/j.mechatronics.2021.102576_b85) 1999; 18 Boffi (10.1016/j.mechatronics.2021.102576_b291) 2020 Patil (10.1016/j.mechatronics.2021.102576_b249) 2015 Platt Jr (10.1016/j.mechatronics.2021.102576_b246) 2006 Berkenkamp (10.1016/j.mechatronics.2021.102576_b279) 2017 de Bruin (10.1016/j.mechatronics.2021.102576_b143) 2018; 3 Neumann (10.1016/j.mechatronics.2021.102576_b180) 1932; 18 Sünderhauf (10.1016/j.mechatronics.2021.102576_b73) 2018; 37 Smola (10.1016/j.mechatronics.2021.102576_b125) 2003 Eysenbach (10.1016/j.mechatronics.2021.102576_b76) 2021 Galceran (10.1016/j.mechatronics.2021.102576_b232) 2013; 61 10.1016/j.mechatronics.2021.102576_b241 10.1016/j.mechatronics.2021.102576_b122 10.1016/j.mechatronics.2021.102576_b243 10.1016/j.mechatronics.2021.102576_b244 Daniel (10.1016/j.mechatronics.2021.102576_b264) 2015; 39 Nelson (10.1016/j.mechatronics.2021.102576_b12) 2006; 192 Smith (10.1016/j.mechatronics.2021.102576_b30) 1982; 5 Cadena (10.1016/j.mechatronics.2021.102576_b179) 2016; 32 10.1016/j.mechatronics.2021.102576_b152 Angluin (10.1016/j.mechatronics.2021.102576_b45) 1983; 15 Ho (10.1016/j.mechatronics.2021.102576_b266) 2016 Breier (10.1016/j.mechatronics.2021.102576_b104) 2020; 5 Gallager (10.1016/j.mechatronics.2021.102576_b126) 2013 Hartmann (10.1016/j.mechatronics.2021.102576_b11) 2001; 11 Ben-David (10.1016/j.mechatronics.2021.102576_b49) 2019; 1 Abraham (10.1016/j.mechatronics.2021.102576_b107) 2018 10.1016/j.mechatronics.2021.102576_b159 Lusch (10.1016/j.mechatronics.2021.102576_b144) 2018; 9 Webb (10.1016/j.mechatronics.2021.102576_b7) 2004; 33 10.1016/j.mechatronics.2021.102576_b155 10.1016/j.mechatronics.2021.102576_b276 Gold (10.1016/j.mechatronics.2021.102576_b41) 1967; 10 Turing (10.1016/j.mechatronics.2021.102576_b38) 1937; s2-42 10.1016/j.mechatronics.2021.102576_b141 Yovel (10.1016/j.mechatronics.2021.102576_b6) 2010; 327 Bekoff (10.1016/j.mechatronics.2021.102576_b28) 1976 Khodayi-mehr (10.1016/j.mechatronics.2021.102576_b210) 2019; 35 Chui (10.1016/j.mechatronics.2021.102576_b286) 1996; 32 Stanton (10.1016/j.mechatronics.2021.102576_b3) 2018; 3 Madokoro (10.1016/j.mechatronics.2021.102576_b146) 2014 Otto (10.1016/j.mechatronics.2021.102576_b129) 2021; 4 Shih (10.1016/j.mechatronics.2021.102576_b145) 2020; 5 Bonet (10.1016/j.mechatronics.2021.102576_b245) 2000 10.1016/j.mechatronics.2021.102576_b269 10.1016/j.mechatronics.2021.102576_b149 Cheng (10.1016/j.mechatronics.2021.102576_b123) 2016; 46 Yin (10.1016/j.mechatronics.2021.102576_b15) 2021 Ryan (10.1016/j.mechatronics.2021.102576_b202) 2010; 58 10.1016/j.mechatronics.2021.102576_b174 Benet (10.1016/j.mechatronics.2021.102576_b151) 2002; 40 Sutton (10.1016/j.mechatronics.2021.102576_b67) 2018 Prentice (10.1016/j.mechatronics.2021.102576_b247) 2009; 28 Guntuboyina (10.1016/j.mechatronics.2021.102576_b108) 2018; 33 Sornkarn (10.1016/j.mechatronics.2021.102576_b227) 2017; 10 Balcan (10.1016/j.mechatronics.2021.102576_b58) 2010; 80 Pfeifer (10.1016/j.mechatronics.2021.102576_b19) 2009 Martin (10.1016/j.mechatronics.2021.102576_b4) 1965; 208 Ijspeert (10.1016/j.mechatronics.2021.102576_b260) 2002; vol. 2 Fox (10.1016/j.mechatronics.2021.102576_b154) 1998; 25 Chen (10.1016/j.mechatronics.2021.102576_b252) 2011; 30 Marsden (10.1016/j.mechatronics.2021.102576_b285) 2013 Basil (10.1016/j.mechatronics.2021.102576_b5) 2000; 203 Ibarz (10.1016/j.mechatronics.2021.102576_b72) 2021 Abraham (10.1016/j.mechatronics.2021.102576_b111) 2017; 2 Ames (10.1016/j.mechatronics.2021.102576_b275) 2013 Li (10.1016/j.mechatronics.2021.102576_b273) 2020; 37 Kearns (10.1016/j.mechatronics.2021.102576_b47) 1998; 45 10.1016/j.mechatronics.2021.102576_b178 10.1016/j.mechatronics.2021.102576_b99 Mayne (10.1016/j.mechatronics.2021.102576_b190) 1966; 3 10.1016/j.mechatronics.2021.102576_b281 10.1016/j.mechatronics.2021.102576_b98 10.1016/j.mechatronics.2021.102576_b282 Chen (10.1016/j.mechatronics.2021.102576_b13) 2020; 9 10.1016/j.mechatronics.2021.102576_b97 Fossum (10.1016/j.mechatronics.2021.102576_b106) 2019; 4 Mammano (10.1016/j.mechatronics.2021.102576_b225) 1993; 93 10.1016/j.mechatronics.2021.102576_b284 10.1016/j.mechatronics.2021.102576_b95 10.1016/j.mechatronics.2021.102576_b93 10.1016/j.mechatronics.2021.102576_b92 10.1016/j.mechatronics.2021.102576_b91 10.1016/j.mechatronics.2021.102576_b90 Oksanen (10.1016/j.mechatronics.2021.102576_b230) 2009; 26 Boots (10.1016/j.mechatronics.2021.102576_b288) 2008 Cover (10.1016/j.mechatronics.2021.102576_b175) 2012 Skinner (10.1016/j.mechatronics.2021.102576_b60) 1938 Berrueta (10.1016/j.mechatronics.2021.102576_b23) 2019; 4 Emery (10.1016/j.mechatronics.2021.102576_b167) 1998; 9 Li (10.1016/j.mechatronics.2021.102576_b33) 2013; 339 Krengel (10.1016/j.mechatronics.2021.102576_b181) 1985 10.1016/j.mechatronics.2021.102576_b168 10.1016/j.mechatronics.2021.102576_b289 Liao (10.1016/j.mechatronics.2021.102576_b166) 2004; 26 Taketomi (10.1016/j.mechatronics.2021.102576_b251) 2017; 9 Dima (10.1016/j.mechatronics.2021.102576_b262) 2005 Kumar (10.1016/j.mechatronics.2021.102576_b193) 2016 10.1016/j.mechatronics.2021.102576_b287 10.1016/j.mechatronics.2021.102576_b89 Picardi (10.1016/j.mechatronics.2021.102576_b103) 2020; 5 10.1016/j.mechatronics.2021.102576_b194 10.1016/j.mechatronics.2021.102576_b195 10.1016/j.mechatronics.2021.102576_b191 Hollinger (10.1016/j.mechatronics.2021.102576_b201) 2014; 33 Rus (10.1016/j.mechatronics.2021.102576_b20) 2015; 521 Frieden (10.1016/j.mechatronics.2021.102576_b170) 2004 Rusu (10.1016/j.mechatronics.2021.102576_b78) 2017; 78 Thuruthel (10.1016/j.mechatronics.2021.102576_b120) 2019; 4 Proctor (10.1016/j.mechatronics.2021.102576_b134) 2018; 17 Barto (10.1016/j.mechatronics.2021.102576_b61) 1981; 40 Settles (10.1016/j.mechatronics.2021.102576_b31) 2009 Choset (10.1016/j.mechatronics.2021.102576_b233) 2001; 31 Ames (10.1016/j.mechatronics.2021.102576_b277) 2016; 62 Singh (10.1016/j.mechatronics.2021.102576_b101) 2009; 34 Stachniss (10.1016/j.mechatronics.2021.102576_b240) 2005; vol. 2 Peng (10.1016/j.mechatronics.2021.102576_b77) 2018 Balcan (10.1016/j.mechatronics.2021.102576_b57) 2013 Best (10.1016/j.mechatronics.2021.102576_b271) 2019; 38 Bellman (10.1016/j.mechatronics.2021.102576_b64) 1966; 153 Hofmann (10.1016/j.mechatronics.2021.102576_b121) 2008 10.1016/j.mechatronics.2021.102576_b199 10.1016/j.mechatronics.2021.102576_b185 Thorndike (10.1016/j.mechatronics.2021.102576_b66) 1927; 39 Mamakoukas (10.1016/j.mechatronics.2021.102576_b138) 2019 Osipov (10.1016/j.mechatronics.2021.102576_b22) 2015; 24 Kappen (10.1016/j.mechatronics.2021.102576_b196) 2005; 2005 Verbraeken (10.1016/j.mechatronics.2021.102576_b272) 2020; 53 Gu (10.1016/j.mechatronics.2021.102576_b70) 2017 Karkus (10.1016/j.mechatronics.2021.102576_b119) 2019 Blumer (10.1016/j.mechatronics.2021.102576_b50) 1987; 24 Ames (10.1016/j.mechatronics.2021.102576_b274) 2014; 59 10.1016/j.mechatronics.2021.102576_b188 10.1016/j.mechatronics.2021.102576_b189 Khan (10.1016/j.mechatronics.2021.102576_b8) 2012; 3 Shannon (10.1016/j.mechatronics.2021.102576_b171) 1948; 27 Silver (10.1016/j.mechatronics.2021.102576_b261) 2012 Turing (10.1016/j.mechatronics.2021.102576_b39) 1950; 59 Sutton (10.1016/j.mechatronics.2021.102576_b65) 1992; 12 Zhang (10.1016/j.mechatronics.2021.102576_b105) 2021; 6 Barto (10.1016/j.mechatronics.2021.102576_b63) 1983; SMC-13 Deisenroth (10.1016/j.mechatronics.2021.102576_b128) 2015; 37 Sumbre (10.1016/j.mechatronics.2021.102576_b226) 2005; 433 Mnih (10.1016/j.mechatronics.2021.102576_b253) 2014; 27 Elfes (10.1016/j.mechatronics.2021.102576_b96) 1989; 22 Abraham (10.1016/j.mechatronics.2021.102576_b283) 2021 Laschi (10.1016/j.mechatronics.2021.102576_b34) 2016; 1 Low (10.1016/j.mechatronics.2021.102576_b100) 2008 Fitzsimons (10.1016/j.mechatronics.2021.102576_b24) 2019; 4 Ab Azar (10.1016/j.mechatronics.2021.102576_b263) 2020 Liu (10.1016/j.mechatronics.2021.102576_b142) 2019 Codevilla (10.1016/j.mechatronics.2021.102576_b258) 2018 García-Garrido (10.1016/j.mechatronics.2021.102576_b238) 2015; 22 Dressel (10.1016/j.mechatronics.2021.102576_b206) 2019; 4 Ben-David (10.1016/j.mechatronics.2021.102576_b48) 1995; 117 Cohn (10.1016/j.mechatronics.2021.102576_b56) 1996; 4 Watson (10.1016/j.mechatronics.2021.102576_b59) 1913; 20 Bruder (10.1016/j.mechatronics.2021.102576_b137) 2019 Nocks (10.1016/j.mechatronics.2021.102576_b54) 2007 Lu (10.1016/j.mechatronics.2021.102576_b163) 2014; 30 Tu (10.1016/j.mechatronics.2021.102576_b131) 2014; 1 Bishop (10.1016/j.mechatronics.2021.102576_b139) 2006 Abraham (10.1016/j.mechatronics.2021.102576_b270) 2018; 3 Tsiamis (10.1016/j.mechatronics.2021.102576_b83) 2021 Atanasov (10.1016/j.mechatronics.2021.102576_b172) 2014; 30 Nguyen-Tuong (10.1016/j.mechatronics.2021.102576_b117) 2009; 23 Vergassola (10.1016/j.mechatronics.2021.102576_b153) 2007; 445 Hasler (10.1016/j.mechatronics.2021.102576_b109) 2010 Williams (10.1016/j.mechatronics.2021.102576_b197) 2017; 40 10.1016/j.mechatronics.2021.102576_b88 10.1016/j.mechatronics.2021.102576_b87 Mathew (10.1016/j.mechatronics.2021.102576_b183) 2011; 240 10.1016/j.mechatronics.2021.102576_b84 Paull (10.1016/j.mechatronics.2021.102576_b229) 2013; 18 10.1016/j.mechatronics.2021.102576_b82 Berrueta (10.1016/j.mechatronics.2021.102576_b115) 2020 Tassa (10.1016/j.mechatronics.2021.102576_ |
| References_xml | – volume: 324 start-page: 81 year: 2009 end-page: 85 ident: b113 article-title: Distilling free-form natural laws from experimental data publication-title: Science – year: 2020 ident: b291 article-title: Learning stability certificates from data – volume: 215 start-page: 1567 year: 2012 end-page: 1574 ident: b9 article-title: Active sensing via movement shapes spatiotemporal patterns of sensory feedback publication-title: J Exp Biol – volume: 15 start-page: 237 year: 1983 end-page: 269 ident: b45 article-title: Inductive inference: Theory and methods publication-title: ACM Comput Surv – reference: Roy N, Earnest C. Dynamic action spaces for information gain maximization in search and exploration. In: American controls conf. (ACC); 2006. p. 1631–36. – reference: Marchant R, Ramos F. Bayesian Optimisation for informative continuous path planning. In: IEEE int. conf. on robotics and automation (ICRA), 2014. p. 6136–43. – year: 2020 ident: b293 article-title: Learning stable models for prediction and control publication-title: IEEE Trans Robot – volume: 5 year: 2020 ident: b103 article-title: Bioinspired underwater legged robot for seabed exploration with low environmental disturbance publication-title: Science Robotics – volume: 401 start-page: 911 year: 1999 end-page: 914 ident: b25 article-title: Optimizing the success of random searches publication-title: Nature – reference: Denzler J, Zobel M, Niemann H. Information theoretic focal length selection for real-time active 3D object tracking. In: IEEE int. conf. on computer vision, 2003. p. 400–7. – volume: 50 year: 2017 ident: b255 article-title: Imitation learning: A survey of learning methods publication-title: ACM Comput Surv – start-page: 1171 year: 2008 end-page: 1220 ident: b121 article-title: Kernel methods in machine learning publication-title: Ann Statist – year: 2017 ident: b136 article-title: Model-based control using Koopman operators publication-title: Robotics: Science and systems proceedings – reference: Bender A, Williams SB, Pizarro O. Autonomous exploration of large-scale benthic environments. In: IEEE Int. Conf. on Robotics and Automation (ICRA); 2013. p. 390–6. – volume: 37 start-page: 50 year: 2020 end-page: 60 ident: b273 article-title: Federated learning: Challenges, methods, and future directions publication-title: IEEE Signal Process Mag – year: 2006 ident: b139 article-title: Pattern recognition and machine learning (Information science and statistics) – start-page: 52 year: 2000 end-page: 61 ident: b245 article-title: Planning with incomplete information as heuristic search in belief space publication-title: Proceedings of the fifth international conference on artificial intelligence planning systems – start-page: 23 year: 2008 end-page: 30 ident: b100 article-title: Adaptive multi-robot wide-area exploration and mapping publication-title: Conference on Autonomous Agents and Multiagent Systems – volume: 1 start-page: 213 year: 2014 end-page: 223 ident: b221 article-title: A resilient, untethered soft robot publication-title: Soft Robot – year: 2021 ident: b283 article-title: An ergodic measure for active learning from equilibrium publication-title: IEEE Trans Autom Sci Eng – start-page: 3812 year: 2017 end-page: 3822 ident: b267 article-title: Infogail: Interpretable imitation learning from visual demonstrations publication-title: Advances in neural information processing systems – start-page: 908 year: 2017 end-page: 918 ident: b279 article-title: Safe model-based reinforcement learning with stability guarantees publication-title: Advances in neural information processing systems – volume: 198 start-page: 203 year: 2000 end-page: 212 ident: b203 article-title: Mechanisms of animal navigation in odor plumes publication-title: Biol Bull – volume: 93 start-page: 3320 year: 1993 end-page: 3332 ident: b225 article-title: Biophysics of the cochlea: linear approximation publication-title: J Acoust Soc Am – volume: 32 start-page: 1309 year: 2016 end-page: 1332 ident: b179 article-title: Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age publication-title: IEEE Trans Robot – reference: Miller LM, Murphey TD. Trajectory optimization for continuous ergodic exploration. In: American controls conf. (ACC), 2013. p. 4196–201. – volume: 33 start-page: 301 year: 2004 end-page: 329 ident: b7 article-title: Sensorimotor control of navigation in arthropod and artificial systems publication-title: Arthropod Struct Develop – volume: 2 start-page: 827 year: 2017 end-page: 834 ident: b111 article-title: Ergodic exploration using binary sensing for non-parametric shape estimation publication-title: IEEE Robot Autom Lett – volume: 46 start-page: 1691 year: 2016 end-page: 1703 ident: b123 article-title: Learning the inverse dynamics of robotic manipulators in structured reproducing kernel Hilbert space publication-title: IEEE Trans Cybern – volume: 30 start-page: 68 year: 2007 end-page: 77 ident: b112 article-title: Aircraft autolander safety analysis through optimal control-based reach set computation publication-title: J Guid Control Dyn – start-page: 200 year: 2012 end-page: 207 ident: b261 article-title: Active learning from demonstration for robust autonomous navigation publication-title: 2012 IEEE international conference on robotics and automation – year: 2004 ident: b170 article-title: Science from fisher information: A unification – volume: 153 start-page: 34 year: 1966 end-page: 37 ident: b64 article-title: Dynamic programming publication-title: Science – volume: 27 start-page: 379 year: 1948 end-page: 423 ident: b171 article-title: A mathematical theory of communication publication-title: Bell Syst Tech J – volume: 28 start-page: 357 year: 2009 end-page: 375 ident: b236 article-title: Decentralized, adaptive coverage control for networked robots publication-title: Int J Robot Res – volume: 75 start-page: 291 year: 2014 end-page: 311 ident: b242 article-title: Active SLAM and exploration with particle filters using Kullback-Leibler divergence publication-title: J Intell Robot Syst – reference: Low KH, Chen J, Dolan JM, Chien S, Thompson DR. Decentralized active robotic exploration and mapping for probabilistic field classification in environmental sensing. In: Proceedings of the 11th international conference on autonomous agents and multiagent systems, 2012. p. 105–12. – volume: 35 start-page: 633 year: 2019 end-page: 652 ident: b210 article-title: Model-based active source identification in complex environments publication-title: IEEE Trans Robot – volume: 21 start-page: 324 year: 2005 end-page: 327 ident: b173 article-title: Information entropy based viewpoint planning for 3-D object reconstruction publication-title: IEEE Trans Robot – volume: 54 start-page: 898 year: 2006 end-page: 910 ident: b86 article-title: Planning under uncertainty using model predictive control for information gathering publication-title: Robot Auton Syst – start-page: 9 year: 2005 end-page: 16 ident: b262 article-title: Active learning for outdoor obstacle detection publication-title: Robotics: science and systems – reference: Mamakoukas G, Xherija O, Murphey TD. Learning memory-efficient stable linear dynamical systems for prediction and control. In: Conference on neural information processing systems (NeurIPS). 2020. – volume: 2 start-page: 319 year: 1988 end-page: 342 ident: b55 article-title: Queries and concept learning publication-title: Mach Learn – volume: 9 start-page: 4950 year: 2018 ident: b144 article-title: Deep learning for universal linear embeddings of nonlinear dynamics publication-title: Nature Commun – volume: 24 start-page: 145 year: 2002 end-page: 157 ident: b160 article-title: Information theoretic sensor data selection for active object recognition and state estimation publication-title: IEEE Trans Pattern Anal Mach Intell – volume: 30 start-page: 1343 year: 2011 end-page: 1377 ident: b252 article-title: Active vision in robotic systems: A survey of recent developments publication-title: Int J Robot Res – reference: Karapetyan N, Benson K, McKinney C, Taslakian P, Rekleitis I. Efficient multi-robot coverage of a known environment. In: 2017 IEEE/RSJ international conference on intelligent robots and systems (IROS), 2017. p. 1846–52. – reference: Wilson A, Schultz J, Ansari A, Murphey TD. Real-time trajectory synthesis for information maximization using sequential action control and least-squares estimation. In: IEEE int. conf. on intelligent robots and systems (IROS), 2015. p. 4935–40. – volume: 10 start-page: 183 year: 2017 end-page: 195 ident: b227 article-title: Can a soft robotic probe use stiffness control like a human finger to improve efficacy of haptic perception? publication-title: IEEE Trans Haptics – year: 2020 ident: b18 article-title: Learning about learning by many-body systems – volume: 54 start-page: 314 year: 2006 end-page: 331 ident: b177 article-title: Planning exploration strategies for simultaneous localization and mapping publication-title: Robot Auton Syst – volume: 5 start-page: 10487 year: 2015 ident: b14 article-title: Information processing via physical soft body publication-title: Sci Rep – volume: 37 start-page: 408 year: 2015 end-page: 423 ident: b128 article-title: Gaussian Processes for data-efficient learning in robotics and control publication-title: IEEE Trans Pattern Anal Mach Intell – volume: 56 start-page: 69 year: 2009 end-page: 98 ident: b164 article-title: An information roadmap method for robotic sensor path planning publication-title: J Intell Robot Syst – volume: 53 start-page: 1 year: 2020 end-page: 33 ident: b272 article-title: A survey on distributed machine learning publication-title: ACM Comput Surv – start-page: 678 year: 2014 end-page: 683 ident: b146 article-title: Adaptive category mapping networks for all-mode topological feature learning used for mobile robot vision publication-title: Proceedings of the 23rd IEEE International Symposium on Robot and Human Interactive Communication – reference: Wong E-M, Bourgault F, Furukawa T. Multi-vehicle Bayesian search for multiple lost targets. In: IEEE int. conf. on robotics and automation (ICRA); 2005. p. 3169–74. – reference: Atanasov N, Le Ny J, Daniilidis K, Pappas GJ. Decentralized active information acquisition: Theory and application to multi-robot SLAM. In: 2015 IEEE international conference on robotics and automation (ICRA), 2015. p. 4775–82. – reference: Souza J, Marchant R, Ott L, Wolf D, Ramos F. Bayesian optimisation for active perception and smooth navigation. In: IEEE Int. Conf. on Robotics and Automation (ICRA); 2014. p. 4081–87. – volume: 20 start-page: 158 year: 1913 end-page: 177 ident: b59 article-title: Psychology as the behaviorist views it publication-title: Psychol Rev – volume: 3 start-page: 2987 year: 2018 end-page: 2994 ident: b270 article-title: Decentralized ergodic control: Distribution-driven sensing and exploration for multi-agent systems publication-title: IEEE Robot Autom Lett – year: 1985 ident: b181 article-title: Ergodic theorems – reference: Southall B, Taylor C. Stochastic road shape estimation. In: Proceedings of the 8th IEEE international conference on computer vision (ICCV). Vol. 1; 2001. p. 205–212. – volume: 11 start-page: 249 year: 2001 end-page: 254 ident: b11 article-title: Active sensing capabilities of the rat whisker system publication-title: Auton Robots – volume: 35 start-page: 1 year: 2018 end-page: 20 ident: b254 article-title: Attention and anticipation in fast visual-inertial navigation publication-title: IEEE Trans Robot – year: 2006 ident: b246 article-title: Belief space planning assuming maximum likelihood observations publication-title: Robotics: science and systems – reference: Theodorou EA, Todorov E. Relative entropy and free energy dualities: Connections to Path Integral and KL control. In: 2012 IEEE 51st IEEE conference on decision and control (CDC), 2012. p. 1466–73. – volume: 78 start-page: 262 year: 2017 end-page: 270 ident: b78 article-title: Sim-to-real robot learning from pixels with progressive nets publication-title: Proceedings of the 1st annual conference on robot learning – volume: 73 start-page: 1235 year: 2000 end-page: 1248 ident: b169 article-title: Optimal sensor location for parameter estimation of distributed processes publication-title: Internat J Control – reference: Ayvali E, Salman H, Choset H. Ergodic coverage in constrained environments using stochastic trajectory optimization. In: IEEE/RSJ international conference on intelligent robots and systems (IROS), 2017. p. 5204–10. – year: 2003 ident: b52 article-title: Computability Theory – volume: 39 start-page: 212 year: 1927 end-page: 222 ident: b66 article-title: The law of effect publication-title: Am J Psychol – volume: 33 start-page: 1271 year: 2014 end-page: 1287 ident: b201 article-title: Sampling-based robotic information gathering algorithms publication-title: Int J Robot Res – volume: 589 start-page: 386 year: 2021 end-page: 390 ident: b16 article-title: A reprogrammable mechanical metamaterial with stable memory publication-title: Nature – year: 2019 ident: b138 article-title: Local Koopman operators for data-driven control of robotic systems publication-title: Robotics: Science and Systems – volume: 29 start-page: 31 year: 1998 end-page: 39 ident: b157 article-title: Active vision system based on information theory publication-title: Syst Comput Japan – volume: 369 start-page: 915 year: 2020 end-page: 916 ident: b71 article-title: The foundation of efficient robot learning publication-title: Science – volume: 410 start-page: 1876 year: 2009 end-page: 1902 ident: b296 article-title: Exploration–exploitation tradeoff using variance estimates in multi-armed bandits publication-title: Theoret Comput Sci – reference: Toh J, Sukkarieh S. A Bayesian formulation for the prioritized search of moving objects. In: IEEE int. conf. on robotics and automation (ICRA), 2006. p. 219–24. – volume: 76 start-page: 996 year: 1988 end-page: 1005 ident: b1 article-title: Active perception publication-title: Proc IEEE – volume: 27 start-page: 1134 year: 1984 end-page: 1142 ident: b43 article-title: A theory of the learnable publication-title: Commun ACM – start-page: 379 year: 2000 end-page: 386 ident: b35 article-title: A historical perspective of robotics publication-title: International symposium on history of machines and mechanisms proceedings HMM 2000 – reference: James S, Wohlhart P, Kalakrishnan M, Kalashnikov D, Irpan A, Ibarz J et al. Sim-to-real via sim-to-sim: Data-efficient robotic grasping via randomized-to-canonical adaptation networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR); 2019. – reference: Kreucher C, Wegrzyn J, Beauvais M, Conti R. Multiplatform information-based sensor management: an inverted UAV demonstration. In: SPIE defense transformation and network-centric systems. Vol. 6578; 2007. p. 65780Y–1–11. – volume: 6 year: 2021 ident: b105 article-title: A system of coordinated autonomous robots for Lagrangian studies of microbes in the oceanic deep chlorophyll maximum publication-title: Science Robotics – volume: 34 start-page: 829 year: 2018 end-page: 834 ident: b239 article-title: On the importance of uncertainty representation in active SLAM publication-title: IEEE Trans Robot – year: 2007 ident: b54 publication-title: The robot: The life story of a technology – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: b2 article-title: Deep learning publication-title: Nature – volume: 34 start-page: 457 year: 2015 end-page: 475 ident: b250 article-title: Active visual SLAM for robotic area coverage: Theory and experiment publication-title: Int J Robot Res – volume: 208 start-page: 59 year: 1965 end-page: 63 ident: b4 article-title: Osmotropotaxis in the honey-bee publication-title: Nature – volume: 30 start-page: 1358 year: 2014 end-page: 1370 ident: b184 article-title: Trajectory synthesis for Fisher information maximization publication-title: IEEE Trans Robot – start-page: 66 year: 2009 end-page: 83 ident: b19 article-title: Morphological computation–connecting brain, body, and environment publication-title: Creating brain-like intelligence – volume: 521 start-page: 467 year: 2015 end-page: 475 ident: b20 article-title: Design, fabrication and control of soft robots publication-title: Nature – start-page: 1168 year: 2014 end-page: 1175 ident: b192 article-title: Control-limited differential dynamic programming publication-title: 2014 IEEE international conference on robotics and automation (ICRA) – start-page: 65 year: 2003 end-page: 117 ident: b125 article-title: BayesIan kernel methods publication-title: Advanced lectures on machine learning – volume: 32 start-page: 3 year: 2013 end-page: 18 ident: b165 article-title: Active planning for underwater inspection and the benefit of adaptivity publication-title: Int J Robot Res – volume: 26 start-page: 651 year: 2009 end-page: 668 ident: b230 article-title: Coverage path planning algorithms for agricultural field machines publication-title: J Field Robotics – volume: 22 start-page: 701 year: 2015 end-page: 712 ident: b238 article-title: A dynamical systems approach to the surface search for debris associated with the disappearance of flight MH370 publication-title: Nonlin Process Geophys – volume: 529 start-page: 484 year: 2016 end-page: 489 ident: b259 article-title: Mastering the game of go with deep neural networks and tree search publication-title: Nature – reference: Tovar B, Murphey TD. Trajectory tracking among landmarks and binary sensor beams. In: IEEE int. conf. on robotics and automation (ICRA), 2012. p. 2121–7. – reference: Dressel L, Kochenderfer MJ. Using neural networks to generate information maps for mobile sensors. In: 2018 IEEE conference on decision and control (CDC), 2018. p. 2555–60. – start-page: 1329 year: 2008 end-page: 1336 ident: b288 article-title: A constraint generation approach to learning stable linear dynamical systems publication-title: Advances in neural information processing systems – volume: 9 start-page: 864 year: 1998 ident: b167 article-title: Optimal experiment design publication-title: Meas Sci Technol – volume: 27 start-page: 2204 year: 2014 end-page: 2212 ident: b253 article-title: Recurrent models of visual attention publication-title: Adv Neural Inf Process Syst – volume: 185 start-page: 60 year: 1951 end-page: 63 ident: b37 article-title: A machine that learns publication-title: Sci Am – volume: 39 start-page: 389 year: 2015 end-page: 405 ident: b264 article-title: Active reward learning with a novel acquisition function publication-title: Auton Robots – volume: vol. 2 start-page: 65 year: 2005 end-page: 72 ident: b240 article-title: Information gain-based exploration using rao-blackwellized particle filters publication-title: Robotics: science and systems – volume: 17 start-page: 909 year: 2018 end-page: 930 ident: b134 article-title: Generalizing Koopman theory to allow for inputs and control publication-title: SIAM J Appl Dyn Syst – reference: Chen Z, Xiao L, Wang Q, Wang Z, Sun Z. Coverage control of multi-agent systems for ergodic exploration. In: 2020 39th Chinese control conference (CCC), 2020. p. 4947–52. – year: 2018 ident: b257 article-title: An algorithmic perspective on imitation learning – reference: Salman H, Ayvali E, Choset H. Multi-agent ergodic coverage with obstacle avoidance. In: International conference on automated planning and scheduling. 2017. – volume: 18 start-page: 1827 year: 2013 end-page: 1838 ident: b229 article-title: Sensor-driven online coverage planning for autonomous underwater vehicles publication-title: IEEE/ASME Trans Mechatronics – start-page: 11126 year: 2019 end-page: 11134 ident: b81 article-title: Learning stable deep dynamics models publication-title: Advances in neural information processing systems – volume: 4 year: 2021 ident: b129 article-title: Koopman operators for estimation and control of dynamical systems publication-title: Annu Rev Control Robotic Auton Syst – volume: 34 start-page: 62 year: 2018 end-page: 80 ident: b216 article-title: Real-time area coverage and target localization using receding-horizon ergodic exploration publication-title: IEEE Trans Robot – reference: De La Torre G, Flaßkamp K, Prabhakar A, Murphey TD. Ergodic exploration with stochastic sensor dynamics. In: American controls conf. (ACC), 2016. p. 2971–6. – volume: 23 year: 2021 ident: b21 article-title: Complexity of body movements during sleep in children with autism spectrum disorder publication-title: Entropy – volume: 24 start-page: 377 year: 1987 end-page: 380 ident: b50 article-title: Occam’s razor publication-title: Inform Process Lett – volume: 3 start-page: 23 year: 2016 end-page: 33 ident: b220 article-title: Soft robotic grippers for biological sampling on deep reefs publication-title: Soft Robot – volume: 4 start-page: 129 year: 1996 end-page: 145 ident: b56 article-title: Active learning with statistical models publication-title: J Artificial Intelligence Res – start-page: 3389 year: 2017 end-page: 3396 ident: b70 article-title: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates publication-title: IEEE International Conference on Robotics and Automation (ICRA) – volume: 58 start-page: 574 year: 2010 end-page: 584 ident: b202 article-title: Particle filter based information-theoretic active sensing publication-title: Robot Auton Syst – year: 2005 ident: b127 article-title: Gaussian processes for machine learning – volume: 3 start-page: 1 year: 2012 end-page: 10 ident: b8 article-title: Rats track odour trails accurately using a multi-layered strategy with near-optimal sampling publication-title: Nature Commun – year: 2018 ident: b297 article-title: Learning actionable representations with goal-conditioned policies – volume: 5 start-page: 139 year: 1982 end-page: 155 ident: b30 article-title: Does play matter? Functional and evolutionary aspects of animal and human play publication-title: Behav Brain Sci – volume: 5 year: 2020 ident: b145 article-title: Electronic skins and machine learning for intelligent soft robots publication-title: Science Robotics – volume: 59 start-page: 433 year: 1950 end-page: 460 ident: b39 article-title: Computing machinery and intelligence publication-title: Mind – reference: Butepage J, Black MJ, Kragic D, Kjellstrom H. Deep representation learning for human motion prediction and classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR); 2017. p. 6158–66. – volume: 32 year: 2017 ident: b198 article-title: Sequential action control: Closed-form optimal control for nonlinear and nonsmooth systems publication-title: IEEE Trans Rob – volume: 45 start-page: 117 year: 1980 end-page: 135 ident: b42 article-title: Inductive inference of formal languages from positive data publication-title: Inf Control – volume: 61 start-page: 1258 year: 2013 end-page: 1276 ident: b232 article-title: A survey on coverage path planning for robotics publication-title: Robot Auton Syst – volume: 1 start-page: 391 year: 2014 ident: b131 article-title: On dynamic mode decomposition: Theory and applications publication-title: J Comput Dyn – volume: 30 start-page: 919 year: 2014 end-page: 934 ident: b163 article-title: An information potential approach to integrated sensor path planning and control publication-title: IEEE Trans Robot – volume: 38 start-page: 316 year: 2019 end-page: 337 ident: b271 article-title: Dec-MCTS: Decentralized planning for multi-robot active perception publication-title: Int J Robot Res – reference: Jan GE, Luo C, Hung L, Shih S. A computationally efficient complete area coverage algorithm for intelligent mobile robot navigation. In: 2014 international joint conference on neural networks, (IJCNN), 2014. p. 961–6. – year: 2011 ident: b94 article-title: An information potential approach for tracking and surveilling multiple moving targets using mobile sensor agents publication-title: SPIE Unmanned Systems Technology. Vol. 8045 – volume: 17 start-page: 315 year: 1931 end-page: 318 ident: b130 article-title: Hamiltonian systems and transformation in Hilbert space publication-title: Proc Natl Acad Sci – start-page: 291 year: 2005 end-page: 297 ident: b182 article-title: Ergodic dynamics by design: A route to predictable multi-robot systems publication-title: Multi-robot systems. from swarms to intelligent automata – reference: Agharese N, Cloyd T, Blumenschein LH, Raitor M, Hawkes EW, Culbertson H et al. HapWRAP: soft growing wearable haptic device. In: IEEE international conference on robotics and automation (ICRA), 2018. p. 5466–72. – reference: Akametalu AK, Fisac JF, Gillula JH, Kaynama S, Zeilinger MN, Tomlin CJ. Reachability-based safe learning with Gaussian processes. In: 53rd IEEE conference on decision and control, 2014. p. 1424–31. – start-page: 631 year: 2018 end-page: 648 ident: b294 article-title: Robot creation from functional specifications publication-title: Robotics research – reference: Cheng R, Orosz G, Murray RM, Burdick JW. End-to-end safe reinforcement learning through barrier functions for safety-critical continuous control tasks. In: Proceedings of the AAAI conference on artificial intelligence. vol. 33, 2019. p. 3387–95. – volume: 327 start-page: 701 year: 2010 end-page: 704 ident: b6 article-title: Optimal localization by pointing off axis publication-title: Science – reference: Huang W-B, Cao L-L, Sun F, Zhao D, Liu H, Yu S. Learning stable linear dynamical systems with the weighted least square method. In: International joint conference on artificial intelligence (IJCAI), 2016. p. 1599–605. – reference: Sim R, Roy N. Global A-optimal robot exploration in SLAM. In: IEEE int. conf. on robotics and automation (ICRA); 2005. p. 661–6. – reference: Stachniss C, Burgard W. Exploring unknown environments with mobile robots using coverage maps. In: International joint conference on artificial intelligence; 2003. p. 1127–34. – volume: 13 start-page: 16 year: 2006 end-page: 25 ident: b162 article-title: Cooperative air and ground surveillance publication-title: IEEE Robot Autom Magaz – volume: 40 start-page: 344 year: 2017 end-page: 357 ident: b197 article-title: Model predictive path integral control: From theory to parallel computation publication-title: J Guid Control Dyn – reference: Akametalu AK, Fisac JF, Gillula JH, Kaynama S, Zeilinger MN, Tomlin CJ. Reachability-based safe learning with Gaussian processes. In: 53rd IEEE conference on decision and control (CDC); 2014. p. 1424–31. – reference: Haarnoja T, Tang H, Abbeel P, Levine S. Reinforcement learning with deep energy-based policies. In: Proceedings of the international conference on machine learning (ICML). Vol. 70; 2017. p. 1352–61. – volume: 32 start-page: 36 year: 2016 end-page: 52 ident: b204 article-title: Ergodic exploration of distributed information publication-title: IEEE Trans Robot – reference: Gao Y, Hendricks LA, Kuchenbecker KJ, Darrell T. Deep learning for tactile understanding from visual and haptic data. In: 2016 IEEE international conference on robotics and automation (ICRA); 2016. p. 536–43. – volume: 2 start-page: 285 year: 1988 end-page: 318 ident: b46 article-title: Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm publication-title: Mach Learn – year: 1954 ident: b36 article-title: Programmable article transfer – volume: 29 start-page: 1050 year: 2013 end-page: 1059 ident: b248 article-title: Planning reliable paths with pose SLAM publication-title: IEEE Trans Robot – year: 2013 ident: b126 article-title: Stochastic processes: Theory for applications – reference: Bansal S, Chen M, Herbert S, Tomlin CJ. Hamilton-Jacobi reachability: A brief overview and recent advances. In: IEEE 56th annual conference on decision and control, 2017. p. 2242–53. – volume: 445 start-page: 406 year: 2007 ident: b153 article-title: Infotaxis as a strategy for searching without gradients publication-title: Nature – reference: Cooper J, Goodrich M. Towards combining UAV and sensor operator roles in UAV-enabled visual search. In: IEEE int. conf. on human robot interaction (HRI), 2008. p. 351–8. – volume: 40 start-page: 201 year: 1981 end-page: 211 ident: b61 article-title: Associative search network: A reinforcement learning associative memory publication-title: Biol Cybernet – reference: Rahimi M, Hansen M, Kaiser W, Sukhatme G, Estrin D. Adaptive sampling for environmental field estimation using robotic sensors. In: IEEE int. conf. on intelligent robots and systems (IROS), 2005. p. 3692–8. – reference: Abraham I, Broad A, Pinosky A, Argall B, Murphey TD. Hybrid control for learning motor skills. In: Workshop on the algorithmic foundations of robotics (WAFR). 2020. – volume: 49 start-page: 232 year: 2013 end-page: 237 ident: b237 article-title: Spatially distributed area coverage optimisation in mobile robotic networks with arbitrary convex anisotropic patterns publication-title: Automatica – volume: 10 start-page: 447 year: 1967 end-page: 474 ident: b41 article-title: Language identification in the limit publication-title: Inf Control – volume: 2 start-page: 265 year: 2016 end-page: 278 ident: b140 article-title: An overview on data representation learning: From traditional feature learning to recent deep learning publication-title: J Financ Data Sci – volume: 73 start-page: 145 year: 1999 end-page: 168 ident: b187 article-title: Sensor planning for 3D object search publication-title: Comput Vis Image Underst – reference: Nishimura H, Schwager M. SACBP: belief space planning for continuous-time dynamical systems via stochastic sequential action control. In: Workshop on the algorithmic foundations of robotics, 2018. p. 267–83. – year: 2008 ident: b295 article-title: The physiology of action and phenomenology – volume: 4 start-page: 169 year: 2019 end-page: 176 ident: b23 article-title: Dynamical system segmentation for information measures in motion publication-title: IEEE Robot Autom Lett – volume: 59 start-page: 876 year: 2014 end-page: 891 ident: b274 article-title: Rapidly exponentially stabilizing control Lyapunov functions and hybrid zero dynamics publication-title: IEEE Trans Automat Control – volume: 1 start-page: 44 year: 2019 end-page: 48 ident: b49 article-title: Learnability can be undecidable publication-title: Nat Mach Intell – year: 1938 ident: b60 article-title: The behavior of organisms: An experimental analysis – reference: Bourgault F, Makarenko AA, Williams S, Grocholsky B, Durrant-Whyte H. Information based adaptive robotic exploration. In: IEEE Int. Conf. on Intelligent Robots and Systems (IROS). Vol. 1; 2002. p. 540–5. – year: 2019 ident: b290 article-title: Physics-informed autoencoders for Lyapunov-stable fluid flow prediction publication-title: ArXiv – volume: SMC-13 start-page: 834 year: 1983 end-page: 846 ident: b63 article-title: Neuronlike adaptive elements that can solve difficult learning control problems publication-title: IEEE Trans Syst Man Cybern – reference: Massios NA, Fisher RB. A best next view selection algorithm incorporating a quality criterion. In: British machine vision conference, 1998. p. 78.1–78.10. – volume: 65 start-page: 386 year: 1958 end-page: 408 ident: b44 article-title: The perceptron: A probabilistic model for information storage and organization in the brain publication-title: Psychol Rev – volume: 40 start-page: 435 year: 2019 end-page: 448 ident: b224 article-title: Morphologically induced stability on an underwater legged robot with a deformable body publication-title: Int J Robot Res – year: 2019 ident: b119 article-title: Differentiable algorithm networks for composable robot learning publication-title: Robot Sci Syst – reference: Carrillo H, Dames P, Kumar V, Castellanos JA. Autonomous robotic exploration using occupancy grid maps and graph SLAM based on Shannon and Rényi entropy. In: IEEE international conference on robotics and automation (ICRA), 2015. p. 487–94. – volume: 5 start-page: 24 year: 2019 end-page: 31 ident: b124 article-title: A data-efficient geometrically inspired polynomial kernel for robot inverse dynamic publication-title: IEEE Robot Autom Lett – volume: 35 start-page: 1071 year: 2019 end-page: 1083 ident: b114 article-title: Active learning of dynamics for data-driven control using Koopman operators publication-title: IEEE Trans Robot – reference: Ucinski D, Korbicz J. Path planning for moving sensors in parameter estimation of distributed systems. In: Workshop on robot motion and control (RoMoCo), 1999. p. 273–8. – volume: 24 start-page: 276 year: 2015 end-page: 282 ident: b22 article-title: Objective identification and analysis of physiological and behavioral signs of schizophrenia publication-title: J Ment Health – volume: 85 start-page: 607 year: 2005 end-page: 624 ident: b158 article-title: Sensor management using an active sensing approach publication-title: Signal Process – volume: 10 start-page: 285 year: 1991 end-page: 313 ident: b150 article-title: Computational methods for task-directed sensor data fusion and sensor planning publication-title: Int J Robot Res – year: 2021 ident: b83 article-title: Linear systems can be hard to learn – volume: 3 start-page: 1394 year: 2018 end-page: 1401 ident: b143 article-title: Integrating state representation learning into deep reinforcement learning publication-title: IEEE Robot Autom Lett – reference: Leung C, Huang S, Dissanayake G. Active SLAM using model predictive control and attractor based exploration. In: 2006 IEEE/RSJ international conference on intelligent robots and systems, 2006. p. 5026–5031. – volume: 22 start-page: 7 year: 2003 end-page: 20 ident: b147 article-title: Dynamic sensor planning and control for optimally tracking targets publication-title: Int J Robot Res – year: 2018 ident: b107 article-title: Data-driven measurement models for active localization in sparse environments publication-title: Robotics: Science and systems proceedings – volume: 22 start-page: 46 year: 1989 end-page: 57 ident: b96 article-title: Using occupancy grids for mobile robot perception and navigation publication-title: Computer – volume: 28 start-page: 1448 year: 2009 end-page: 1465 ident: b247 article-title: The belief roadmap: Efficient planning in belief space by factoring the covariance publication-title: Int J Robot Res – volume: 88 start-page: 135 year: 1981 end-page: 170 ident: b62 article-title: Toward a modern theory of adaptive networks: Expectation and prediction publication-title: Psychol Rev – reference: Cao N, Low KH, Dolan JM. Multi-robot informative path planning for active sensing of environmental phenomena: A tale of two algorithms. In: International conference on autonomous agents and multi-agent systems; 2013. p. 7–14. – volume: 18 start-page: 70 year: 1932 end-page: 82 ident: b180 article-title: Proof of the quasi-ergodic hypothesis publication-title: Proc Natl Acad Sci – volume: 3 start-page: 91 year: 2020 end-page: 114 ident: b208 article-title: Mobile sensor networks and control: Adaptive sampling of spatiotemporal processes publication-title: Annu Rev Control Robot Auton Syst – volume: 433 start-page: 595 year: 2005 end-page: 596 ident: b226 article-title: Motor control of flexible octopus arms publication-title: Nature – volume: 5 year: 2020 ident: b104 article-title: Revealing ocean-scale biochemical structure with a deep-diving vertical profiling autonomous vehicle publication-title: Science Robotics – volume: 9 year: 2020 ident: b13 article-title: Tuning movement for sensing in an uncertain world publication-title: ELIfe – volume: 1 year: 2016 ident: b34 article-title: Soft robotics: Technologies and systems pushing the boundaries of robot abilities publication-title: Science Robotics – year: 2020 ident: b280 article-title: Reinforcement learning for safety-critical control under model uncertainty, using control Lyapunov functions and control barrier functions – year: 2018 ident: b67 article-title: Reinforcement learning: An introduction – reference: Vander Hook J, Tokekar P, Isler V. Cautious greedy strategy for bearing-based active localization: Experiments and theoretical analysis. In: IEEE international conference on robotics and automation (ICRA); 2012. p. 1787–92. – reference: Ames AD, Coogan S, Egerstedt M, Notomista G, Sreenath K, Tabuada P. Control barrier functions: Theory and applications. In: 2019 18th european control conference (ECC), 2019. p. 3420–3431. – volume: 16 start-page: 35 year: 2009 end-page: 42 ident: b161 article-title: Autonomous UAV path planning and estimation publication-title: IEEE Robot Autom Magaz – volume: 29 start-page: 2172 year: 2016 end-page: 2180 ident: b268 article-title: Infogan: Interpretable representation learning by information maximizing generative adversarial nets publication-title: Adv Neural Inf Process Syst – year: 2013 ident: b285 article-title: Introduction to mechanics and symmetry: A basic exposition of classical mechanical systems – volume: 203 start-page: 1409 year: 2000 end-page: 1414 ident: b5 article-title: Three-dimensional odor tracking by nautilus pompilius publication-title: J Exp Biol – reference: Gehring C, Precup D. Smart exploration in reinforcement learning using absolute temporal difference errors. In: Proceedings of the 2013 international conference on autonomous agents and multi-agent systems; 2013. p. 1037–44. – start-page: 431 year: 1969 end-page: 450 ident: b40 article-title: Some philosophical problems from the standpoint of artificial intelligence publication-title: Readings in artificial intelligence – volume: 80 start-page: 111 year: 2010 end-page: 139 ident: b58 article-title: The true sample complexity of active learning publication-title: Mach Learn – start-page: 1 year: 2018 end-page: 9 ident: b258 article-title: End-to-end driving via conditional imitation learning publication-title: 2018 IEEE international conference on robotics and automation (ICRA) – volume: 33 start-page: 568 year: 2018 end-page: 594 ident: b108 article-title: Nonparametric shape-restricted regression publication-title: Statist Sci – volume: 33 start-page: 661 year: 2017 end-page: 674 ident: b278 article-title: Safety barrier certificates for collisions-free multirobot systems publication-title: IEEE Trans Robot – volume: 16 start-page: 1437 year: 2015 end-page: 1480 ident: b80 article-title: A comprehensive survey on safe reinforcement learning publication-title: J Mach Learn Res – start-page: 6957 year: 2019 end-page: 6962 ident: b211 article-title: Ergodic flocking publication-title: 2019 IEEE/RSJ international conference on intelligent robots and systems (IROS) – volume: 26 start-page: 961 year: 2004 end-page: 972 ident: b166 article-title: Application of the theory of optimal experiments to adaptive electromagnetic-induction sensing of buried targets publication-title: IEEE Trans Pattern Anal Mach Intell – year: 2012 ident: b175 article-title: Elements of information theory – year: 2009 ident: b31 article-title: Active learning literature survey – volume: 42 year: 2009 ident: b26 article-title: Optimal search behavior and classic foraging theory publication-title: J Phys A – year: 2019 ident: b17 article-title: Self-organized novelty detection in driven spin glasses – reference: Prabhakar A, Abraham I, Schlafly M, Taylor A, Popovic K, Diniz G et al. Ergodic specifications for flexible swarm control: from user commands to persistent adaptation. In: Robotics: science and systems proceedings, 2020. – volume: 3 start-page: 316 year: 2021 end-page: 323 ident: b118 article-title: Teaching recurrent neural networks to infer global temporal structure from local examples publication-title: Nat Mach Intell – volume: vol. 87 start-page: 466 year: 2018 end-page: 476 ident: b292 article-title: The Lyapunov neural network: Adaptive stability certification for safe learning of dynamical systems publication-title: Proceedings of the 2nd conference on robot learning – year: 2021 ident: b15 article-title: Integration of deep learning and soft robotics for a biomimetic approach to nonlinear sensing publication-title: Nat Mach Intell – year: 2019 ident: b137 article-title: Modeling and control of soft robots using the Koopman operator and model predictive control publication-title: Robotics: Science and systems – year: 2015 ident: b176 article-title: From pixels to torques: Policy learning with deep dynamical models – start-page: 1577 year: 2016 end-page: 1604 ident: b228 article-title: Disaster robotics publication-title: Springer handbook of robotics – volume: 31 start-page: 113 year: 2001 end-page: 126 ident: b233 article-title: Coverage for robotics–a survey of recent results publication-title: Ann Math Artif Intell – volume: 37 start-page: 405 year: 2018 end-page: 420 ident: b73 article-title: The limits and potentials of deep learning for robotics publication-title: Int J Robot Res – volume: 29 start-page: 741 year: 1982 end-page: 765 ident: b53 article-title: Inference of reversible languages publication-title: J ACM – year: 2016 ident: b193 article-title: Learning dexterous manipulation policies from experience and imitation – reference: Haarnoja T, Zhou A, Abbeel P, Levine S. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of the international conference on machine learning (ICML). Vol. 80; 2018. p. 1861–70. – year: 2016 ident: b266 article-title: Generative adversarial imitation learning – volume: 9 start-page: 16 year: 2017 ident: b251 article-title: Visual SLAM algorithms: a survey from 2010 to 2016 publication-title: IPSJ Trans Comput Vision Appl – start-page: 219 year: 2013 end-page: 240 ident: b275 article-title: Towards the unification of locomotion and manipulation through control Lyapunov functions and quadratic programs publication-title: Control of cyber-physical systems – reference: Williams G, Wagener N, Goldfain B, Drews P, Rehg JM, Boots B et al. Information theoretic MPC for model-based reinforcement learning. In: International conference on robotics and automation (ICRA). 2017. – volume: 365 start-page: 1180 year: 2019 end-page: 1183 ident: b29 article-title: Behavioral and neural correlates of hide-and-seek in rats publication-title: Science – volume: 45 start-page: 983 year: 1998 end-page: 1006 ident: b47 article-title: Efficient noise-tolerant learning from statistical queries publication-title: J ACM – reference: Marchant R, Ramos F. Bayesian optimisation for intelligent environmental monitoring. In: IEEE int. conf. on intelligent robots and systems (IROS); 2012. p. 2242–49. – start-page: 515 year: 2015 end-page: 533 ident: b249 article-title: Scaling up Gaussian belief space planning through covariance-free trajectory optimization and automatic differentiation publication-title: Workshop on the algorithmic foundations of robotics – volume: 11 start-page: 1 year: 2016 end-page: 19 ident: b133 article-title: Koopman invariant subspaces and finite linear representations of nonlinear dynamical systems for control publication-title: PLOS ONE – reference: Bellman R. On the theory of dynamic programming. In: Proceedings of the national academy. vol. 38.8, 1952. p. 716. – volume: 4 start-page: 6079 year: 2019 ident: b24 article-title: Ergodicity reveals assistance and learning in physical human robot interaction publication-title: Sci Robot – volume: 4 year: 2019 ident: b120 article-title: Soft robot perception using embedded soft sensors and recurrent neural networks publication-title: Science Robotics – volume: 192 start-page: 573 year: 2006 end-page: 586 ident: b12 article-title: Sensory acquisition in active sensing systems publication-title: J Comp Physiol [A] – volume: 57 start-page: 469 year: 2009 end-page: 483 ident: b256 article-title: A survey of robot learning from demonstration publication-title: Robot Auton Syst – volume: 36 start-page: 929 year: 1989 end-page: 965 ident: b51 article-title: Learnability and the vapnik-chervonenkis dimension publication-title: J ACM – start-page: 165 year: 1976 end-page: 188 ident: b28 article-title: Animal play: Problems and perspectives publication-title: Perspectives in ethology: Volume 2 – volume: 117 start-page: 240 year: 1995 end-page: 250 ident: b48 article-title: Learning by distances publication-title: Inform and Comput – reference: Schaal S, Atkeson C, Vijayakumar S. Real-time robot learning with locally weighted statistical learning. In: Proceedings of the IEEE international conference on robotics and automation (ICRA). Vol. 1; 2000. p. 288–93. – year: 2012 ident: b265 article-title: Active imitation learning via reduction to iid active learning – volume: 25 start-page: 195 year: 1998 end-page: 207 ident: b154 article-title: Active Markov localization for mobile robots publication-title: Robot Auton Syst – volume: 2 start-page: 3 year: 2014 ident: b223 article-title: Soft robotics: new perspectives for robot bodyware and control publication-title: Front Bioeng Biotechnol – reference: Zhang G, Ferrari S. An adaptive artificial potential function approach for geometric sensing. In: IEEE int. conf. on decision and control (CDC); 2009. p. 7903–10. – volume: 30 start-page: 1078 year: 2014 end-page: 1090 ident: b172 article-title: Nonmyopic view planning for active object classification and pose estimation publication-title: IEEE Trans Robot – year: 2013 ident: b57 article-title: Statistical active learning algorithms publication-title: Advances in neural information processing systems (NeurIPS). Vol. 26 – volume: 4 start-page: 1 year: 2013 end-page: 8 ident: b10 article-title: Stereo and serial sniffing guide navigation to an odour source in a mammal publication-title: Nature Commun – volume: 240 start-page: 432 year: 2011 end-page: 442 ident: b183 article-title: Metrics for ergodicity and design of ergodic dynamics for multi-agent systems publication-title: Physica D – reference: Duan Y, Chen X, Houthooft R, Schulman J, Abbeel P. Benchmarking deep reinforcement learning for continuous control. In: Proceedings of the International Conference on Machine Learning (ICML). Vol. 48; 2016. p. 1329–38. – volume: 18 start-page: 650 year: 1999 end-page: 668 ident: b85 article-title: Adaptive mobile robot navigation and mapping publication-title: Int J Robot Res – reference: Arbel T, Ferrie F. Viewpoint selection by navigation through entropy maps. In: IEEE int. conf. on computer vision, 1999. p. 248–54. – year: 2020 ident: b263 article-title: From inverse optimal control to inverse reinforcement learning: A historical review publication-title: Annu Rev Control – volume: 40 start-page: 255 year: 2002 end-page: 266 ident: b151 article-title: Using infrared sensors for distance measurement in mobile robots publication-title: Robot Auton Syst – year: 2021 ident: b72 article-title: How to train your robot with deep reinforcement learning: lessons we have learned publication-title: Int J Robot Res – reference: -Bayes-optimal active learning of Gaussian processes. In: International conference on machine learning; 2014. p. 739–47. – start-page: 681 year: 2019 end-page: 689 ident: b142 article-title: Time-frequency deep representation learning for speech emotion recognition integrating self-attention publication-title: Neural information processing – reference: Hoang TN, Low KH, Jaillet P, Kankanhalli M. Nonmyopic – start-page: 421 year: 2020 end-page: 450 ident: b115 article-title: Experimental applications of the Koopman operator in active learning for control publication-title: The Koopman operator in systems and control: Concepts, methodologies, and applications – reference: Miller L, Murphey TD. Optimal planning for target localization and coverage using range sensing. In: IEEE int. conf. on automation science and engineering (CASE), 2015. p. 501–8. – reference: Gillespie MT, Best CM, Townsend EC, Wingate D, Killpack MD. Learning nonlinear dynamic models of soft robots for model predictive control with neural networks. In: 2018 IEEE international conference on soft robotics (RoboSoft), 2018. p. 39–45. – volume: 62 start-page: 3861 year: 2016 end-page: 3876 ident: b277 article-title: Control barrier function based quadratic programs for safety critical systems publication-title: IEEE Trans Automat Control – volume: 2005 start-page: P11011 year: 2005 ident: b196 article-title: Path integrals and symmetry breaking for optimal control theory publication-title: J Stat Mech Theory Exp – volume: 19 start-page: 103 year: 2010 end-page: 114 ident: b116 article-title: A neural framework for adaptive robot control publication-title: Neural Comput Appl – volume: vol. 1 start-page: 273 year: 2001 end-page: 280 ident: b156 article-title: Viewpoint selection using viewpoint entropy publication-title: Vision modeling and visualization conference – volume: 3 start-page: 4978 year: 2018 ident: b3 article-title: Situated experimental agents for scientific discovery publication-title: Science Robotics – year: 2021 ident: b76 article-title: Maximum entropy RL (provably) solves some robust RL problems – volume: 4 start-page: 89 year: 2019 end-page: 100 ident: b206 article-title: Tutorial on the generation of ergodic trajectories with projection-based gradient descent publication-title: IET Cyber-Phys Syst Theory Appl – volume: 339 start-page: 1408 year: 2013 end-page: 1412 ident: b33 article-title: A terradynamics of legged locomotion on granular media publication-title: Science – volume: 34 start-page: 707 year: 2009 end-page: 755 ident: b101 article-title: Efficient informative sensing using multiple robots publication-title: J Artif Intell Res (JAIR) – volume: s2-42 start-page: 230 year: 1937 end-page: 265 ident: b38 article-title: On computable numbers, with an application to the entscheidungsproblem publication-title: Proc Lond Math Soc – reference: Englot B, Hover FS. Sampling-based coverage path planning for inspection of complex structures. In: International conference on automated planning and scheduling (ICAPS). 2012. – volume: 16 year: 2019 ident: b27 article-title: Optimal foraging and the information theory of gambling publication-title: J R Soc Interface – volume: 39 start-page: 672 year: 2009 end-page: 689 ident: b186 article-title: Information-driven sensor path planning by approximate cell decomposition publication-title: IEEE Trans Syst Man Cybern – volume: 32 start-page: 1587 year: 1996 end-page: 1595 ident: b286 article-title: Realization of stable models with subspace methods publication-title: Automatica – year: 2017 ident: b135 article-title: Data-driven discovery of Koopman eigenfunctions for control – volume: 3 start-page: 85 year: 1966 end-page: 95 ident: b190 article-title: A second-order gradient method for determining optimal trajectories of non-linear discrete-time systems publication-title: Internat J Control – start-page: 3803 year: 2018 end-page: 3810 ident: b77 article-title: Sim-to-real transfer of robotic control with dynamics randomization publication-title: 2018 IEEE international conference on robotics and automation (ICRA) – volume: 4 year: 2019 ident: b106 article-title: Toward adaptive robotic sampling of phytoplankton in the coastal ocean publication-title: Science Robotics – volume: 65 start-page: 1773 year: 2006 end-page: 1793 ident: b148 article-title: Honey-pot constrained searching with local sensory information publication-title: Nonlinear Anal TMA – volume: vol. 2 start-page: 1398 year: 2002 end-page: 1403 vol.2 ident: b260 article-title: Movement imitation with nonlinear dynamical systems in humanoid robots publication-title: Proceedings 2002 IEEE international conference on robotics and automation (Cat. No.02CH37292) – volume: 23 start-page: 2015 year: 2009 end-page: 2034 ident: b117 article-title: Model learning with local Gaussian process regression publication-title: Adv Robot – volume: 12 start-page: 19 year: 1992 end-page: 22 ident: b65 article-title: Reinforcement learning is direct adaptive optimal control publication-title: IEEE Control Syst Mag – reference: Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y et al. Continuous control with deep reinforcement learning. In: Proceedings of the international conference on learning representations (ICLR); 2016. – start-page: 1823 year: 2010 end-page: 1830 ident: b109 article-title: Multilinear pose and body shape estimation of dressed subjects from image sets publication-title: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition – volume: 25 start-page: 1307 year: 2015 end-page: 1346 ident: b132 article-title: A data–driven approximation of the Koopman operator: Extending dynamic mode decomposition publication-title: J Nonlinear Sci – volume: 53 start-page: 1 issue: 2 year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b272 article-title: A survey on distributed machine learning publication-title: ACM Comput Surv doi: 10.1145/3377454 – ident: 10.1016/j.mechatronics.2021.102576_b235 doi: 10.1109/IJCNN.2014.6889862 – volume: 203 start-page: 1409 issue: 9 year: 2000 ident: 10.1016/j.mechatronics.2021.102576_b5 article-title: Three-dimensional odor tracking by nautilus pompilius publication-title: J Exp Biol doi: 10.1242/jeb.203.9.1409 – volume: 25 start-page: 195 issue: 3–4 year: 1998 ident: 10.1016/j.mechatronics.2021.102576_b154 article-title: Active Markov localization for mobile robots publication-title: Robot Auton Syst doi: 10.1016/S0921-8890(98)00049-9 – ident: 10.1016/j.mechatronics.2021.102576_b79 doi: 10.1109/CVPR.2019.01291 – volume: 45 start-page: 117 issue: 2 year: 1980 ident: 10.1016/j.mechatronics.2021.102576_b42 article-title: Inductive inference of formal languages from positive data publication-title: Inf Control doi: 10.1016/S0019-9958(80)90285-5 – volume: 192 start-page: 573 issue: 6 year: 2006 ident: 10.1016/j.mechatronics.2021.102576_b12 article-title: Sensory acquisition in active sensing systems publication-title: J Comp Physiol [A] doi: 10.1007/s00359-006-0099-4 – volume: 32 start-page: 1309 issue: 6 year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b179 article-title: Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age publication-title: IEEE Trans Robot doi: 10.1109/TRO.2016.2624754 – ident: 10.1016/j.mechatronics.2021.102576_b89 doi: 10.1109/IROS.2012.6385653 – volume: 31 start-page: 113 issue: 1–4 year: 2001 ident: 10.1016/j.mechatronics.2021.102576_b233 article-title: Coverage for robotics–a survey of recent results publication-title: Ann Math Artif Intell doi: 10.1023/A:1016639210559 – ident: 10.1016/j.mechatronics.2021.102576_b185 doi: 10.1145/1349822.1349868 – volume: 56 start-page: 69 issue: 1–2 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b164 article-title: An information roadmap method for robotic sensor path planning publication-title: J Intell Robot Syst doi: 10.1007/s10846-009-9318-x – volume: 73 start-page: 1235 issue: 13 year: 2000 ident: 10.1016/j.mechatronics.2021.102576_b169 article-title: Optimal sensor location for parameter estimation of distributed processes publication-title: Internat J Control doi: 10.1080/002071700417876 – volume: 24 start-page: 276 issue: 5 year: 2015 ident: 10.1016/j.mechatronics.2021.102576_b22 article-title: Objective identification and analysis of physiological and behavioral signs of schizophrenia publication-title: J Ment Health doi: 10.3109/09638237.2015.1019048 – ident: 10.1016/j.mechatronics.2021.102576_b82 – start-page: 1171 year: 2008 ident: 10.1016/j.mechatronics.2021.102576_b121 article-title: Kernel methods in machine learning publication-title: Ann Statist – year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b67 – volume: 40 start-page: 344 issue: 2 year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b197 article-title: Model predictive path integral control: From theory to parallel computation publication-title: J Guid Control Dyn doi: 10.2514/1.G001921 – volume: vol. 1 start-page: 273 year: 2001 ident: 10.1016/j.mechatronics.2021.102576_b156 article-title: Viewpoint selection using viewpoint entropy – start-page: 431 year: 1969 ident: 10.1016/j.mechatronics.2021.102576_b40 article-title: Some philosophical problems from the standpoint of artificial intelligence – ident: 10.1016/j.mechatronics.2021.102576_b212 doi: 10.1609/icaps.v27i1.13816 – year: 2007 ident: 10.1016/j.mechatronics.2021.102576_b54 doi: 10.5040/9798216009511 – ident: 10.1016/j.mechatronics.2021.102576_b234 doi: 10.1109/IROS.2017.8206000 – volume: 50 issn: 0360-0300 issue: 2 year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b255 article-title: Imitation learning: A survey of learning methods publication-title: ACM Comput Surv doi: 10.1145/3054912 – volume: 30 start-page: 68 issue: 1 year: 2007 ident: 10.1016/j.mechatronics.2021.102576_b112 article-title: Aircraft autolander safety analysis through optimal control-based reach set computation publication-title: J Guid Control Dyn doi: 10.2514/1.21562 – volume: 30 start-page: 919 issn: 1552-3098 issue: 4 year: 2014 ident: 10.1016/j.mechatronics.2021.102576_b163 article-title: An information potential approach to integrated sensor path planning and control publication-title: IEEE Trans Robot doi: 10.1109/TRO.2014.2312812 – year: 2003 ident: 10.1016/j.mechatronics.2021.102576_b52 – volume: 2005 start-page: P11011 issue: 11 year: 2005 ident: 10.1016/j.mechatronics.2021.102576_b196 article-title: Path integrals and symmetry breaking for optimal control theory publication-title: J Stat Mech Theory Exp doi: 10.1088/1742-5468/2005/11/P11011 – volume: 54 start-page: 898 issue: 11 year: 2006 ident: 10.1016/j.mechatronics.2021.102576_b86 article-title: Planning under uncertainty using model predictive control for information gathering publication-title: Robot Auton Syst doi: 10.1016/j.robot.2006.05.008 – volume: 24 start-page: 377 issn: 0020-0190 issue: 6 year: 1987 ident: 10.1016/j.mechatronics.2021.102576_b50 article-title: Occam’s razor publication-title: Inform Process Lett doi: 10.1016/0020-0190(87)90114-1 – start-page: 200 year: 2012 ident: 10.1016/j.mechatronics.2021.102576_b261 article-title: Active learning from demonstration for robust autonomous navigation – volume: 16 start-page: 35 issue: 2 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b161 article-title: Autonomous UAV path planning and estimation publication-title: IEEE Robot Autom Magaz doi: 10.1109/MRA.2009.932529 – ident: 10.1016/j.mechatronics.2021.102576_b178 doi: 10.1109/ICRA.2012.6224748 – ident: 10.1016/j.mechatronics.2021.102576_b214 doi: 10.15607/RSS.2020.XVI.067 – ident: 10.1016/j.mechatronics.2021.102576_b218 doi: 10.1109/CoASE.2015.7294129 – year: 2011 ident: 10.1016/j.mechatronics.2021.102576_b94 article-title: An information potential approach for tracking and surveilling multiple moving targets using mobile sensor agents – volume: 18 start-page: 650 issue: 7 year: 1999 ident: 10.1016/j.mechatronics.2021.102576_b85 article-title: Adaptive mobile robot navigation and mapping publication-title: Int J Robot Res doi: 10.1177/02783649922066484 – volume: 30 start-page: 1078 issn: 1552-3098 issue: 5 year: 2014 ident: 10.1016/j.mechatronics.2021.102576_b172 article-title: Nonmyopic view planning for active object classification and pose estimation publication-title: IEEE Trans Robot doi: 10.1109/TRO.2014.2320795 – volume: 35 start-page: 1071 issue: 5 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b114 article-title: Active learning of dynamics for data-driven control using Koopman operators publication-title: IEEE Trans Robot doi: 10.1109/TRO.2019.2923880 – ident: 10.1016/j.mechatronics.2021.102576_b289 – year: 1938 ident: 10.1016/j.mechatronics.2021.102576_b60 – volume: 445 start-page: 406 issue: 7126 year: 2007 ident: 10.1016/j.mechatronics.2021.102576_b153 article-title: Infotaxis as a strategy for searching without gradients publication-title: Nature doi: 10.1038/nature05464 – volume: 17 start-page: 909 issue: 1 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b134 article-title: Generalizing Koopman theory to allow for inputs and control publication-title: SIAM J Appl Dyn Syst doi: 10.1137/16M1062296 – year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b293 article-title: Learning stable models for prediction and control publication-title: IEEE Trans Robot – volume: 3 start-page: 4978 issue: 24 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b3 article-title: Situated experimental agents for scientific discovery publication-title: Science Robotics doi: 10.1126/scirobotics.aau4978 – ident: 10.1016/j.mechatronics.2021.102576_b215 doi: 10.1109/ACC.2016.7525371 – ident: 10.1016/j.mechatronics.2021.102576_b219 doi: 10.1109/ICRA.2018.8460891 – ident: 10.1016/j.mechatronics.2021.102576_b141 doi: 10.1109/CVPR.2017.173 – year: 2021 ident: 10.1016/j.mechatronics.2021.102576_b283 article-title: An ergodic measure for active learning from equilibrium publication-title: IEEE Trans Autom Sci Eng doi: 10.1109/TASE.2020.3043636 – ident: 10.1016/j.mechatronics.2021.102576_b209 doi: 10.23919/CCC50068.2020.9189276 – volume: 215 start-page: 1567 issue: 9 year: 2012 ident: 10.1016/j.mechatronics.2021.102576_b9 article-title: Active sensing via movement shapes spatiotemporal patterns of sensory feedback publication-title: J Exp Biol doi: 10.1242/jeb.068007 – volume: 521 start-page: 467 issue: 7553 year: 2015 ident: 10.1016/j.mechatronics.2021.102576_b20 article-title: Design, fabrication and control of soft robots publication-title: Nature doi: 10.1038/nature14543 – volume: 4 issue: 26 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b120 article-title: Soft robot perception using embedded soft sensors and recurrent neural networks publication-title: Science Robotics doi: 10.1126/scirobotics.aav1488 – volume: 10 start-page: 183 issue: 2 year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b227 article-title: Can a soft robotic probe use stiffness control like a human finger to improve efficacy of haptic perception? publication-title: IEEE Trans Haptics doi: 10.1109/TOH.2016.2615924 – volume: 80 start-page: 111 issn: 1573-0565 issue: 2 year: 2010 ident: 10.1016/j.mechatronics.2021.102576_b58 article-title: The true sample complexity of active learning publication-title: Mach Learn doi: 10.1007/s10994-010-5174-y – ident: 10.1016/j.mechatronics.2021.102576_b69 – volume: 30 start-page: 1358 issue: 6 year: 2014 ident: 10.1016/j.mechatronics.2021.102576_b184 article-title: Trajectory synthesis for Fisher information maximization publication-title: IEEE Trans Robot doi: 10.1109/TRO.2014.2345918 – volume: 12 start-page: 19 issue: 2 year: 1992 ident: 10.1016/j.mechatronics.2021.102576_b65 article-title: Reinforcement learning is direct adaptive optimal control publication-title: IEEE Control Syst Mag doi: 10.1109/37.126844 – ident: 10.1016/j.mechatronics.2021.102576_b95 doi: 10.1109/IRDS.2002.1041446 – volume: 32 start-page: 36 issue: 1 year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b204 article-title: Ergodic exploration of distributed information publication-title: IEEE Trans Robot doi: 10.1109/TRO.2015.2500441 – ident: 10.1016/j.mechatronics.2021.102576_b199 doi: 10.1007/978-3-030-66723-8_27 – volume: 5 start-page: 139 issue: 1 year: 1982 ident: 10.1016/j.mechatronics.2021.102576_b30 article-title: Does play matter? Functional and evolutionary aspects of animal and human play publication-title: Behav Brain Sci doi: 10.1017/S0140525X0001092X – volume: 39 start-page: 212 issue: 1 year: 1927 ident: 10.1016/j.mechatronics.2021.102576_b66 article-title: The law of effect publication-title: Am J Psychol doi: 10.2307/1415413 – volume: 339 start-page: 1408 issn: 0036-8075 issue: 6126 year: 2013 ident: 10.1016/j.mechatronics.2021.102576_b33 article-title: A terradynamics of legged locomotion on granular media publication-title: Science doi: 10.1126/science.1229163 – volume: 23 issn: 1099-4300 issue: 4 year: 2021 ident: 10.1016/j.mechatronics.2021.102576_b21 article-title: Complexity of body movements during sleep in children with autism spectrum disorder publication-title: Entropy doi: 10.3390/e23040418 – ident: 10.1016/j.mechatronics.2021.102576_b195 doi: 10.1109/CDC.2012.6426381 – volume: 21 start-page: 324 issue: 3 year: 2005 ident: 10.1016/j.mechatronics.2021.102576_b173 article-title: Information entropy based viewpoint planning for 3-D object reconstruction publication-title: IEEE Trans Robot doi: 10.1109/TRO.2004.837239 – volume: 11 start-page: 1 issue: 2 year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b133 article-title: Koopman invariant subspaces and finite linear representations of nonlinear dynamical systems for control publication-title: PLOS ONE doi: 10.1371/journal.pone.0150171 – volume: 410 start-page: 1876 issue: 19 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b296 article-title: Exploration–exploitation tradeoff using variance estimates in multi-armed bandits publication-title: Theoret Comput Sci doi: 10.1016/j.tcs.2009.01.016 – start-page: 908 year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b279 article-title: Safe model-based reinforcement learning with stability guarantees – volume: 40 start-page: 255 issn: 0921-8890 issue: 4 year: 2002 ident: 10.1016/j.mechatronics.2021.102576_b151 article-title: Using infrared sensors for distance measurement in mobile robots publication-title: Robot Auton Syst doi: 10.1016/S0921-8890(02)00271-3 – ident: 10.1016/j.mechatronics.2021.102576_b191 doi: 10.1073/pnas.38.8.716 – year: 2012 ident: 10.1016/j.mechatronics.2021.102576_b265 – volume: 35 start-page: 633 issue: 3 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b210 article-title: Model-based active source identification in complex environments publication-title: IEEE Trans Robot doi: 10.1109/TRO.2019.2894039 – year: 2021 ident: 10.1016/j.mechatronics.2021.102576_b72 article-title: How to train your robot with deep reinforcement learning: lessons we have learned publication-title: Int J Robot Res doi: 10.1177/0278364920987859 – volume: 3 start-page: 1394 issue: 3 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b143 article-title: Integrating state representation learning into deep reinforcement learning publication-title: IEEE Robot Autom Lett doi: 10.1109/LRA.2018.2800101 – year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b31 – ident: 10.1016/j.mechatronics.2021.102576_b93 doi: 10.1109/ACC.2006.1656452 – ident: 10.1016/j.mechatronics.2021.102576_b207 doi: 10.1109/CDC.2018.8619820 – volume: 2 start-page: 285 issn: 1573-0565 issue: 4 year: 1988 ident: 10.1016/j.mechatronics.2021.102576_b46 article-title: Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm publication-title: Mach Learn doi: 10.1007/BF00116827 – ident: 10.1016/j.mechatronics.2021.102576_b168 doi: 10.1109/ROMOCO.1999.791086 – start-page: 1577 year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b228 article-title: Disaster robotics doi: 10.1007/978-3-319-32552-1_60 – volume: 19 start-page: 103 issue: 1 year: 2010 ident: 10.1016/j.mechatronics.2021.102576_b116 article-title: A neural framework for adaptive robot control publication-title: Neural Comput Appl doi: 10.1007/s00521-009-0262-2 – year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b257 – volume: 1 start-page: 213 issue: 3 year: 2014 ident: 10.1016/j.mechatronics.2021.102576_b221 article-title: A resilient, untethered soft robot publication-title: Soft Robot doi: 10.1089/soro.2014.0008 – volume: 9 start-page: 4950 issn: 2041-1723 issue: 1 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b144 article-title: Deep learning for universal linear embeddings of nonlinear dynamics publication-title: Nature Commun doi: 10.1038/s41467-018-07210-0 – volume: 3 start-page: 91 year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b208 article-title: Mobile sensor networks and control: Adaptive sampling of spatiotemporal processes publication-title: Annu Rev Control Robot Auton Syst doi: 10.1146/annurev-control-073119-090634 – year: 2006 ident: 10.1016/j.mechatronics.2021.102576_b246 article-title: Belief space planning assuming maximum likelihood observations – volume: 29 start-page: 741 issue: 3 year: 1982 ident: 10.1016/j.mechatronics.2021.102576_b53 article-title: Inference of reversible languages publication-title: J ACM doi: 10.1145/322326.322334 – volume: 34 start-page: 707 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b101 article-title: Efficient informative sensing using multiple robots publication-title: J Artif Intell Res (JAIR) doi: 10.1613/jair.2674 – volume: 16 issue: 157 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b27 article-title: Optimal foraging and the information theory of gambling publication-title: J R Soc Interface doi: 10.1098/rsif.2019.0162 – volume: 29 start-page: 1050 issue: 4 year: 2013 ident: 10.1016/j.mechatronics.2021.102576_b248 article-title: Planning reliable paths with pose SLAM publication-title: IEEE Trans Robot doi: 10.1109/TRO.2013.2257577 – year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b136 article-title: Model-based control using Koopman operators – volume: 401 start-page: 911 issn: 1476-4687 issue: 6756 year: 1999 ident: 10.1016/j.mechatronics.2021.102576_b25 article-title: Optimizing the success of random searches publication-title: Nature doi: 10.1038/44831 – ident: 10.1016/j.mechatronics.2021.102576_b149 doi: 10.1109/CDC.2009.5399490 – volume: 26 start-page: 961 issue: 8 year: 2004 ident: 10.1016/j.mechatronics.2021.102576_b166 article-title: Application of the theory of optimal experiments to adaptive electromagnetic-induction sensing of buried targets publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2004.38 – year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b107 article-title: Data-driven measurement models for active localization in sparse environments – ident: 10.1016/j.mechatronics.2021.102576_b75 – ident: 10.1016/j.mechatronics.2021.102576_b189 doi: 10.1109/ICRA.2014.6907763 – start-page: 1329 year: 2008 ident: 10.1016/j.mechatronics.2021.102576_b288 article-title: A constraint generation approach to learning stable linear dynamical systems – volume: 5 issue: 42 year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b103 article-title: Bioinspired underwater legged robot for seabed exploration with low environmental disturbance publication-title: Science Robotics doi: 10.1126/scirobotics.aaz1012 – volume: 2 start-page: 3 year: 2014 ident: 10.1016/j.mechatronics.2021.102576_b223 article-title: Soft robotics: new perspectives for robot bodyware and control publication-title: Front Bioeng Biotechnol doi: 10.3389/fbioe.2014.00003 – ident: 10.1016/j.mechatronics.2021.102576_b102 doi: 10.1109/ICRA.2014.6907452 – ident: 10.1016/j.mechatronics.2021.102576_b284 doi: 10.1609/aaai.v33i01.33013387 – volume: vol. 2 start-page: 1398 year: 2002 ident: 10.1016/j.mechatronics.2021.102576_b260 article-title: Movement imitation with nonlinear dynamical systems in humanoid robots – volume: s2-42 start-page: 230 issn: 0024-6115 issue: 1 year: 1937 ident: 10.1016/j.mechatronics.2021.102576_b38 article-title: On computable numbers, with an application to the entscheidungsproblem publication-title: Proc Lond Math Soc doi: 10.1112/plms/s2-42.1.230 – volume: 33 start-page: 568 issue: 4 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b108 article-title: Nonparametric shape-restricted regression publication-title: Statist Sci doi: 10.1214/18-STS665 – start-page: 1823 year: 2010 ident: 10.1016/j.mechatronics.2021.102576_b109 article-title: Multilinear pose and body shape estimation of dressed subjects from image sets – volume: 15 start-page: 237 issue: 3 year: 1983 ident: 10.1016/j.mechatronics.2021.102576_b45 article-title: Inductive inference: Theory and methods publication-title: ACM Comput Surv doi: 10.1145/356914.356918 – year: 2008 ident: 10.1016/j.mechatronics.2021.102576_b295 – volume: 1 issue: 1 year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b34 article-title: Soft robotics: Technologies and systems pushing the boundaries of robot abilities publication-title: Science Robotics doi: 10.1126/scirobotics.aah3690 – volume: 65 start-page: 1773 issue: 9 year: 2006 ident: 10.1016/j.mechatronics.2021.102576_b148 article-title: Honey-pot constrained searching with local sensory information publication-title: Nonlinear Anal TMA doi: 10.1016/j.na.2005.10.049 – year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b280 – volume: 10 start-page: 285 issue: 4 year: 1991 ident: 10.1016/j.mechatronics.2021.102576_b150 article-title: Computational methods for task-directed sensor data fusion and sensor planning publication-title: Int J Robot Res doi: 10.1177/027836499101000401 – volume: 75 start-page: 291 issue: 2 year: 2014 ident: 10.1016/j.mechatronics.2021.102576_b242 article-title: Active SLAM and exploration with particle filters using Kullback-Leibler divergence publication-title: J Intell Robot Syst doi: 10.1007/s10846-013-9981-9 – year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b138 article-title: Local Koopman operators for data-driven control of robotic systems – ident: 10.1016/j.mechatronics.2021.102576_b194 doi: 10.1109/ICRA.2017.7989202 – ident: 10.1016/j.mechatronics.2021.102576_b174 doi: 10.1109/IROS.2005.1545070 – ident: 10.1016/j.mechatronics.2021.102576_b281 doi: 10.1109/CDC.2014.7039601 – ident: 10.1016/j.mechatronics.2021.102576_b222 doi: 10.1109/ROBOSOFT.2018.8404894 – ident: 10.1016/j.mechatronics.2021.102576_b98 – year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b137 article-title: Modeling and control of soft robots using the Koopman operator and model predictive control – volume: 240 start-page: 432 issn: 0167-2789 issue: 4 year: 2011 ident: 10.1016/j.mechatronics.2021.102576_b183 article-title: Metrics for ergodicity and design of ergodic dynamics for multi-agent systems publication-title: Physica D doi: 10.1016/j.physd.2010.10.010 – volume: 4 start-page: 129 year: 1996 ident: 10.1016/j.mechatronics.2021.102576_b56 article-title: Active learning with statistical models publication-title: J Artificial Intelligence Res doi: 10.1613/jair.295 – year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b193 – volume: 33 start-page: 301 issue: 3 year: 2004 ident: 10.1016/j.mechatronics.2021.102576_b7 article-title: Sensorimotor control of navigation in arthropod and artificial systems publication-title: Arthropod Struct Develop doi: 10.1016/j.asd.2004.05.009 – start-page: 291 year: 2005 ident: 10.1016/j.mechatronics.2021.102576_b182 article-title: Ergodic dynamics by design: A route to predictable multi-robot systems – volume: 73 start-page: 145 issn: 1077-3142 issue: 2 year: 1999 ident: 10.1016/j.mechatronics.2021.102576_b187 article-title: Sensor planning for 3D object search publication-title: Comput Vis Image Underst doi: 10.1006/cviu.1998.0736 – ident: 10.1016/j.mechatronics.2021.102576_b241 doi: 10.1109/ICRA.2015.7139224 – year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b290 article-title: Physics-informed autoencoders for Lyapunov-stable fluid flow prediction publication-title: ArXiv – volume: 16 start-page: 1437 issue: 42 year: 2015 ident: 10.1016/j.mechatronics.2021.102576_b80 article-title: A comprehensive survey on safe reinforcement learning publication-title: J Mach Learn Res – volume: 22 start-page: 46 issue: 6 year: 1989 ident: 10.1016/j.mechatronics.2021.102576_b96 article-title: Using occupancy grids for mobile robot perception and navigation publication-title: Computer doi: 10.1109/2.30720 – ident: 10.1016/j.mechatronics.2021.102576_b92 doi: 10.1117/12.719395 – ident: 10.1016/j.mechatronics.2021.102576_b110 doi: 10.1109/ICCV.2001.937519 – year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b135 – start-page: 6957 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b211 article-title: Ergodic flocking – volume: 3 start-page: 2987 issue: 4 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b270 article-title: Decentralized ergodic control: Distribution-driven sensing and exploration for multi-agent systems publication-title: IEEE Robot Autom Lett doi: 10.1109/LRA.2018.2849588 – volume: 59 start-page: 876 issue: 4 year: 2014 ident: 10.1016/j.mechatronics.2021.102576_b274 article-title: Rapidly exponentially stabilizing control Lyapunov functions and hybrid zero dynamics publication-title: IEEE Trans Automat Control doi: 10.1109/TAC.2014.2299335 – volume: 208 start-page: 59 issue: 5005 year: 1965 ident: 10.1016/j.mechatronics.2021.102576_b4 article-title: Osmotropotaxis in the honey-bee publication-title: Nature doi: 10.1038/208059a0 – volume: 1 start-page: 391 issn: 2158-2491 year: 2014 ident: 10.1016/j.mechatronics.2021.102576_b131 article-title: On dynamic mode decomposition: Theory and applications publication-title: J Comput Dyn doi: 10.3934/jcd.2014.1.391 – volume: 18 start-page: 1827 issue: 6 year: 2013 ident: 10.1016/j.mechatronics.2021.102576_b229 article-title: Sensor-driven online coverage planning for autonomous underwater vehicles publication-title: IEEE/ASME Trans Mechatronics doi: 10.1109/TMECH.2012.2213607 – volume: 32 year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b198 article-title: Sequential action control: Closed-form optimal control for nonlinear and nonsmooth systems publication-title: IEEE Trans Rob – volume: 5 issue: 41 year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b145 article-title: Electronic skins and machine learning for intelligent soft robots publication-title: Science Robotics doi: 10.1126/scirobotics.aaz9239 – volume: 78 start-page: 262 year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b78 article-title: Sim-to-real robot learning from pixels with progressive nets – volume: 29 start-page: 31 issue: 11 year: 1998 ident: 10.1016/j.mechatronics.2021.102576_b157 article-title: Active vision system based on information theory publication-title: Syst Comput Japan doi: 10.1002/(SICI)1520-684X(199810)29:11<31::AID-SCJ4>3.0.CO;2-T – volume: 4 start-page: 169 issue: 1 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b23 article-title: Dynamical system segmentation for information measures in motion publication-title: IEEE Robot Autom Lett doi: 10.1109/LRA.2018.2884091 – ident: 10.1016/j.mechatronics.2021.102576_b87 – volume: 198 start-page: 203 issue: 2 year: 2000 ident: 10.1016/j.mechatronics.2021.102576_b203 article-title: Mechanisms of animal navigation in odor plumes publication-title: Biol Bull doi: 10.2307/1542524 – volume: 42 issue: 43 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b26 article-title: Optimal search behavior and classic foraging theory publication-title: J Phys A doi: 10.1088/1751-8113/42/43/434002 – volume: 13 start-page: 16 issn: 1070-9932 issue: 3 year: 2006 ident: 10.1016/j.mechatronics.2021.102576_b162 article-title: Cooperative air and ground surveillance publication-title: IEEE Robot Autom Magaz doi: 10.1109/MRA.2006.1678135 – year: 2013 ident: 10.1016/j.mechatronics.2021.102576_b285 – volume: 185 start-page: 60 year: 1951 ident: 10.1016/j.mechatronics.2021.102576_b37 article-title: A machine that learns publication-title: Sci Am doi: 10.1038/scientificamerican0851-60 – start-page: 1168 year: 2014 ident: 10.1016/j.mechatronics.2021.102576_b192 article-title: Control-limited differential dynamic programming – ident: 10.1016/j.mechatronics.2021.102576_b122 doi: 10.1109/ROBOT.2000.844072 – volume: 5 start-page: 24 issue: 1 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b124 article-title: A data-efficient geometrically inspired polynomial kernel for robot inverse dynamic publication-title: IEEE Robot Autom Lett – start-page: 1 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b258 article-title: End-to-end driving via conditional imitation learning – start-page: 3812 year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b267 article-title: Infogail: Interpretable imitation learning from visual demonstrations – volume: 529 start-page: 484 issue: 7587 year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b259 article-title: Mastering the game of go with deep neural networks and tree search publication-title: Nature doi: 10.1038/nature16961 – volume: 3 start-page: 23 issue: 1 year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b220 article-title: Soft robotic grippers for biological sampling on deep reefs publication-title: Soft Robot doi: 10.1089/soro.2015.0019 – volume: vol. 87 start-page: 466 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b292 article-title: The Lyapunov neural network: Adaptive stability certification for safe learning of dynamical systems – volume: 27 start-page: 379 year: 1948 ident: 10.1016/j.mechatronics.2021.102576_b171 article-title: A mathematical theory of communication publication-title: Bell Syst Tech J doi: 10.1002/j.1538-7305.1948.tb01338.x – volume: 37 start-page: 50 issue: 3 year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b273 article-title: Federated learning: Challenges, methods, and future directions publication-title: IEEE Signal Process Mag doi: 10.1109/MSP.2020.2975749 – volume: 4 start-page: 89 issue: 2 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b206 article-title: Tutorial on the generation of ergodic trajectories with projection-based gradient descent publication-title: IET Cyber-Phys Syst Theory Appl doi: 10.1049/iet-cps.2018.5032 – start-page: 9 year: 2005 ident: 10.1016/j.mechatronics.2021.102576_b262 article-title: Active learning for outdoor obstacle detection – volume: 1 start-page: 44 issue: 1 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b49 article-title: Learnability can be undecidable publication-title: Nat Mach Intell doi: 10.1038/s42256-018-0002-3 – ident: 10.1016/j.mechatronics.2021.102576_b231 doi: 10.1609/icaps.v22i1.13529 – ident: 10.1016/j.mechatronics.2021.102576_b200 doi: 10.1109/IROS.2015.7354071 – ident: 10.1016/j.mechatronics.2021.102576_b91 – volume: 93 start-page: 3320 issue: 6 year: 1993 ident: 10.1016/j.mechatronics.2021.102576_b225 article-title: Biophysics of the cochlea: linear approximation publication-title: J Acoust Soc Am doi: 10.1121/1.405716 – ident: 10.1016/j.mechatronics.2021.102576_b213 doi: 10.1109/IROS.2017.8206410 – volume: 39 start-page: 389 issue: 3 year: 2015 ident: 10.1016/j.mechatronics.2021.102576_b264 article-title: Active reward learning with a novel acquisition function publication-title: Auton Robots doi: 10.1007/s10514-015-9454-z – volume: 10 start-page: 447 issue: 5 year: 1967 ident: 10.1016/j.mechatronics.2021.102576_b41 article-title: Language identification in the limit publication-title: Inf Control doi: 10.1016/S0019-9958(67)91165-5 – ident: 10.1016/j.mechatronics.2021.102576_b244 doi: 10.1109/ICRA.2015.7139863 – start-page: 165 year: 1976 ident: 10.1016/j.mechatronics.2021.102576_b28 article-title: Animal play: Problems and perspectives doi: 10.1007/978-1-4615-7572-6_4 – ident: 10.1016/j.mechatronics.2021.102576_b188 doi: 10.5244/C.12.78 – start-page: 52 year: 2000 ident: 10.1016/j.mechatronics.2021.102576_b245 article-title: Planning with incomplete information as heuristic search in belief space – volume: 153 start-page: 34 issue: 3731 year: 1966 ident: 10.1016/j.mechatronics.2021.102576_b64 article-title: Dynamic programming publication-title: Science doi: 10.1126/science.153.3731.34 – ident: 10.1016/j.mechatronics.2021.102576_b159 – start-page: 11126 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b81 article-title: Learning stable deep dynamics models – start-page: 379 year: 2000 ident: 10.1016/j.mechatronics.2021.102576_b35 article-title: A historical perspective of robotics doi: 10.1007/978-94-015-9554-4_43 – volume: 32 start-page: 3 issue: 1 year: 2013 ident: 10.1016/j.mechatronics.2021.102576_b165 article-title: Active planning for underwater inspection and the benefit of adaptivity publication-title: Int J Robot Res doi: 10.1177/0278364912467485 – year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b297 – volume: 5 issue: 48 year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b104 article-title: Revealing ocean-scale biochemical structure with a deep-diving vertical profiling autonomous vehicle publication-title: Science Robotics doi: 10.1126/scirobotics.abc7104 – volume: 35 start-page: 1 issue: 1 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b254 article-title: Attention and anticipation in fast visual-inertial navigation publication-title: IEEE Trans Robot doi: 10.1109/TRO.2018.2872402 – volume: 23 start-page: 2015 issue: 15 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b117 article-title: Model learning with local Gaussian process regression publication-title: Adv Robot doi: 10.1163/016918609X12529286896877 – ident: 10.1016/j.mechatronics.2021.102576_b74 – volume: 22 start-page: 7 issue: 1 year: 2003 ident: 10.1016/j.mechatronics.2021.102576_b147 article-title: Dynamic sensor planning and control for optimally tracking targets publication-title: Int J Robot Res doi: 10.1177/0278364903022001002 – volume: 589 start-page: 386 issn: 1476-4687 issue: 7842 year: 2021 ident: 10.1016/j.mechatronics.2021.102576_b16 article-title: A reprogrammable mechanical metamaterial with stable memory publication-title: Nature doi: 10.1038/s41586-020-03123-5 – volume: 11 start-page: 249 issue: 3 year: 2001 ident: 10.1016/j.mechatronics.2021.102576_b11 article-title: Active sensing capabilities of the rat whisker system publication-title: Auton Robots doi: 10.1023/A:1012439023425 – year: 2004 ident: 10.1016/j.mechatronics.2021.102576_b170 – volume: 38 start-page: 316 issue: 2–3 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b271 article-title: Dec-MCTS: Decentralized planning for multi-robot active perception publication-title: Int J Robot Res doi: 10.1177/0278364918755924 – issn: 2522-5839 year: 2021 ident: 10.1016/j.mechatronics.2021.102576_b15 article-title: Integration of deep learning and soft robotics for a biomimetic approach to nonlinear sensing publication-title: Nat Mach Intell doi: 10.1038/s42256-021-00330-1 – volume: 45 start-page: 983 issue: 6 year: 1998 ident: 10.1016/j.mechatronics.2021.102576_b47 article-title: Efficient noise-tolerant learning from statistical queries publication-title: J ACM doi: 10.1145/293347.293351 – ident: 10.1016/j.mechatronics.2021.102576_b99 doi: 10.1007/978-3-662-44845-8_43 – volume: 9 year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b13 article-title: Tuning movement for sensing in an uncertain world publication-title: ELIfe doi: 10.7554/eLife.52371 – volume: 28 start-page: 357 issue: 3 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b236 article-title: Decentralized, adaptive coverage control for networked robots publication-title: Int J Robot Res doi: 10.1177/0278364908100177 – ident: 10.1016/j.mechatronics.2021.102576_b269 – volume: 27 start-page: 2204 year: 2014 ident: 10.1016/j.mechatronics.2021.102576_b253 article-title: Recurrent models of visual attention publication-title: Adv Neural Inf Process Syst – ident: 10.1016/j.mechatronics.2021.102576_b152 doi: 10.1109/ICCV.2003.1238372 – volume: 37 start-page: 408 issue: 2 year: 2015 ident: 10.1016/j.mechatronics.2021.102576_b128 article-title: Gaussian Processes for data-efficient learning in robotics and control publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2013.218 – volume: 3 start-page: 85 issue: 1 year: 1966 ident: 10.1016/j.mechatronics.2021.102576_b190 article-title: A second-order gradient method for determining optimal trajectories of non-linear discrete-time systems publication-title: Internat J Control doi: 10.1080/00207176608921369 – start-page: 65 year: 2003 ident: 10.1016/j.mechatronics.2021.102576_b125 article-title: BayesIan kernel methods – volume: 54 start-page: 314 issue: 4 year: 2006 ident: 10.1016/j.mechatronics.2021.102576_b177 article-title: Planning exploration strategies for simultaneous localization and mapping publication-title: Robot Auton Syst doi: 10.1016/j.robot.2005.11.006 – year: 2021 ident: 10.1016/j.mechatronics.2021.102576_b76 – start-page: 23 year: 2008 ident: 10.1016/j.mechatronics.2021.102576_b100 article-title: Adaptive multi-robot wide-area exploration and mapping – year: 2012 ident: 10.1016/j.mechatronics.2021.102576_b175 – volume: 61 start-page: 1258 issue: 12 year: 2013 ident: 10.1016/j.mechatronics.2021.102576_b232 article-title: A survey on coverage path planning for robotics publication-title: Robot Auton Syst doi: 10.1016/j.robot.2013.09.004 – volume: 33 start-page: 661 issue: 3 year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b278 article-title: Safety barrier certificates for collisions-free multirobot systems publication-title: IEEE Trans Robot doi: 10.1109/TRO.2017.2659727 – year: 2013 ident: 10.1016/j.mechatronics.2021.102576_b57 article-title: Statistical active learning algorithms – start-page: 421 year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b115 article-title: Experimental applications of the Koopman operator in active learning for control doi: 10.1007/978-3-030-35713-9_16 – year: 2006 ident: 10.1016/j.mechatronics.2021.102576_b139 – volume: 26 start-page: 651 issue: 8 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b230 article-title: Coverage path planning algorithms for agricultural field machines publication-title: J Field Robotics doi: 10.1002/rob.20300 – volume: 433 start-page: 595 issue: 7026 year: 2005 ident: 10.1016/j.mechatronics.2021.102576_b226 article-title: Motor control of flexible octopus arms publication-title: Nature doi: 10.1038/433595a – year: 2005 ident: 10.1016/j.mechatronics.2021.102576_b127 – volume: 24 start-page: 145 issue: 2 year: 2002 ident: 10.1016/j.mechatronics.2021.102576_b160 article-title: Information theoretic sensor data selection for active object recognition and state estimation publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/34.982896 – ident: 10.1016/j.mechatronics.2021.102576_b84 doi: 10.1109/CDC.2014.7039601 – volume: SMC-13 start-page: 834 issue: 5 year: 1983 ident: 10.1016/j.mechatronics.2021.102576_b63 article-title: Neuronlike adaptive elements that can solve difficult learning control problems publication-title: IEEE Trans Syst Man Cybern doi: 10.1109/TSMC.1983.6313077 – volume: 3 start-page: 1 issue: 1 year: 2012 ident: 10.1016/j.mechatronics.2021.102576_b8 article-title: Rats track odour trails accurately using a multi-layered strategy with near-optimal sampling publication-title: Nature Commun doi: 10.1038/ncomms1712 – volume: 36 start-page: 929 issue: 4 year: 1989 ident: 10.1016/j.mechatronics.2021.102576_b51 article-title: Learnability and the vapnik-chervonenkis dimension publication-title: J ACM doi: 10.1145/76359.76371 – volume: 3 start-page: 316 issn: 2522-5839 issue: 4 year: 2021 ident: 10.1016/j.mechatronics.2021.102576_b118 article-title: Teaching recurrent neural networks to infer global temporal structure from local examples publication-title: Nat Mach Intell doi: 10.1038/s42256-021-00321-2 – volume: 30 start-page: 1343 issue: 11 year: 2011 ident: 10.1016/j.mechatronics.2021.102576_b252 article-title: Active vision in robotic systems: A survey of recent developments publication-title: Int J Robot Res doi: 10.1177/0278364911410755 – volume: 62 start-page: 3861 issue: 8 year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b277 article-title: Control barrier function based quadratic programs for safety critical systems publication-title: IEEE Trans Automat Control doi: 10.1109/TAC.2016.2638961 – ident: 10.1016/j.mechatronics.2021.102576_b97 doi: 10.1109/ICRA.2013.6630605 – ident: 10.1016/j.mechatronics.2021.102576_b32 doi: 10.1109/ICRA.2016.7487176 – ident: 10.1016/j.mechatronics.2021.102576_b205 doi: 10.1007/978-3-030-44051-0_16 – start-page: 681 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b142 article-title: Time-frequency deep representation learning for speech emotion recognition integrating self-attention doi: 10.1007/978-3-030-36808-1_74 – volume: 49 start-page: 232 issue: 1 year: 2013 ident: 10.1016/j.mechatronics.2021.102576_b237 article-title: Spatially distributed area coverage optimisation in mobile robotic networks with arbitrary convex anisotropic patterns publication-title: Automatica doi: 10.1016/j.automatica.2012.09.012 – year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b18 – volume: 365 start-page: 1180 issue: 6458 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b29 article-title: Behavioral and neural correlates of hide-and-seek in rats publication-title: Science doi: 10.1126/science.aax4705 – volume: 27 start-page: 1134 issue: 11 year: 1984 ident: 10.1016/j.mechatronics.2021.102576_b43 article-title: A theory of the learnable publication-title: Commun ACM doi: 10.1145/1968.1972 – volume: 57 start-page: 469 issue: 5 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b256 article-title: A survey of robot learning from demonstration publication-title: Robot Auton Syst doi: 10.1016/j.robot.2008.10.024 – volume: 2 start-page: 265 issn: 2405-9188 issue: 4 year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b140 article-title: An overview on data representation learning: From traditional feature learning to recent deep learning publication-title: J Financ Data Sci doi: 10.1016/j.jfds.2017.05.001 – start-page: 515 year: 2015 ident: 10.1016/j.mechatronics.2021.102576_b249 article-title: Scaling up Gaussian belief space planning through covariance-free trajectory optimization and automatic differentiation – volume: 39 start-page: 672 issue: 3 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b186 article-title: Information-driven sensor path planning by approximate cell decomposition publication-title: IEEE Trans Syst Man Cybern doi: 10.1109/TSMCB.2008.2008561 – ident: 10.1016/j.mechatronics.2021.102576_b217 doi: 10.1109/ACC.2013.6580484 – volume: 117 start-page: 240 issn: 0890-5401 issue: 2 year: 1995 ident: 10.1016/j.mechatronics.2021.102576_b48 article-title: Learning by distances publication-title: Inform and Comput doi: 10.1006/inco.1995.1042 – volume: 34 start-page: 62 issue: 1 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b216 article-title: Real-time area coverage and target localization using receding-horizon ergodic exploration publication-title: IEEE Trans Robot doi: 10.1109/TRO.2017.2766265 – year: 2015 ident: 10.1016/j.mechatronics.2021.102576_b176 – start-page: 3803 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b77 article-title: Sim-to-real transfer of robotic control with dynamics randomization – volume: 4 start-page: 6079 issue: 29 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b24 article-title: Ergodicity reveals assistance and learning in physical human robot interaction publication-title: Sci Robot doi: 10.1126/scirobotics.aav6079 – volume: 22 start-page: 701 year: 2015 ident: 10.1016/j.mechatronics.2021.102576_b238 article-title: A dynamical systems approach to the surface search for debris associated with the disappearance of flight MH370 publication-title: Nonlin Process Geophys doi: 10.5194/npg-22-701-2015 – volume: 40 start-page: 201 issue: 3 year: 1981 ident: 10.1016/j.mechatronics.2021.102576_b61 article-title: Associative search network: A reinforcement learning associative memory publication-title: Biol Cybernet doi: 10.1007/BF00453370 – volume: 9 start-page: 16 issue: 1 year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b251 article-title: Visual SLAM algorithms: a survey from 2010 to 2016 publication-title: IPSJ Trans Comput Vision Appl doi: 10.1186/s41074-017-0027-2 – volume: 37 start-page: 405 issue: 4–5 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b73 article-title: The limits and potentials of deep learning for robotics publication-title: Int J Robot Res doi: 10.1177/0278364918770733 – volume: 59 start-page: 433 issue: 236 year: 1950 ident: 10.1016/j.mechatronics.2021.102576_b39 article-title: Computing machinery and intelligence publication-title: Mind doi: 10.1093/mind/LIX.236.433 – volume: 6 issue: 50 year: 2021 ident: 10.1016/j.mechatronics.2021.102576_b105 article-title: A system of coordinated autonomous robots for Lagrangian studies of microbes in the oceanic deep chlorophyll maximum publication-title: Science Robotics doi: 10.1126/scirobotics.abb9138 – volume: 28 start-page: 1448 issue: 11–12 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b247 article-title: The belief roadmap: Efficient planning in belief space by factoring the covariance publication-title: Int J Robot Res doi: 10.1177/0278364909341659 – start-page: 66 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b19 article-title: Morphological computation–connecting brain, body, and environment – ident: 10.1016/j.mechatronics.2021.102576_b68 – year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b263 article-title: From inverse optimal control to inverse reinforcement learning: A historical review publication-title: Annu Rev Control doi: 10.1016/j.arcontrol.2020.06.001 – year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b266 – volume: 85 start-page: 607 issue: 3 year: 2005 ident: 10.1016/j.mechatronics.2021.102576_b158 article-title: Sensor management using an active sensing approach publication-title: Signal Process doi: 10.1016/j.sigpro.2004.11.004 – year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b119 article-title: Differentiable algorithm networks for composable robot learning publication-title: Robot Sci Syst doi: 10.15607/RSS.2019.XV.039 – volume: 17 start-page: 315 issue: 5 year: 1931 ident: 10.1016/j.mechatronics.2021.102576_b130 article-title: Hamiltonian systems and transformation in Hilbert space publication-title: Proc Natl Acad Sci doi: 10.1073/pnas.17.5.315 – volume: 40 start-page: 435 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b224 article-title: Morphologically induced stability on an underwater legged robot with a deformable body publication-title: Int J Robot Res doi: 10.1177/0278364919840426 – year: 1954 ident: 10.1016/j.mechatronics.2021.102576_b36 – volume: 25 start-page: 1307 issn: 1432-1467 year: 2015 ident: 10.1016/j.mechatronics.2021.102576_b132 article-title: A data–driven approximation of the Koopman operator: Extending dynamic mode decomposition publication-title: J Nonlinear Sci doi: 10.1007/s00332-015-9258-5 – volume: 29 start-page: 2172 year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b268 article-title: Infogan: Interpretable representation learning by information maximizing generative adversarial nets publication-title: Adv Neural Inf Process Syst – volume: 369 start-page: 915 issn: 0036-8075 issue: 6506 year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b71 article-title: The foundation of efficient robot learning publication-title: Science doi: 10.1126/science.aaz7597 – volume: 2 start-page: 319 issue: 4 year: 1988 ident: 10.1016/j.mechatronics.2021.102576_b55 article-title: Queries and concept learning publication-title: Mach Learn doi: 10.1007/BF00116828 – volume: 88 start-page: 135 issue: 2 year: 1981 ident: 10.1016/j.mechatronics.2021.102576_b62 article-title: Toward a modern theory of adaptive networks: Expectation and prediction publication-title: Psychol Rev doi: 10.1037/0033-295X.88.2.135 – volume: 4 issue: 1 year: 2021 ident: 10.1016/j.mechatronics.2021.102576_b129 article-title: Koopman operators for estimation and control of dynamical systems publication-title: Annu Rev Control Robotic Auton Syst – ident: 10.1016/j.mechatronics.2021.102576_b90 – ident: 10.1016/j.mechatronics.2021.102576_b88 doi: 10.1109/ICRA.2012.6225244 – volume: 46 start-page: 1691 issue: 7 year: 2016 ident: 10.1016/j.mechatronics.2021.102576_b123 article-title: Learning the inverse dynamics of robotic manipulators in structured reproducing kernel Hilbert space publication-title: IEEE Trans Cybern doi: 10.1109/TCYB.2015.2454334 – volume: vol. 2 start-page: 65 year: 2005 ident: 10.1016/j.mechatronics.2021.102576_b240 article-title: Information gain-based exploration using rao-blackwellized particle filters – volume: 76 start-page: 996 issue: 8 year: 1988 ident: 10.1016/j.mechatronics.2021.102576_b1 article-title: Active perception publication-title: Proc IEEE doi: 10.1109/5.5968 – year: 2021 ident: 10.1016/j.mechatronics.2021.102576_b83 – ident: 10.1016/j.mechatronics.2021.102576_b155 doi: 10.1109/ICCV.1999.791227 – volume: 33 start-page: 1271 issue: 9 year: 2014 ident: 10.1016/j.mechatronics.2021.102576_b201 article-title: Sampling-based robotic information gathering algorithms publication-title: Int J Robot Res doi: 10.1177/0278364914533443 – ident: 10.1016/j.mechatronics.2021.102576_b276 doi: 10.23919/ECC.2019.8796030 – volume: 2 start-page: 827 issue: 2 year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b111 article-title: Ergodic exploration using binary sensing for non-parametric shape estimation publication-title: IEEE Robot Autom Lett doi: 10.1109/LRA.2017.2654542 – volume: 58 start-page: 574 issue: 5 year: 2010 ident: 10.1016/j.mechatronics.2021.102576_b202 article-title: Particle filter based information-theoretic active sensing publication-title: Robot Auton Syst doi: 10.1016/j.robot.2010.01.001 – volume: 327 start-page: 701 issue: 5966 year: 2010 ident: 10.1016/j.mechatronics.2021.102576_b6 article-title: Optimal localization by pointing off axis publication-title: Science doi: 10.1126/science.1183310 – volume: 4 start-page: 1 issue: 1 year: 2013 ident: 10.1016/j.mechatronics.2021.102576_b10 article-title: Stereo and serial sniffing guide navigation to an odour source in a mammal publication-title: Nature Commun doi: 10.1038/ncomms2444 – volume: 521 start-page: 436 issn: 1476-4687 issue: 7553 year: 2015 ident: 10.1016/j.mechatronics.2021.102576_b2 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – volume: 5 start-page: 10487 issn: 2045-2322 issue: 1 year: 2015 ident: 10.1016/j.mechatronics.2021.102576_b14 article-title: Information processing via physical soft body publication-title: Sci Rep doi: 10.1038/srep10487 – volume: 9 start-page: 864 issue: 6 year: 1998 ident: 10.1016/j.mechatronics.2021.102576_b167 article-title: Optimal experiment design publication-title: Meas Sci Technol doi: 10.1088/0957-0233/9/6/003 – volume: 32 start-page: 1587 issue: 11 year: 1996 ident: 10.1016/j.mechatronics.2021.102576_b286 article-title: Realization of stable models with subspace methods publication-title: Automatica doi: 10.1016/S0005-1098(96)00104-5 – ident: 10.1016/j.mechatronics.2021.102576_b243 doi: 10.1109/IROS.2006.282530 – year: 2013 ident: 10.1016/j.mechatronics.2021.102576_b126 doi: 10.1017/CBO9781139626514 – volume: 20 start-page: 158 issue: 2 year: 1913 ident: 10.1016/j.mechatronics.2021.102576_b59 article-title: Psychology as the behaviorist views it publication-title: Psychol Rev doi: 10.1037/h0074428 – start-page: 678 year: 2014 ident: 10.1016/j.mechatronics.2021.102576_b146 article-title: Adaptive category mapping networks for all-mode topological feature learning used for mobile robot vision – start-page: 3389 year: 2017 ident: 10.1016/j.mechatronics.2021.102576_b70 article-title: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates – volume: 4 issue: 27 year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b106 article-title: Toward adaptive robotic sampling of phytoplankton in the coastal ocean publication-title: Science Robotics doi: 10.1126/scirobotics.aav3041 – volume: 65 start-page: 386 issue: 6 year: 1958 ident: 10.1016/j.mechatronics.2021.102576_b44 article-title: The perceptron: A probabilistic model for information storage and organization in the brain publication-title: Psychol Rev doi: 10.1037/h0042519 – year: 2019 ident: 10.1016/j.mechatronics.2021.102576_b17 – ident: 10.1016/j.mechatronics.2021.102576_b282 doi: 10.1109/CDC.2017.8263977 – year: 2020 ident: 10.1016/j.mechatronics.2021.102576_b291 – year: 1985 ident: 10.1016/j.mechatronics.2021.102576_b181 – volume: 34 start-page: 457 issue: 4–5 year: 2015 ident: 10.1016/j.mechatronics.2021.102576_b250 article-title: Active visual SLAM for robotic area coverage: Theory and experiment publication-title: Int J Robot Res doi: 10.1177/0278364914547893 – volume: 324 start-page: 81 issn: 0036-8075 issue: 5923 year: 2009 ident: 10.1016/j.mechatronics.2021.102576_b113 article-title: Distilling free-form natural laws from experimental data publication-title: Science doi: 10.1126/science.1165893 – volume: 18 start-page: 70 issn: 0027-8424 issue: 1 year: 1932 ident: 10.1016/j.mechatronics.2021.102576_b180 article-title: Proof of the quasi-ergodic hypothesis publication-title: Proc Natl Acad Sci doi: 10.1073/pnas.18.1.70 – ident: 10.1016/j.mechatronics.2021.102576_b287 – start-page: 219 year: 2013 ident: 10.1016/j.mechatronics.2021.102576_b275 article-title: Towards the unification of locomotion and manipulation through control Lyapunov functions and quadratic programs – volume: 34 start-page: 829 issue: 3 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b239 article-title: On the importance of uncertainty representation in active SLAM publication-title: IEEE Trans Robot doi: 10.1109/TRO.2018.2808902 – start-page: 631 year: 2018 ident: 10.1016/j.mechatronics.2021.102576_b294 article-title: Robot creation from functional specifications |
| SSID | ssj0017117 |
| Score | 2.5544732 |
| Snippet | Active learning is a decision-making process. In both abstract and physical settings, active learning demands both analysis and action. This is a review of... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 102576 |
| SubjectTerms | Active learning Artificial intelligence Learning theory Perception and sensing Robot control Robotics |
| Title | Active learning in robotics: A review of control principles |
| URI | https://dx.doi.org/10.1016/j.mechatronics.2021.102576 |
| Volume | 77 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NS8NAEB1KvehB_MT6UfbgNdbdbJKN4iEUS1XsRQu9hd3NRiualFqv_nYzm02p4KHgMWEHksfwZkjevAE4z4Kc56h5ynyWeTzLfE9VZdOTJogNN5SaGIeTH0fhcMzvJ8GkBf1mFgZllY77a063bO3u9Byavdl02nuqmgMsh4JRW0hxiI_zCLP84nsp86ARtVt38bCHpxvjUavx-jD6Vda7ZtC6m1F0MgjQf-SvIrVSeAY7sO06RpLUD7ULLVPswdaKj-A-XCeWtYhbAfFCpgWZl6pEC-YrkpB6PoWUOXHKdDJrvrF_HsB4cPvcH3puK4KnKzJYVFBGOJ_NZVC9G5NMhllocqqozowdG6VS0UjGTFDOTMQN_j-5pEKGQlApQ_8Q2kVZmCMgWuRKR0wqKQVXhimhKHYoMgqVL7TfgbiBIdXOMhw3V7ynjTbsLV2FMEUI0xrCDvjL2FltnLFW1E2DdvorDdKK4deIP_5n_Als4lWt8DuF9mL-Zc6qrmOhujaturCR3D0MRz_o09hY |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV09T8MwED2VMgAD4lOUTw-sodhxEgfEUFVUBdoutFK3yE4cKIKkKmXlt-NLnKpIDJVYE5-UPNnvTsm7dwCXiZfyFDVPicsShyeJ6yiTNh2pvVBzTakOsTm5P_C7I_449sY1aFe9MCirtNxfcnrB1vZK06LZnE4mzWdTHGA6FIwWiTRcg3Vuji-OMbj6Xug8aECLsbu42sHllfNoIfL60PGrLIfNoHc3o2hl4KEByV9ZainzdHZg25aMpFU-1S7UdLYHW0tGgvtw2ypoi9gZEC9kkpFZrnL0YL4hLVI2qJA8JVaaTqbVR_bPAxh17oftrmPHIjixYYO5wTLABm0uPfNuTDLpJ75OqaJxoou-USoVDWTIBOVMB1zjD5RrKqQvBJXSdw-hnuWZPgISi1TFAZNKSsGVZkooiiWKDHzlithtQFjBEMXWMxxHV7xHlTjsLVqGMEIIoxLCBriL2GnpnLFS1F2FdvRrH0SG4leIP_5n_AVsdIf9XtR7GDydwCbeKeV-p1Cfz770mSlB5uq82GI__PLZ5g |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Active+learning+in+robotics%3A+A+review+of+control+principles&rft.jtitle=Mechatronics+%28Oxford%29&rft.au=Taylor%2C+Annalisa+T.&rft.au=Berrueta%2C+Thomas+A.&rft.au=Murphey%2C+Todd+D.&rft.date=2021-08-01&rft.issn=0957-4158&rft.volume=77&rft.spage=102576&rft_id=info:doi/10.1016%2Fj.mechatronics.2021.102576&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_mechatronics_2021_102576 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0957-4158&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0957-4158&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0957-4158&client=summon |