A versatile door opening system with mobile manipulator through adaptive position-force control and reinforcement learning
The ability of robots to navigate through doors is crucial for their effective operation in indoor environments. Consequently, extensive research has been conducted to develop robots capable of opening specific doors. However, the diverse combinations of door handles and opening directions necessita...
Saved in:
Published in | Robotics and autonomous systems Vol. 180; p. 104760 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Elsevier B.V
01.10.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The ability of robots to navigate through doors is crucial for their effective operation in indoor environments. Consequently, extensive research has been conducted to develop robots capable of opening specific doors. However, the diverse combinations of door handles and opening directions necessitate a more versatile door opening system for robots to successfully operate in real-world environments. In this paper, we propose a mobile manipulator system that can autonomously open various doors without prior knowledge. By using convolutional neural networks, point cloud extraction techniques, and external force measurements during exploratory motion, we obtained information regarding handle types, poses, and door characteristics. Through two different approaches, adaptive position-force control and deep reinforcement learning, we successfully opened doors without precise trajectory or excessive external force. The adaptive position-force control method involves moving the end-effector in the direction of the door opening while responding compliantly to external forces, ensuring safety and manipulator workspace. Meanwhile, the deep reinforcement learning policy minimizes applied forces and eliminates unnecessary movements, enabling stable operation across doors with different poses and widths. The RL-based approach outperforms the adaptive position-force control method in terms of compensating for external forces, ensuring smooth motion, and achieving efficient speed. It reduces the maximum force required by 3.27 times and improves motion smoothness by 1.82 times. However, the non-learning-based adaptive position-force control method demonstrates more versatility in opening a wider range of doors, encompassing revolute doors with four distinct opening directions and varying widths.
•Versatile mobile manipulator door opening system without prior knowledge.•Applicable to doors with various handle types and different kinematic constraints.•Adaptive position-force control-based and RL-based systems for adaptive door opening.•Extensive evaluation in real-world scenarios. |
---|---|
AbstractList | The ability of robots to navigate through doors is crucial for their effective operation in indoor environments. Consequently, extensive research has been conducted to develop robots capable of opening specific doors. However, the diverse combinations of door handles and opening directions necessitate a more versatile door opening system for robots to successfully operate in real-world environments. In this paper, we propose a mobile manipulator system that can autonomously open various doors without prior knowledge. By using convolutional neural networks, point cloud extraction techniques, and external force measurements during exploratory motion, we obtained information regarding handle types, poses, and door characteristics. Through two different approaches, adaptive position-force control and deep reinforcement learning, we successfully opened doors without precise trajectory or excessive external force. The adaptive position-force control method involves moving the end-effector in the direction of the door opening while responding compliantly to external forces, ensuring safety and manipulator workspace. Meanwhile, the deep reinforcement learning policy minimizes applied forces and eliminates unnecessary movements, enabling stable operation across doors with different poses and widths. The RL-based approach outperforms the adaptive position-force control method in terms of compensating for external forces, ensuring smooth motion, and achieving efficient speed. It reduces the maximum force required by 3.27 times and improves motion smoothness by 1.82 times. However, the non-learning-based adaptive position-force control method demonstrates more versatility in opening a wider range of doors, encompassing revolute doors with four distinct opening directions and varying widths.
•Versatile mobile manipulator door opening system without prior knowledge.•Applicable to doors with various handle types and different kinematic constraints.•Adaptive position-force control-based and RL-based systems for adaptive door opening.•Extensive evaluation in real-world scenarios. |
ArticleNumber | 104760 |
Author | Shim, David Hyunchul Seong, Hyunki Lee, Daegyu Kang, Gyuree |
Author_xml | – sequence: 1 givenname: Gyuree orcidid: 0000-0001-7769-4651 surname: Kang fullname: Kang, Gyuree email: fingb20@kaist.ac.kr organization: School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea – sequence: 2 givenname: Hyunki orcidid: 0000-0002-7169-3006 surname: Seong fullname: Seong, Hyunki email: hynkis@kaist.ac.kr organization: School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea – sequence: 3 givenname: Daegyu orcidid: 0000-0002-9336-5759 surname: Lee fullname: Lee, Daegyu email: lee.dk@etri.re.kr organization: Digital Convergence Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea – sequence: 4 givenname: David Hyunchul orcidid: 0000-0002-1929-7022 surname: Shim fullname: Shim, David Hyunchul email: hcshim@kaist.ac.kr organization: School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea |
BookMark | eNp9kL9uwyAQhxlSqUnaJ-jCCzjFBtswdIii_pMidWlnBPicENlgAUmVPn3tpHOnk353393pW6CZ8w4QesjJKid59XhYBa99WhWkYGPC6orM0JyIIs84F-QWLWI8EEJoWdM5-lnjE4Soku0AN94H7Adw1u1wPMcEPf62aY97r6d-r5wdjp1K41jaB3_c7bFq1JDsCfDgo03Wu6z1wQA23qXgO6xcgwNYd0l7cAl3oMJ04Q7dtKqLcP9Xl-jr5flz85ZtP17fN-ttZoqCp4wJYirQvKQ5VC3ljLaa6YqSQgheNSAU1CyvuSG0YYIJrVuuSk5KwVjRaEKXiF73muBjDNDKIdhehbPMiZyUyYO8KJOTMnlVNlJPVwrG104WgozGgjPQ2AAmycbbf_lfqfR8_g |
Cites_doi | 10.1109/ICAR.2017.8023522 10.1109/IROS.2000.895316 10.1126/scirobotics.aax8177 10.1109/ITSC48978.2021.9564720 10.1109/LRA.2019.2927955 10.3390/s20030939 10.3390/s20205911 10.1109/ACCESS.2021.3120618 10.23919/IConAC.2019.8895183 10.1109/ICRA.2019.8793506 10.1016/j.tre.2022.102834 10.3390/robotics10010022 10.3390/app12105204 10.3390/app10196923 10.1007/s11370-021-00366-7 10.1109/ICRA48506.2021.9561858 10.1016/S0168-1699(00)00176-9 10.1109/TMECH.2012.2191301 10.1109/LRA.2021.3092685 10.1145/358669.358692 10.3390/app9020348 10.1109/ICRA.2017.7989385 10.1109/ICRA.2019.8793866 10.1109/CVPR52688.2022.00831 10.1177/0278364920987859 10.1109/ROBIO49542.2019.8961852 10.1109/ICRA.2019.8794127 |
ContentType | Journal Article |
Copyright | 2024 Elsevier B.V. |
Copyright_xml | – notice: 2024 Elsevier B.V. |
DBID | AAYXX CITATION |
DOI | 10.1016/j.robot.2024.104760 |
DatabaseName | CrossRef |
DatabaseTitle | CrossRef |
DatabaseTitleList | |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering |
ExternalDocumentID | 10_1016_j_robot_2024_104760 S0921889024001441 |
GroupedDBID | --K --M -~X .~1 0R~ 123 1B1 1~. 1~5 29P 4.4 457 4G. 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABFRF ABIVO ABJNI ABMAC ABXDB ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEFWE AEKER AENEX AFFNX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHPGS AHZHX AIALX AIEXJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM LG9 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ RXW SBC SCC SDF SDG SDP SES SET SEW SPC SPCBC SST SSV SSZ T5K TAE UNMZH WUQ XPP ~G- 0SF AAXKI AAYXX AFJKZ CITATION |
ID | FETCH-LOGICAL-c228t-490c6eb8531e6f3843fb4b63029986de9ae74178c03d4949bbf8a58059442db03 |
IEDL.DBID | AIKHN |
ISSN | 0921-8890 |
IngestDate | Wed Oct 16 15:15:05 EDT 2024 Sat Aug 24 15:42:06 EDT 2024 |
IsDoiOpenAccess | false |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | Door opening robot Deep reinforcement learning Indoor robotics Real-time autonomous system Mobile manipulator |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c228t-490c6eb8531e6f3843fb4b63029986de9ae74178c03d4949bbf8a58059442db03 |
ORCID | 0000-0002-1929-7022 0000-0001-7769-4651 0000-0002-9336-5759 0000-0002-7169-3006 |
OpenAccessLink | https://arxiv.org/pdf/2307.04422 |
ParticipantIDs | crossref_primary_10_1016_j_robot_2024_104760 elsevier_sciencedirect_doi_10_1016_j_robot_2024_104760 |
PublicationCentury | 2000 |
PublicationDate | October 2024 2024-10-00 |
PublicationDateYYYYMMDD | 2024-10-01 |
PublicationDate_xml | – month: 10 year: 2024 text: October 2024 |
PublicationDecade | 2020 |
PublicationTitle | Robotics and autonomous systems |
PublicationYear | 2024 |
Publisher | Elsevier B.V |
Publisher_xml | – name: Elsevier B.V |
References | L. Peterson, D. Austin, D. Kragic, High-level control of a mobile manipulator for door opening, in: Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000)(Cat. No. 00CH37113), Vol. 3, 2000, pp. 2333–2338. Srinivas, Ramachandiran, Rajendran (b2) 2022; 165 Ahmad, Zhang, Liu (b7) 2012; 18 B. Nemec, L. Žlajpah, A. Ude, Door opening by joining reinforcement learning and intelligent control, in: 2017 18th International Conference on Advanced Robotics, ICAR, 2017, pp. 222–228. (b38) 2021 Ma, Gao, Ding, Tao, Xia, Yu, Deng (b8) 2018 Minniti, Farshidian, Grandia, Hutter (b11) 2019; 4 Prianto, Kim, Park, Bae, Kim (b34) 2020; 20 Tanner, Kyriakopoulos, Krikelis (b3) 2001; 31 (b37) 2018 S. Gu, E. Holly, T. Lillicrap, S. Levine, Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates, in: 2017 IEEE International Conference on Robotics and Automation, ICRA, 2017, pp. 3389–3396. Ibarz, Tan, Finn, Kalakrishnan, Pastor, Levine (b20) 2021; 40 Urakami, Hodgkinson, Carlin, Leu, Rigazio, Abbeel (b23) 2019 M. Stuede, K. Nuelle, S. Tappe, T. Ortmaier, Door opening and traversal with an industrial cartesian impedance controlled mobile robot, in: 2019 International Conference on Robotics and Automation, ICRA, 2019, pp. 966–972. M. Yang, E. Yang, R. Zante, M. Post, X. Liu, Collaborative mobile industrial manipulator: a review of system architecture and applications, in: 2019 25th International Conference On Automation And Computing, ICAC, 2019, pp. 1–6. Kindle, Furrer, Novkovic, Chung, Siegwart, Nieto (b16) 2020 J. Luo, E. Solowjow, C. Wen, J. Ojea, A. Agogino, A. Tamar, P. Abbeel, Reinforcement learning on variable impedance controller for high-precision robotic assembly, in: 2019 International Conference on Robotics and Automation, ICRA, 2019, pp. 3080–3087. Wang, Wang, Zhao (b24) 2022; 12 T. Haarnoja, A. Zhou, P. Abbeel, S. Levine, Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor, in: International Conference On Machine Learning, 2018, pp. 1861–1870. Beltran-Hernandez, Petit, Ramirez-Alpizar, Harada (b14) 2020; 10 Honerkamp, Welschehold, Valada (b17) 2021; 6 X. Lai, J. Liu, L. Jiang, L. Wang, H. Zhao, S. Liu, X. Qi, J. Jia, Stratified transformer for 3d point cloud segmentation, in: Proceedings of The IEEE/CVF Conference On Computer Vision And Pattern Recognition, 2022, pp. 8500–8509. Lee, Kang, Kim, Shim (b1) 2021; 9 Fischler, Bolles (b28) 1981; 24 Haarnoja, Zhou, Hartikainen, Tucker, Ha, Tan, Kumar, Zhu, Gupta, Abbeel (b35) 2018 Ito, Yamamoto, Mori, Ogata (b25) 2022; 7 Fuchs, Song, Kaufmann, Scaramuzza, Duerr (b31) 2020 Wang, Zhang, Tian, Li, Wang, Lane, Petillot, Wang (b15) 2020; 20 Arduengo, Torras, Sentis (b10) 2021; 14 H. Seong, C. Jung, S. Lee, D. Shim, Learning to drive at unsignalized intersections using attention-based deep reinforcement learning, in: 2021 IEEE International Intelligent Transportation Systems Conference, ITSC, 2021, pp. 559–566. Iriondo, Lazkano, Susperregi, Urain, Fernandez, Molina (b4) 2019; 9 C. Yang, J. Yang, X. Wang, B. Liang, Control of space flexible manipulator using soft actor-critic and random network distillation, in: 2019 IEEE International Conference on Robotics and Biomimetics, ROBIO, 2019, pp. 3019–3024. C. Sun, J. Orbik, C. Devin, B. Yang, A. Gupta, G. Berseth, S. Levine, Fully autonomous real-world reinforcement learning with applications to mobile manipulation, in: Conference On Robot Learning, 2022, pp. 308–319. Liu, Nageotte, Zanne, Mathelin, Dresp-Langley (b19) 2021; 10 S. Fujimoto, H. Hoof, D. Meger, Addressing function approximation error in actor-critic methods, in: International Conference On Machine Learning, 2018, pp. 1587–1596. H. Liu, R. Soto, F. Xiao, Y. Lee, Yolactedge: Real-time instance segmentation on the edge, in: 2021 IEEE International Conference on Robotics and Automation, ICRA, 2021, pp. 9579–9585. Lynch, Park (b29) 2017 T. Johannink, S. Bahl, A. Nair, J. Luo, A. Kumar, M. Loskyll, J. Ojea, E. Solowjow, S. Levine, Residual reinforcement learning for robot control, in: 2019 International Conference on Robotics and Automation, ICRA, 2019, pp. 6023–6029. Prianto (10.1016/j.robot.2024.104760_b34) 2020; 20 10.1016/j.robot.2024.104760_b9 Srinivas (10.1016/j.robot.2024.104760_b2) 2022; 165 Ito (10.1016/j.robot.2024.104760_b25) 2022; 7 Ma (10.1016/j.robot.2024.104760_b8) 2018 10.1016/j.robot.2024.104760_b21 10.1016/j.robot.2024.104760_b22 Wang (10.1016/j.robot.2024.104760_b24) 2022; 12 10.1016/j.robot.2024.104760_b26 Lee (10.1016/j.robot.2024.104760_b1) 2021; 9 10.1016/j.robot.2024.104760_b27 (10.1016/j.robot.2024.104760_b38) 2021 Fischler (10.1016/j.robot.2024.104760_b28) 1981; 24 Kindle (10.1016/j.robot.2024.104760_b16) 2020 Lynch (10.1016/j.robot.2024.104760_b29) 2017 10.1016/j.robot.2024.104760_b6 Urakami (10.1016/j.robot.2024.104760_b23) 2019 10.1016/j.robot.2024.104760_b5 Arduengo (10.1016/j.robot.2024.104760_b10) 2021; 14 Ibarz (10.1016/j.robot.2024.104760_b20) 2021; 40 Fuchs (10.1016/j.robot.2024.104760_b31) 2020 Haarnoja (10.1016/j.robot.2024.104760_b35) 2018 (10.1016/j.robot.2024.104760_b37) 2018 Ahmad (10.1016/j.robot.2024.104760_b7) 2012; 18 10.1016/j.robot.2024.104760_b18 Tanner (10.1016/j.robot.2024.104760_b3) 2001; 31 10.1016/j.robot.2024.104760_b32 10.1016/j.robot.2024.104760_b33 10.1016/j.robot.2024.104760_b12 10.1016/j.robot.2024.104760_b13 10.1016/j.robot.2024.104760_b36 Liu (10.1016/j.robot.2024.104760_b19) 2021; 10 Minniti (10.1016/j.robot.2024.104760_b11) 2019; 4 Iriondo (10.1016/j.robot.2024.104760_b4) 2019; 9 Beltran-Hernandez (10.1016/j.robot.2024.104760_b14) 2020; 10 Wang (10.1016/j.robot.2024.104760_b15) 2020; 20 Honerkamp (10.1016/j.robot.2024.104760_b17) 2021; 6 10.1016/j.robot.2024.104760_b30 |
References_xml | – volume: 18 start-page: 833 year: 2012 end-page: 844 ident: b7 article-title: Multiple working mode control of door opening with a mobile modular and reconfigurable robot publication-title: IEEE/ASME Trans. Mechatron. contributor: fullname: Liu – year: 2019 ident: b23 article-title: Doorgym: A scalable door opening environment and baseline agent contributor: fullname: Abbeel – volume: 4 start-page: 3687 year: 2019 end-page: 3694 ident: b11 article-title: Whole-body mpc for a dynamically stable mobile manipulator publication-title: IEEE Robot. Autom. Lett. contributor: fullname: Hutter – year: 2018 ident: b35 article-title: Soft actor-critic algorithms and applications contributor: fullname: Abbeel – volume: 24 start-page: 381 year: 1981 end-page: 395 ident: b28 article-title: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography publication-title: Commun. ACM contributor: fullname: Bolles – volume: 165 year: 2022 ident: b2 article-title: Autonomous robot-driven deliveries: A review of recent developments and future directions publication-title: Transp. Res. E: Logist. Transp. Rev. contributor: fullname: Rajendran – year: 2018 ident: b37 article-title: Kinovarobotics ros_kortex. GitHub Repository – volume: 9 start-page: 348 year: 2019 ident: b4 article-title: Pick and place operations in logistics using a mobile manipulator controlled with deep reinforcement learning publication-title: Appl. Sci. contributor: fullname: Molina – volume: 6 start-page: 6289 year: 2021 end-page: 6296 ident: b17 article-title: Learning kinematic feasibility for mobile manipulation through deep reinforcement learning publication-title: IEEE Robot. Autom. Lett. contributor: fullname: Valada – volume: 20 start-page: 939 year: 2020 ident: b15 article-title: Learning mobile manipulation through deep reinforcement learning publication-title: Sensors contributor: fullname: Wang – year: 2018 ident: b8 article-title: Optimal energy consumption for mobile manipulators executing door opening task publication-title: Mathematical Problems In Engineering contributor: fullname: Deng – volume: 40 start-page: 698 year: 2021 end-page: 721 ident: b20 article-title: How to train your robot with deep reinforcement learning: lessons we have learned publication-title: Int. J. Robot. Res. contributor: fullname: Levine – volume: 12 start-page: 5204 year: 2022 ident: b24 article-title: Research on door opening operation of mobile robotic arm based on reinforcement learning publication-title: Appl. Sci. contributor: fullname: Zhao – volume: 10 start-page: 6923 year: 2020 ident: b14 article-title: Variable compliance control for robotic peg-in-hole assembly: A deep-reinforcement-learning approach publication-title: Appl. Sci. contributor: fullname: Harada – year: 2020 ident: b16 article-title: Whole-body control of a mobile manipulator using end-to-end reinforcement learning contributor: fullname: Nieto – volume: 9 start-page: 141981 year: 2021 end-page: 141998 ident: b1 article-title: Assistive delivery robot application for real-world postal services publication-title: IEEE Access contributor: fullname: Shim – volume: 20 start-page: 5911 year: 2020 ident: b34 article-title: Path planning for multi-arm manipulators using deep reinforcement learning: Soft actor–critic with hindsight experience replay publication-title: Sensors contributor: fullname: Kim – volume: 7 year: 2022 ident: b25 article-title: Efficient multitask learning with an embodied predictive model for door opening and entry with whole-body control publication-title: Sci. Robot. contributor: fullname: Ogata – volume: 31 start-page: 91 year: 2001 end-page: 105 ident: b3 article-title: Advanced agricultural robots: kinematics and dynamics of multiple mobile manipulators handling non-rigid material publication-title: Comput. Electron. Agricult. contributor: fullname: Krikelis – year: 2020 ident: b31 article-title: Super-human performance in gran turismo sport using deep reinforcement learning contributor: fullname: Duerr – year: 2017 ident: b29 article-title: Modern Robotics contributor: fullname: Park – year: 2021 ident: b38 article-title: omorobot omo_r1. GitHub Repository – volume: 14 start-page: 409 year: 2021 end-page: 425 ident: b10 article-title: Robust and adaptive door operation with a mobile robot publication-title: Intell. Serv. Robot. contributor: fullname: Sentis – volume: 10 start-page: 22 year: 2021 ident: b19 article-title: Deep reinforcement learning for the control of robotic manipulation: a focussed mini-review publication-title: Robotics contributor: fullname: Dresp-Langley – ident: 10.1016/j.robot.2024.104760_b22 doi: 10.1109/ICAR.2017.8023522 – ident: 10.1016/j.robot.2024.104760_b6 doi: 10.1109/IROS.2000.895316 – volume: 7 year: 2022 ident: 10.1016/j.robot.2024.104760_b25 article-title: Efficient multitask learning with an embodied predictive model for door opening and entry with whole-body control publication-title: Sci. Robot. doi: 10.1126/scirobotics.aax8177 contributor: fullname: Ito – year: 2018 ident: 10.1016/j.robot.2024.104760_b8 article-title: Optimal energy consumption for mobile manipulators executing door opening task contributor: fullname: Ma – year: 2018 ident: 10.1016/j.robot.2024.104760_b35 contributor: fullname: Haarnoja – ident: 10.1016/j.robot.2024.104760_b32 doi: 10.1109/ITSC48978.2021.9564720 – volume: 4 start-page: 3687 year: 2019 ident: 10.1016/j.robot.2024.104760_b11 article-title: Whole-body mpc for a dynamically stable mobile manipulator publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/LRA.2019.2927955 contributor: fullname: Minniti – volume: 20 start-page: 939 year: 2020 ident: 10.1016/j.robot.2024.104760_b15 article-title: Learning mobile manipulation through deep reinforcement learning publication-title: Sensors doi: 10.3390/s20030939 contributor: fullname: Wang – year: 2019 ident: 10.1016/j.robot.2024.104760_b23 contributor: fullname: Urakami – volume: 20 start-page: 5911 year: 2020 ident: 10.1016/j.robot.2024.104760_b34 article-title: Path planning for multi-arm manipulators using deep reinforcement learning: Soft actor–critic with hindsight experience replay publication-title: Sensors doi: 10.3390/s20205911 contributor: fullname: Prianto – volume: 9 start-page: 141981 year: 2021 ident: 10.1016/j.robot.2024.104760_b1 article-title: Assistive delivery robot application for real-world postal services publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3120618 contributor: fullname: Lee – ident: 10.1016/j.robot.2024.104760_b5 doi: 10.23919/IConAC.2019.8895183 – ident: 10.1016/j.robot.2024.104760_b12 doi: 10.1109/ICRA.2019.8793506 – volume: 165 year: 2022 ident: 10.1016/j.robot.2024.104760_b2 article-title: Autonomous robot-driven deliveries: A review of recent developments and future directions publication-title: Transp. Res. E: Logist. Transp. Rev. doi: 10.1016/j.tre.2022.102834 contributor: fullname: Srinivas – volume: 10 start-page: 22 year: 2021 ident: 10.1016/j.robot.2024.104760_b19 article-title: Deep reinforcement learning for the control of robotic manipulation: a focussed mini-review publication-title: Robotics doi: 10.3390/robotics10010022 contributor: fullname: Liu – year: 2020 ident: 10.1016/j.robot.2024.104760_b31 contributor: fullname: Fuchs – volume: 12 start-page: 5204 year: 2022 ident: 10.1016/j.robot.2024.104760_b24 article-title: Research on door opening operation of mobile robotic arm based on reinforcement learning publication-title: Appl. Sci. doi: 10.3390/app12105204 contributor: fullname: Wang – volume: 10 start-page: 6923 year: 2020 ident: 10.1016/j.robot.2024.104760_b14 article-title: Variable compliance control for robotic peg-in-hole assembly: A deep-reinforcement-learning approach publication-title: Appl. Sci. doi: 10.3390/app10196923 contributor: fullname: Beltran-Hernandez – ident: 10.1016/j.robot.2024.104760_b18 – volume: 14 start-page: 409 year: 2021 ident: 10.1016/j.robot.2024.104760_b10 article-title: Robust and adaptive door operation with a mobile robot publication-title: Intell. Serv. Robot. doi: 10.1007/s11370-021-00366-7 contributor: fullname: Arduengo – year: 2018 ident: 10.1016/j.robot.2024.104760_b37 – ident: 10.1016/j.robot.2024.104760_b27 doi: 10.1109/ICRA48506.2021.9561858 – volume: 31 start-page: 91 year: 2001 ident: 10.1016/j.robot.2024.104760_b3 article-title: Advanced agricultural robots: kinematics and dynamics of multiple mobile manipulators handling non-rigid material publication-title: Comput. Electron. Agricult. doi: 10.1016/S0168-1699(00)00176-9 contributor: fullname: Tanner – year: 2017 ident: 10.1016/j.robot.2024.104760_b29 contributor: fullname: Lynch – ident: 10.1016/j.robot.2024.104760_b30 – volume: 18 start-page: 833 year: 2012 ident: 10.1016/j.robot.2024.104760_b7 article-title: Multiple working mode control of door opening with a mobile modular and reconfigurable robot publication-title: IEEE/ASME Trans. Mechatron. doi: 10.1109/TMECH.2012.2191301 contributor: fullname: Ahmad – volume: 6 start-page: 6289 year: 2021 ident: 10.1016/j.robot.2024.104760_b17 article-title: Learning kinematic feasibility for mobile manipulation through deep reinforcement learning publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/LRA.2021.3092685 contributor: fullname: Honerkamp – volume: 24 start-page: 381 year: 1981 ident: 10.1016/j.robot.2024.104760_b28 article-title: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography publication-title: Commun. ACM doi: 10.1145/358669.358692 contributor: fullname: Fischler – volume: 9 start-page: 348 year: 2019 ident: 10.1016/j.robot.2024.104760_b4 article-title: Pick and place operations in logistics using a mobile manipulator controlled with deep reinforcement learning publication-title: Appl. Sci. doi: 10.3390/app9020348 contributor: fullname: Iriondo – ident: 10.1016/j.robot.2024.104760_b21 doi: 10.1109/ICRA.2017.7989385 – ident: 10.1016/j.robot.2024.104760_b9 doi: 10.1109/ICRA.2019.8793866 – ident: 10.1016/j.robot.2024.104760_b26 doi: 10.1109/CVPR52688.2022.00831 – volume: 40 start-page: 698 year: 2021 ident: 10.1016/j.robot.2024.104760_b20 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 contributor: fullname: Ibarz – ident: 10.1016/j.robot.2024.104760_b36 – ident: 10.1016/j.robot.2024.104760_b33 doi: 10.1109/ROBIO49542.2019.8961852 – year: 2020 ident: 10.1016/j.robot.2024.104760_b16 contributor: fullname: Kindle – year: 2021 ident: 10.1016/j.robot.2024.104760_b38 – ident: 10.1016/j.robot.2024.104760_b13 doi: 10.1109/ICRA.2019.8794127 |
SSID | ssj0003573 |
Score | 2.4672673 |
Snippet | The ability of robots to navigate through doors is crucial for their effective operation in indoor environments. Consequently, extensive research has been... |
SourceID | crossref elsevier |
SourceType | Aggregation Database Publisher |
StartPage | 104760 |
SubjectTerms | Deep reinforcement learning Door opening robot Indoor robotics Mobile manipulator Real-time autonomous system |
Title | A versatile door opening system with mobile manipulator through adaptive position-force control and reinforcement learning |
URI | https://dx.doi.org/10.1016/j.robot.2024.104760 |
Volume | 180 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwED71scCAeIryqDwwEuomjmuPVQUqVOoAVHSL4thBRZBUVVkY-O34HAcVCTGwJErsk6Iv0d3Z9-U7gAvRzwc8C3VgF8g6YLk9SM1ZEEuhNDexCY1jW0z5eMbu5vG8AaP6XxikVXrfX_l05639nZ5Hs7dcLHoPVNrwhGUyRt2yoAltG44Ya0F7eDsZT78dchRXhWY7P0CDWnzI0bxWpSqRUxkyLHcOnFTlLwFqI-jc7MKOzxbJsHqgPWiYYh-2NzQED-BjSJBZYQF-NUSX5YpgQyw7RCqRZoI7reStVDiOYheuYZed5jv0kFSnS_R5pOZvBTaPzQzxJHaSFpqsjBNYzdxeIvGdJp4PYXZz_TgaB76hQpCFoVgHTNKMG2UjdN_wPBIsyhVTPKI2JgmujUyNTTAGIqORRtUapXKRxgIlXVioFY2OoFWUhTkGInKhDNWSCgt5bkLphO2lzFKudaTTDlzWKCbLSjcjqQllL4kDPUHQkwr0DvAa6eTH60-sZ__L8OS_hqewhVcVL-8MWuvVuzm3-cVadaF59dnv-q8Iz5P7p8kXNxrTlg |
link.rule.ids | 315,786,790,4521,24144,27955,27956,45618,45712 |
linkProvider | Elsevier |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV09T8MwELVKGYAB8SnKpwdGTN3Ece2xqkAFShdaqZsVxw4qgqSqysLAb8fnOKJIiIElQ-4sRS_R3dn38g6hS9HJuzyLDHEbZENY7i7ScEYSKbThNrGR9WyLER9M2P00mTZQv_4XBmiVIfZXMd1H63CnHdBsz2ez9hOVLj1Bm4xRvy1YQ-tQDQCv6_rzm-cRJ1Wb2XkTcK-lhzzJa1HqEhiVEYNmZ9cLVf6SnlZSzu0O2g61Iu5Vj7OLGrbYQ1srCoL76KOHgVfh4H212JTlAsM4LGfClUQzhnNW_FZqsIPUhR_X5dzCfB6cmnQOEQ_X7C3iqtjM4kBhx2lh8MJ6edXMnyTiMGfi-QBNbm_G_QEJ4xRIFkViSZikGbfa5eeO5XksWJxrpnlMXUYS3FiZWldedEVGYwOaNVrnIk0ECLqwyGgaH6JmURb2CGGRC22pkVSwDsttJL2svZRZyo2JTdpCVzWKal6pZqiaTvaiPOgKQFcV6C3Ea6TVj5evXFz_a-HxfxdeoI3B-HGohnejhxO0CZaKoXeKmsvFuz1zlcZSn_sv6Qt_e9LI |
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=A+versatile+door+opening+system+with+mobile+manipulator+through+adaptive+position-force+control+and+reinforcement+learning&rft.jtitle=Robotics+and+autonomous+systems&rft.au=Kang%2C+Gyuree&rft.au=Seong%2C+Hyunki&rft.au=Lee%2C+Daegyu&rft.au=Shim%2C+David+Hyunchul&rft.date=2024-10-01&rft.pub=Elsevier+B.V&rft.issn=0921-8890&rft.volume=180&rft_id=info:doi/10.1016%2Fj.robot.2024.104760&rft.externalDocID=S0921889024001441 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0921-8890&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0921-8890&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0921-8890&client=summon |