Efficiently Combining Human Demonstrations and Interventions for Safe Training of Autonomous Systems in Real-Time
This paper investigates how to utilize different forms of human interaction to safely train autonomous systems in real-time by learning from both human demonstrations and interventions. We implement two components of the Cycle-of-Learning for Autonomous Systems, which is our framework for combining...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
28.11.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | This paper investigates how to utilize different forms of human interaction to safely train autonomous systems in real-time by learning from both human demonstrations and interventions. We implement two components of the Cycle-of-Learning for Autonomous Systems, which is our framework for combining multiple modalities of human interaction. The current effort employs human demonstrations to teach a desired behavior via imitation learning, then leverages intervention data to correct for undesired behaviors produced by the imitation learner to teach novel tasks to an autonomous agent safely, after only minutes of training. We demonstrate this method in an autonomous perching task using a quadrotor with continuous roll, pitch, yaw, and throttle commands and imagery captured from a downward-facing camera in a high-fidelity simulated environment. Our method improves task completion performance for the same amount of human interaction when compared to learning from demonstrations alone, while also requiring on average 32% less data to achieve that performance. This provides evidence that combining multiple modes of human interaction can increase both the training speed and overall performance of policies for autonomous systems. |
---|---|
AbstractList | This paper investigates how to utilize different forms of human interaction to safely train autonomous systems in real-time by learning from both human demonstrations and interventions. We implement two components of the Cycle-of-Learning for Autonomous Systems, which is our framework for combining multiple modalities of human interaction. The current effort employs human demonstrations to teach a desired behavior via imitation learning, then leverages intervention data to correct for undesired behaviors produced by the imitation learner to teach novel tasks to an autonomous agent safely, after only minutes of training. We demonstrate this method in an autonomous perching task using a quadrotor with continuous roll, pitch, yaw, and throttle commands and imagery captured from a downward-facing camera in a high-fidelity simulated environment. Our method improves task completion performance for the same amount of human interaction when compared to learning from demonstrations alone, while also requiring on average 32% less data to achieve that performance. This provides evidence that combining multiple modes of human interaction can increase both the training speed and overall performance of policies for autonomous systems. |
Author | Valasek, John Goecks, Vinicius G Lawhern, Vernon J Waytowich, Nicholas R Gremillion, Gregory M |
Author_xml | – sequence: 1 givenname: Vinicius surname: Goecks middlename: G fullname: Goecks, Vinicius G – sequence: 2 givenname: Gregory surname: Gremillion middlename: M fullname: Gremillion, Gregory M – sequence: 3 givenname: Vernon surname: Lawhern middlename: J fullname: Lawhern, Vernon J – sequence: 4 givenname: John surname: Valasek fullname: Valasek, John – sequence: 5 givenname: Nicholas surname: Waytowich middlename: R fullname: Waytowich, Nicholas R |
BookMark | eNqNi8sKwjAQRYMo-PyHAdeFNlWrS_GBbm33EnUikWZG8xD8e4v6Aa4OnHtuX7SJCVuiJ_M8S-YTKbti5P0tTVM5K-R0mvfEY6O1ORukUL9gxfZkyNAVdtEqgjVaJh-cCqYhKLrAngK6Z5N_jGYHpdIIlVPfI2tYxsDElqOH8uUDWg-G4ICqTipjcSg6WtUeRz8OxHi7qVa75O74EdGH442jo2Y6ykwWabHIsiL_r3oDF_NNRA |
ContentType | Paper |
Copyright | 2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Engineering Collection ProQuest Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_21270791173 |
IEDL.DBID | BENPR |
IngestDate | Thu Oct 10 18:34:33 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_21270791173 |
OpenAccessLink | https://www.proquest.com/docview/2127079117?pq-origsite=%requestingapplication% |
PQID | 2127079117 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2127079117 |
PublicationCentury | 2000 |
PublicationDate | 20181128 |
PublicationDateYYYYMMDD | 2018-11-28 |
PublicationDate_xml | – month: 11 year: 2018 text: 20181128 day: 28 |
PublicationDecade | 2010 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2018 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.1829488 |
SecondaryResourceType | preprint |
Snippet | This paper investigates how to utilize different forms of human interaction to safely train autonomous systems in real-time by learning from both human... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Human behavior Imagery Learning Military technology Pitch (inclination) Real time Rolling motion Throttles Training Yaw |
Title | Efficiently Combining Human Demonstrations and Interventions for Safe Training of Autonomous Systems in Real-Time |
URI | https://www.proquest.com/docview/2127079117 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1bS8MwFD64FcE3r3iZ44C-BtumS7sn8dI5hY0xJ-xtpG0Kgrbb2j344m_3JGYqCHsMgZDryZeTc74P4DIRoivzsMPcKM9ZIHjGJCFTRsstlSJ82jWUQoOh6L8ET9PO1DrcKhtWubaJxlBnZap95FeaidwN6WiG1_MF06pR-nfVSmg0wPG9QH_TOrfxcDT-8bL4IiTMzP8ZWnN79HbBGcm5Wu7Blir2YdsEXabVASxiw99AZv_tA-lgJkasAY1fHe_Vu4Zu3wtUIT348fFPfGKFhDbxWeYKJ1blAcscb1a1zlKg5zxaLnJ8LXBMaJDpZI9DuOjFk7s-W_dzZvdSNfsdOT-CZlEW6hhQi1rmktANF2kgEjeJMk9zh3k84ZEM0xNobWrpdHP1GewQMIh0zp0ftaBZL1fqnC7fOmlDI-o9tO08U2nwGX8BSlaQfw |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEB40QfTmEx9VB_S6mDbtJj2Jj5RU21BqhN7CJtmAoOkj6cF_7-y6VUHoeWHZ18x-OzvzfQDXKeddUXgd5vhFwdrczZkgZMpou4WUhE-7mlJoGPHwtf006UxMwK0yaZUrn6gddT7NVIz8RjGROx6Zpnc7mzOlGqV-V42ExibYinLTt8C-D6LR-CfK0uIeYWb3n6PVt0dvF-yRmMnFHmzIch-2dNJlVh3APND8DeT23z-RDDPVYg2o4-r4KD8UdPveoArpwY_9P_mJFRLaxBdRSIyNygNOC7xb1qpKgZ7zaLjI8a3EMaFBpoo9DuGqF8QPIVuNMzFnqUp-Z-4egVVOS3kMqEQtC0HoxuVZm6dO6udNxR3WdFPXF152Ao11PZ2ub76E7TAeDpJBP3o-gx0CCb6qv2v5DbDqxVKe00Vcpxdmtb8Act2RXg |
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=Efficiently+Combining+Human+Demonstrations+and+Interventions+for+Safe+Training+of+Autonomous+Systems+in+Real-Time&rft.jtitle=arXiv.org&rft.au=Goecks%2C+Vinicius+G&rft.au=Gremillion%2C+Gregory+M&rft.au=Lawhern%2C+Vernon+J&rft.au=Valasek%2C+John&rft.date=2018-11-28&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |