Adaptive locomotion learning in modular self-reconfigurable robots: A game theoretic approach

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Modular self-reconfigurable robots (MSRs) are mostly used in environments where it is difficult to navigate and explore otherwise. Especially, the shape-changing ability of MSRs makes them more dexterous in these situations compared to fixed-body robots. But when the MSR forms a new configuration, usually, the locomotion pattern for that particular configuration is not known by its constituting robotic modules. The main challenge for modules is to learn how to move in that specific configuration within a reasonable amount of time. In this paper, we study the problem where an MSR needs to learn its movement pattern on-the-fly. To solve this problem, we have proposed a game theoretic solution based on multi-agent reinforcement learning using which the constituting modules distributedly learn the best actions that they need to perform to travel more distance in less time. We have implemented this approach in simulation on both ModRED and Yamor MSR platforms. Results show that our approach performs better (up to 7.86 times) in terms of average speed achieved for most of the tested configurations as compared to an existing locomotion learning approach.

Original languageEnglish (US)
Title of host publicationIROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3556-3561
Number of pages6
ISBN (Electronic)9781538626825
DOIs
StatePublished - Dec 13 2017
Event2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2017 - Vancouver, Canada
Duration: Sep 24 2017Sep 28 2017

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
Volume2017-September
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Other

Other2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2017
CountryCanada
CityVancouver
Period9/24/179/28/17

Fingerprint

Robots
Reinforcement learning
Robotics

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Dutta, A., Dasgupta, P., & Nelson, C. (2017). Adaptive locomotion learning in modular self-reconfigurable robots: A game theoretic approach. In IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 3556-3561). [8206200] (IEEE International Conference on Intelligent Robots and Systems; Vol. 2017-September). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IROS.2017.8206200

Adaptive locomotion learning in modular self-reconfigurable robots : A game theoretic approach. / Dutta, Ayan; Dasgupta, Prithviraj; Nelson, Carl.

IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems. Institute of Electrical and Electronics Engineers Inc., 2017. p. 3556-3561 8206200 (IEEE International Conference on Intelligent Robots and Systems; Vol. 2017-September).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dutta, A, Dasgupta, P & Nelson, C 2017, Adaptive locomotion learning in modular self-reconfigurable robots: A game theoretic approach. in IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems., 8206200, IEEE International Conference on Intelligent Robots and Systems, vol. 2017-September, Institute of Electrical and Electronics Engineers Inc., pp. 3556-3561, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2017, Vancouver, Canada, 9/24/17. https://doi.org/10.1109/IROS.2017.8206200
Dutta A, Dasgupta P, Nelson C. Adaptive locomotion learning in modular self-reconfigurable robots: A game theoretic approach. In IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems. Institute of Electrical and Electronics Engineers Inc. 2017. p. 3556-3561. 8206200. (IEEE International Conference on Intelligent Robots and Systems). https://doi.org/10.1109/IROS.2017.8206200
Dutta, Ayan ; Dasgupta, Prithviraj ; Nelson, Carl. / Adaptive locomotion learning in modular self-reconfigurable robots : A game theoretic approach. IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 3556-3561 (IEEE International Conference on Intelligent Robots and Systems).
@inproceedings{2d82deeef4f9477f99ae1a1dde2c2ed7,
title = "Adaptive locomotion learning in modular self-reconfigurable robots: A game theoretic approach",
abstract = "Modular self-reconfigurable robots (MSRs) are mostly used in environments where it is difficult to navigate and explore otherwise. Especially, the shape-changing ability of MSRs makes them more dexterous in these situations compared to fixed-body robots. But when the MSR forms a new configuration, usually, the locomotion pattern for that particular configuration is not known by its constituting robotic modules. The main challenge for modules is to learn how to move in that specific configuration within a reasonable amount of time. In this paper, we study the problem where an MSR needs to learn its movement pattern on-the-fly. To solve this problem, we have proposed a game theoretic solution based on multi-agent reinforcement learning using which the constituting modules distributedly learn the best actions that they need to perform to travel more distance in less time. We have implemented this approach in simulation on both ModRED and Yamor MSR platforms. Results show that our approach performs better (up to 7.86 times) in terms of average speed achieved for most of the tested configurations as compared to an existing locomotion learning approach.",
author = "Ayan Dutta and Prithviraj Dasgupta and Carl Nelson",
year = "2017",
month = "12",
day = "13",
doi = "10.1109/IROS.2017.8206200",
language = "English (US)",
series = "IEEE International Conference on Intelligent Robots and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "3556--3561",
booktitle = "IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems",

}

TY - GEN

T1 - Adaptive locomotion learning in modular self-reconfigurable robots

T2 - A game theoretic approach

AU - Dutta, Ayan

AU - Dasgupta, Prithviraj

AU - Nelson, Carl

PY - 2017/12/13

Y1 - 2017/12/13

N2 - Modular self-reconfigurable robots (MSRs) are mostly used in environments where it is difficult to navigate and explore otherwise. Especially, the shape-changing ability of MSRs makes them more dexterous in these situations compared to fixed-body robots. But when the MSR forms a new configuration, usually, the locomotion pattern for that particular configuration is not known by its constituting robotic modules. The main challenge for modules is to learn how to move in that specific configuration within a reasonable amount of time. In this paper, we study the problem where an MSR needs to learn its movement pattern on-the-fly. To solve this problem, we have proposed a game theoretic solution based on multi-agent reinforcement learning using which the constituting modules distributedly learn the best actions that they need to perform to travel more distance in less time. We have implemented this approach in simulation on both ModRED and Yamor MSR platforms. Results show that our approach performs better (up to 7.86 times) in terms of average speed achieved for most of the tested configurations as compared to an existing locomotion learning approach.

AB - Modular self-reconfigurable robots (MSRs) are mostly used in environments where it is difficult to navigate and explore otherwise. Especially, the shape-changing ability of MSRs makes them more dexterous in these situations compared to fixed-body robots. But when the MSR forms a new configuration, usually, the locomotion pattern for that particular configuration is not known by its constituting robotic modules. The main challenge for modules is to learn how to move in that specific configuration within a reasonable amount of time. In this paper, we study the problem where an MSR needs to learn its movement pattern on-the-fly. To solve this problem, we have proposed a game theoretic solution based on multi-agent reinforcement learning using which the constituting modules distributedly learn the best actions that they need to perform to travel more distance in less time. We have implemented this approach in simulation on both ModRED and Yamor MSR platforms. Results show that our approach performs better (up to 7.86 times) in terms of average speed achieved for most of the tested configurations as compared to an existing locomotion learning approach.

UR - http://www.scopus.com/inward/record.url?scp=85041953909&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041953909&partnerID=8YFLogxK

U2 - 10.1109/IROS.2017.8206200

DO - 10.1109/IROS.2017.8206200

M3 - Conference contribution

AN - SCOPUS:85041953909

T3 - IEEE International Conference on Intelligent Robots and Systems

SP - 3556

EP - 3561

BT - IROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems

PB - Institute of Electrical and Electronics Engineers Inc.

ER -