Lifelong learning for disturbance rejection on mobile robots

David Isele; José Marcio Luna; Eric Eaton; Gabriel V. De La Cruz; James Irwin; Brandon Kallaher; Matthew E. Taylor

doi:10.1109/IROS.2016.7759588

Lifelong learning for disturbance rejection on mobile robots

David Isele, José Marcio Luna, Eric Eaton, Gabriel V. De La Cruz, James Irwin, Brandon Kallaher, Matthew E. Taylor

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Scopus citations

Abstract

No two robots are exactly the same-even for a given model of robot, different units will require slightly different controllers. Furthermore, because robots change and degrade over time, a controller will need to change over time to remain optimal. This paper leverages lifelong learning in order to learn controllers for different robots. In particular, we show that by learning a set of control policies over robots with different (unknown) motion models, we can quickly adapt to changes in the robot, or learn a controller for a new robot with a unique set of disturbances. Furthermore, the approach is completely model-free, allowing us to apply this method to robots that have not, or cannot, be fully modeled.

Original language	English
Title of host publication	IROS 2016 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3993-3998
Number of pages	6
ISBN (Electronic)	9781509037629
DOIs	https://doi.org/10.1109/IROS.2016.7759588
State	Published - Nov 28 2016
Event	2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016 - Daejeon, Korea, Republic of Duration: Oct 9 2016 → Oct 14 2016

Publication series

Name	IEEE International Conference on Intelligent Robots and Systems
Volume	2016-November
ISSN (Print)	2153-0858
ISSN (Electronic)	2153-0866

Conference

Conference	2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016
Country/Territory	Korea, Republic of
City	Daejeon
Period	10/9/16 → 10/14/16

Access to Document

10.1109/IROS.2016.7759588

Cite this

Isele, D., Luna, J. M., Eaton, E., De La Cruz, G. V., Irwin, J., Kallaher, B., & Taylor, M. E. (2016). Lifelong learning for disturbance rejection on mobile robots. In IROS 2016 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 3993-3998). Article 7759588 (IEEE International Conference on Intelligent Robots and Systems; Vol. 2016-November). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IROS.2016.7759588

@inproceedings{102ff55cb7214c71af09475cc158b0b4,

title = "Lifelong learning for disturbance rejection on mobile robots",

abstract = "No two robots are exactly the same-even for a given model of robot, different units will require slightly different controllers. Furthermore, because robots change and degrade over time, a controller will need to change over time to remain optimal. This paper leverages lifelong learning in order to learn controllers for different robots. In particular, we show that by learning a set of control policies over robots with different (unknown) motion models, we can quickly adapt to changes in the robot, or learn a controller for a new robot with a unique set of disturbances. Furthermore, the approach is completely model-free, allowing us to apply this method to robots that have not, or cannot, be fully modeled.",

author = "David Isele and Luna, {Jos{\'e} Marcio} and Eric Eaton and {De La Cruz}, {Gabriel V.} and James Irwin and Brandon Kallaher and Taylor, {Matthew E.}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016 ; Conference date: 09-10-2016 Through 14-10-2016",

year = "2016",

month = nov,

day = "28",

doi = "10.1109/IROS.2016.7759588",

language = "English",

series = "IEEE International Conference on Intelligent Robots and Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3993--3998",

booktitle = "IROS 2016 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems",

}

Isele, D, Luna, JM, Eaton, E, De La Cruz, GV, Irwin, J, Kallaher, B & Taylor, ME 2016, Lifelong learning for disturbance rejection on mobile robots. in IROS 2016 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems., 7759588, IEEE International Conference on Intelligent Robots and Systems, vol. 2016-November, Institute of Electrical and Electronics Engineers Inc., pp. 3993-3998, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016, Daejeon, Korea, Republic of, 10/9/16. https://doi.org/10.1109/IROS.2016.7759588

Lifelong learning for disturbance rejection on mobile robots. / Isele, David; Luna, José Marcio; Eaton, Eric et al.
IROS 2016 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems. Institute of Electrical and Electronics Engineers Inc., 2016. p. 3993-3998 7759588 (IEEE International Conference on Intelligent Robots and Systems; Vol. 2016-November).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Lifelong learning for disturbance rejection on mobile robots

AU - Isele, David

AU - Luna, José Marcio

AU - Eaton, Eric

AU - De La Cruz, Gabriel V.

AU - Irwin, James

AU - Kallaher, Brandon

AU - Taylor, Matthew E.

PY - 2016/11/28

Y1 - 2016/11/28

N2 - No two robots are exactly the same-even for a given model of robot, different units will require slightly different controllers. Furthermore, because robots change and degrade over time, a controller will need to change over time to remain optimal. This paper leverages lifelong learning in order to learn controllers for different robots. In particular, we show that by learning a set of control policies over robots with different (unknown) motion models, we can quickly adapt to changes in the robot, or learn a controller for a new robot with a unique set of disturbances. Furthermore, the approach is completely model-free, allowing us to apply this method to robots that have not, or cannot, be fully modeled.

AB - No two robots are exactly the same-even for a given model of robot, different units will require slightly different controllers. Furthermore, because robots change and degrade over time, a controller will need to change over time to remain optimal. This paper leverages lifelong learning in order to learn controllers for different robots. In particular, we show that by learning a set of control policies over robots with different (unknown) motion models, we can quickly adapt to changes in the robot, or learn a controller for a new robot with a unique set of disturbances. Furthermore, the approach is completely model-free, allowing us to apply this method to robots that have not, or cannot, be fully modeled.

UR - http://www.scopus.com/inward/record.url?scp=85006414848&partnerID=8YFLogxK

U2 - 10.1109/IROS.2016.7759588

DO - 10.1109/IROS.2016.7759588

M3 - Conference contribution

AN - SCOPUS:85006414848

T3 - IEEE International Conference on Intelligent Robots and Systems

SP - 3993

EP - 3998

BT - IROS 2016 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016

Y2 - 9 October 2016 through 14 October 2016

ER -

Isele D, Luna JM, Eaton E, De La Cruz GV, Irwin J, Kallaher B et al. Lifelong learning for disturbance rejection on mobile robots. In IROS 2016 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems. Institute of Electrical and Electronics Engineers Inc. 2016. p. 3993-3998. 7759588. (IEEE International Conference on Intelligent Robots and Systems). doi: 10.1109/IROS.2016.7759588

Lifelong learning for disturbance rejection on mobile robots

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this