Data-driven robot gait modeling via symbolic time series analysis

Yusuke Seto, Noboru Takahashi, Devesh K. Jha, Nurali Virani, Asok Ray

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

2 Citations (Scopus)

Abstract

This paper addresses data-driven mode modeling and Bayesian mode estimation in hidden-mode hybrid systems (HMHS). For experimental validation in a laboratory setting, an HMHS is built upon a six-legged T-hex robot that makes use of a library of gaits (i.e., the modes of walking) to perform different motion maneuvers. To accurately predict the behavior of the robot, it is important to first infer the gait being used by the robot. The walking robot's motion behavior can then be modeled as a transition system based on the pattern of switching among these gaits. In this paper, a symbolic time-series-based statistical learning method has been adopted to construct the generative models of the gaits. Efficacy of the proposed algorithm is demonstrated by laboratory experimentation to model and then infer the hidden dynamics of different gaits for the T-hex walking robot.

Original languageEnglish (US)
Title of host publication2016 American Control Conference, ACC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3904-3909
Number of pages6
ISBN (Electronic)9781467386821
DOIs
StatePublished - Jul 28 2016
Event2016 American Control Conference, ACC 2016 - Boston, United States
Duration: Jul 6 2016Jul 8 2016

Publication series

NameProceedings of the American Control Conference
Volume2016-July
ISSN (Print)0743-1619

Other

Other2016 American Control Conference, ACC 2016
CountryUnited States
CityBoston
Period7/6/167/8/16

Fingerprint

Time series analysis
Robots
Hybrid systems
Time series

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Seto, Y., Takahashi, N., Jha, D. K., Virani, N., & Ray, A. (2016). Data-driven robot gait modeling via symbolic time series analysis. In 2016 American Control Conference, ACC 2016 (pp. 3904-3909). [7525522] (Proceedings of the American Control Conference; Vol. 2016-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ACC.2016.7525522
Seto, Yusuke ; Takahashi, Noboru ; Jha, Devesh K. ; Virani, Nurali ; Ray, Asok. / Data-driven robot gait modeling via symbolic time series analysis. 2016 American Control Conference, ACC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 3904-3909 (Proceedings of the American Control Conference).
@inproceedings{750672148744478cb724c41d3be1d4e8,
title = "Data-driven robot gait modeling via symbolic time series analysis",
abstract = "This paper addresses data-driven mode modeling and Bayesian mode estimation in hidden-mode hybrid systems (HMHS). For experimental validation in a laboratory setting, an HMHS is built upon a six-legged T-hex robot that makes use of a library of gaits (i.e., the modes of walking) to perform different motion maneuvers. To accurately predict the behavior of the robot, it is important to first infer the gait being used by the robot. The walking robot's motion behavior can then be modeled as a transition system based on the pattern of switching among these gaits. In this paper, a symbolic time-series-based statistical learning method has been adopted to construct the generative models of the gaits. Efficacy of the proposed algorithm is demonstrated by laboratory experimentation to model and then infer the hidden dynamics of different gaits for the T-hex walking robot.",
author = "Yusuke Seto and Noboru Takahashi and Jha, {Devesh K.} and Nurali Virani and Asok Ray",
year = "2016",
month = "7",
day = "28",
doi = "10.1109/ACC.2016.7525522",
language = "English (US)",
series = "Proceedings of the American Control Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "3904--3909",
booktitle = "2016 American Control Conference, ACC 2016",
address = "United States",

}

Seto, Y, Takahashi, N, Jha, DK, Virani, N & Ray, A 2016, Data-driven robot gait modeling via symbolic time series analysis. in 2016 American Control Conference, ACC 2016., 7525522, Proceedings of the American Control Conference, vol. 2016-July, Institute of Electrical and Electronics Engineers Inc., pp. 3904-3909, 2016 American Control Conference, ACC 2016, Boston, United States, 7/6/16. https://doi.org/10.1109/ACC.2016.7525522

Data-driven robot gait modeling via symbolic time series analysis. / Seto, Yusuke; Takahashi, Noboru; Jha, Devesh K.; Virani, Nurali; Ray, Asok.

2016 American Control Conference, ACC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 3904-3909 7525522 (Proceedings of the American Control Conference; Vol. 2016-July).

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

TY - GEN

T1 - Data-driven robot gait modeling via symbolic time series analysis

AU - Seto, Yusuke

AU - Takahashi, Noboru

AU - Jha, Devesh K.

AU - Virani, Nurali

AU - Ray, Asok

PY - 2016/7/28

Y1 - 2016/7/28

N2 - This paper addresses data-driven mode modeling and Bayesian mode estimation in hidden-mode hybrid systems (HMHS). For experimental validation in a laboratory setting, an HMHS is built upon a six-legged T-hex robot that makes use of a library of gaits (i.e., the modes of walking) to perform different motion maneuvers. To accurately predict the behavior of the robot, it is important to first infer the gait being used by the robot. The walking robot's motion behavior can then be modeled as a transition system based on the pattern of switching among these gaits. In this paper, a symbolic time-series-based statistical learning method has been adopted to construct the generative models of the gaits. Efficacy of the proposed algorithm is demonstrated by laboratory experimentation to model and then infer the hidden dynamics of different gaits for the T-hex walking robot.

AB - This paper addresses data-driven mode modeling and Bayesian mode estimation in hidden-mode hybrid systems (HMHS). For experimental validation in a laboratory setting, an HMHS is built upon a six-legged T-hex robot that makes use of a library of gaits (i.e., the modes of walking) to perform different motion maneuvers. To accurately predict the behavior of the robot, it is important to first infer the gait being used by the robot. The walking robot's motion behavior can then be modeled as a transition system based on the pattern of switching among these gaits. In this paper, a symbolic time-series-based statistical learning method has been adopted to construct the generative models of the gaits. Efficacy of the proposed algorithm is demonstrated by laboratory experimentation to model and then infer the hidden dynamics of different gaits for the T-hex walking robot.

UR - http://www.scopus.com/inward/record.url?scp=84992065220&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992065220&partnerID=8YFLogxK

U2 - 10.1109/ACC.2016.7525522

DO - 10.1109/ACC.2016.7525522

M3 - Conference contribution

AN - SCOPUS:84992065220

T3 - Proceedings of the American Control Conference

SP - 3904

EP - 3909

BT - 2016 American Control Conference, ACC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Seto Y, Takahashi N, Jha DK, Virani N, Ray A. Data-driven robot gait modeling via symbolic time series analysis. In 2016 American Control Conference, ACC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 3904-3909. 7525522. (Proceedings of the American Control Conference). https://doi.org/10.1109/ACC.2016.7525522