A simple reinforcement learning algorithm for biped walking

Jun Morimoto; Gordon Cheng; Christopher G. Atkeson; Garth Zeglin

doi:10.1109/robot.2004.1307522

A simple reinforcement learning algorithm for biped walking

Jun Morimoto, Gordon Cheng, Christopher G. Atkeson, Garth Zeglin

Research output: Contribution to journal › Conference article › peer-review

64 Scopus citations

Abstract

We propose a model-based reinforcement learning algorithm for biped walking in which the robot learns to appropriately place the swing leg. This decision is based on a learned model of the Poincare map of the periodic walking pattern. The model maps from a state at the middle of a step and foot placement to a state at next middle of a step. We also modify the desired walking cycle frequency based on online measurements. We present simulation results, and are currently implementing this approach on an actual biped robot.

Original language	English
Pages (from-to)	3030-3035
Number of pages	6
Journal	Proceedings - IEEE International Conference on Robotics and Automation
Volume	2004
Issue number	3
DOIs	https://doi.org/10.1109/robot.2004.1307522
State	Published - 2004
Externally published	Yes
Event	Proceedings- 2004 IEEE International Conference on Robotics and Automation - New Orleans, LA, United States Duration: 26 Apr 2004 → 1 May 2004

Access to Document

10.1109/robot.2004.1307522

Cite this

@article{c3d4df662e5a4e7c831f7d2793ff2938,

title = "A simple reinforcement learning algorithm for biped walking",

abstract = "We propose a model-based reinforcement learning algorithm for biped walking in which the robot learns to appropriately place the swing leg. This decision is based on a learned model of the Poincare map of the periodic walking pattern. The model maps from a state at the middle of a step and foot placement to a state at next middle of a step. We also modify the desired walking cycle frequency based on online measurements. We present simulation results, and are currently implementing this approach on an actual biped robot.",

author = "Jun Morimoto and Gordon Cheng and Atkeson, {Christopher G.} and Garth Zeglin",

year = "2004",

doi = "10.1109/robot.2004.1307522",

language = "English",

volume = "2004",

pages = "3030--3035",

journal = "Proceedings - IEEE International Conference on Robotics and Automation",

issn = "1050-4729",

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

number = "3",

note = "Proceedings- 2004 IEEE International Conference on Robotics and Automation ; Conference date: 26-04-2004 Through 01-05-2004",

}

TY - JOUR

T1 - A simple reinforcement learning algorithm for biped walking

AU - Morimoto, Jun

AU - Cheng, Gordon

AU - Atkeson, Christopher G.

AU - Zeglin, Garth

PY - 2004

Y1 - 2004

N2 - We propose a model-based reinforcement learning algorithm for biped walking in which the robot learns to appropriately place the swing leg. This decision is based on a learned model of the Poincare map of the periodic walking pattern. The model maps from a state at the middle of a step and foot placement to a state at next middle of a step. We also modify the desired walking cycle frequency based on online measurements. We present simulation results, and are currently implementing this approach on an actual biped robot.

AB - We propose a model-based reinforcement learning algorithm for biped walking in which the robot learns to appropriately place the swing leg. This decision is based on a learned model of the Poincare map of the periodic walking pattern. The model maps from a state at the middle of a step and foot placement to a state at next middle of a step. We also modify the desired walking cycle frequency based on online measurements. We present simulation results, and are currently implementing this approach on an actual biped robot.

UR - http://www.scopus.com/inward/record.url?scp=3042678716&partnerID=8YFLogxK

U2 - 10.1109/robot.2004.1307522

DO - 10.1109/robot.2004.1307522

M3 - Conference article

AN - SCOPUS:3042678716

SN - 1050-4729

VL - 2004

SP - 3030

EP - 3035

JO - Proceedings - IEEE International Conference on Robotics and Automation

JF - Proceedings - IEEE International Conference on Robotics and Automation

IS - 3

T2 - Proceedings- 2004 IEEE International Conference on Robotics and Automation

Y2 - 26 April 2004 through 1 May 2004

ER -

A simple reinforcement learning algorithm for biped walking

Abstract

Access to Document

Other files and links

Fingerprint

Cite this