Acquisition of a biped walking pattern using a poincare map

Jun Morimoto, Jun Nakanishi, Gen Endo, Gordon Cheng, Christopher G. Atkeson, Garth Zeglin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 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 a single support phase and foot placement to a state at the next single support phase. We applied this approach to both a simulated robot model and an actual biped robot. We show that successful walking patterns are acquired.

Original languageEnglish
Title of host publication2004 4th IEEE-RAS International Conference on Humanoid Robots
Pages912-924
Number of pages13
StatePublished - 2004
Externally publishedYes
Event2004 4th IEEE-RAS International Conference on Humanoid Robots - Santa Monica, CA, United States
Duration: 10 Nov 200412 Nov 2004

Publication series

Name2004 4th IEEE-RAS International Conference on Humanoid Robots
Volume2

Conference

Conference2004 4th IEEE-RAS International Conference on Humanoid Robots
Country/TerritoryUnited States
CitySanta Monica, CA
Period10/11/0412/11/04

Keywords

  • Biped Walking
  • Poincare map
  • Reinforcement Learning

Fingerprint

Dive into the research topics of 'Acquisition of a biped walking pattern using a poincare map'. Together they form a unique fingerprint.

Cite this