Optimization of obstacle avoidance using reinforcement learning

Keishi Kominami*, Tomohito Takubo, Kenichi Ohara, Yasushi Mae, Tatsuo Arai

*Corresponding author for this work

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

3 Citations (Scopus)

Abstract

Walking through narrow space for multi-legged robot is optimized using reinforcement learning in this paper. The walking is generated by the virtual repulsive force from the estimated obstacle position and the virtual impedance field. The resulted action depends on the parameter of the virtual impedance coefficients. The reinforcement learning is employed to find an optimal motion. The temporal walking through motion consists of each parameter optimized for a situation. Optimization of integrated walking through motion is finally achieved evaluating walking in compound encountering obstacle on simulator. The resulted motion is implemented to a real multi-legged robot and results show the effectiveness of the proposed method.

Original languageEnglish
Title of host publication2012 IEEE/SICE International Symposium on System Integration, SII 2012
Pages67-72
Number of pages6
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event2012 IEEE/SICE International Symposium on System Integration, SII 2012 - Fukuoka, Japan
Duration: 16 Dec 201218 Dec 2012

Publication series

Name2012 IEEE/SICE International Symposium on System Integration, SII 2012

Conference

Conference2012 IEEE/SICE International Symposium on System Integration, SII 2012
Country/TerritoryJapan
CityFukuoka
Period16/12/1218/12/12

Keywords

  • Multi-Legged Robot
  • Obstacle Avoidance
  • Reinforcement Learning
  • Virtual Impedance Wall

Fingerprint

Dive into the research topics of 'Optimization of obstacle avoidance using reinforcement learning'. Together they form a unique fingerprint.

Cite this