Obstacle avoidance strategy for biped robot based on Fuzzy Q-Learning

C. Sabourin, K. Madani, W. Yu, J. Yan

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

2 Scopus citations

Abstract

In this paper, we present the first results about dynamic obstacle avoidances using stepping over strategy for biped robots. The proposed approach is based on the Fuzzy Q-Iearning (FQL) concept. The originality of our strategy is that we consider it shouldbe possible to design separately the high-level (path planning) control and the low-level control (gait pattern). The first results show the effectiveness of the proposed approach in the case of a flat dynamic obstacle.

Original languageEnglish
Title of host publicationAdvances in Mobile Robotics - Proceedings of the 11th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2008
PublisherWorld Scientific Publishing Co. Pte Ltd
Pages695-702
Number of pages8
ISBN (Print)9812835768, 9789812835765
DOIs
StatePublished - 2008
Event11th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2008 - Coimbra, Portugal
Duration: 8 Sep 200810 Sep 2008

Publication series

NameAdvances in Mobile Robotics - Proceedings of the 11th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2008

Conference

Conference11th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, CLAWAR 2008
Country/TerritoryPortugal
CityCoimbra
Period8/09/0810/09/08

Keywords

  • Biped robot
  • Fuzzy Q-learning
  • Obstacle avoidance

Fingerprint

Dive into the research topics of 'Obstacle avoidance strategy for biped robot based on Fuzzy Q-Learning'. Together they form a unique fingerprint.

Cite this