Generating high-speed three-dimensional dynamic quadruped walking using an evolutionary search

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

1 Scopus citations

Abstract

This paper presents an evolutionary computation approach to generate three-dimensional fast forward gaits for quadruped robots with three motor-driven joints on each limb. We use linear constraints to reduce the high-dimensional space of parameters in order to generate the speed effectively. Real robot experiments show that the evolutionary approach is effective in developing quadruped gaits. Satisfactory results are obtained in about an hour by the autonomous learning process, which starts with a set of hand-tuned parameters.

Original languageEnglish
Title of host publicationICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings
Pages167-172
Number of pages6
StatePublished - 2009
Externally publishedYes
EventICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics - Milan, Italy
Duration: 2 Jul 20095 Jul 2009

Publication series

NameICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings
Volume1 ICSO

Conference

ConferenceICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics
Country/TerritoryItaly
CityMilan
Period2/07/095/07/09

Keywords

  • Evolutionary search
  • Legged robots
  • Locomotion
  • Quadruped walking
  • Three-dimensional gaits

Fingerprint

Dive into the research topics of 'Generating high-speed three-dimensional dynamic quadruped walking using an evolutionary search'. Together they form a unique fingerprint.

Cite this