Analysis of two evolutionary gait generation techniques for different coordinate approaches

IEICE Electronics Express

Kisung Seo¹  Soohwan Hyun¹ 

[1] Dept. of Electronic Engineering, Seokyeong University

关键词: robot automatic gait generation;    Cartesian space locus;    joint space trajectory;    Genetic Algorithm;    genetic programming;    quadruped robot;   

DOI  :  10.1587/elex.8.873

学科分类：电子、光学、磁材料

来源: Denshi Jouhou Tsuushin Gakkai

【 摘 要 】

References(8)Planning gaits for legged robots is an important and challenging task that requires optimizing parameters in a highly irregular and multidimensional space. Two evolutionary gait generation techniques using GA (Genetic Algorithm), GP (genetic programming) based on Cartesian and joint space are compared to develop fast locomotion for a quadruped robot. Optimizations for two proposed methods are executed and analyzed using a Webots simulation and real experiment of the quadruped robot. The performance and motion features of GA-, GP-based methods are compared and analyzed.

【 授权许可】

Unknown