Title: Study of similar motion imitation of stepping upstairs for humanoid robot

Authors: Wen-De Ke; Zhi-Ping Peng; Ke Chen; Liang Hao

Addresses: Department of Computer Science, Guangdong University of Petrochemical Technology, Maoming 525000, China; School of Computer Science, Harbin Institute of Technology, Harbin 150001, China ' Department of Computer Science, Guangdong University of Petrochemical Technology, Maoming 525000, China ' Department of Computer Science, Guangdong University of Petrochemical Technology, Maoming 525000, China ' School of Computer Science, Harbin Institute of Technology, Harbin 150001, China

Abstract: Aimed at the situation of fitting variable environments in similarity imitation of stepping upstairs for humanoid robot, the process of designing similarity imitation was analysed as well as the rhythm control of key posture in similar locomotion. The simplified locomotion model and retargeting, connection of motion phases, and ZMP stability constraints were shown in similarity locomotion. The hierarchical reinforcement learning MaxQ was used to adjust the movement tracks of similarity to fit the variable stairs. The experiments showed the validity of the method.

Keywords: humanoid robots; hierarchical reinforcement learning; similarity imitation; retargeting; motion imitation; stepping upstairs; robot walking; robot climbing; stair climbing; stairs; robot locomotion; locomotion modelling; robot motion.

DOI: 10.1504/IJCSM.2013.055215

International Journal of Computing Science and Mathematics, 2013 Vol.4 No.2, pp.120 - 130

Received: 12 Apr 2013
Accepted: 29 Apr 2013

Published online: 10 May 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article