On Human Motion Imitation by Humanoid Robot

Wael Suleiman (1) , Eiichi Yoshida (2) , Fumio Kanehiro (2) , Jean-Paul Laumond (1) , André Monin (1)

1 LAAS - Laboratoire d'analyse et d'architecture des systèmes
2 AIST - National Institute of Advanced Industrial Science and Technology

In this paper, the imitation of human recorded motions by a humanoid robot is considered. The main objective is to reproduce an imitated motion as closely as possible to the original human recored motion. To achieve this goal, the imitation problem is formulated as an optimization problem and the physical limits of the humanoid robot is considered as constraints. The optimization problem is then solved recursively by using an efficient dynamics algorithm, which allows the calculation of the gradient function with respect to the control parameters analytically. The simulation results using OpenHRP platform, which is a dynamical simulator for humanoid robot motions, have pointed out that the imitated motions preserve the salient characteristics of the original human captured motion and the optimization procedure converges well thanks to the analytical calculation of gradient function.

Mots clés: Humanoid robot; Motion capture; Imitation; Recursive dynamics; Optimization

Domaines: Automatique / Robotique

Wael Suleiman, Eiichi Yoshida, Fumio Kanehiro, Jean-Paul Laumond, André Monin. On Human Motion Imitation by Humanoid Robot. 2008 IEEE International Conference on Robotics and Automation., May 2008, Califorina, United States. pp.CD Rom. ⟨hal-00166838v2⟩