USING JOINT TRAJECTORIES AND TIME-SCALING OPTIMIZATION FOR HUMANOID MOTION IMITATION OF HUMAN BEINGS

This paper presents a hybrid approach involving geometric and temporal evolution of joint motion for the imitation from human beings to a humanoid robots. We emphasize to extract the key advantages of temporal evolution of joint motion like tracking the defined motion trajectory and combine with geometric evolution of joint motion to ensure balance and obey the physical limits of the humanoid robot during motion imitation. In order to achieve this objective, we have framed the multi objective optimization problem with the constraints on balance and the physical limits of the humanoid robot. As a result, we have obtained the feasible joint trajectories for the humanoid robot, which can track the human reference trajectory to achieve a natural imitation between the human and the humanoid motion with optimum time delay and joint angle error. We validated this approach with the NAO humanoid robot with a kick motion in a single-support phase of stance.

[1]  Kazuhito Yokoi,et al.  Generating whole body motions for a biped humanoid robot from captured human dances , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[2]  Yoshihiko Nakamura,et al.  Motion capture based human motion recognition and imitation by direct marker control , 2008, Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots.

[3]  Tamim Asfour,et al.  Imitation of human motion on a humanoid robot using non-linear optimization , 2008, Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots.

[4]  Katsu Yamane,et al.  Simultaneous tracking and balancing of humanoid robots for imitating human motion capture data , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Pierre Blazevic,et al.  Mechatronic design of NAO humanoid , 2009, 2009 IEEE International Conference on Robotics and Automation.

[6]  Christine Chevallereau,et al.  Dynamic motion imitation of two articulated systems using nonlinear time scaling of joint trajectories , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Eiichi Yoshida,et al.  On human motion imitation by humanoid robot , 2008, 2008 IEEE International Conference on Robotics and Automation.

[8]  Behzad Dariush,et al.  Whole body humanoid control from human motion descriptors , 2008, 2008 IEEE International Conference on Robotics and Automation.

[9]  Christopher G. Atkeson,et al.  Adapting human motion for the control of a humanoid robot , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[10]  C. Breazeal,et al.  Robots that imitate humans , 2002, Trends in Cognitive Sciences.

[11]  Jun Morimoto,et al.  Spatio-temporal synchronization of periodic movements by style-phase adaptation: Application to biped walking , 2012, 2012 IEEE International Conference on Robotics and Automation.

[12]  Christine Chevallereau.  Time-scaling control for an underactuated biped robot , 2003, IEEE Trans. Robotics Autom..

[13]  Kazuhito Yokoi,et al.  Imitating human dance motions through motion structure analysis , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Seokmin Hong,et al.  Online footprint imitation of a humanoid robot by walking motion parameterization , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  ChangHwan Kim,et al.  Stable whole-body motion generation for humanoid robots to imitate human motions , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.