Using eigenposes for lossless periodic human motion imitation
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Simultaneous tracking and balancing of humanoid robots for imitating human motion capture data
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Segmentation of human body parts using deformable triangulation
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans - Special issue on recent advances in biometrics
From Canonical Poses to 3D Motion Capture Using a Single Camera
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
Similarity motion imitation on humanoid robot from the captured tracks of human actor has attracted more and more attention. We described the basic system of similarity imitation that was formed by three modules - the image capture, imitation control and imitation on real robot. The similarity degree was analysed by the differences of angle, angular velocity and acceleration between human actor and robot, and the function of spatio-temporal harmony for simultaneous actions was provided as well. In order to make the humanoid robot walk like the human actor by following the captured tracks, the constraints of kinematics and zero moment point ZMP shall be considered. We proposed a method of similarity imitation constraint on biped walking for humanoid robot. The walking process was divided into three phases and the corresponding kinematics and ZMP constraints were set on them. Besides, the trigonometric functions were used to connect the consecutive phases to make the track smooth, and the constraint of avoiding singular pose was also accomplished by making the knee flexible. We applied the constraints of similarity imitation and reached the similar biped walking on the humanoid robot Aldebaran Nao.