Seminar: Dr. Eiichi Yoshida, AIST Japan
Motion planning for whole-body tasks by humanoid robots
| What |
|
|---|---|
| When |
Mar 19, 2012 from 11:00 am to 12:00 pm |
| Where | IF 4.31/4.33 |
| Add event to calendar |
|
We have been working on whole-body motion planning and control to achieve complex tasks by humanoid robots at our international joint laboratory CNRS-AIST JRL (Joint Robotics Laboratory), UMI3218/CRT. First, a two-stage motion planning method is developed: at the first stage, a global path is planned by using a reduced robot model with a non-holonomic vehicle. This path is then transformed into whole-body dynamic motion including walking and 3-D collision avoidance. Next, a whole-body motion generation method based on generalized inverse kinematics has been developed, which is exploited to plan various motions. One example is whole-body manipulation of large objects without lifting them but by “pivoting”. We have also investigated online motion planning in changing environments in order to allow humanoid robots generate reactive behavior though parallel motion planning and execution. Finally, some perspectives on applications of those research results are addressed.
Biography:
Eiichi Yoshida received Ph.D degrees on Precision Machinery Engineering from Graduate School of Engineering, the University of Tokyo in 1996. He then joined former Mechanical Engineering Laboratory, which was reorganized into National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan. From 1990 to 1991, he was visiting research associate at Swiss Federal Institute of Technology at Lausanne (EPFL). He served as Co-Director of AIST/IS-CNRS/ST2I Joint French-Japanese Robotics Laboratory (JRL) at LAAS-CNRS, Toulouse, France, from 2004 to 2008. He is currently Co-Director of CNRS-AIST JRL (Joint Robotics Laboratory), UMI3218/CRT, Intelligent Systems Research Institute, AIST, Japan, since 2009. His research interests include robot task and motion planning, modular robotic systems, and humanoid robots.


