Interactive task generation for humanoid based on human motion strategy

The objective of this research is to propose an interactive method for "task" generating of humanoid robots to accomplish adaptable motions to environments. It is likely that task generation by using the interaction between strategies of human's motions and humanoid robots is effective because the structure of humanoid have a resemblance to that of human. To confirm the effectiveness of proposed method, first, we measured the human's motions such as walking and stair ascending with motion capturing system, and analyzed the patterns of joints angles and floor reaction force. Secondly, each measured motion is divided into meaningful components called "phases" which contained the trajectories for end-effector of humanoid's motions and composed a task. Thirdly, we constructed the task library with phases and tasks for the humanoid's motions. As a result, we found the task such as walking and stair ascending could be generated based on human motion strategy, and motion trajectory of these tasks could be changed by Bezier curve. A series of motions for humanoids was carried out by using task library which consisted of these tasks. These works were simulated by OpenHRP. In conclusion, it was verified that the humanoid's task could be generated according to different environments by the proposed method.