Motion planning based on hierarchical knowledge using genetic programming

There are many researches about the motion planning problem. In this field, main research is to generate the motion for specific robot and task without the previously acquired motions. We consider the motion planning by reusing knowledge. It is our object to realize the hierarchical knowledge with reusing. In this paper, we adopt tree-based representation for expressing the knowledge of the motion and adopt genetic programming as a learning method. We construct the motion planning system using the hierarchical knowledge. We apply the proposed method to the six legged locomotion robot to show its availability