抄録
This paper describes trajectory planning for a manipulator to grasp an object placed on a table. The more obstacles are on the table, the more calculation costs are needed to find a course for avoiding the obstacles. To overcome this problem, we use accumulated behavior data, which is a set of planning results that succeeded reaching task under various situation. One behavior data is composed of obstacles arrangement and manipulation trajectory. The manipulator acts on the information that is decided by comparing data arrangement and present arrangement. For evaluating this planning, we performed experiments in different conditions on a simulator.
