Strategy generation and skill acquisition for automated robotic assembly task

A practical method for generating task strategies applicable to chamferless and high-precision assembly is treated. The difficulties in devising reliable assembly strategies result from various forms of uncertainty, such as an imperfect knowledge of the parts being assembled and limitations of the devices performing the assembly. This problem is approached by having the robot learn the appropriate control response to measured force signals, that is, the mapping relation between sensing data and corrective motion of the robot, through iterative task execution. The strategy is acquired by using a learning algorithm and is represented by a binary tree type database. Experimental results show that an ideal mapping is acquired effectively by using the proposed method and that the assembly task is carried out smoothly