Robot motion classification from the standpoint of learning control

In robot learning control, the learning space for executing the general motions of multijoint robot manipulators is very complicated. Therefore, in spite of their ability to generalize, the learning controllers are usually used as subordinates to conventional controllers or the learning process needs to be repeated each time a new trajectory is encountered, because the motion variety requires them to consume excessive amount of memory when they are employed as major roles in motion governing. To simplify learning space complexity, we propose, from the standpoint of learning control, that robot motions be classified according to their similarities. The learning controller can then be designed to govern groups of robot motions with high degrees of similarity without consuming excessive memory resources. Motion classification based on using the PUMA 560 robot manipulator demonstrates the effectiveness of the proposed approach.