Betterment process of contract motion by learning method

Contact motion between a robotic manipulator and a workpiece is a fundamental operation which occurs frequently. The contact motion is a very short time phenomenon and a so-called impact force arises. If one uses only a feedback control scheme, it is difficult to realize a desirable contact motion. In the paper, a new control method, for the contact motion by learning control is proposed. The learning control is based on an iterative operation, and is one of the feed forward control methods which do not need precise values of system parameters or a model of the impact force. The proposed learning controller has two features as follows: it observes input and output signals at the different period so as to improve a transient response of a system and it can learn an initial state of the system, which includes the approach velocity of the manipulator. By learning the approach velocity, fast contact motion can be achieved. Simulation results are shown to verify an effectiveness of the proposed method.<>