Sensor-based learning control of real robots

To make a robot track a given desired motion trajectory, a learning control method is proposed which is based on the repeatability of robot motion. In this method the robot obtains a desired motion by repeating trials (test motion). A merit of this control method is that the input torque pattern that generates the desired motion can be formed without estimating the physical parameters of robot dynamics. Another merit is that acceleration feedback is added in control to make the number of trials decrease. In practice, to allow the robot motion to approach the desired one in each trial the input torque given to the robot at the present trial is modified only by the velocity signal of the real robot motion at the previous trial and the desired one. The convergence to the desired motion is theoretically proved for an approximate representation of nonlinear robot dynamics in the vicinity of the desired motion. Moreover, effectiveness of this control method is demonstrated through actual experiments in which PUMA 560 robot with first three degrees of freedom is used.