Robot Learning Control Based on Neural Network Prediction

摘要

Learning feedforward control based on the available dynamic/kinematic system model and sensor information is generally effective for reducing the repeatable errors of a learned trajectory. For new trajectories, however, the system cannot benefit from previous learning data and it has to go through the learning process again to regain its performance. In industrial applications, this means production line has to stop for learning, and the overall productivity of the process is compromised. To solve this problem, this paper proposes a learning control scheme based on neural network (NN) prediction. Learning/training is performed for the neural networks for a set of trajectories in advance. Then the feedforward compensation torque for any trajectory in the set can be calculated according to the predicted error from multiple neural networks managed with expert logic. Experimental study on a 6-DOF industrial robot has shown the superior performance of the proposed NN based learning scheme in the position tracking as well as the residual vibration reduction, without any further learning or end-effector sensors during operation after completion learning/training of motion trajectories in advance.© 2012 ASME