Towards a comparative study of neural networks in inverse model learning and compensation applied to dynamic robot control

This paper deals with the applications of neural networks in inverse model learning and compensation to the mobile manipulator dynamic trajectory tracking and control. The mobile base is subject to a nonholonomic constraint and the base and onboard manipulator cause disturbances to each other. Compensational neural network controllers are proposed to track dynamic trajectories under a nonholonomic constraint and uncertainties, and compensate the interactions between the base and the manipulator. Comparison was made between neural network controllers with and without model information. It is shown through various simulations that the proposed neural network compensation schemes can give good performances