Artificial Neural Network-based Hybrid Force/Position Control of an Assembly Task

Abstract

In the case of complex robotics tasks, pure position control is ineffective since forces appearing during the contacts must also be controlled. However, simultaneous position and force control called hybrid control is then required. Moreover, the non-linear plant dynamics, the complexity of the dynamic parameters determination and computation constraints makes more difficult the synthesis of control laws. In order to satisfy all these constraints, an effective hybrid force/position approach based on artificial neural networks for MIMO systems is proposed. This approach realizes, simultaneously, an identification and control, and it is implemented according to two phases: at first, a neural observer is trained off line on the basis of the data acquired during contact motion, in order to realize a smooth transition from free to contact motion; then, an online learning of the neural controller is implemented using neural observer parameters so that the closed-loop system maintains a good performance. A typical example on which we shall focus is an assembly task. Experimental results on a C5 links parallel robot demonstrate that the robot's skill improves effectively and the force control performances are satisfactory