Redundant arm kinematic control with recurrent loop

Abstract

A new neural network approach to robot arm kinematic control based on an iterative update of joint vector is presented. In the proposed method, the pseudo-inverse of the gradient of a Lyapunov function is defined in the joint space to update the joint vector toward a solution. Especially, this paper establishes explicit convergence control schemes to achieve fast and stable convergence. Furthermore, the proposed method allows direct incorporation of potential field approaches to obstacle avoidance into joint trajectory planning. The simulation results demonstrate that the proposed method is effective for the real-time kinematic control of a redundant arm as well as the real-time generation of collision-free joint trajectories. >