Bi-criteria kinematic control of redundant manipulators using a dual neural network

Abstract

A dual neural network is presented for the bicriteria kinematic control of redundant manipulators. To diminish the discontinuity problem of minimum effort solutions, the neural kinematic-control scheme is formulated in the bi-criteria sense of the infinity and Euclidean norms. Physical constraints such as joint limits and joint velocity limits are incorporated simultaneously into the proposed online control scheme. The dual neural network is shown to be globally exponentially convergent to optimal solutions in the bi-criteria sense. The neural network is simulated to control the PA10 robot manipulator with effectiveness demonstrated.