Joint torque optimization for redundant manipulators using neuralnetworks

摘要

One of the important applications for the resolution of redundantmanipulators is torque optimization. To achieve this objective, findingout the most desirable configuration from the infinite number ofpossible configurations that satisfy the end-effector constraint isrequired. It has been previously shown that the pseudoinverse plays acrucial role in doing such calculations. In this work, the Tank-Hopfield(TH) network is adopted for pseudoinverse calculations and theconnection weights of the network can be directly obtained from theknown matrices at each sampling time. At acceleration level, the jointacceleration commands related to torque optimization are generated fromthe outputs of the network. Incorporating the TH network into theNull-Space (NS) algorithm allows a torque optimization to be implementedin real-time. Simulation results for a three-link planar manipulator aregiven to prove that the proposed scheme is efficient and practical