Varying-Parameter RNN Activated by Finite-Time Functions for Solving Joint-Drift Problems of Redundant Robot Manipulators

Joint-drift problem may lead to task execution failure or robot damage. To solve this problem, a finite-time varying-parameter recurrent neural network (FT-VP-RNN) is proposed and investigated in this paper. First, a quadratic programming (QP) based joint-drift-free (JDF) scheme is developed, which consists of an optimization criterion and a kinematic equation at velocity layer. A feedback control is then added into the kinematic equation as the equality constraint, and a feedback-considered joint-drift-free (FC-JDF) scheme is obtained. Second, a novel FT-VP-RNN is designed to solve the FC-JDF scheme and a corresponding finite-time convergence theorem is proposed. The outstanding advantages of the proposed FT-VP-RNN are the real-time computation, exponential convergence, and the ability to eliminate the initial errors. Finally, three path-tracking simulations and comparisons are conducted to verify the effectiveness, accuracy, practicability, and safety of the proposed FT-VP-RNN for solving the joint-drift problems of redundant robot manipulators.