Kinematic Resolutions of Redundant Robot Manipulators using Integration-Enhanced RNNs

TL;DR

This paper introduces an integration-enhanced RNN for redundant robot manipulator control, improving accuracy and robustness against measurement noise through theoretical analysis, simulations, and practical experiments.

Contribution

It proposes a novel IE-RNN that enhances kinematic resolution of redundant robots, demonstrating superior noise robustness and convergence properties.

Findings

IE-RNN achieves zero residual error under noise

The method demonstrates strong robustness in practical experiments

Theoretical analysis confirms convergence properties

Abstract

Recently, a time-varying quadratic programming (QP) framework that describes the tracking operations of redundant robot manipulators is introduced to handle the kinematic resolutions of many robot control tasks. Based on the generalization of such a time-varying QP framework, two schemes, i.e., the Repetitive Motion Scheme and the Hybrid Torque Scheme, are proposed. However, measurement noises are unavoidable when a redundant robot manipulator is executing a tracking task. To solve this problem, a novel integration-enhanced recurrent neural network (IE-RNN) is proposed in this paper. Associating with the aforementioned two schemes, the tracking task can be accurately completed by IE-RNN. Both theoretical analyses and simulations results prove that the residual errors of IE-RNN can converge to zero under different kinds of measurement noises. Moreover, practical experiments are elaborately made to verify the excellent convergence and strong robustness properties of the proposed IE-RNN.