Cooperative working performance of a dual-arm robot system optimised by a neural network adaptive preset control

Abstract

This paper innovatively integrates preset performance control technology with adaptive neural network control targeting a dual-arm robot system with nonlinear uncertainties, developing a strategy demonstrating exceptional control performance under dynamic conditions. First, a comprehensive and precise co-control model for the dual-arm robot is constructed based on an in-depth analysis of robotic kinematics and dynamics. Subsequently, the system model's intrinsic uncertainties and external disturbances are studied and integrated into a unified uncertainty module. Based on this, neural networks are introduced as an excellent approximation tool to approximate the uncertainty module. Furthermore, by introducing preset performance control strategies and ingeniously transforming error constraints, the output constraint problem of the robot system is successfully solved, ensuring a significant improvement in system convergence speed and control accuracy. The effectiveness and superiority of the proposed adaptive neural network control strategy were verified through a series of simulation experiments in the MATLAB environment.