机器人计算力矩不确定性的神经网络补偿控制*

提出一种由计算力矩控制器和神经网络补偿控制器相结合的控制方案,探讨了用神经网络补偿机器人计算力矩不确定性的方法,推导了网络权值的自适应调整律,并证明了系统的稳定性和误差的收敛性.该方案结构简单、鲁棒性强,且神经网络补偿器有较好的适应性,无须事先知道机器人动力学参数和结构的精确值.对机器人轨迹跟踪的仿真结果表明,所提方案具有很好的鲁棒性和抗干扰能力.

Neural network compensation control of robot computed torque uncertainties

This paper proposed a novel control scheme, whick was based on the combination of computed torque control as a feed-forward structure and a neural network as a compensation structure, to improve the computed torque control uncertainties of a pol.ishing robot. The resulting control scheme had a simple structure with enhanced robustness. Since the neuro-compensator had good adaptability, accurate knowledge of both the robot dynamic parameters and structure were not required in advance. Simulation studies on robot trajectory tracking verify the robustness and anti-disturbance capacity of the proposed control method.