不确定性机器人的神经网络补偿控制

Neural Compensating Control of Uncertain Robots

中文关键词  机器人  RBF神经网络  鲁棒补偿控制

英文关键词  robot manipulator  RBF neural network  robust compensating control

中文摘要

      本文研究具有不确定性的机器人的轨迹跟踪控制问题。提出了一种由计算力矩控制器和神经网络补偿控制器构成的控制方案。探讨了一种用神经网络估计机器人系统不确定性的途径。给出了神经补偿控制器的设计方法，并证明了闭环系统的收敛性。仿真结构表明所提方案具有很好的鲁棒性和抗干扰能力。

英文摘要

      A new trajectory tracking control scheme of robot manipulators is developed in this paper. The proposed scheme consists of a well known computed torque controller, which is based on the known nominal robot dynamics model, and a compensating controller, which is realized incorporating an radial basis function (RBF) neural network estimator and a discontinuous control signal. The compensating controller works like an add-on device. The proposed control scheme is effective to the robot systems with unknown parameters and disturbance such as Coulomb friction. The simulation results have demonstrated the feasibility of the proposed scheme.