论文部分内容阅读
针对具有参数不确定刚性机器人系统的跟踪控制问题,提出了一种基于视觉反馈和全调节RBF神经网络的自适应反演控制器设计方法。根据安装在末端执行器的CCD摄像机提取的特征点确定期望位置,利用与一般设计不同的全调节RBF神经网络逼近系统的不确定项及外界干扰。在调节RBF神经网络权值的同时调节中心点值和影响范围,使得全调节RBF神经网络具有了更强的在线逼近能力。应用Lyapunov稳定性理论,证明了系统的所有信号均有界,控制器可以保证机械臂的运动按指数收敛到期望位置。仿真结果验证了所提控制器的有效性。
In order to solve the tracking control problem of rigid robotic systems with uncertain parameters, an adaptive inversion controller design method based on visual feedback and fully-tuned RBF neural networks is proposed. Based on the feature points extracted by the CCD camera installed in the end effector, the desired position is determined, and the fully adjustable RBF neural network, which is different from the general design, is used to approximate the system uncertainties and external disturbances. When the weight of RBF neural network is adjusted, the center point value and the influence range are adjusted, which makes the fully-tuned RBF neural network have stronger online approximation ability. Applying Lyapunov stability theory, it is proved that all the signals of the system are bounded, and the controller can ensure that the movement of the manipulator exponentially converges to the desired position. The simulation results verify the effectiveness of the proposed controller.