Adaptive neural network-based finite-time impedance control of constrained robotic manipulators with disturbance observer
Adaptive neural network-based finite-time impedance control of constrained robotic manipulators with disturbance observer
复制标题
基于自适应神经网络的扰动观测器约束机器人机械臂有限时间阻抗控制
DOI：
10.1109/tcsii.2021.3109257
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
and J. Liu
中科院分区：
文献类型：
--
作者：
G. Li;X. Chen;J. Yu;and J. Liu
本文提出了一种基于自适应神经网络的带干扰观测器的受限机器人有限时间阻抗控制方法。首先，通过将障碍李雅普诺夫函数与有限时间稳定控制理论相结合，使得控制系统在不违反全状态约束的情况下具有更快的收敛速度。其次，引入自适应神经网络来逼近未建模动态，并设计干扰观测器来补偿未知时变干扰。然后，采用带有误差补偿机制的指令滤波控制技术，解决了传统反推控制的“复杂性爆炸”问题，提高了控制精度。仿真结果表明了所提出的控制方法的有效性。
This brief proposes an adaptive neural network-based finite-time impedance control method for constrained robotic manipulators with disturbance observer. Firstly, by combining barrier Lyapunov functions with the finite-time stability control theory, the control system has a faster convergence rate without violating the full state constraints. Secondly, the adaptive neural network is introduced to approximate the unmodeled dynamics and a disturbance observer is designed to compensate for the unknown time-varying disturbances. Then, the command filtered control technique with error compensation mechanism is used to deal with the “explosion of complexity” of traditional backstepping and improve the control accuracy. The simulation results show the effectiveness of the proposed control method.