IEEE Trans Neural Netw Learn Syst. 2022 Aug;33(8):3331-3342. doi: 10.1109/TNNLS.2021.3051946. Epub 2022 Aug 3.
This article proposes an adaptive neural network (NN) control method for an n -link constrained robotic manipulator. Driven by actual demands, manipulator and actuator dynamics, state and input constraints, and unknown time-varying delays are taken into account simultaneously. NNs are employed to approximate unknown nonlinearities. Time-varying barrier Lyapunov functions are utilized to cope with full-state constraints. By resorting to saturation function and Lyapunov-Krasovskii functionals, the effects of actuator saturation and time delays are eliminated. It is proved that all the closed-loop signals are semiglobally uniformly ultimately bounded, full-state constraints and actuator saturation are not violated, and error signals remain within compact sets around zero. Simulation studies are given to demonstrate the validity and advantages of this control scheme.
本文提出了一种用于 n 连杆约束机器人的自适应神经网络（NN）控制方法。受实际需求的驱动，同时考虑了机械手和执行器动力学、状态和输入约束以及未知时变延迟。NN 用于逼近未知的非线性。时变障碍李雅普诺夫函数用于处理全状态约束。通过使用饱和函数和李雅普诺夫 - 克拉索夫斯基泛函，消除了执行器饱和和时滞的影响。证明了所有闭环信号都是半全局一致有界的，全状态约束和执行器饱和都不会违反，并且误差信号保持在零附近的紧集中。仿真研究证明了该控制方案的有效性和优势。
