迭代学习控制
人工神经网络
控制理论(社会学)
自适应控制
计算机科学
有界函数
跟踪误差
弹道
机器人
边界(拓扑)
数学优化
人工智能
数学
控制(管理)
天文
物理
数学分析
作者
Lingwei Wu,Qiuzhen Yan,Jianping Cai
出处
期刊:IEEE Access
[Institute of Electrical and Electronics Engineers]
日期:2019-01-01
卷期号:7: 180194-180204
被引量:32
标识
DOI:10.1109/access.2019.2958371
摘要
In this paper, a neural network-based adaptive iterative learning control scheme is developed to solve the trajectory tracking problem for rigid robot manipulators with arbitrary initial errors. Time-varying boundary layers are used to relax the zero initial error condition which must be observed in traditional iterative learning control design, and adaptive learning neural networks are constructed to approximate uncertainties in robotic systems, whose optimal weights are estimated by using partial saturation difference learning method. For arbitrary bounded initial state errors, the tracking error of robot manipulators will asymptotically converge to a tunable residual set as the iteration number increases. An illustrative example and the comparisons are provided to demonstrate the effectiveness of the proposed neural network-based adaptive iterative learning control scheme.
科研通智能强力驱动
Strongly Powered by AbleSci AI