Robust Neurooptimal Control for a Robot via Adaptive Dynamic Programming

被引:60
作者
Kong, Linghuan [1 ,2 ,3 ]
He, Wei [1 ,2 ,3 ]
Yang, Chenguang [4 ]
Sun, Changyin [5 ]
机构
[1] Univ Sci & Technol Beijing, Inst Artificial Intelligence, Beijing 100083, Peoples R China
[2] Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
[3] Univ Sci & Technol Beijing, Key Lab Knowledge Automat Ind Proc, Minist Educ, Beijing 100083, Peoples R China
[4] Univ West England, Bristol Robot Lab, Bristol BS16 1QY, Avon, England
[5] Southeast Univ, Sch Automat, Nanjing 210096, Peoples R China
基金
中国国家自然科学基金;
关键词
Robots; Artificial neural networks; Optimal control; Robustness; Perturbation methods; Mathematical model; Adaptive systems; Adaptive dynamic programming (ADP); neural networks (NNs); robots; robust optimal control; TRACKING CONTROL; NEURAL-NETWORKS; PID CONTROL; DESIGN; STABILIZATION; MANIPULATORS; SYSTEMS;
D O I
10.1109/TNNLS.2020.3006850
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We aim at the optimization of the tracking control of a robot to improve the robustness, under the effect of unknown nonlinear perturbations. First, an auxiliary system is introduced, and optimal control of the auxiliary system can be seen as an approximate optimal control of the robot. Then, neural networks (NNs) are employed to approximate the solution of the Hamilton-Jacobi-Isaacs equation under the frame of adaptive dynamic programming. Next, based on the standard gradient attenuation algorithm and adaptive critic design, NNs are trained depending on the designed updating law with relaxing the requirement of initial stabilizing control. In light of the Lyapunov stability theory, all the error signals can be proved to be uniformly ultimately bounded. A series of simulation studies are carried out to show the effectiveness of the proposed control.
引用
收藏
页码:2584 / 2594
页数:11
相关论文
共 64 条
[1]  
[Anonymous], 2020, IEEE T CYBERNETICS, DOI DOI 10.1109/TCYB.2018.2869084
[2]   Observer-Based Adaptive Backstepping Consensus Tracking Control for High-Order Nonlinear Semi-Strict-Feedback Multiagent Systems [J].
Chen, C. L. Philip ;
Wen, Guo-Xing ;
Liu, Yan-Jun ;
Liu, Zhi .
IEEE TRANSACTIONS ON CYBERNETICS, 2016, 46 (07) :1591-1601
[3]   Muscle-Synergies-Based Neuromuscular Control for Motion Learning and Generalization of a Musculoskeletal System [J].
Chen, Jiahao ;
Qiao, Hong .
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2021, 51 (06) :3993-4006
[4]   Learning Driving Models From Parallel End-to-End Driving Data Set [J].
Chen, Long ;
Wang, Qing ;
Lu, Xiankai ;
Cao, Dongpu ;
Wang, Fei-Yue .
PROCEEDINGS OF THE IEEE, 2020, 108 (02) :262-273
[5]   Adaptive Neural Control of Uncertain Nonlinear Systems Using Disturbance Observer [J].
Chen, Mou ;
Shao, Shu-Yi ;
Jiang, Bin .
IEEE TRANSACTIONS ON CYBERNETICS, 2017, 47 (10) :3110-3123
[6]   Platoon Formation Control With Prescribed Performance Guarantees for USVs [J].
Dai, Shi-Lu ;
He, Shude ;
Lin, Hai ;
Wang, Cong .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2018, 65 (05) :4237-4246
[7]  
Dierks T, 2010, P AMER CONTR CONF, P1568
[8]   Exponential L1 Filtering of Networked Linear Switched Systems: An Event-Triggered Approach [J].
Duan, Dandan ;
Zong, Guangdeng .
JOURNAL OF SYSTEMS SCIENCE & COMPLEXITY, 2020, 33 (02) :383-400
[9]   Adaptive Finite-Time Stabilization of a Class of Uncertain Nonlinear Systems via Logic-Based Switchings [J].
Fu, Jun ;
Ma, Ruicheng ;
Chai, Tianyou .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2017, 62 (11) :5998-6003
[10]   Sampled-data-based stabilization of switched linear neutral systems [J].
Fu, Jun ;
Li, Tai-Fang ;
Chai, Tianyou ;
Su, Chun-Yi .
AUTOMATICA, 2016, 72 :92-99