A Data-Driven Model-Reference Adaptive Control Approach Based on Reinforcement Learning

被引:2
作者
Abouheaf, Mohammed [1 ]
Gueaieb, Wail [2 ]
Spinello, Davide [3 ]
Al-Sharhan, Salah [4 ]
机构
[1] Bowling Green State Univ, Coll Technol Architecture & Appl Engn, Bowling Green, OH 43402 USA
[2] Univ Ottawa, Sch Elect Engn & Comp Sci, Ottawa, ON K1N 6N5, Canada
[3] Univ Ottawa, Dept Mech Engn, Ottawa, ON K1N 6N5, Canada
[4] Machine Intelligence Res Labs, Auburn, WA 98071 USA
来源
2021 IEEE INTERNATIONAL SYMPOSIUM ON ROBOTIC AND SENSORS ENVIRONMENTS (ROSE 2021) | 2021年
基金
加拿大自然科学与工程研究理事会;
关键词
Model-Reference Control; Integral Bellman Equation; Integral Reinforcement Learning; Adaptive Critics; TRACKING CONTROL; SYSTEMS;
D O I
10.1109/ROSE52750.2021.9611772
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Model-reference adaptive systems refer to a consortium of techniques that guide plants to track desired reference trajectories. Approaches based on theories like Lyapunov, sliding surfaces, and backstepping are typically employed to advise adaptive control strategies. The resulting solutions are often challenged by the complexity of the reference model and those of the derived control strategies. Additionally, the explicit dependence of the control strategies on the process dynamics and reference dynamical models may contribute in degrading their efficiency in the face of uncertain or unknown dynamics. A model-reference adaptive solution is developed here for autonomous systems where it solves the Hamilton-Jacobi-Bellman equation of an error-based structure. The proposed approach describes the process with an integral temporal difference equation and solves it using an integral reinforcement learning mechanism. This is done in real-time without knowing or employing the dynamics of either the process or reference model in the control strategies. A class of aircraft is adopted to validate the proposed technique.
引用
收藏
页数:7
相关论文
共 31 条
[1]  
Abdullahi A, 2020, INT CONF SYST THEO, P904, DOI [10.1109/ICSTCC50638.2020.9259641, 10.1109/icstcc50638.2020.9259641]
[2]  
Abouheaf M., 2017, International Journal of Digital Signals and Smart Systems, V1, P143
[3]   Discrete-time dynamic graphical games: model-free reinforcement learning solution [J].
Abouheaf M.I. ;
Lewis F.L. ;
Mahmoud M.S. ;
Mikulski D.G. .
Control theory technol., 1 (55-69) :55-69
[4]   Responding to Illegal Activities Along the Canadian Coastlines Using Reinforcement Learning [J].
Abouheaf, Mohammed ;
Qu, Shuzheng ;
Gueaieb, Wail ;
Abielmona, Rami ;
Harb, Moufid .
IEEE INSTRUMENTATION & MEASUREMENT MAGAZINE, 2021, 24 (02) :118-126
[5]  
Abouheaf M, 2020, IEEE SYS MAN CYBERN, P1866, DOI [10.1109/smc42975.2020.9283399, 10.1109/SMC42975.2020.9283399]
[6]   Guidance Mechanism for Flexible-Wing Aircraft Using Measurement-Interfaced Machine-Learning Platform [J].
Abouheaf, Mohammed ;
Mailhot, Nathaniel Q. ;
Gueaieb, Wail ;
Spinello, Davide .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2020, 69 (07) :4637-4648
[7]  
Abouheaf M, 2019, 2019 IEEE INTERNATIONAL SYMPOSIUM ON ROBOTIC AND SENSORS ENVIRONMENTS (ROSE 2019), P96, DOI [10.1109/rose.2019.8790424, 10.1109/rose.2019.8790432]
[8]   Load frequency regulation for multi-area power system using integral reinforcement learning [J].
Abouheaf, Mohammed ;
Gueaieb, Wail ;
Sharaf, Adel .
IET GENERATION TRANSMISSION & DISTRIBUTION, 2019, 13 (19) :4311-4323
[9]   Multi-agent discrete-time graphical games and reinforcement learning solutions [J].
Abouheaf, Mohammed I. ;
Lewis, Frank L. ;
Vamvoudakis, Kyriakos G. ;
Haesaert, Sofie ;
Babuska, Robert .
AUTOMATICA, 2014, 50 (12) :3038-3053
[10]  
Abouheaf MI, 2013, IEEE DECIS CONTR P, P5803, DOI 10.1109/CDC.2013.6760804