Adaptive Optimal Control of UAV Formation Based on Policy Iteration

被引：1

作者：

Xu, Guangyan ^{[1
]}

Zhang, Shugang ^{[1
]}

Lin, Hao ^{[1
]}

机构：

[1] Shenyang Aerosp Univ, Sch Automat, Shenyang 110136, Peoples R China

来源：

2022 34TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC | 2022年

关键词：

Policy iteration; Adaptive dynamic programming; Optimal control; UAV formation; ZERO-SUM GAMES; TIME; SYSTEMS;

D O I：

10.1109/CCDC55256.2022.10033911

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, aiming at the problem of UAV formation control, a method based on policy iteration is proposed to study the optimal control policy of UAV formation. When the system model is unknown, this algorithm transforms the problem into online solving the Algebraic Riccati Equation. Through online iteration, the value function and the control policy can be updated at the same time. Finally, the optimal control policy is obtained and the nonlinear system is converged. Experimental results show that compared with the traditional control policy, the controller improves the stability of the UAV formation. The convergence speed and robustness of the system are also significantly enhanced, and the control performance is more optimized. At last, the simulation results verify the effectiveness of the proposed method.

引用

页码：4145 / 4150

页数：6

共 13 条

[1] Policy Iteration Based Online Adaptive Optimal Fault Compensation Control for Spacecraft
Du, Yanbin
Jiang, Bin
Ma, Yajie
[J]. INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS, 2021, 19 (04) : 1607 - 1617
[2] Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics
Jiang, Yu
Jiang, Zhong-Ping
[J]. AUTOMATICA, 2012, 48 (10) : 2699 - 2704
[3] Lewis F. L., 2012, APPROXIMATE DYNAMIC
[4] Reinforcement Learning and Feedback Control USING NATURAL DECISION METHODS TO DESIGN OPTIMAL ADAPTIVE CONTROLLERS
Lewis, Frank L.
Vrabie, Draguna
Vamvoudakis, Kyriakos G.
[J]. IEEE CONTROL SYSTEMS MAGAZINE, 2012, 32 (06): : 76 - 105
[5] Optimal control for discrete-time affine non-linear systems using general value iteration
Li, H.
Liu, D.
[J]. IET CONTROL THEORY AND APPLICATIONS, 2012, 6 (18) : 2725 - 2736
[6] Integral Reinforcement Learning for Linear Continuous-Time Zero-Sum Games With Completely Unknown Dynamics
Li, Hongliang
Liu, Derong
Wang, Ding
[J]. IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2014, 11 (03) : 706 - 714
[7] Liang Mingminga, 2020, NEUROCOMPUTING, P23
[8] Sutton R. S., 2019, Reinforcement Learning, V2nd
[9] Online solution of nonlinear two-player zero-sum games using synchronous policy iteration
Vamvoudakis, Kyriakos G.
Lewis, F. L.
[J]. INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2012, 22 (13) : 1460 - 1483
[10] Adaptive optimal control for continuous-time linear systems based on policy iteration
Vrabie, D.
Pastravanu, O.
Abu-Khalaf, M.
Lewis, F. L.
[J]. AUTOMATICA, 2009, 45 (02) : 477 - 484

← 1 2 →