Safe deep reinforcement learning-based adaptive control for USV interception mission

被引：62

作者：

Du, Bin

Lin, Bin

Zhang, Chenming

Dong, Botao

Zhang, Weidong ^{[1
]}

机构：

[1] Shanghai Jiao Tong Univ, Dept Automat, Shanghai 200240, Peoples R China

来源：

OCEAN ENGINEERING | 2022年 / 246卷

基金：

国家重点研发计划;

关键词：

Unmanned surface vessels; Safe reinforcement learning; Data-based learning control; Uniformly ultimate bounded stability; Interception mission; UNIFORM ULTIMATE BOUNDEDNESS; SYSTEMS;

D O I：

10.1016/j.oceaneng.2021.110477

中图分类号：

U6 [水路运输]; P75 [海洋工程];

学科分类号：

0814 ; 081505 ; 0824 ; 082401 ;

摘要：

This paper aims to develop a safe learning scheme of the USV interception mission. A safe Lyapunov boundary deep deterministic policy gradient (SLDDPG) algorithm is presented for the USV interception mission. The uniformly ultimate bounded (UUB) stability of control systems is analyzed under finite safety constraints. A single neuron proportional adaptive control (SNPAC) is applied to pre-train the deep policy network for speeding up the training process. The proposed method is evaluated by a series of simulations of the USVs interception and tracking mission. Compared with the existing results, our method can fast converge to the feasible solution subject to safety constraints and demonstrate a high performance in stability and safety by virtual-reality experiments.

引用

页数：13

共 50 条

[1] USV Path-Following Control Based On Deep Reinforcement Learning and Adaptive Control
Gonzalez-Garcia, Alejandro
Castaneda, Herman
Garrido, Leonardo
[J]. GLOBAL OCEANS 2020: SINGAPORE - U.S. GULF COAST, 2020,
[2] Adaptive Cruise Control Based on Safe Deep Reinforcement Learning
Zhao, Rui
Wang, Kui
Che, Wenbo
Li, Yun
Fan, Yuze
Gao, Fei
[J]. SENSORS, 2024, 24 (08)
[3] Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning
Brunke, Lukas
Greeff, Melissa
Hall, Adam W.
Yuan, Zhaocong
Zhou, Siqi
Panerati, Jacopo
Schoellig, Angela P.
[J]. ANNUAL REVIEW OF CONTROL ROBOTICS AND AUTONOMOUS SYSTEMS, 2022, 5 : 411 - 444
[4] Deep Reinforcement Learning-Based Adaptive IRS Control with Limited Feedback Codebooks
Kim, Junghoon
Hosseinalipour, Seyyedali
Marcum, Andrew C.
Kim, Taejoon
Love, David J.
Brinton, Christopher G.
[J]. IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, : 5171 - 5177
[5] Deep Adaptive Control: Deep Reinforcement Learning-Based Adaptive Vehicle Trajectory Control Algorithms for Different Risk Levels
He, Yixu
Liu, Yang
Yang, Lan
Qu, Xiaobo
[J]. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2024, 9 (01): : 1654 - 1666
[6] AdapSafe: Adaptive and Safe-Certified Deep Reinforcement Learning-Based Frequency Control for Carbon-Neutral Power Systems
Wan, Xu
Sun, Mingyang
Chen, Boli
Chu, Zhongda
Teng, Fei
[J]. THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 4, 2023, : 5294 - 5302
[7] Safe Deep Reinforcement Learning-Based Constrained Optimal Control Scheme for HEV Energy Management
Liu, Zemin Eitan
Zhou, Quan
Li, Yanfei
Shuai, Shijin
Xu, Hongming
[J]. IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION, 2023, 9 (03): : 4278 - 4293
[8] Safe deep reinforcement learning-based constrained optimal control scheme for active distribution networks
Kou, Peng
Liang, Deliang
Wang, Chen
Wu, Zihao
Gao, Lin
[J]. APPLIED ENERGY, 2020, 264
[9] Deep Reinforcement Learning-based Traffic Signal Control
Ruan, Junyun
Tang, Jinzhuo
Gao, Ge
Shi, Tianyu
Khamis, Alaa
[J]. 2023 IEEE INTERNATIONAL CONFERENCE ON SMART MOBILITY, SM, 2023, : 21 - 26
[10] A Deep Reinforcement Learning-based Adaptive Charging Policy for WRSNs
Ngoc Bui
Phi Le Nguyen
Viet Anh Nguyen
Phan Thuan Do
[J]. 2022 IEEE 19TH INTERNATIONAL CONFERENCE ON MOBILE AD HOC AND SMART SYSTEMS (MASS 2022), 2022, : 661 - 667

← 1 2 3 4 5 →