TY - GEN
T1 - Research on Intelligent Evasion Methods for UAV Based on Deep Reinforcement Learning
AU - Duan, Heran
AU - Zhu, Zhanxia
AU - Sun, Chong
AU - Li, Jie
AU - Wang, Chuang
AU - Xue, Mengqi
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - To address the issue of unmanned aerial vehicle (UAV) autonomously evading aerial incoming target, this paper proposes an intelligent evasion method for the UA V based on Soft Actor-Critic (SAC) algorithm. Given the state information of the UA V and the aerial incoming target as input, the proposed method can generate control commands for the UA V as output, achieving end-to-end autonomous evasion decision-making. Based on the evasion model proposed in this paper, we built the air combat environment. This paper introduces a novel reward function used for generating autonomous evasion strategies for UAV, taking into account the situational information of both the UA V and the aerial incoming target. Finally, by comparing the training and simulation results with the Deep Deterministic Policy Gradient (DDPG) algorithm, the paper validates that the intelligent evasion method based on SAC algorithm converges faster, exhibits superior performance, and learns more flexible and intelligent strategy.
AB - To address the issue of unmanned aerial vehicle (UAV) autonomously evading aerial incoming target, this paper proposes an intelligent evasion method for the UA V based on Soft Actor-Critic (SAC) algorithm. Given the state information of the UA V and the aerial incoming target as input, the proposed method can generate control commands for the UA V as output, achieving end-to-end autonomous evasion decision-making. Based on the evasion model proposed in this paper, we built the air combat environment. This paper introduces a novel reward function used for generating autonomous evasion strategies for UAV, taking into account the situational information of both the UA V and the aerial incoming target. Finally, by comparing the training and simulation results with the Deep Deterministic Policy Gradient (DDPG) algorithm, the paper validates that the intelligent evasion method based on SAC algorithm converges faster, exhibits superior performance, and learns more flexible and intelligent strategy.
KW - deep deterministic policy gradient
KW - deep reinforcement learning
KW - intelligent evasion
KW - soft actor critic
KW - unmanned aerial vehicle
UR - http://www.scopus.com/inward/record.url?scp=85195801265&partnerID=8YFLogxK
U2 - 10.1109/ICIT58233.2024.10541040
DO - 10.1109/ICIT58233.2024.10541040
M3 - 会议稿件
AN - SCOPUS:85195801265
T3 - Proceedings of the IEEE International Conference on Industrial Technology
BT - ICIT 2024 - 2024 25th International Conference on Industrial Technology
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 25th IEEE International Conference on Industrial Technology, ICIT 2024
Y2 - 25 March 2024 through 27 March 2024
ER -