This paper proposes a novel pursuit strategy for a quadrotor-type UAV pursuit evasion game. The novel guidance law considering 3-dimensional and quadrotor UAV maneuvers is proposed as a baseline and expert knowledge for UAV pursuit-evasion games. In this paper, we propose guided exploration reinforcement learning (GE-DDPG) to enhance convergence time and exploration efficiency compared to pure DDPG with Gaussian noise and behavior cloning. The simulation results show that the proposed method outperforms the baseline guidance law and other DDPG methods in capture time and performance in UAV maneuvering scenarios.
Guided Exploration Reinforcement Learning for UAV Pursuit-Evasion Games
Lect. Notes in Networks, Syst.
International Conference on Robot Intelligence Technology and Applications ; 2023 ; Taicang December 06, 2023 - December 08, 2023
22.11.2024
16 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Pursuit Evasion Games using Collision Cones
AIAA | 2018
|Double Threat in Pursuit-Evasion Games
British Library Conference Proceedings | 1994
|Pursuit Evasion Games with Imperfect Information Revisited
British Library Conference Proceedings | 2018
|Orbital Multi-Player Pursuit-Evasion Game with Deep Reinforcement Learning
Springer Verlag | 2024
|