Deep reinforcement learning for UAV swarm rendezvous behavior

• Published in: Journal of systems engineering and electronics 2023-04, Vol.34 (2), p.360-373
• Main Authors: Zhang, Yaozhong, Li, Yike, Wu, Zhuoran, Xu, Jialin
• Format: Article
• Language: English
• ISSN: 1004-4132; 1004-4132
• DOI: 10.23919/JSEE.2023.000056

The unmanned aerial vehicle (UAV) swarm techno-logy is one of the research hotspots in recent years. With the continuous improvement of autonomous intelligence of UAV,the swarm technology of UAV will become one of the main trends of UAV development in the future. This paper studies the behavior decision-making process of UAV swarm rendezvous task based on the double deep Q network (DDQN) algorithm. We design a guided reward function to effectively solve the problem of algo-rithm convergence caused by the sparse return problem in deep reinforcement learning (DRL) for the long period task. We also propose the concept of temporary storage area,optimizing the memory playback unit of the traditional DDQN algorithm,improving the convergence speed of the algorithm,and speed-ing up the training process of the algorithm. Different from tradi-tional task environment,this paper establishes a continuous state-space task environment model to improve the authentica-tion process of UAV task environment. Based on the DDQN algorithm,the collaborative tasks of UAV swarm in different task scenarios are trained. The experimental results validate that the DDQN algorithm is efficient in terms of training UAV swarm to complete the given collaborative tasks while meeting the requirements of UAV swarm for centralization and autonomy,and improving the intelligence of UAV swarm collaborative task execution. The simulation results show that after training,the proposed UAV swarm can carry out the ren-dezvous task well,and the success rate of the mission reaches 90％.