Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2021, 4(3); doi: 10.25236/AJCIS.2021.040308.

Research on multi UAV attack defense confrontation algorithm based on machine learning


Bo Liu, Xuan Li, Tianci Zheng, Wenyu Gao, Xinyu Zhang, Xiaoyan Wang

Corresponding Author:
Bo Liu

College of Materials Science and Engineering, Jilin University, Changchun 130022, China


In recent years, with the continuous development and wide application of unmanned technology, the use of unmanned aircraft in various fields such as agriculture, industry, disaster, leisure and military purposes has increased, and even played an irreplaceable role in certain fields. However, the functions of a single drone are very limited and cannot meet the increasing diversified needs of people. Among the many diverse needs of people, target tracking is a very important task that unmanned aircraft systems need to undertake in future application scenarios. Therefore, how to make multiple drones work together to complete the tracking of the same target has become an important research topic. However, so far, the path planning of many unmanned cooperative tracking targets has not been well resolved. This paper combines a DQN-based MADDPG (Multi-Agent Deep Deterministic Policy Gradient) algorithm to propose a path planning method for multiple UAVs to cooperatively track targets, which can dynamically plan and adjust the flight path of multiple cooperative UAVs in real time and get better tracking effect in a period of time.


DQN, MADDPG, Multiple UAVs, Path Planning

Cite This Paper

Bo Liu, Xuan Li, Tianci Zheng, Wenyu Gao, Xinyu Zhang, Xiaoyan Wang. Research on multi UAV attack defense confrontation algorithm based on machine learning. Academic Journal of Computing & Information Science (2021), Vol. 4, Issue 3: 52-59. https://doi.org/10.25236/AJCIS.2021.040308.


[1] Volodymyr Mnih, Koray Kavukcuoglu,David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, et al. Human-level control through deepreinforcement learning.Nature, 518(7540): 529–533, 2015.

[2] WEI H. Research of UCAV air combat based on reinforcement learning[D].Harbin :Harbin Institute of Technology,2015(in Chinese).

[3] I. Mordatch and P. Abbeel. Emergence of grounded compositional language in multi-agent populations. arXiv preprint arXiv:1703.04908, 2017.

[4] J. N. Foerster, Y. M. Assael, N. de Freitas, and S. Whiteson. Learning to communicate with deep multi-agent reinforcement learning. CoRR, abs/1605.06676, 2016.

[5] LUO D L,XU Y,ZHANG J P.New progresses on UAV swarm confrontation[J]. Science & Technology Review,2017,35(7) :26-31(in Chinese).

[6] ZHANG Yaozhong, XU Jialin, YAO Kangjia, LIU Jieling. Pursuit missions for UAV swarms based on DDPG algorithm [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(10): 324000-324000.

[7] Lowe R, Wu Y, Tamar A, et al. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments [J]. 2017.