Intelligent Air Combat Maneuvering Decision Method of Multi-UAV System Based on TA-MASAC

Kai Zhang, Yang Xu, Chaolun Liu, Yangyang Zhai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

To meet the cooperation needs of multiple UAVs in the three-dimensional air combat environment, a multi-agent soft actor-critic algorithm based on the maximum entropy and target allocation named TA-MASAC is proposed. Firstly, this paper expands the air combat environment from two-dimensional to three-dimensional and constructs a multi-UAV air combat mission model and decision-making model in the three-dimensional environment. Then, a multi-UAV countermeasure target allocation based on the Hungarian algorithm is proposed, which is introduced into the MASAC algorithm to explore strategies under the condition of effective cluster coordination. Finally, a 2vs2 multi-UA V air combat simulation is carried out, and the proposed algorithm has proved its feasibility and effectiveness.

Original languageEnglish
Title of host publication2023 5th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages299-303
Number of pages5
ISBN (Electronic)9798350357950
DOIs
StatePublished - 2023
Event5th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2023 - Hangzhou, China
Duration: 1 Dec 20233 Dec 2023

Publication series

Name2023 5th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2023

Conference

Conference5th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2023
Country/TerritoryChina
CityHangzhou
Period1/12/233/12/23

Keywords

  • air combat
  • multi-agent system
  • reinforcement learning
  • UAV

Fingerprint

Dive into the research topics of 'Intelligent Air Combat Maneuvering Decision Method of Multi-UAV System Based on TA-MASAC'. Together they form a unique fingerprint.

Cite this