Optimizing Unmanned Aerial Vehicle Swarm Mission Chains with Communication Coupling Considerations

Unmanned aerial vehicle (UAV) swarm will play a significant role in both civilian and military applications in the future, with mission chains reflecting the Observe-Orient-Decide-Act (OODA) loop, effectively integrating distributed mission capabilities of UAV swarms. Thus, a fast and efficient method for optimizing these mission chains is crucial. However, due to the high uncertainty inherent in swarm missions and the coupled relationship between mission and communication, optimizing mission chains presents significant challenges. Building on complex network theory and network flow theory, this paper establishes a fundamental optimization model for mission chains that takes into account both communication and mission layers within UAV swarms. Furthermore, it incorporates the coupled relationships between swarm communication and missions into the optimization objectives and constraints, resulting in a multi-dimensional optimization model. To solve this mission chain optimization problem, Proximal Policy Optimization (PPO) algorithm is employed, with special consideration given to target change scenarios encountered by UAV swarms during mission execution. Through case studies, the effectiveness of this method is demonstrated, providing valuable guidance for mission scheduling in UAV swarms.