Autonomous Conflict Resolution Method for multi-UAVs Based on Preorder Flight Information

In complex low altitude airspace, some factors may cause that flight information cannot interact properly between UAVs. UAV cannot normally obtain flight information of others within its communication range. Therefore, we propose a distributed approach to multi-aircraft real-time conflict resolution. UAVs can enhance the ability of autonomous conflict resolution through the study of preorder flight information with the prerequisite for the unavailability of others' flight information. First, we obtain the payoff of safety and efficiency adopting speed and heading adjustments as maneuver strategy of collision avoidance. Then, according to the preorder flight information, UAV builds a memory pool which is learned by it to obtain the most rewarding collision avoidance strategy. Finally, the simulation results on the random flight scenario of two concentric circles show that our approach is promising in terms of safety and system efficiency.