Multi-unmanned aerial vehicle cooperative air combat maneuver decision-making method based on multi-agent reinforcement learning

Abstract

The invention discloses a multi-unmanned aerial vehicle cooperative air combat maneuver decision-making method based on multi-agent reinforcement learning. The problem of autonomous decision-making of maneuver actions in multi-unmanned aerial vehicle cooperative air combat in simulation of many-to-many air combat is solved. The method comprises the following steps: creating a motion model of an unmanned aerial vehicle platform; analyzing a state space, an action space and a reward value of a multi-machine air combat maneuvering decision based on multi-machine air combat situation assessment of an attack area, a distance and an angle factor; designing a target distribution method and a strategy coordination mechanism in a collaborative air combat, defining behavior feedback of each unmanned aerial vehicle in target distribution, situation advantages and safe collision avoidance through distribution of reward values, and achieving strategy coordination after training. According to the method, the ability of multiple unmanned aerial vehicles to carry out collaborative air combat maneuvering autonomous decision making can be effectively improved, higher collaboration and autonomous optimization are achieved, and the decision making level of unmanned aerial vehicle formation in continuous simulation and learning is continuously improved.

Description

technical field [0001] The invention belongs to the technical field of unmanned aerial vehicles, and in particular relates to a multi-unmanned aerial vehicle cooperative air combat maneuver decision-making method. Background technique [0002] At present, drones have been able to complete tasks such as reconnaissance, surveillance and ground attack, and are playing an increasingly irreplaceable role in modern warfare. However, due to the limitation of the level of intelligence, UAVs are still unable to make autonomous air combat maneuver decisions, especially the autonomous coordinated air combat of multiple UAVs. Therefore, improving the intelligence level of UAVs and enabling UAVs to automatically generate control commands to complete maneuvers in air combat according to the situational environment is the current main research direction. [0003] The essence of allowing UAVs to complete autonomous decision-making in air combat maneuvers is to complete the mapping from air...

AI Technical Summary

Problems solved by technology

The existing distributed collaborative air combat decision-making methods mostly use target allocation first, and then convert the many-to-many air combat into a one-to-one situation according to the result of the target allocation. This method cannot make good use of multi-target attack capabilities and formation operations. The tactical synergy cannot achieve the effect of 1+1>2

Images