The Study on a Fighter Against a Medium-range Air-to-air Missile Based on Deep Deterministic Policy Gradient Algorithm

Abstract

The evasive maneuver strategy for a fighter against a medium-range air-to-air missile is crucial to improving aircraft survivability.In this paper, the deep deterministic policy gradient algorithm to train the agent to learn the evasive maneuver strategy is studied.The missile-aircraft engagement model parameters are the input states.The aircraft control commands are taken as the output actions.The missile-aircraft pursuit-evasion model is taken as the learning environment.The shaping reward, including engagement model parameters and flight parameters, and the sparse reward of the engagement results are designed.Finally, the end-to-end evasive maneuver strategy from the state parameters to the aircraft control variables is realized.The attack zones of four classic evasive maneuvers based on prior knowledge by simulating are compared.It is proved that the evasion strategy developed in this paper is second only to the tail dive maneuver.However, this strategy has the lowest dependence on the specialized domain knowledge of missile evasion.

Keywords

• missile evasion
• evasive maneuver strategy
• deep deterministic policy gradient
• deep reinforcement learning