Research on Application of LSTM-QDN in Intelligent Air Combat Simulation

Abstract

Aiming at the problem of the lack of intelligence of virtual machine opponents in the human-machine confrontation semi-physical simulation environment, it is proposed to apply the deep reinforcement learning method into tactical making-decision for building an AI virtual pilot with self-confrontation and self-learning ability. First, flight dynamics and kinematics are used to build basic flight models in the simulation environment, and a missile attack area is established for weapon model; Second, inspired by the framework of interaction between the agent and the environment in reinforcement learning, a tactical decision architecture for flight agent based on the one-to-one tactical confrontation process is organized. Finally, the improved DQN method is used to fit the value function in the continuous state space, and the network training is completed by means of agent self-antagonism and human-machine confrontation. the well-trained AI model can undertake the role of virtual opponents in human-machine confrontation environment, and shows a certain degree of intelligence in the confrontation process with pilots.