Heterogeneous platform conflict resolution method based on graph neural network reinforcement learning

Abstract

The invention provides a heterogeneous platform conflict resolution method based on graph neural network reinforcement learning. The heterogeneous platform conflict resolution method comprises the following steps: firstly, setting corresponding state vectors and action space vectors according to specific types and features of various heterogeneous aircrafts; initializing the initial position, the target point position and related state information of each heterogeneous aircraft, establishing a conflict network diagram structure according to the state and environment information, and establishing a conflict degree evaluation function; then establishing a graph neural network structure, and performing training; and finally, completing conflict resolution of heterogeneous platforms by using the trained graph neural network model. According to the graph neural network structure, state vectors of heterogeneous aircrafts are coded into state vectors of the same dimension through the state information coding module, the graph convolutional network module extracts feature vectors, the action selection module obtains state-action values, and the heterogeneous aircrafts are trained by combining reinforcement learning, and an effective and feasible solution is provided for the conflict resolution problem of heterogeneous platforms.

Description

technical field [0001] The invention belongs to the technical field of aircraft, and relates to a conflict resolution method for heterogeneous multi-aircraft based on graph neural network reinforcement learning. Background technique [0002] The air-to-air platform refers to the part between the space in the aviation field and the aerospace field, and its height ranges between 20-100km. The air-to-air platform aircraft refers to the aircraft that flies on the air-to-air platform and performs related tasks. Its different types It can complete tasks such as reconnaissance, environmental monitoring, electronic countermeasures, material delivery, and military strikes. It has very important strategic value for social people's livelihood and national security. In recent years, due to the advancement of science and technology and the importance attached to the air-to-air platform by governments of various countries, the research and development of the air-to-air platform aircraft h...

AI Technical Summary

Problems solved by technology

In view of the fact that the deep reinforcement learning method is difficult to solve the conflict resolution problem of heterogeneous platform aircraft, a conflict resolution method that can solve heterogeneous platforms is proposed based on graph neural network reinforcement learning

Images