A Conflict Resolution Method for Heterogeneous Platforms Based on Graph Neural Network Reinforcement Learning

Abstract

The present invention provides a conflict resolution method for heterogeneous platforms based on graph neural network reinforcement learning, which includes the following steps: first, set corresponding state vectors and action space vectors according to the specific types and characteristics of each heterogeneous aircraft; The starting position of the quality aircraft, the position of the target point and related state information, establish a conflict network graph structure according to the state and environmental information, and establish a conflict degree evaluation function; then establish a graph neural network structure and conduct training; finally use the trained graph neural network The network model completes the conflict resolution of heterogeneous platforms. The graph neural network structure of the present invention encodes the state vectors of heterogeneous aircraft into state vectors of the same dimension through the state information encoding module, the graph convolution network module extracts feature vectors, the action selection module obtains state-action values, and combines reinforcement learning to train each The heterogeneous aircraft provides an effective and feasible solution to 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