Design and Development of Unmanned Combat Game Platform

Abstract

The unmanned combat game platform is the technical carrier to research unmanned combat issues. Although most current unmanned combat simulation platforms can effectively simulate the unmanned combat process, their scenes are fixed and single. They cannot carry out the secondary design of the scene. At the same time, they also lack an effective description of the scene information. Therefore, this paper takes air-ground unmanned combat as a specific task scenario and independently develops an unmanned combat deduction platform based on the Hybrid Stochastic Time Delay Petri Net (HSTPN) modelling theory and PyQt development tool. The platform supports scene modelling and model changes, deep reinforcement learning algorithm battles, animation deductions, file storage, etc. At the same time, a battle decision algorithm is designed based on Proximal Policy Optimization (PPO). The experimental results show that the unmanned combat game platform can fully realize the combat process simulation. Its scene modelling function can show all the hybrid characteristics of the combat process and support the modification of the scene model and its secondary development. The battle function can complete the confrontation game of the decision-making algorithm.