Deep Reinforcement Learning-Based Cooperative Survivability Maximization for a UAV Fleet on an Air-to-Ground Mission

Authors

  • Barış Başpınar Istanbul Technical University

Abstract

This study focuses on the cooperative strategy development of a UAV team that operates in a hostile environment in which the radar and weapon systems try to track and eliminate them. To simulate the hostile defense system, we present Markov models that generate the detecting and tracking probabilities of a radar system, and calculate the multiple-shot survivability of air vehicles that fly within the hostile environment. A cooperative strategy development procedure is presented based on proximal policy optimization algorithm, which is a deep reinforcement learning method. It is shown that the UAV team can develop cooperative strategies by exploiting enemy’s weakness to maximize team survivability in an air-to-ground mission after training with the proposed reinforcement learning scheme.

Downloads

Published

29-07-2022

How to Cite

[1]
B. Başpınar, “Deep Reinforcement Learning-Based Cooperative Survivability Maximization for a UAV Fleet on an Air-to-Ground Mission”, JAST, vol. 15, no. 2, pp. 94–107, Jul. 2022.

Issue

Section

Articles