Data-Driven Distributed Common Operational Picture from Heterogeneous Platforms using Multi-Agent Reinforcement Learning

TL;DR

This paper introduces a multi-agent reinforcement learning framework for real-time, resilient formation of a common operational picture from heterogeneous unmanned platforms, improving military situational awareness under adverse conditions.

Contribution

It presents a novel multi-agent learning approach that enables autonomous, secure communication and COP formation, with joint training of COP models and agent policies for resilience.

Findings

Less than 5% error in COP accuracy

Resilience to GPS denial and communication disruptions

Effective in Starcraft-2 simulation environment

Abstract

The integration of unmanned platforms equipped with advanced sensors promises to enhance situational awareness and mitigate the "fog of war" in military operations. However, managing the vast influx of data from these platforms poses a significant challenge for Command and Control (C2) systems. This study presents a novel multi-agent learning framework to address this challenge. Our method enables autonomous and secure communication between agents and humans, which in turn enables real-time formation of an interpretable Common Operational Picture (COP). Each agent encodes its perceptions and actions into compact vectors, which are then transmitted, received and decoded to form a COP encompassing the current state of all agents (friendly and enemy) on the battlefield. Using Deep Reinforcement Learning (DRL), we jointly train COP models and agent's action selection policies. We demonstrate resilience to degraded conditions such as denied GPS and disrupted communications. Experimental validation is performed in the Starcraft-2 simulation environment to evaluate the precision of the COPs and robustness of policies. We report less than 5% error in COPs and policies resilient to various adversarial conditions. In summary, our contributions include a method for autonomous COP formation, increased resilience through distributed prediction, and joint training of COP models and multi-agent RL policies. This research advances adaptive and resilient C2, facilitating effective control of heterogeneous unmanned platforms.