Human-Machine Teaming for UAVs: An Experimentation Platform

TL;DR

This paper introduces the Cogment platform, a lightweight experimentation environment designed to facilitate research and development of human-machine teaming in defense and critical systems involving heterogeneous AI agents and humans.

Contribution

The paper presents the Cogment platform, a novel experimentation tool enabling complex human-AI team interactions for research in defense environments.

Findings

Platform supports heterogeneous multi-agent systems

Used in academic research and defense scenarios

Facilitates development and validation of human-machine teaming algorithms

Abstract

Full automation is often not achievable or desirable in critical systems with high-stakes decisions. Instead, human-AI teams can achieve better results. To research, develop, evaluate, and validate algorithms suited for such teaming, lightweight experimentation platforms that enable interactions between humans and multiple AI agents are necessary. However, there are limited examples of such platforms for defense environments. To address this gap, we present the Cogment human-machine teaming experimentation platform, which implements human-machine teaming (HMT) use cases that features heterogeneous multi-agent systems and can involve learning AI agents, static AI agents, and humans. It is built on the Cogment platform and has been used for academic research, including work presented at the ALA workshop at AAMAS this year [1]. With this platform, we hope to facilitate further research on human-machine teaming in critical systems and defense environments.