Towards Physically Talented Aerial Robots with Tactically Smart Swarm Behavior thereof: An Efficient Co-design Approach

TL;DR

This paper presents a co-design framework that jointly optimizes morphology and tactical behavior of aerial swarm robots, enhancing mission performance in reconnaissance and rescue tasks through a novel reinforcement learning approach.

Contribution

It introduces a computationally efficient method for joint morphology and behavior optimization using physical talent metrics and modified graph reinforcement learning architectures.

Findings

Co-designed swarms outperform fixed Pareto designs in mission metrics.

Significant morphological and behavioral differences are observed between baseline and co-designed swarms.

Enhanced simulation tools support variable aerial capabilities for better co-design outcomes.

Abstract

The collective performance or capacity of collaborative autonomous systems such as a swarm of robots is jointly influenced by the morphology and the behavior of individual systems in that collective. In that context, this paper explores how morphology impacts the learned tactical behavior of unmanned aerial/ground robots performing reconnaissance and search & rescue. This is achieved by presenting a computationally efficient framework to solve this otherwise challenging problem of jointly optimizing the morphology and tactical behavior of swarm robots. Key novel developments to this end include the use of physical talent metrics and modification of graph reinforcement learning architectures to allow joint learning of the swarm tactical policy and the talent metrics (search speed, flight range, and cruising speed) that constrain mobility and object/victim search capabilities of the aerial robots executing these tactics. Implementation of this co-design approach is supported by advancements to an open-source Pybullet-based swarm simulator that allows the use of variable aerial asset capabilities. The results of the co-design are observed to outperform those of tactics learning with a fixed Pareto design, when compared in terms of mission performance metrics. Significant differences in morphology and learned behavior are also observed by comparing the baseline design and the co-design outcomes.