A Framework for Automatic Behavior Generation in Multi-Function Swarms

TL;DR

This paper presents a framework using MAP-elites for automatic behavior generation in multi-function swarms, enabling adaptive task handling and robustness analysis through controller repertoire evolution.

Contribution

It introduces a novel framework combining MAP-elites with a controller structure to generate diverse behaviors for multi-function swarms, addressing conflicting task requirements.

Findings

Repertoire of controllers enables online behavior trade-off transitions.

Moderate re-evaluations improve robustness with low computational cost.

Parameter variation analysis reveals input importance for controller behavior.

Abstract

Multi-function swarms are swarms that solve multiple tasks at once. For example, a quadcopter swarm could be tasked with exploring an area of interest while simultaneously functioning as ad-hoc relays. With this type of multi-function comes the challenge of handling potentially conflicting requirements simultaneously. Using the Quality-Diversity algorithm MAP-elites in combination with a suitable controller structure, a framework for automatic behavior generation in multi-function swarms is proposed. The framework is tested on a scenario with three simultaneous tasks: exploration, communication network creation and geolocation of RF emitters. A repertoire is evolved, consisting of a wide range of controllers, or behavior primitives, with different characteristics and trade-offs in the different tasks. This repertoire would enable the swarm to transition between behavior trade-offs online, according to the situational requirements. Furthermore, the effect of noise on the behavior characteristics in MAP-elites is investigated. A moderate number of re-evaluations is found to increase the robustness while keeping the computational requirements relatively low. A few selected controllers are examined, and the dynamics of transitioning between these controllers are explored. Finally, the study develops a methodology for analyzing the makeup of the resulting controllers. This is done through a parameter variation study where the importance of individual inputs to the swarm controllers is assessed and analyzed.