A Framework for Automatic Behavior Generation in Multi-Function Swarms
This work addresses the problem of managing complex, simultaneous tasks in robotic swarms for applications like surveillance or disaster response, but it is incremental as it builds on existing quality-diversity algorithms.
The authors tackled the challenge of generating automatic behaviors for multi-function swarms that handle conflicting tasks simultaneously, such as exploration, communication, and geolocation, by proposing a framework using MAP-elites and evolving a repertoire of controllers with different trade-offs, enabling online transitions based on situational needs.
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.