SHaSTA: An Open-Source Simulator for Human and Swarm Team Applications

Abstract

Human-swarm teaming combines the dynamic capabilities of robot swarms with the strategic cognition of humans to perform complex tasks. As robotic systems and unmanned vehicles gain enhanced autonomy, there is an imperative need for for a human-in-the-loop simulation framework to study both human action/cognition as well as swarm behaviors and their interaction within operational contexts. Such a framework is essential for developing and testing the coordination of human supervisor and robotic swarms with different level of autonomy and exploring the role of machine learning in enhancing their collective behaviors beyond basic functionalities. This paper introduces SHaSTA(Simulator for Human And Swarm Team Applications), a versatile, open-source simulation platform designed to advance research in swarm learning and human-swarm interaction. SHaSTA offers a comprehensive interface that allows both human operators and machine learning algorithms to direct and refine swarm tactics and behaviors. The platform incorporates a range of functionalities, including individual robot controls, swarm behavior primitives like formation control and path planning, and customizable interfaces for defining novel behavioral primitives. A standout feature of SHaSTA is its capability to integrate and synchronize physiological data from human operators with robotic swarm simulations. This integration provides a deeper understanding of human factors in swarm control and enhances the simulation’s realism and applicability. We demonstrate SHaSTA’s effectiveness and scalability through a case study in a search-andrescue scenario, showcasing its computational efficiency and the practical benefits of its human-swarm interaction model. Additionally, we present findings from our human subject study that illustrate how SHaSTA effectively captures and utilizes physiological features to inform and improve human-swarm interaction strategies.