A Stochastic Approach to Generate Emergent Behaviors in Robotic Swarms

This research introduces a novel stochastic methodology leveraging Gibbs Random Fields (GRFs) to promote a variety of emergent behaviors in robotic swarms, such as flocking, segregation, cooperative object transport, and pattern formation. By utilizing only local information and decentralized control mechanisms, the approach ensures robust and scalable swarm behaviors. Through both numerical simulations and real-world experiments using HeRo 2.0, a low-cost swarm robotic platform developed in this work, we demonstrate the benefits of the proposed methodology, including adaptability, robustness, and resilience. The stochastic approach proposed here is positioned to significantly advance the field of swarm robotics by enabling diverse behaviors, contributing to the evolution of the field, and shaping the way for new applications.