Distributed Coordination of Heterogeneous Robotic Swarms Using Stochastic Diffusion Search

• Eneko Osaba ^[1] ; Ser, Javier del ^{[1] [2]} ; Xabier Jubeto ^[2] ; Andrés Iglesias ^{[3] [5]} ; Iztok Fister Jr. ^[4] ; Akemi Gálvez ^{[3] [5]} ; Iztok Fister ^[4]
  1. [1] Tecnalia

     Tecnalia

     Derio, España

     
  2. [2] Universidad del País Vasco/Euskal Herriko Unibertsitatea

     Universidad del País Vasco/Euskal Herriko Unibertsitatea

     Leioa, España

     
  3. [3] Universidad de Cantabria

     Universidad de Cantabria

     Santander, España

     
  4. [4] University of Maribor

     University of Maribor

     Eslovenia

     
  5. [5] Toho University

     Toho University

     Japón

     

  Mostrar afiliaciones +
• Localización: Intelligent Data Engineering and Automated Learning – IDEAL 2020. 21st International Conference: Guimarães, Portugal; November 4–6, 2020. Proceedings / Cesar Analide (ed. lit.), Paulo Novais (ed. lit.) , David Camacho Fernández (ed. lit.) , Hujun Yin (ed. lit.), Vol. 2, 2020 (Part II), ISBN 978-3-030-62365-4, págs. 79-91
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • The term Swarm Robotics collectively refers to a population of robotic devices that efficiently undertakes diverse tasks in a collaborative way by virtue of computational intelligence techniques. This paradigm has given rise to a profitable stream of contributions in recent years, all sharing a clear consensus on the performance benefits derived from the increased exploration capabilities offered by Swarm Robotics. This manuscript falls within this topic: specifically, it gravitates on an heterogeneous Swarm Robotics system that relies on Stochastic Diffusion Search (SDS) as the coordination heuristics for the exploration, location and delimitation of areas scattered over the area in which robots are deployed. The swarm is composed by agents of diverse kind, which can be ground robots or flying devices. These agents communicate to each other and cooperate towards the accomplishment of the exploration tasks comprising the mission of the overall swarm. Furthermore, maps contain several obstacles and dangers, implying that in order to enter a specific area, robots should meet certain conditions. Experiments are conducted over three different maps and three implemented solving approaches. Conclusions are drawn from the obtained results, confirming that i) SDS allows for a lightweight, heuristic mechanism for the coordination of the robots; and ii) the most efficient swarming approach is the one comprising a heterogeneity of ground and aerial robots.