Seeking Specialization Through Novelty in Distributed Online Collective Robotics - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Seeking Specialization Through Novelty in Distributed Online Collective Robotics

Résumé

Online Embodied Evolution is a distributed learning method for collective heterogeneous robotic swarms, in which evolution is carried out in a decentralized manner. In this work, we address the problem of promoting reproductive isolation, a feature that has been identified as crucial in situations where behavioral specialization is desired. We hypothesize that one way to allow a swarm of robots to specialize on different tasks is through the promotion of diversity. Our contribution is twofold, we describe a method that allows a swarm of heterogeneous agents evolving online to maintain a high degree of diversity in behavioral space in which selection is based on originality. We also introduce a behavioral distance measure that compares behaviors in the same conditions to provide reliable measurements in online distributed situations. We test the hypothesis on a concurrent foraging task and the experiments show that diversity is indeed preserved and, that different behaviors emerge in the swarm; suggesting the emergence of reproductive isolation. Finally, we employ different analysis tools from computational biology that further support this claim.
Fichier principal
Vignette du fichier
article.pdf (580.56 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03563761 , version 1 (09-02-2022)

Identifiants

Citer

Amine Boumaza. Seeking Specialization Through Novelty in Distributed Online Collective Robotics. EvoApplications 2022 - 25th International Conference on the Applications of Evolutionary Computation, Apr 2022, Madrid, Spain. pp.635-650, ⟨10.1007/978-3-031-02462-7_40⟩. ⟨hal-03563761⟩
41 Consultations
98 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More