Speciation in Behavioral Space for Evolutionary Robotics

Abstract : In Evolutionary Robotics, population-based evolutionary computation is used to design robot neurocontrollers that produce behaviors which allow the robot to fulfill a user-defined task. However, the standard approach is to use canonical evolutionary algorithms, where the search tends to make the evolving population converge towards a single behavioral solution, even if the high-level task could be accomplished by structurally different behaviors. In this work, we present an approach that preserves behavioral diversity within the population in order to produce a diverse set of structurally different behaviors that the robot can use. In order to achieve this, we employ the concept of speciation, where the population is dynamically subdivided into sub-groups, or species, each one characterized by a particular behavioral structure that all individuals within that species share. Speciation is achieved by describing each neurocontroller using a representations that we call a behavior signature, these are descriptors that characterize the traversed path of the robot within the environment. Behavior signatures are coded using character strings, this allows us to compare them using a string similarity measure, and three measures are tested. The proposed behavior-based speciation is compared with canonical evolution and a method that speciates based on network topology. Experimental tests were carried out using two robot tasks (navigation and homing behavior), several training environments, and two different robots (Khepera and Pioneer), both real and simulated. Results indicate that behavior-based speciation increases the diversity of the behaviors based on their structure, without sacrificing performance. Moreover, the evolved controllers exhibit good robustness when the robot is placed within environments that were not used during training. In conclusion, the speciation method presented in this work allows an evolutionary algorithm to produce several robot behaviors that are structurally different but all are able to solve the same robot task.
Type de document :
Article dans une revue
Journal of Intelligent and Robotic Systems, Springer Verlag (Germany), 2011, 64 (3-4), pp.323-351. <http://link.springer.com/article/10.1007%2Fs10846-011-9542-z>
Liste complète des métadonnées


https://hal.inria.fr/hal-00642312
Contributeur : Evelyne Lutton <>
Soumis le : jeudi 17 novembre 2011 - 18:18:10
Dernière modification le : jeudi 9 février 2017 - 15:48:05
Document(s) archivé(s) le : samedi 18 février 2012 - 02:36:04

Fichier

trujillo_behaviors_final.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00642312, version 1

Collections

Citation

Leonardo Trujillo, Gustavo Olague, Evelyne Lutton, Francisco Fernandez de Vega, Leon Dozal, et al.. Speciation in Behavioral Space for Evolutionary Robotics. Journal of Intelligent and Robotic Systems, Springer Verlag (Germany), 2011, 64 (3-4), pp.323-351. <http://link.springer.com/article/10.1007%2Fs10846-011-9542-z>. <hal-00642312>

Partager

Métriques

Consultations de
la notice

258

Téléchargements du document

186