Obtaining fault tolerance avoidance behavior using deep reinforcement learning

Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10045/91549
Información del item - Informació de l'item - Item information
Título: Obtaining fault tolerance avoidance behavior using deep reinforcement learning
Autor/es: Aznar Gregori, Fidel | Pujol, Mar | Rizo, Ramón
Grupo/s de investigación o GITE: Informática Industrial e Inteligencia Artificial
Centro, Departamento o Servicio: Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial
Palabras clave: Deep reinforcement learning | Obstacle avoidance | Fault tolerance
Área/s de conocimiento: Ciencia de la Computación e Inteligencia Artificial
Fecha de publicación: 14-jun-2019
Editor: Elsevier
Cita bibliográfica: Neurocomputing. 2019, 345: 77-91. doi:10.1016/j.neucom.2018.11.090
Resumen: In this article, a mapless movement policy for mobile agents, designed specifically to be fault-tolerant, is presented. The provided policy, which is learned using deep reinforcement learning, has advantages compared to the usual mapless policies: this policy is capable of handling a robot even when some of its sensors are broken. It is an end-to-end policy based on three neuronal models capable not only of moving the robot and maximizing the coverage of the environment but also of learning the best movement behavior to adapt it to its perception needs. A custom robot, for which none of the readings of the sensors overlap each other, has been used. This setup makes it possible to determine the operation of a robust failure policy, since the failure of a sensor unequivocally affects the perceptions. The proposed system exhibits several advantages in terms of robustness, extensibility and utility. The system has been trained and tested exhaustively in a simulator, obtaining very good results. It has also been transferred to real robots, verifying the generalization and the good functioning of our model in real environments.
Patrocinador/es: This work has been supported by the Ministerio de Economia y Competitividad (Spain), project TIN2013-40982-R (project co-financed with FEDER funds) and by the Erasmus + EUROBOTIQUE Project with reference 2016-1-ES01-KA201-024990.
URI: http://hdl.handle.net/10045/91549
ISSN: 0925-2312 (Print) | 1872-8286 (Online)
DOI: 10.1016/j.neucom.2018.11.090
Idioma: eng
Tipo: info:eu-repo/semantics/article
Derechos: © 2019 Elsevier B.V.
Revisión científica: si
Versión del editor: https://doi.org/10.1016/j.neucom.2018.11.090
Aparece en las colecciones:INV - i3a - Proyecto Erasmus+ EUROBOTIQUE
INV - i3a - Artículos de Revistas

Archivos en este ítem:
Archivos en este ítem:
Archivo Descripción TamañoFormato 
Thumbnail2019_Aznar_etal_Neurocomputing_final.pdfVersión final (acceso restringido)3,72 MBAdobe PDFAbrir    Solicitar una copia
Thumbnail2019_Aznar_etal_Neurocomputing_accepted.pdfAccepted Manuscript (acceso abierto)9,61 MBAdobe PDFAbrir Vista previa


Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.