Self-Learning Robot Autonomous Navigation with Deep Reinforcement Learning Techniques

Pintos Gómez de las Heras, Borja, Martínez Tomás, Rafael y Cuadra Troncoso, José Manuel . (2023) Self-Learning Robot Autonomous Navigation with Deep Reinforcement Learning Techniques. Applied Sciences

Ficheros (Some files may be inaccessible until you login with your e-spacio credentials)
Nombre Descripción Tipo MIME Size
Martinez_Tomas_Rafael_SelfLearning_Robot_Auto.pdf Martinez Tomas_Rafael_SelfLearning Robot Auto.pdf application/pdf 5.62MB

Título Self-Learning Robot Autonomous Navigation with Deep Reinforcement Learning Techniques
Autor(es) Pintos Gómez de las Heras, Borja
Martínez Tomás, Rafael
Cuadra Troncoso, José Manuel
Materia(s) Ingeniería Informática
Abstract Complex and high-computational-cost algorithms are usually the state-of-the-art solution for autonomous driving cases in which non-holonomic robots must be controlled in scenarios with spatial restrictions and interaction with dynamic obstacles while fulfilling at all times safety, comfort, and legal requirements. These highly complex software solutions must cover the high variability of use cases that might appear in traffic conditions, especially when involving scenarios with dynamic obstacles. Reinforcement learning algorithms are seen as a powerful tool in autonomous driving scenarios since the complexity of the algorithm is automatically learned by trial and error with the help of simple reward functions. This paper proposes a methodology to properly define simple reward functions and come up automatically with a complex and successful autonomous driving policy. The proposed methodology has no motion planning module so that the computational power can be limited like in the reactive robotic paradigm. Reactions are learned based on the maximization of the cumulative reward obtained during the learning process. Since the motion is based on the cumulative reward, the proposed algorithm is not bound to any embedded model of the robot and is not being affected by uncertainties of these models or estimators, making it possible to generate trajectories with the consideration of non-holonomic constrains. This paper explains the proposed methodology and discusses the setup of experiments and the results for the validation of the methodology in scenarios with dynamic obstacles. A comparison between the reinforcement learning algorithm and state-of-the-art approaches is also carried out to highlight how the methodology proposed outperforms state-of-the-art algorithms.
Palabras clave autonomous robots
deep reinforcement learning
dynamic environment
comfort driving
self-learning
Editor(es) MDPI
Fecha 2023-12-30
Formato application/pdf
Identificador bibliuned:95-Rmartinez-0006
http://e-spacio.uned.es/fez/view/bibliuned:95-Rmartinez-0006
DOI - identifier 10.3390/app14010366
ISSN - identifier 2076-3417
Nombre de la revista Applied Sciences
Número de Volumen 14
Número de Issue 1
Publicado en la Revista Applied Sciences
Idioma eng
Versión de la publicación publishedVersion
Tipo de recurso Article
Derechos de acceso y licencia http://creativecommons.org/licenses/by/4.0
info:eu-repo/semantics/openAccess
Tipo de acceso Acceso abierto
Notas adicionales The registered version of this article, first published in Applied Sciences, is available online at the publisher's website: MDPI https://doi.org/10.3390/app14010366
Notas adicionales La versión registrada de este artículo, publicado por primera vez en Applied Sciences, está disponible en línea en el sitio web del editor: MDPI https://doi.org/10.3390/app14010366

 
Versiones
Versión Tipo de filtro
Contador de citas: Google Scholar Search Google Scholar
Estadísticas de acceso: 36 Visitas, 10 Descargas  -  Estadísticas en detalle
Creado: Sat, 27 Jan 2024, 00:10:05 CET