Cargando…

Mobile robots exploration through cnn-based reinforcement learning

Exploration in an unknown environment is an elemental application for mobile robots. In this paper, we outlined a reinforcement learning method aiming for solving the exploration problem in a corridor environment. The learning model took the depth image from an RGB-D sensor as the only input. The fe...

Descripción completa

Detalles Bibliográficos
Autores principales: Tai, Lei, Liu, Ming
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Berlin Heidelberg 2016
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5177670/
https://www.ncbi.nlm.nih.gov/pubmed/28066702
http://dx.doi.org/10.1186/s40638-016-0055-x
_version_ 1782485036212158464
author Tai, Lei
Liu, Ming
author_facet Tai, Lei
Liu, Ming
author_sort Tai, Lei
collection PubMed
description Exploration in an unknown environment is an elemental application for mobile robots. In this paper, we outlined a reinforcement learning method aiming for solving the exploration problem in a corridor environment. The learning model took the depth image from an RGB-D sensor as the only input. The feature representation of the depth image was extracted through a pre-trained convolutional-neural-networks model. Based on the recent success of deep Q-network on artificial intelligence, the robot controller achieved the exploration and obstacle avoidance abilities in several different simulated environments. It is the first time that the reinforcement learning is used to build an exploration strategy for mobile robots through raw sensor information.
format Online
Article
Text
id pubmed-5177670
institution National Center for Biotechnology Information
language English
publishDate 2016
publisher Springer Berlin Heidelberg
record_format MEDLINE/PubMed
spelling pubmed-51776702017-01-06 Mobile robots exploration through cnn-based reinforcement learning Tai, Lei Liu, Ming Robotics Biomim Research Exploration in an unknown environment is an elemental application for mobile robots. In this paper, we outlined a reinforcement learning method aiming for solving the exploration problem in a corridor environment. The learning model took the depth image from an RGB-D sensor as the only input. The feature representation of the depth image was extracted through a pre-trained convolutional-neural-networks model. Based on the recent success of deep Q-network on artificial intelligence, the robot controller achieved the exploration and obstacle avoidance abilities in several different simulated environments. It is the first time that the reinforcement learning is used to build an exploration strategy for mobile robots through raw sensor information. Springer Berlin Heidelberg 2016-12-21 2016 /pmc/articles/PMC5177670/ /pubmed/28066702 http://dx.doi.org/10.1186/s40638-016-0055-x Text en © The Author(s) 2016 Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
spellingShingle Research
Tai, Lei
Liu, Ming
Mobile robots exploration through cnn-based reinforcement learning
title Mobile robots exploration through cnn-based reinforcement learning
title_full Mobile robots exploration through cnn-based reinforcement learning
title_fullStr Mobile robots exploration through cnn-based reinforcement learning
title_full_unstemmed Mobile robots exploration through cnn-based reinforcement learning
title_short Mobile robots exploration through cnn-based reinforcement learning
title_sort mobile robots exploration through cnn-based reinforcement learning
topic Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5177670/
https://www.ncbi.nlm.nih.gov/pubmed/28066702
http://dx.doi.org/10.1186/s40638-016-0055-x
work_keys_str_mv AT tailei mobilerobotsexplorationthroughcnnbasedreinforcementlearning
AT liuming mobilerobotsexplorationthroughcnnbasedreinforcementlearning