eprintid: 15270
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/52/70
datestamp: 2023-11-10 03:29:53
lastmod: 2023-11-10 03:29:53
status_changed: 2023-11-10 01:59:05
type: article
metadata_visibility: show
creators_name: Ejaz, M.M.
creators_name: Tang, T.B.
creators_name: Lu, C.-K.
title: Vision-Based Autonomous Navigation Approach for a Tracked Robot Using Deep Reinforcement Learning
ispublished: pub
keywords: Air navigation; Collision avoidance; Convolutional neural networks; Deep neural networks; Network architecture; Reinforcement learning; Reliability analysis; Robots, Autonomous navigation; Autonomous steering; Average reward; Changing environment; Network parameters; Real world environments; Simulation environment; Static and dynamic obstacles, Deep learning
note: cited By 11
abstract: Tracked robots need to achieve safe autonomous steering in various changing environments. In this article, a novel end-to-end network architecture is proposed for tracked robots to learn collision-free autonomous navigation through deep reinforcement learning. Specifically, this research improved the learning time and exploratory nature of the robot by normalizing the input data and injecting parametric noise into the network parameters. Features were extracted from the four consecutive depth images by deep convolutional neural networks, which were used to derive the tracked robot. In addition, a comparison was made between three Q-variant models in terms of average reward, variance, and dispersion across episodes. Also, a detailed statistical analysis was performed to measure the reliability of all the models. The proposed model was superior in all the environments. It is worth noting that our proposed model, layer normalisation dueling double deep Q-network (LND3QN), could be directly transferred to a real robot without any fine-tuning after being trained in a simulation environment. The proposed model also demonstrated outstanding performance in several cluttered real-world environments considering both static and dynamic obstacles. © 2001-2012 IEEE.
date: 2021
publisher: Institute of Electrical and Electronics Engineers Inc.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85098142899&doi=10.1109%2fJSEN.2020.3016299&partnerID=40&md5=485df683ab0c1b1d1a6d2bb15a4d1b8a
id_number: 10.1109/JSEN.2020.3016299
full_text_status: none
publication: IEEE Sensors Journal
volume: 21
number: 2
pagerange: 2230-2240
refereed: TRUE
issn: 1530437X
citation:   Ejaz, M.M. and Tang, T.B. and Lu, C.-K.  (2021) Vision-Based Autonomous Navigation Approach for a Tracked Robot Using Deep Reinforcement Learning.  IEEE Sensors Journal, 21 (2).  pp. 2230-2240.  ISSN 1530437X