000118215 001__ 118215
000118215 005__ 20240319081021.0
000118215 0247_ $$2doi$$a10.3390/s22103847
000118215 0248_ $$2sideral$$a129612
000118215 037__ $$aART-2022-129612
000118215 041__ $$aeng
000118215 100__ $$aMackay, A. K.
000118215 245__ $$aRL-DOVS: Reinforcement Learning for Autonomous Robot Navigation in Dynamic Environments
000118215 260__ $$c2022
000118215 5060_ $$aAccess copy available to the general public$$fUnrestricted
000118215 5203_ $$aAutonomous navigation in dynamic environments where people move unpredictably is an essential task for service robots in real-world populated scenarios. Recent works in reinforcement learning (RL) have been applied to autonomous vehicle driving and to navigation around pedestrians. In this paper, we present a novel planner (reinforcement learning dynamic object velocity space, RL-DOVS) based on an RL technique for dynamic environments. The method explicitly considers the robot kinodynamic constraints for selecting the actions in every control period. The main contribution of our work is to use an environment model where the dynamism is represented in the robocentric velocity space as input to the learning system. The use of this dynamic information speeds the training process with respect to other techniques that learn directly either from raw sensors (vision, lidar) or from basic information about obstacle location and kinematics. We propose two approaches using RL and dynamic obstacle velocity (DOVS), RL-DOVS-A, which automatically learns the actions having the maximum utility, and RL-DOVS-D, in which the actions are selected by a human driver. Simulation results and evaluation are presented using different numbers of active agents and static and moving passive agents with random motion directions and velocities in many different scenarios. The performance of the technique is compared with other state-of-the-art techniques for solving navigation problems in environments such as ours.
000118215 536__ $$9info:eu-repo/grantAgreement/ES/DGA-FSE/T45-20R$$9info:eu-repo/grantAgreement/ES/MINECO-FEDER/PID2019-105390RB-I00
000118215 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000118215 590__ $$a3.9$$b2022
000118215 592__ $$a0.764$$b2022
000118215 591__ $$aCHEMISTRY, ANALYTICAL$$b26 / 86 = 0.302$$c2022$$dQ2$$eT1
000118215 593__ $$aInstrumentation$$c2022$$dQ1
000118215 591__ $$aINSTRUMENTS & INSTRUMENTATION$$b19 / 63 = 0.302$$c2022$$dQ2$$eT1
000118215 593__ $$aAnalytical Chemistry$$c2022$$dQ1
000118215 591__ $$aENGINEERING, ELECTRICAL & ELECTRONIC$$b100 / 274 = 0.365$$c2022$$dQ2$$eT2
000118215 593__ $$aMedicine (miscellaneous)$$c2022$$dQ2
000118215 593__ $$aInformation Systems$$c2022$$dQ2
000118215 593__ $$aBiochemistry$$c2022$$dQ2
000118215 593__ $$aAtomic and Molecular Physics, and Optics$$c2022$$dQ2
000118215 593__ $$aElectrical and Electronic Engineering$$c2022$$dQ2
000118215 594__ $$a6.8$$b2022
000118215 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000118215 700__ $$0(orcid)0000-0002-6722-5541$$aRiazuelo, L.$$uUniversidad de Zaragoza
000118215 700__ $$0(orcid)0000-0002-0449-2300$$aMontano, L.$$uUniversidad de Zaragoza
000118215 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát.
000118215 773__ $$g22, 10 (2022), 3847 [20 pp]$$pSensors$$tSensors$$x1424-8220
000118215 8564_ $$s2560053$$uhttps://zaguan.unizar.es/record/118215/files/texto_completo.pdf$$yVersión publicada
000118215 8564_ $$s2771240$$uhttps://zaguan.unizar.es/record/118215/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000118215 909CO $$ooai:zaguan.unizar.es:118215$$particulos$$pdriver
000118215 951__ $$a2024-03-18-16:14:18
000118215 980__ $$aARTICLE