000148224 001__ 148224
000148224 005__ 20250114175435.0
000148224 0247_ $$2doi$$a10.1109/ICRA48891.2023.10160876
000148224 0248_ $$2sideral$$a141695
000148224 037__ $$aART-2023-141695
000148224 041__ $$aeng
000148224 100__ $$aMartinez-Baselga, Diego$$uUniversidad de Zaragoza
000148224 245__ $$aImproving robot navigation in crowded environments using intrinsic rewards
000148224 260__ $$c2023
000148224 5060_ $$aAccess copy available to the general public$$fUnrestricted
000148224 5203_ $$aAutonomous navigation in crowded environments is an open problem with many applications, essential for the coexistence of robots and humans in the smart cities of the future. In recent years, deep reinforcement learning approaches have proven to outperform model-based algorithms. Nevertheless, even though the results provided are promising, the works are not able to take advantage of the capabilities that their models offer. They usually get trapped in local optima in the training process, that prevent them from learning the optimal policy. They are not able to visit and interact with every possible state appropriately, such as with the states near the goal or near the dynamic obstacles. In this work, we propose using intrinsic rewards to balance between exploration and exploitation and explore depending on the uncertainty of the states instead of on the time the agent has been trained, encouraging the agent to get more curious about unknown states. We explain the benefits of the approach and compare it with other exploration algorithms that may be used for crowd navigation. Many simulation experiments are performed modifying several algorithms of the state-of-the-art, showing that the use of intrinsic rewards makes the robot learn faster and reach higher rewards and success rates (fewer collisions) in shorter navigation times, outperforming the state-of-the-art.
000148224 536__ $$9info:eu-repo/grantAgreement/ES/DGA-FSE/T45-20R$$9info:eu-repo/grantAgreement/ES/MICINN/PID2019-105390RB-I00
000148224 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000148224 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/submittedVersion
000148224 700__ $$0(orcid)0000-0002-6722-5541$$aRiazuelo, Luis$$uUniversidad de Zaragoza
000148224 700__ $$0(orcid)0000-0002-0449-2300$$aMontano, Luis$$uUniversidad de Zaragoza
000148224 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát.
000148224 773__ $$g(2023), 9428-9434$$pIEEE Int. conf. robot. autom.$$tIEEE International Conference on Robotics and Automation$$x2152-4092
000148224 8564_ $$s2852099$$uhttps://zaguan.unizar.es/record/148224/files/texto_completo.pdf$$yPreprint
000148224 8564_ $$s3193228$$uhttps://zaguan.unizar.es/record/148224/files/texto_completo.jpg?subformat=icon$$xicon$$yPreprint
000148224 909CO $$ooai:zaguan.unizar.es:148224$$particulos$$pdriver
000148224 951__ $$a2025-01-14-15:49:48
000148224 980__ $$aARTICLE