{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T19:47:06Z","timestamp":1782589626741,"version":"3.54.5"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Wallenberg AI, Autonomous Systems and Software Program"},{"name":"Knut and Alice Wallenberg (KAW) Foundation"},{"DOI":"10.13039\/501100001858","name":"Vinnova Project, Human-Centered Autonomous Regional Airport","doi-asserted-by":"publisher","award":["Dnr 2022-02678"],"award-info":[{"award-number":["Dnr 2022-02678"]}],"id":[{"id":"10.13039\/501100001858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Strategic Research Environment, Excellence Center at Link\u00f6ping-Lund in Information Technology"},{"name":"Swedish Government"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3581035","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:40:10Z","timestamp":1750268410000},"page":"106883-106905","source":"Crossref","is-referenced-by-count":4,"title":["Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3434-2522","authenticated-orcid":false,"given":"Arvi","family":"Jonnarth","sequence":"first","affiliation":[{"name":"Manta Systems, Linköping, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1386-3230","authenticated-orcid":false,"given":"Ola","family":"Johansson","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Linköping University, Linköping, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3924-5537","authenticated-orcid":false,"given":"Jie","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6096-3648","authenticated-orcid":false,"given":"Michael","family":"Felsberg","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Linköping University, Linköping, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932525"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2013.09.004"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/rob.4620050202"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1988.12333"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2016.7784279"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812344"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAE50850.2020.9310796"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3052391"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196540"},{"key":"ref12","first-page":"1","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Nagabandi"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811771"},{"key":"ref15","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref16","first-page":"22491","article-title":"Learning coverage paths in unknown environments with deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zheng"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3384\/9789180757218"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-1273-0_32"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/027836402320556359"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1013479"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570413"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2018.8581245"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202319"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561328"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967793"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1063\/1.5114220"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3045027"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891991"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3034800"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR53236.2021.9659343"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793769"},{"key":"ref32","article-title":"Reinforcement learning-based coverage path planning with implicit cellular decomposition","author":"Heydari","year":"2021","journal-title":"arXiv:2110.09018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICARA51699.2021.9376477"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461054"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref36","first-page":"1","article-title":"Sim-to-real transfer of accurate grasping with eye-in-hand observations and continuous control","volume-title":"Proc. Workshop Acting Interacting Real World, Adv. Neural Inf. Process. Syst.","author":"Yan"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1642157"},{"key":"ref38","first-page":"1","article-title":"Real-time reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ramstedt"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.011"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160684"},{"key":"ref41","first-page":"1","article-title":"Learning exploration policies for navigation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340934"},{"key":"ref43","first-page":"1","article-title":"Learning to explore using active neural SLAM","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chaplot"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"issue":"268","key":"ref45","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"issue":"267","key":"ref46","first-page":"1","article-title":"Tianshou: A highly modularized deep reinforcement learning library","volume":"23","author":"Weng","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref47","article-title":"Spinning up in deep reinforcement learning","author":"Achiam","year":"2018"},{"key":"ref48","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref49","volume-title":"Husqvarna Research Platform","year":"2017"},{"key":"ref50","volume-title":"Qualisys Motion Capture System","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460566"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref58","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"issue":"1","key":"ref60","first-page":"7382","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref61","first-page":"1","article-title":"Illuminating generalization in deep reinforcement learning through procedural level generation","volume-title":"Proc. NeurIPS Workshop Deep Reinforcement Learn.","author":"Justesen"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11039829.pdf?arnumber=11039829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T05:24:43Z","timestamp":1750829083000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11039829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3581035","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}