{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:32:27Z","timestamp":1791487947260,"version":"4.3.4"},"reference-count":48,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3585182","type":"journal-article","created":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T13:45:39Z","timestamp":1751463939000},"page":"118678-118694","source":"Crossref","is-referenced-by-count":3,"title":["Human-in-the-Loop Reinforcement Learning to Track Excavation Paths for a Hydraulic Excavator in a Short Period of Time"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3062-1396","authenticated-orcid":false,"given":"Tatsuya","family":"Mori","sequence":"first","affiliation":[{"name":"NEC Visual Intelligence Research Laboratories, Kawasaki, Kanagawa, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4986-5489","authenticated-orcid":false,"given":"Tatsuya","family":"Yoshimoto","sequence":"additional","affiliation":[{"name":"NEC Visual Intelligence Research Laboratories, Kawasaki, Kanagawa, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6777-5263","authenticated-orcid":false,"given":"Hiroshi","family":"Yoshida","sequence":"additional","affiliation":[{"name":"NEC Visual Intelligence Research Laboratories, Kawasaki, Kanagawa, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Where Did the Workers Go? Construction Jobs Are Plentiful, but Workers Are Scarce","author":"Yang","year":"2023"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2024.105523","article-title":"Hybrid-driven autonomous excavator trajectory generation combining empirical driver skills and optimization","volume":"165","author":"Shen","year":"2024","journal-title":"Autom. Construct."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3267120"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635965"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.22260\/ISARC2020\/0080"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3058071"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341598"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49439.2021.9551504"},{"key":"ref9","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3040246"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.22260\/ISARC2020\/0064"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3189834"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TFR.2024.3432508"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3532203"},{"key":"ref16","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3152865"},{"key":"ref18","first-page":"1","article-title":"Data-driven control of a weakly-instrumented excavator with deep learning","volume-title":"Proc. IEEE 3rd Int. Conf. Intell. Reality (ICIR)","author":"Hoffmann"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342052"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA61710.2024.10633010"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3419394.3423643"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.22260\/ICRA2024\/0009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref25","article-title":"Mastering Atari with discrete world models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hafner"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.056"},{"key":"ref27","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Haarnoja"},{"key":"ref28","article-title":"Efficient learning of safe driving policy via human-AI copilot optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3100603"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref31","first-page":"410","article-title":"Intervention aided reinforcement learning for safe and practical policy optimization in navigation","volume-title":"Proc. 2nd Conf. Robot Learn.","volume":"87","author":"Wang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.055"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2009.2035462"},{"key":"ref35","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Hafner"},{"key":"ref36","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hafner"},{"key":"ref37","article-title":"Mastering diverse domains through world models","author":"Hafner","year":"2023","journal-title":"arXiv:2301.04104"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2865891"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6074"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-015-0034-5"},{"key":"ref42","volume-title":"JAX: Composable Transformations of Python+NumPy Programs","author":"Bradbury","year":"2018"},{"key":"ref43","volume-title":"Flax: A Neural Network Library and Ecosystem for JAX","author":"Heek","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref45","article-title":"3D operation of autonomous excavator based on reinforcement learning through independent reward for individual joints","author":"Yoo","year":"2024","journal-title":"arXiv:2406.19848"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802743"},{"key":"ref47","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11062842.pdf?arnumber=11062842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T05:35:54Z","timestamp":1752557754000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11062842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3585182","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}