{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T16:29:34Z","timestamp":1774974574378,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:00:00Z","timestamp":1705017600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:00:00Z","timestamp":1705017600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,12]]},"DOI":"10.1109\/icrca60878.2024.10649133","type":"proceedings-article","created":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T17:37:55Z","timestamp":1725471475000},"page":"197-205","source":"Crossref","is-referenced-by-count":1,"title":["Trajectory State Model-based Reinforcement Learning for Truck-trailer Reverse Driving"],"prefix":"10.1109","author":[{"given":"Hao","family":"Yan","sequence":"first","affiliation":[{"name":"Oakland University,Electrical and Computer Engineering Department,Rochster,USA"}]},{"given":"Mohamed A.","family":"Zohdy","sequence":"additional","affiliation":[{"name":"Oakland University,Electrical and Computer Engineering Department,Rochster,USA"}]},{"given":"Edrees","family":"Alhawsawi","sequence":"additional","affiliation":[{"name":"Oakland University,Electrical and Computer Engineering Department,Rochster,USA"}]},{"given":"Amr","family":"Mahmoud","sequence":"additional","affiliation":[{"name":"Oakland University,Electrical and Computer Engineering Department,Rochster,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/37.55119"},{"key":"ref2","first-page":"2021","journal-title":"Semi-trailer Market Size, Share & Trends Analysis Report by Type (Flat Bed Trailer, Dry Vans, Refrigerated Trailers, Lowboy Trailers, Tankers), by Region (North America, Europe, APAC, LATAM, MEA), and Segment Forecasts"},{"issue":"4","key":"ref3","first-page":"124","article-title":"Recurrent Proximal Policy Optimization Based Tractor-Trailer Wheeled Robot Automatic Parking Algorithm","volume":"11","author":"Yan","year":"2023","journal-title":"TECS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cdc.2016.7798630"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2016.7759544"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2019.12.003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iv47402.2020.9304668"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.10.006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/joe.2019.2896397"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s12239-020-0085-9"},{"key":"ref11","article-title":"Trust Region Policy Optimization","author":"Schulman","year":"2017","journal-title":"arXiv"},{"key":"ref12","article-title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","author":"Nagabandi","year":"2017","journal-title":"arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1561\/2300000021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907424"},{"key":"ref15","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proceedings of the 28th International Conference on machine learning (ICML-11)","author":"Deisenroth"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SDPC.2018.8664956"},{"key":"ref17","volume-title":"Playing Atari with Deep Reinforcement Learning","author":"Mnih","year":"2013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s42154-021-00151-3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1049\/itr2.12107"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref21","volume-title":"Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO","author":"Engstrom","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref23","volume-title":"Model-Based Reinforcement Learning for Atari","author":"Kaiser","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"ref25","volume-title":"TreeQN and ATreeC: Differentiable tree planning for deep reinforcement learning","author":"Whiteson","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref27","first-page":"8583","article-title":"Planning to Explore via Self-Supervised World Models","volume-title":"Proceedings of the 37th International Conference on Machine Learning, PMLR","author":"Sekar"},{"key":"ref28","first-page":"895","article-title":"Building Portable Options: Skill Transfer in Reinforcement Learning","author":"Konidaris","year":"2023","journal-title":"Ijcai"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00237-3"},{"key":"ref30","article-title":"Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences","author":"van der Waa","year":"2018","journal-title":"arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0954406218792589"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2019.2895513"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3062392"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ivs.2017.7995816"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2009.02.010"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.2307\/2372560"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2018.2876888"}],"event":{"name":"2024 8th International Conference on Robotics, Control and Automation (ICRCA)","location":"Shanghai, China","start":{"date-parts":[[2024,1,12]]},"end":{"date-parts":[[2024,1,14]]}},"container-title":["2024 8th International Conference on Robotics, Control and Automation (ICRCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10648987\/10648988\/10649133.pdf?arnumber=10649133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T16:15:39Z","timestamp":1725552939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10649133\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,12]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icrca60878.2024.10649133","relation":{},"subject":[],"published":{"date-parts":[[2024,1,12]]}}}