{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T02:44:16Z","timestamp":1775529856548,"version":"3.50.1"},"reference-count":27,"publisher":"World Scientific Pub Co Pte Ltd","issue":"02","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U23B2059"],"award-info":[{"award-number":["U23B2059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62173034"],"award-info":[{"award-number":["62173034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61925303"],"award-info":[{"award-number":["61925303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Un. Sys."],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:p>This paper addresses the problem of guiding a quadrotor through a predefined sequence of waypoints in cluttered environments, aiming to minimize the flight time while avoiding collisions. Previous approaches either suffer from prolonged computational time caused by solving complex non-convex optimization problems or are limited by the inherent smoothness of polynomial trajectory representations, thereby restricting the flexibility of movement. In this work, we present a safe reinforcement learning approach for autonomous drone racing with time-optimal flight in cluttered environments. The reinforcement learning policy, trained using safety and terminal rewards specifically designed to enforce near time-optimal and collision-free flight, outperforms current state-of-the-art algorithms. Additionally, experimental results demonstrate the efficacy of the proposed approach in achieving both minimum flight time and obstacle avoidance objectives in complex environments, with a commendable [Formula: see text] success rate in unseen, challenging settings.<\/jats:p>","DOI":"10.1142\/s230138502650007x","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T01:15:26Z","timestamp":1737508526000},"page":"391-400","source":"Crossref","is-referenced-by-count":2,"title":["Time-Optimal Flight in Cluttered Environments via Safe Reinforcement Learning"],"prefix":"10.1142","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2623-2555","authenticated-orcid":false,"given":"Wei","family":"Xiao","sequence":"first","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing 100081, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9055-9276","authenticated-orcid":false,"given":"Zhaohan","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing 100081, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9485-7336","authenticated-orcid":false,"given":"Ziyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing 100081, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9898-3129","authenticated-orcid":false,"given":"Jian","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing 100081, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7266-2412","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing 100081, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2449-9793","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing 100081, China"},{"name":"Department of Control Science and Engineering, Tongji University, Shanghai 201804, China"}]}],"member":"219","published-online":{"date-parts":[[2025,3,22]]},"reference":[{"key":"S230138502650007XBIB001","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968116"},{"key":"S230138502650007XBIB002","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-021-10011-y"},{"key":"S230138502650007XBIB003","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-018-00271-6"},{"key":"S230138502650007XBIB004","first-page":"177","volume-title":"Proceedings of the NeurIPS 2019 Competition and Demonstration Track","volume":"123","author":"Madaan R.","year":"2020"},{"key":"S230138502650007XBIB005","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385022500108"},{"key":"S230138502650007XBIB006","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2479878"},{"key":"S230138502650007XBIB007","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2819195"},{"key":"S230138502650007XBIB008","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385024500225"},{"key":"S230138502650007XBIB009","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adg1462"},{"key":"S230138502650007XBIB010","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3113976"},{"key":"S230138502650007XBIB011","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2856526"},{"key":"S230138502650007XBIB012","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910385586"},{"key":"S230138502650007XBIB013","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385024410206"},{"key":"S230138502650007XBIB014","doi-asserted-by":"crossref","unstructured":"C. Qin, M. S. Michet, J. Chen and H. H.T. Liu, Time-optimal gate-traversing planner for autonomous drone racing, preprint (2023), arXiv:2309.06837.","DOI":"10.1109\/ICRA57147.2024.10610148"},{"key":"S230138502650007XBIB015","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abh1221"},{"key":"S230138502650007XBIB016","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3322075"},{"key":"S230138502650007XBIB017","doi-asserted-by":"publisher","DOI":"10.1109\/TLA.2019.9011550"},{"key":"S230138502650007XBIB018","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"S230138502650007XBIB019","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abg5810"},{"key":"S230138502650007XBIB020","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.040"},{"key":"S230138502650007XBIB021","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3181755"},{"key":"S230138502650007XBIB022","first-page":"1147","volume-title":"Proc. Conf. Robot Learn., PMLR","author":"Song Y."},{"key":"S230138502650007XBIB023","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R. S.","year":"2018"},{"key":"S230138502650007XBIB024","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"S230138502650007XBIB025","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811564"},{"key":"S230138502650007XBIB026","unstructured":"J. Schulman, F. Wolski, P. Dhariwal, A. Radford and O. Klimov, Proximal policy optimization algorithms, arXiv:1707.06347 (2017)."},{"issue":"268","key":"S230138502650007XBIB027","first-page":"1","volume":"22","author":"Raffin A.","year":"2021","journal-title":"Journal of Machine Learning Research"}],"container-title":["Unmanned Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S230138502650007X","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:29:11Z","timestamp":1770251351000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S230138502650007X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,22]]},"references-count":27,"journal-issue":{"issue":"02","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1142\/S230138502650007X"],"URL":"https:\/\/doi.org\/10.1142\/s230138502650007x","relation":{},"ISSN":["2301-3850","2301-3869"],"issn-type":[{"value":"2301-3850","type":"print"},{"value":"2301-3869","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,22]]}}}