{"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":1775529856331,"version":"3.50.1"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T00:00:00Z","timestamp":1719273600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T00:00:00Z","timestamp":1719273600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s11432-023-4059-6","type":"journal-article","created":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T05:01:57Z","timestamp":1721278917000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Continuous advantage learning for minimum-time trajectory planning of autonomous vehicles"],"prefix":"10.1007","volume":"67","author":[{"given":"Zhuo","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiran","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jialin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,25]]},"reference":[{"key":"4059_CR1","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.eng.2021.10.007","volume":"12","author":"J Chen","year":"2022","unstructured":"Chen J, Sun J, Wang G. From unmanned systems to autonomous intelligent systems. Engineering, 2022, 12: 16\u201319","journal-title":"Engineering"},{"key":"4059_CR2","doi-asserted-by":"publisher","first-page":"108853","DOI":"10.1016\/j.automatica.2020.108853","volume":"115","author":"Z Li","year":"2020","unstructured":"Li Z, You K Y, Song S J. Cooperative source seeking via networked multi-vehicle systems. Automatica, 2020, 115: 108853","journal-title":"Automatica"},{"key":"4059_CR3","doi-asserted-by":"publisher","first-page":"110112","DOI":"10.1016\/j.automatica.2021.110112","volume":"137","author":"S Cheng","year":"2022","unstructured":"Cheng S, Paley D A. Optimal guidance and estimation of a 2D diffusion-advection process by a team of mobile sensors. Automatica, 2022, 137: 110112","journal-title":"Automatica"},{"key":"4059_CR4","doi-asserted-by":"publisher","first-page":"152202","DOI":"10.1007\/s11432-022-3629-1","volume":"66","author":"Y F Li","year":"2023","unstructured":"Li Y F, Wang X, Sun J, et al. Data-driven consensus control of fully distributed event-triggered multi-agent systems. Sci China Inf Sci, 2023, 66: 152202","journal-title":"Sci China Inf Sci"},{"key":"4059_CR5","doi-asserted-by":"publisher","first-page":"952","DOI":"10.1109\/TVT.2016.2555853","volume":"66","author":"J Ji","year":"2016","unstructured":"Ji J, Khajepour A, Melek W W, et al. Path planning and tracking for vehicle collision avoidance based on model predictive control with multiconstraints. IEEE Trans Veh Technol, 2016, 66: 952\u2013964","journal-title":"IEEE Trans Veh Technol"},{"key":"4059_CR6","doi-asserted-by":"publisher","first-page":"11617","DOI":"10.1109\/LRA.2022.3203224","volume":"7","author":"Y Liu","year":"2022","unstructured":"Liu Y, Wang Y, Guan X, et al. Direction and trajectory tracking control for nonholonomic spherical robot by combining sliding mode controller and model prediction controller. IEEE Robot Autom Lett, 2022, 7: 11617\u201311624","journal-title":"IEEE Robot Autom Lett"},{"key":"4059_CR7","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1109\/TMECH.2022.3209873","volume":"28","author":"Z Chen","year":"2022","unstructured":"Chen Z, Helian B, Zhou Y, et al. An integrated trajectory planning and motion control strategy of a variable rotational speed pump-controlled electro-hydraulic actuator. IEEE ASME Trans Mechatron, 2022, 28: 588\u2013597","journal-title":"IEEE ASME Trans Mechatron"},{"key":"4059_CR8","volume-title":"Reinforcement Learning: An Introduction","author":"R S Sutton","year":"2018","unstructured":"Sutton R S, Barto A G. Reinforcement Learning: An Introduction. Cambridge: MIT Press, 2018"},{"key":"4059_CR9","doi-asserted-by":"publisher","first-page":"eab","DOI":"10.1126\/scirobotics.abm6597","volume":"7","author":"M O\u2019Connell","year":"2022","unstructured":"O\u2019Connell M, Shi G Y, Shi X C, et al. Neural-fly enables rapid learning for agile flight in strong winds. Sci Robot, 2022, 7: eabm6597","journal-title":"Sci Robot"},{"key":"4059_CR10","unstructured":"Dong L, He Z, Song C, et al. A review of mobile robot motion planning methods: from classical motion planning workflows to reinforcement learning-based architectures. 2021. ArXiv:2108.13619"},{"key":"4059_CR11","doi-asserted-by":"publisher","first-page":"132202","DOI":"10.1007\/s11432-022-3543-4","volume":"66","author":"J W Zhu","year":"2023","unstructured":"Zhu J W, Zhang H, Zhao S B, et al. Multi-constrained intelligent gliding guidance via optimal control and DQN. Sci China Inf Sci, 2023, 66: 132202","journal-title":"Sci China Inf Sci"},{"key":"4059_CR12","unstructured":"Wang Z, Schaul T, Hessel M, et al. Dueling network architectures for deep reinforcement learning. In: Proceedings of the 33rd International Conference on Machine Learning, New York, 2016. 1995\u20132003"},{"key":"4059_CR13","doi-asserted-by":"publisher","first-page":"6932","DOI":"10.1109\/LRA.2020.3026638","volume":"5","author":"B Y Wang","year":"2020","unstructured":"Wang B Y, Liu Z, Li Q B, et al. Mobile robot path planning in dynamic environments through globally guided reinforcement learning. IEEE Robot Autom Lett, 2020, 5: 6932\u20136939","journal-title":"IEEE Robot Autom Lett"},{"key":"4059_CR14","first-page":"2306","volume":"21","author":"Y Wei","year":"2020","unstructured":"Wei Y, Zheng R. A reinforcement learning framework for efficient informative sensing. IEEE Trans Mobile Comput, 2020, 21: 2306\u20132317","journal-title":"IEEE Trans Mobile Comput"},{"key":"4059_CR15","doi-asserted-by":"publisher","first-page":"170203","DOI":"10.1007\/s11432-022-3729-7","volume":"66","author":"Y Xu","year":"2023","unstructured":"Xu Y, Wu Z-G, Che W-W, et al. Reinforcement learning-based unknown reference tracking control of HMASs with nonidentical communication delays. Sci China Inf Sci, 2023, 66: 170203","journal-title":"Sci China Inf Sci"},{"key":"4059_CR16","doi-asserted-by":"publisher","first-page":"2114","DOI":"10.1109\/TRO.2022.3141602","volume":"38","author":"Y L Song","year":"2022","unstructured":"Song Y L, Scaramuzza D. Policy search for model predictive control with application to agile drone flight. IEEE Trans Robot, 2022, 38: 2114\u20132130","journal-title":"IEEE Trans Robot"},{"key":"4059_CR17","doi-asserted-by":"publisher","first-page":"150210","DOI":"10.1007\/s11432-019-2663-y","volume":"63","author":"L Dong","year":"2020","unstructured":"Dong L, Yuan X, Sun C Y. Event-triggered receding horizon control via actor-critic design. Sci China Inf Sci, 2020, 63: 150210","journal-title":"Sci China Inf Sci"},{"key":"4059_CR18","doi-asserted-by":"publisher","first-page":"9540","DOI":"10.1109\/TVT.2021.3102161","volume":"70","author":"B Zhu","year":"2021","unstructured":"Zhu B, Bedeer E, Nguyen H H, et al. UAV trajectory planning in wireless sensor networks for energy consumption minimization by deep reinforcement learning. IEEE Trans Veh Technol, 2021, 70: 9540\u20139554","journal-title":"IEEE Trans Veh Technol"},{"key":"4059_CR19","first-page":"A187","volume":"8","author":"T P Lillicrap","year":"2015","unstructured":"Lillicrap T P, Hunt J J, Pritzel A, et al. Continuous control with deep reinforcement learning. Comput Sci, 2015, 8: A187","journal-title":"Comput Sci"},{"key":"4059_CR20","unstructured":"Ackermann J, Gabler V, Osa T, et al. Reducing overestimation bias in multi-agent domains using double centralized critics. 2019. ArXiv:1910.01465"},{"key":"4059_CR21","unstructured":"Gu S, Lillicrap T, Sutskever I, et al. Continuous deep Q-learning with model-based acceleration. In: Proceedings of the 33rd International Conference on Machine Learning, New York, 2016. 2829\u20132838"},{"key":"4059_CR22","unstructured":"Haarnoja T, Zhou A, Abbeel P, et al. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of the 35th International Conference on Machine Learning, Stockholm, 2018. 1861\u20131870"},{"key":"4059_CR23","doi-asserted-by":"publisher","first-page":"5435","DOI":"10.1109\/TNNLS.2021.3084685","volume":"32","author":"L X Zhang","year":"2021","unstructured":"Zhang L X, Zhang R X, Wu T, et al. Safe reinforcement learning with stability guarantee for motion planning of autonomous vehicles. IEEE Trans Neural Netw Learn Syst, 2021, 32: 5435\u20135444","journal-title":"IEEE Trans Neural Netw Learn Syst"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-4059-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-023-4059-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-4059-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T20:46:48Z","timestamp":1757105208000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-023-4059-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,25]]},"references-count":23,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["4059"],"URL":"https:\/\/doi.org\/10.1007\/s11432-023-4059-6","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,25]]},"assertion":[{"value":"19 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"172206"}}