{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:27:57Z","timestamp":1779294477453,"version":"3.51.4"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T00:00:00Z","timestamp":1670457600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T00:00:00Z","timestamp":1670457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1932370"],"award-info":[{"award-number":["CNS-1932370"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014717","name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52272426"],"award-info":[{"award-number":["52272426"]}],"id":[{"id":"10.13039\/100014717","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s10489-022-04358-7","type":"journal-article","created":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T04:29:27Z","timestamp":1670473767000},"page":"16473-16486","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Hierarchical framework integrating rapidly-exploring random tree with deep reinforcement learning for autonomous vehicle"],"prefix":"10.1007","volume":"53","author":[{"given":"Jiaxing","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aliasghar","family":"Arab","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingang","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Pei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuexun","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,8]]},"reference":[{"issue":"8","key":"4358_CR1","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1002\/rob.20253","volume":"25","author":"I Miller","year":"2008","unstructured":"Miller I, Campbell M, Huttenlocher D, Kline F-R, Nathan A, Lupashin S, Catlin J, Schimpf B, Moran P, Zych N, Garcia E, Kurdziel M, Fujishima H (2008) Team cornell\u2019s skynet: robust perception and planning in an urban environment. J Field Robot 25(8):493\u2013527. https:\/\/doi.org\/10.1002\/rob.20253","journal-title":"J Field Robot"},{"key":"4358_CR2","doi-asserted-by":"publisher","unstructured":"Chae H, Kang CM, Kim B, Kim J, Chung CC, Choi JW (2017) Autonomous braking system via deep reinforcement learning. In: IEEE Int Conf Intell Transp Syst pp 1\u20136. https:\/\/doi.org\/10.1109\/ITSC.2017.8317839","DOI":"10.1109\/ITSC.2017.8317839"},{"key":"4358_CR3","doi-asserted-by":"publisher","unstructured":"Isele D, Rahimi R, Cosgun A, Subramanian K, Fujimura K (2018) Navigating occluded intersections with autonomous vehicles using deep reinforcement learning. In: Proc IEEE Int Conf Robot Autom pp 2034\u20132039. https:\/\/doi.org\/10.1109\/ICRA.2018.8461233","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"4358_CR4","doi-asserted-by":"publisher","unstructured":"Yuan W, Yang M, He Y, Wang C, Wang B (2019) Multi-reward architecture based reinforcement learning for highway driving policies. In: IEEE Int Conf Intell Transp Syst pp 3810\u20133815. https:\/\/doi.org\/10.1109\/ITSC.2019.8917304","DOI":"10.1109\/ITSC.2019.8917304"},{"key":"4358_CR5","doi-asserted-by":"publisher","unstructured":"Hoel C-J, Wolff K, Laine L (2018) Automated speed and lane change decision making using deep reinforcement learning. In: IEEE Int Conf Intell Transp Syst pp 2148\u20132155. https:\/\/doi.org\/10.1109\/ITSC.2018.8569568","DOI":"10.1109\/ITSC.2018.8569568"},{"key":"4358_CR6","doi-asserted-by":"publisher","unstructured":"An H, Jung J-I (2019) Decision-making system for lane change using deep reinforcement learning in connected and automated driving. Electronics 8(5). https:\/\/doi.org\/10.3390\/electronics8050543","DOI":"10.3390\/electronics8050543"},{"key":"4358_CR7","doi-asserted-by":"crossref","unstructured":"Wolf P, Hubschneider C, Weber M, Bauer A, H\u00e4rtl J, D\u00fcrr F, Z\u00f6llner JM (2017) Learning how to drive in a real world simulation with deep q-networks. In: IEEE Intell Veh Symp Proc pp 244\u2013250","DOI":"10.1109\/IVS.2017.7995727"},{"key":"4358_CR8","doi-asserted-by":"crossref","unstructured":"Deshpande N, Spalanzani A (2019) Deep reinforcement learning based vehicle navigation amongst pedestrians using a grid-based state representation*. In: IEEE Int Conf Intell Transp Syst pp 2081\u20132086","DOI":"10.1109\/ITSC.2019.8917299"},{"key":"4358_CR9","doi-asserted-by":"publisher","unstructured":"Deshpande N, Vaufreydaz D, Spalanzani A (2020) Behavioral decision- making for urban autonomous driving in the presence of pedestrians using deep recurrent q-network. In: Int Conf CTRL, Autonmn and Vis pp 428\u2013433. https:\/\/doi.org\/10.1109\/ICARCV50220.2020.9305435","DOI":"10.1109\/ICARCV50220.2020.9305435"},{"key":"4358_CR10","doi-asserted-by":"crossref","unstructured":"Kurzer K, Sch\u00f6rner P, Albers A, Thomsen H, Daaboul K, Z\u00f6llner JM (2021) Generalizing decision making for automated driving with an invariant environment representation using deep reinforcement learning","DOI":"10.1109\/IV48863.2021.9575669"},{"key":"4358_CR11","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/ACCESS.2014.2302442","volume":"2","author":"M Elbanhawi","year":"2014","unstructured":"Elbanhawi M, Simic M (2014) Sampling-based robot motion planning: a review. IEEE Access 2:56\u201377. https:\/\/doi.org\/10.1109\/ACCESS.2014.2302442","journal-title":"IEEE Access"},{"key":"4358_CR12","doi-asserted-by":"publisher","unstructured":"Karaman S, Walter MR, Perez A, Frazzoli E, Teller S (2011) Anytime motion planning using the rrt*. In: Proc IEEE Int Conf Robot Autom pp 1478\u20131483. https:\/\/doi.org\/10.1109\/ICRA.2011.5980479","DOI":"10.1109\/ICRA.2011.5980479"},{"key":"4358_CR13","doi-asserted-by":"publisher","unstructured":"Gammell JD, Srinivasa SS, Barfoot TD (2014) Informed RRT*: Optimal sampling-based path planning focused via direct sampling of an admissible ellipsoidal heuristic. In: Proc IEEE\/RSJ Int Conf Intell Robot Syst pp 2997\u20133004. https:\/\/doi.org\/10.1109\/IROS.2014.6942976","DOI":"10.1109\/IROS.2014.6942976"},{"key":"4358_CR14","doi-asserted-by":"publisher","unstructured":"Islam F, Nasir J, Malik U, Ayaz Y, Hasan O (2012) RRT*-smart: Rapid convergence implementation of RRT* towards optimal solution. In: Proc IEEE Int Conf Mechatronics & Automat pp 1651\u20131656. https:\/\/doi.org\/10.1109\/ICMA.2012.6284384","DOI":"10.1109\/ICMA.2012.6284384"},{"key":"4358_CR15","doi-asserted-by":"publisher","first-page":"113425","DOI":"10.1016\/j.eswa.2020.113425","volume":"152","author":"Y Li","year":"2020","unstructured":"Li Y, Wei W, Gao Y, Wang D, Fan Z (2020) PQ-RRT*: An improved path planning algorithm for mobile robots. Expert Syst Appl 152:113425. https:\/\/doi.org\/10.1016\/j.eswa.2020.113425","journal-title":"Expert Syst Appl"},{"issue":"5","key":"4358_CR16","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1109\/TCST.2008.2012116","volume":"17","author":"Y Kuwata","year":"2009","unstructured":"Kuwata Y, Teo J, Fiore G, Karaman S, Frazzoli E, How JP (2009) Real- time motion planning with applications to autonomous urban driving. IEEE Trans Control Syst Technol 17(5):1105\u20131118. https:\/\/doi.org\/10.1109\/TCST.2008.2012116","journal-title":"IEEE Trans Control Syst Technol"},{"key":"4358_CR17","doi-asserted-by":"publisher","unstructured":"Webb DJ, van den Berg J (2013) Kinodynamic rrt*: Asymptotically opti- mal motion planning for robots with linear dynamics. In: Proc IEEE Int Conf Robot Autom pp 5054\u20135061. https:\/\/doi.org\/10.1109\/ICRA.2013.6631299","DOI":"10.1109\/ICRA.2013.6631299"},{"issue":"4","key":"4358_CR18","doi-asserted-by":"publisher","first-page":"1961","DOI":"10.1109\/TITS.2015.2389215","volume":"16","author":"L Ma","year":"2015","unstructured":"Ma L, Xue J, Kawabata K, Zhu J, Ma C, Zheng N (2015) Efficient sampling-based motion planning for on-road autonomous driving. IEEE Trans Intell Transp Syst 16(4):1961\u20131976. https:\/\/doi.org\/10.1109\/TITS.2015.2389215","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"11","key":"4358_CR19","doi-asserted-by":"publisher","first-page":"8718","DOI":"10.1109\/TIE.2018.2816000","volume":"65","author":"Y Li","year":"2018","unstructured":"Li Y, Cui R, Li Z, Xu D (2018) Neural network approximation based near- optimal motion planning with kinodynamic constraints using rrt. IEEE Trans Ind Electron 65(11):8718\u20138729. https:\/\/doi.org\/10.1109\/TIE.2018.2816000","journal-title":"IEEE Trans Ind Electron"},{"key":"4358_CR20","unstructured":"Zhu Z, Zhao H (2021) A survey of deep rl and il for autonomous driving policy learning. arXiv preprint arXiv:2101.01993"},{"key":"4358_CR21","doi-asserted-by":"crossref","unstructured":"Kochenderfer MJ (2015) Decision making under uncertainty: theory and application. MIT press","DOI":"10.7551\/mitpress\/10187.001.0001"},{"issue":"7540","key":"4358_CR22","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Belle-mare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533. https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"4358_CR23","doi-asserted-by":"crossref","unstructured":"van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. Proc AAAI conf AI 30(1)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"4358_CR24","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2015) Prioritized experience replay. arXiv preprint arXiv:1511.05952"},{"key":"4358_CR25","doi-asserted-by":"publisher","first-page":"19842","DOI":"10.1109\/ACCESS.2020.2969316","volume":"8","author":"R Mashayekhi","year":"2020","unstructured":"Mashayekhi R, Idris MYI, Anisi MH, Ahmedy I, Ali I (2020) Informed RRT*-connect: An asymptotically optimal single-query path planning method. IEEE Access 8:19842\u201319852. https:\/\/doi.org\/10.1109\/ACCESS.2020.2969316","journal-title":"IEEE Access"},{"key":"4358_CR26","doi-asserted-by":"publisher","unstructured":"Hu Z, Wan K, Gao X, Zhai Y (2019) A dynamic adjusting reward function method for deep reinforcement learning with adjustable parameters. Math Probl Eng. https:\/\/doi.org\/10.1155\/2019\/7619483","DOI":"10.1155\/2019\/7619483"},{"key":"4358_CR27","doi-asserted-by":"publisher","unstructured":"Bouton M, Nakhaei A, Fujimura K, Kochenderfer MJ (2019) Safe reinforcement learning with scene decomposition for navigating complex urban environments. In: IEEE Intell Veh Symp Proc pp 1469\u20131476. https:\/\/doi.org\/10.1109\/IVS.2019.8813803","DOI":"10.1109\/IVS.2019.8813803"},{"issue":"4","key":"4358_CR28","doi-asserted-by":"publisher","first-page":"3418","DOI":"10.1109\/LRA.2018.2852793","volume":"3","author":"Y Luo","year":"2018","unstructured":"Luo Y, Cai P, Bera A, Hsu D, Lee WS, Manocha D (2018) PORCA: Modeling and planning for autonomous driving among many pedestrians. IEEE Robot Autom Lett 3(4):3418\u20133425. https:\/\/doi.org\/10.1109\/LRA.2018.2852793","journal-title":"IEEE Robot Autom Lett"},{"key":"4358_CR29","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.ymssp.2015.10.021","volume":"87","author":"X Li","year":"2017","unstructured":"Li X, Sun Z, Cao D, Liu D, He H (2017) Development of a new integrated local trajectory planning and tracking control framework for autonomous ground vehicles. Mech Syst Signal Process 87:118\u2013137. https:\/\/doi.org\/10.1016\/j.ymssp.2015.10.021","journal-title":"Mech Syst Signal Process"},{"key":"4358_CR30","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.cam.2018.03.029","volume":"341","author":"E Bertolazzi","year":"2018","unstructured":"Bertolazzi E, Frego M (2018) On the g2 hermite interpolation problem with clothoids. J Comput Appl Math 341:99\u2013116. https:\/\/doi.org\/10.1016\/j.cam.2018.03.029","journal-title":"J Comput Appl Math"},{"key":"4358_CR31","doi-asserted-by":"publisher","unstructured":"Chen D, Jiang L, Wang Y, Li Z (2020) Autonomous driving using safe reinforcement learning by incorporating a regret-based human lane-changing decision model. In: Proc Amer Control Conf pp 4355\u20134361. https:\/\/doi.org\/10.23919\/ACC45564.2020.9147626","DOI":"10.23919\/ACC45564.2020.9147626"},{"key":"4358_CR32","doi-asserted-by":"publisher","unstructured":"Porav H, Newman P (2018) Imminent collision mitigation with reinforcement learning and vision. In: IEEE Int Conf Intell Transp Syst pp 958\u2013964. https:\/\/doi.org\/10.1109\/ITSC.2018.8569222","DOI":"10.1109\/ITSC.2018.8569222"},{"key":"4358_CR33","doi-asserted-by":"publisher","unstructured":"Hoel C-J, Wolff K, Laine L (2020) Tactical decision-making in autonomous driving by reinforcement learning with uncertainty estimation. In: IEEE Intell Veh Symp Proc pp 1563\u20131569. https:\/\/doi.org\/10.1109\/IV47402.2020.9304614","DOI":"10.1109\/IV47402.2020.9304614"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04358-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-04358-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04358-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T05:06:04Z","timestamp":1688187964000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-04358-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,8]]},"references-count":33,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["4358"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-04358-7","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,8]]},"assertion":[{"value":"22 November 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}