{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T09:46:53Z","timestamp":1774000013550,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,12]]},"DOI":"10.1145\/3788149.3788204","type":"proceedings-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:35:19Z","timestamp":1773988519000},"page":"126-131","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Nonholonomic Narrow Dead-End Escape with Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0657-1787","authenticated-orcid":false,"given":"Denghan","family":"Xiong","sequence":"first","affiliation":[{"name":"Zhejiang University, Jiaxing, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5342-6611","authenticated-orcid":false,"given":"Yanzhe","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9202-1673","authenticated-orcid":false,"given":"Yutong","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing Jiao Tong University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7596-1353","authenticated-orcid":false,"given":"Zichun","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Nottingham Ningbo China, Ningbo, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"Xiuquan Cheng Shaobo Zhang Sizhu Cheng Qinxiang Xia and Junhao Zhang. [n. d.]. Path-Following and Obstacle Avoidance Control of Nonholonomic Wheeled Mobile Robot Based on Deep Reinforcement Learning. 12 14 ([n. d.]) 6874. 10.3390\/app12146874","DOI":"10.3390\/app12146874"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.5220\/0011123600003271"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","unstructured":"Peter\u00a0E. Hart Nils\u00a0J. Nilsson and Bertram Raphael. 1968. A Formal Basis for the Heuristic Determination of Minimum Cost Paths. IEEE Transactions on Systems Science and Cybernetics 4 2 (1968) 100\u2013107. 10.1109\/TSSC.1968.300136","DOI":"10.1109\/TSSC.1968.300136"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Shyr-Long Jeng and Chienhsun Chiang. [n. d.]. End-to-End Autonomous Navigation Based on Deep Reinforcement Learning with a Survival Penalty Function. 23 20 ([n. d.]) 8651. 10.3390\/s23208651","DOI":"10.3390\/s23208651"},{"key":"e_1_3_3_1_6_2","unstructured":"Mingyang Jiang Yueyuan Li Songan Zhang Siyuan Chen Chunxiang Wang and Ming Yang. 2024. HOPE: A Reinforcement Learning-based Hybrid Policy Path Planner for Diverse Parking Scenarios. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.20579 (2024)."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","unstructured":"J.-P. Laumond P.E. Jacobs M. Taix and R.M. Murray. 1994. A motion planner for nonholonomic mobile robots. IEEE Transactions on Robotics and Automation 10 5 (Oct. 1994) 577\u2013593. 10.1109\/70.326564","DOI":"10.1109\/70.326564"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0036070"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Zhuoren Li Guizhe Jin Ran Yu Zhiwen Chen Nan Li Wei Han Lu Xiong Bo Leng Jia Hu Ilya Kolmanovsky and Dimitar Filev. 2025. A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective. 10.48550\/arXiv.2503.23650arXiv:https:\/\/arXiv.org\/abs\/2503.23650 [cs].","DOI":"10.48550\/arXiv.2503.23650"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Andreas Orthey and Marc Toussaint. 2021. Section Patterns: Efficiently Solving Narrow Passage Problems in Multilevel Motion Planning. IEEE Transactions on Robotics 37 6 (Dec. 2021) 1891\u20131905. 10.1109\/TRO.2021.3070975","DOI":"10.1109\/TRO.2021.3070975"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561207"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"James Reeds and Lawrence Shepp. 1990. Optimal paths for a car that goes both forwards and backwards. Pacific J. Math. 145 2 (Oct. 1990) 367\u2013393. 10.2140\/pjm.1990.145.367","DOI":"10.2140\/pjm.1990.145.367"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Taizhou University Taizhou 225300 China Shuai Xiaoying Yin Yuxia and Zhang Bin. 2021. A Fast Convergence ALOHA Based on Reinforcement Learning. International Journal of Computer Theory and Engineering 13 3 (2021) 96\u201399. 10.7763\/IJCTE.2021.V13.1296","DOI":"10.7763\/IJCTE.2021.V13.1296"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Shinya Yasuda Taichi Kumagai and Hiroshi Yoshida. 2023. Safe and Efficient Dynamic Window Approach for Differential Mobile Robots With Stochastic Dynamics Using Deterministic Sampling. IEEE Robotics and Automation Letters 8 5 (May 2023) 2614\u20132621. 10.1109\/LRA.2023.3257681","DOI":"10.1109\/LRA.2023.3257681"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.03208"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Zheng Sun D. Hsu Tingting Jiang H. Kurniawati and J.H. Reif. 2005. Narrow passage sampling for probabilistic roadmap planning. IEEE Transactions on Robotics 21 6 (Dec. 2005) 1105\u20131115. 10.1109\/TRO.2005.853485","DOI":"10.1109\/TRO.2005.853485"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Kai Zhu and Tao Zhang. 2021. Deep reinforcement learning based mobile robot navigation: A review. Tsinghua Science and Technology 26 5 (2021) 674\u2013691. 10.26599\/TST.2021.9010012","DOI":"10.26599\/TST.2021.9010012"}],"event":{"name":"CSAI 2025: 2025 The 9th International Conference on Computer Science and Artificial Intelligence","location":"Beijing China","acronym":"CSAI 2025"},"container-title":["Proceedings of the 2025 9th International Conference on Computer Science and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788149.3788204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:35:34Z","timestamp":1773988534000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788149.3788204"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,12]]},"references-count":17,"alternative-id":["10.1145\/3788149.3788204","10.1145\/3788149"],"URL":"https:\/\/doi.org\/10.1145\/3788149.3788204","relation":{},"subject":[],"published":{"date-parts":[[2025,12,12]]},"assertion":[{"value":"2026-03-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}