{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T00:45:31Z","timestamp":1774658731469,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2021,8,18]],"date-time":"2021-08-18T00:00:00Z","timestamp":1629244800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,18]],"date-time":"2021-08-18T00:00:00Z","timestamp":1629244800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"2030 National Key AI Program of China","award":["2018AAA0100500"],"award-info":[{"award-number":["2018AAA0100500"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61573386"],"award-info":[{"award-number":["61573386"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","award":["2017B010110011"],"award-info":[{"award-number":["2017B010110011"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1007\/s42979-021-00817-z","type":"journal-article","created":{"date-parts":[[2021,8,18]],"date-time":"2021-08-18T04:37:59Z","timestamp":1629261479000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Deep Reinforcement Learning of Map-Based Obstacle Avoidance for Mobile Robot Navigation"],"prefix":"10.1007","volume":"2","author":[{"given":"Guangda","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lifan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu\u2019an","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peichen","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1515-0402","authenticated-orcid":false,"given":"Jianmin","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoping","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,18]]},"reference":[{"key":"817_CR1","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.artint.2014.11.003","volume":"247","author":"F Ingrand","year":"2017","unstructured":"Ingrand F, Ghallab M. Deliberation for autonomous robots: a survey. Artif Intell. 2017;247:10\u201344.","journal-title":"Artif Intell"},{"key":"817_CR2","doi-asserted-by":"crossref","unstructured":"Minguez J, Lamiraux F, Laumond J-P. Motion planning and obstacle avoidance. In: Springer handbook of robotics. Springer, 2016;1177\u2013202.","DOI":"10.1007\/978-3-319-32552-1_47"},{"key":"817_CR3","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.robot.2017.10.011","volume":"100","author":"M Mohanan","year":"2018","unstructured":"Mohanan M, Salgoankar A. A survey of robotic motion planning in dynamic environments. Robot Auton Syst. 2018;100:171\u201385.","journal-title":"Robot Auton Syst"},{"issue":"12","key":"817_CR4","doi-asserted-by":"publisher","first-page":"2742","DOI":"10.3390\/s17122742","volume":"17","author":"W Zhang","year":"2017","unstructured":"Zhang W, Wei S, Teng Y, Zhang J, Wang X, Yan Z. Dynamic obstacle avoidance for unmanned underwater vehicles based on an improved velocity obstacle method. Sensors. 2017;17(12):2742.","journal-title":"Sensors"},{"issue":"2","key":"817_CR5","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1109\/LRA.2017.2656241","volume":"2","author":"D Zhou","year":"2017","unstructured":"Zhou D, Wang Z, Bandyopadhyay S, Schwager M. Fast, on-line collision avoidance for dynamic vehicles using buffered Voronoi cells. IEEE Robot Autom Lett. 2017;2(2):1047\u201354.","journal-title":"IEEE Robot Autom Lett"},{"key":"817_CR6","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.robot.2016.11.007","volume":"88","author":"C R\u00f6smann","year":"2017","unstructured":"R\u00f6smann C, Hoffmann F, Bertram T. Integrated online trajectory planning and optimization in distinctive topologies. Robot Auton Syst. 2017;88:142\u201353.","journal-title":"Robot Auton Syst"},{"key":"817_CR7","doi-asserted-by":"crossref","unstructured":"Kahn G, Villaflor A, Ding B, Abbeel P, Levine S. Self-supervised deep reinforcement learning with generalized computation graphs for robot navigation. In: Proceedings of the IEEE international conference on robotics and automation (ICRA), 2018;1\u20138.","DOI":"10.1109\/ICRA.2018.8460655"},{"issue":"7676","key":"817_CR8","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver D, Schrittwieser J, Simonyan K, Antonoglou I, Huang A, Guez A, Hubert T, Baker L, Lai M, Bolton A, et al. Mastering the game of go without human knowledge. Nature. 2017;550(7676):354\u20139.","journal-title":"Nature"},{"issue":"7782","key":"817_CR9","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals O, Babuschkin I, Czarnecki WM, Mathieu M, Dudzik A, Chung J, Choi DH, Powell R, Ewalds T, Georgiev P, et al. Grandmaster level in starcraft II using multi-agent reinforcement learning. Nature. 2019;575(7782):350\u20134.","journal-title":"Nature"},{"issue":"4\u20135","key":"817_CR10","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1177\/0278364917710318","volume":"37","author":"S Levine","year":"2018","unstructured":"Levine S, Pastor P, Krizhevsky A, Ibarz J, Quillen D. Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. Int J Robot Res. 2018;37(4\u20135):421\u201336.","journal-title":"Int J Robot Res"},{"key":"817_CR11","doi-asserted-by":"crossref","unstructured":"Xie L, Wang S, Rosa S, Markham A, Trigoni N. Learning with training wheels: speeding up training with a simple controller for deep reinforcement learning. In: Proceedings of the IEEE international conference on robotics and automation (ICRA), 2018;6276\u201383.","DOI":"10.1109\/ICRA.2018.8461203"},{"issue":"7","key":"817_CR12","doi-asserted-by":"publisher","first-page":"2685","DOI":"10.1109\/JSEN.2018.2889805","volume":"19","author":"G Chen","year":"2018","unstructured":"Chen G, Cui G, Jin Z, Wu F, Chen X. Accurate intrinsic and extrinsic calibration of RGB-D cameras with GP-based depth correction. IEEE Sens J. 2018;19(7):2685\u201394.","journal-title":"IEEE Sens J"},{"key":"817_CR13","doi-asserted-by":"crossref","unstructured":"Chen G, Pan L, Chen Y, Xu P, Wang Z, Wu P, Ji J, Chen X. Robot navigation with map-based deep reinforcement learning. In: Proceedings of the 2020 IEEE international conference on networking, sensing and control (ICNSC), 2020;1\u20136.","DOI":"10.1109\/ICNSC48988.2020.9238090"},{"issue":"2","key":"817_CR14","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/LRA.2015.2509024","volume":"1","author":"A Giusti","year":"2015","unstructured":"Giusti A, Guzzi J, Cire\u015fan DC, He F-L, Rodr\u00edguez JP, Fontana F, Faessler M, Forster C, Schmidhuber J, Di Caro G, et al. A machine learning approach to visual perception of forest trails for mobile robots. IEEE Robot Autom Lett. 2015;1(2):661\u20137.","journal-title":"IEEE Robot Autom Lett"},{"key":"817_CR15","doi-asserted-by":"crossref","unstructured":"Gandhi D, Pinto L, Gupta A. Learning to fly by crashing. In: Proceedings of the IEEE\/RSJ international conference on intelligent robots and systems (IROS), 2017;3948\u201355.","DOI":"10.1109\/IROS.2017.8206247"},{"key":"817_CR16","doi-asserted-by":"crossref","unstructured":"Tai L, Li S, Liu M. A deep-network solution towards model-less obstacle avoidance. In: Proceedings of the IEEE\/RSJ international conference on intelligent robots and systems (IROS), 2016;2759\u201364.","DOI":"10.1109\/IROS.2016.7759428"},{"key":"817_CR17","doi-asserted-by":"crossref","unstructured":"Pfeiffer M, Schaeuble M, Nieto J, Siegwart R, Cadena C. From perception to decision: a data-driven approach to end-to-end motion planning for autonomous ground robots. In: Proceedings of the IEEE international conference on robotics and automation (ICRA), 2017;1527\u201333.","DOI":"10.1109\/ICRA.2017.7989182"},{"issue":"1","key":"817_CR18","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/100.580977","volume":"4","author":"D Fox","year":"1997","unstructured":"Fox D, Burgard W, Thrun S. The dynamic window approach to collision avoidance. IEEE Robot Autom Mag. 1997;4(1):23\u201333.","journal-title":"IEEE Robot Autom Mag"},{"key":"817_CR19","doi-asserted-by":"crossref","unstructured":"Liu Y, Xu A, Chen Z. Map-based deep imitation learning for obstacle avoidance. In: Proceedings of the IEEE\/RSJ international conference on intelligent robots and systems (IROS), 2018;8644\u20139.","DOI":"10.1109\/IROS.2018.8593683"},{"key":"817_CR20","doi-asserted-by":"crossref","unstructured":"Chen YF, Liu M, Everett M, How JP. Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning. In: Proceedings of the IEEE international conference on robotics and automation (ICRA), 2017;285\u201392.","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"817_CR21","doi-asserted-by":"crossref","unstructured":"Chen YF, Everett M, Liu M, How JP. \u201cSocially aware motion planning with deep reinforcement learning,\u201d In Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017;1343\u20131350.","DOI":"10.1109\/IROS.2017.8202312"},{"key":"817_CR22","doi-asserted-by":"crossref","unstructured":"Tai L, Paolo G, Liu M. Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation. In: Proceedings of the IEEE\/RSJ international conference on intelligent robots and systems (IROS), 2017;31\u20136.","DOI":"10.1109\/IROS.2017.8202134"},{"key":"817_CR23","doi-asserted-by":"crossref","unstructured":"Long P, Fanl T, Liao X, Liu W, Zhang H, Pan J. Towards optimally decentralized multi-robot collision avoidance via deep reinforcement learning. In: Proceedings of the IEEE international conference on robotics and automation (ICRA), 2018;6252\u20139.","DOI":"10.1109\/ICRA.2018.8461113"},{"issue":"4","key":"817_CR24","doi-asserted-by":"publisher","first-page":"3247","DOI":"10.1109\/LRA.2018.2851148","volume":"3","author":"K Lobos-Tsunekawa","year":"2018","unstructured":"Lobos-Tsunekawa K, Leiva F, Ruiz-del Solar J. Visual navigation for biped humanoid robots using deep reinforcement learning. IEEE Robot Autom Lett. 2018;3(4):3247\u201354.","journal-title":"IEEE Robot Autom Lett"},{"issue":"11","key":"817_CR25","doi-asserted-by":"publisher","first-page":"3650","DOI":"10.3390\/s18113650","volume":"18","author":"K Wu","year":"2018","unstructured":"Wu K, Abolfazli Esfahani M, Yuan S, Wang H. Learn to steer through deep reinforcement learning. Sensors. 2018;18(11):3650.","journal-title":"Sensors"},{"key":"817_CR26","doi-asserted-by":"crossref","unstructured":"Zhang J, Springenberg JT, Boedecker J, Burgard W. Deep reinforcement learning with successor features for navigation across similar environments. In: Proceedings of the IEEE\/RSJ international conference on intelligent robots and systems (IROS), 2017;2371\u20138.","DOI":"10.1109\/IROS.2017.8206049"},{"key":"817_CR27","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt H, Guez A, Silver D. Deep reinforcement learning with double Q-learning. In: Proceedings of the thirtieth AAAI conference on artificial intelligence (AAAI), 2016.","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"817_CR28","unstructured":"Wang Z, Schaul T, Hessel M, Hasselt H, Lanctot M, Freitas N. Dueling network architectures for deep reinforcement learning. In: Proceedings of the 33rd international conference on machine learning (ICML), 2016;1995\u20132003."},{"key":"817_CR29","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D. Prioritized experience replay. In 2016."},{"key":"817_CR30","doi-asserted-by":"crossref","unstructured":"Lu DV, Hershberger D, Smart WD. Layered costmaps for context-sensitive navigation. In: Proceedings of the IEEE\/RSJ international conference on intelligent robots and systems (IROS), 2014;709\u201315.","DOI":"10.1109\/IROS.2014.6942636"},{"key":"817_CR31","first-page":"278","volume":"99","author":"AY Ng","year":"1999","unstructured":"Ng AY, Harada D, Russell S. Policy invariance under reward transformations: theory and application to reward shaping. ICML. 1999;99:278\u201387.","journal-title":"ICML"},{"key":"817_CR32","doi-asserted-by":"crossref","unstructured":"Bengio Y, Louradour J, Collobert R, Weston J. Curriculum learning. In: Proceedings of the 26th annual international conference on machine learning (ICML). ACM, 2009;41\u20138.","DOI":"10.1145\/1553374.1553380"},{"issue":"1","key":"817_CR33","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/0010-0277(93)90058-4","volume":"48","author":"JL Elman","year":"1993","unstructured":"Elman JL. Learning and development in neural networks: the importance of starting small. Cognition. 1993;48(1):71\u201399.","journal-title":"Cognition"},{"key":"817_CR34","first-page":"2149","volume":"3","author":"N Koenig","year":"2004","unstructured":"Koenig N, Howard A. Design and use paradigms for gazebo, an open-source multi-robot simulator. Proc IEEE\/RSJ Int Confe Intell Robot Syst. 2004;3:2149\u201354.","journal-title":"Proc IEEE\/RSJ Int Confe Intell Robot Syst"},{"key":"817_CR35","unstructured":"Kingma DP, Ba J. Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014."},{"key":"817_CR36","first-page":"2505","volume":"3","author":"I Ulrich","year":"2000","unstructured":"Ulrich I, Borenstein J. Vfh\/sup*: local obstacle avoidance with look-ahead verification. Proc IEEE Int Conf Robot Autom. 2000;3:2505\u201311.","journal-title":"Proc IEEE Int Conf Robot Autom"},{"key":"817_CR37","first-page":"1398","volume":"2","author":"Y Koren","year":"1991","unstructured":"Koren Y, Borenstein J, et al. Potential field methods and their inherent limitations for mobile robot navigation. Proc IEEE Int Conf Robot Autom. 1991;2:1398\u2013404.","journal-title":"Proc IEEE Int Conf Robot Autom"},{"issue":"3","key":"817_CR38","doi-asserted-by":"publisher","first-page":"4616","DOI":"10.1109\/LRA.2021.3068662","volume":"6","author":"B Brito","year":"2021","unstructured":"Brito B, Everett M, How JP, Alonso-Mora J. Where to go next: learning a subgoal recommendation policy for navigation in dynamic environments. IEEE Robot Autom Lett. 2021;6(3):4616\u201323.","journal-title":"IEEE Robot Autom Lett"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-021-00817-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-021-00817-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-021-00817-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T14:53:28Z","timestamp":1673103208000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-021-00817-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,18]]},"references-count":38,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["817"],"URL":"https:\/\/doi.org\/10.1007\/s42979-021-00817-z","relation":{},"ISSN":["2662-995X","2661-8907"],"issn-type":[{"value":"2662-995X","type":"print"},{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,18]]},"assertion":[{"value":"21 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"417"}}