{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T14:16:42Z","timestamp":1784989002831,"version":"3.55.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T00:00:00Z","timestamp":1720828800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T00:00:00Z","timestamp":1720828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant No.61973320"],"award-info":[{"award-number":["Grant No.61973320"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019091","name":"Key Research and Development Program of Hunan Province of China","doi-asserted-by":"publisher","award":["2022GK2059"],"award-info":[{"award-number":["2022GK2059"]}],"id":[{"id":"10.13039\/501100019091","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Xinjiang Province of China","award":["2022294793"],"award-info":[{"award-number":["2022294793"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s10489-024-05679-5","type":"journal-article","created":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T06:02:21Z","timestamp":1720850541000},"page":"9295-9312","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Deep reinforcement learning based mapless navigation for industrial AMRs: advancements in generalization via potential risk state augmentation"],"prefix":"10.1007","volume":"54","author":[{"given":"Degang","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianhan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3595-0412","authenticated-orcid":false,"given":"Yizhi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanzheng","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,13]]},"reference":[{"issue":"6","key":"5679_CR1","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1109\/TRO.2016.2624754","volume":"32","author":"C Cadena","year":"2016","unstructured":"Cadena C, Carlone L, Carrillo H et al (2016) Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Trans Robot 32(6):1309\u20131332","journal-title":"IEEE Trans Robot"},{"issue":"1","key":"5679_CR2","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1109\/TTE.2022.3199255","volume":"9","author":"H Yang","year":"2022","unstructured":"Yang H, Xu X, Hong J (2022) Automatic parking path planning of tracked vehicle based on improved a* and dwa algorithms. IEEE Trans Transp Electrif 9(1):283\u2013292","journal-title":"IEEE Trans Transp Electrif"},{"key":"5679_CR3","doi-asserted-by":"publisher","first-page":"1557","DOI":"10.1007\/s12239-021-0134-z","volume":"22","author":"J Liu","year":"2021","unstructured":"Liu J, Ji J, Ren Y et al (2021) Path planning for vehicle active collision avoidance based on virtual flow field. Int J Automot Technol 22:1557\u20131567","journal-title":"Int J Automot Technol"},{"issue":"5","key":"5679_CR4","doi-asserted-by":"publisher","first-page":"674","DOI":"10.26599\/TST.2021.9010012","volume":"26","author":"K Zhu","year":"2021","unstructured":"Zhu K, Zhang T (2021) Deep reinforcement learning based mobile robot navigation: a review. Tsinghua Sci Technol 26(5):674\u2013691","journal-title":"Tsinghua Sci Technol"},{"key":"5679_CR5","doi-asserted-by":"crossref","unstructured":"Tai L, Paolo G, Liu M (2017) Virtual-to-real deep reinforcement learning: continuous control of mobile robots for mapless navigation. In: 2017 IEEE\/RSJ International conference on intelligent robots and systems (IROS), IEEE, pp 31\u201336","DOI":"10.1109\/IROS.2017.8202134"},{"issue":"4","key":"5679_CR6","doi-asserted-by":"publisher","first-page":"2393","DOI":"10.1109\/TII.2019.2936167","volume":"16","author":"H Shi","year":"2019","unstructured":"Shi H, Shi L, Xu M et al (2019) End-to-end navigation strategy with deep reinforcement learning for mobile robots. IEEE Trans Ind Inform 16(4):2393\u20132402","journal-title":"IEEE Trans Ind Inform"},{"issue":"5","key":"5679_CR7","doi-asserted-by":"publisher","first-page":"5342","DOI":"10.1109\/TIE.2021.3078353","volume":"69","author":"K Wu","year":"2021","unstructured":"Wu K, Wang H, Esfahani MA et al (2021) Learn to navigate autonomously through deep reinforcement learning. IEEE Trans Ind Electron 69(5):5342\u20135352","journal-title":"IEEE Trans Ind Electron"},{"issue":"1","key":"5679_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10846-020-01262-5","volume":"101","author":"M Luong","year":"2021","unstructured":"Luong M, Pham C (2021) Incremental learning for autonomous navigation of mobile robots based on deep reinforcement learning. J Intell Robot Syst 101(1):1","journal-title":"J Intell Robot Syst"},{"issue":"6","key":"5679_CR9","doi-asserted-by":"publisher","first-page":"5451","DOI":"10.1109\/TMECH.2022.3182427","volume":"27","author":"W Zhang","year":"2022","unstructured":"Zhang W, Zhang Y, Liu N et al (2022) Ipaprec: A promising tool for learning high-performance mapless navigation skills with deep reinforcement learning. IEEE\/ASME Trans Mechatron 27(6):5451\u20135461","journal-title":"IEEE\/ASME Trans Mechatron"},{"issue":"3","key":"5679_CR10","doi-asserted-by":"publisher","first-page":"2124","DOI":"10.1109\/TVT.2018.2890773","volume":"68","author":"C Wang","year":"2019","unstructured":"Wang C, Wang J, Shen Y et al (2019) Autonomous navigation of uavs in large-scale complex environments: a deep reinforcement learning approach. IEEE Trans Veh Technol 68(3):2124\u20132136","journal-title":"IEEE Trans Veh Technol"},{"key":"5679_CR11","doi-asserted-by":"crossref","unstructured":"Xie Z, Dames P (2023) Drl-vo: Learning to navigate through crowded dynamic scenes using velocity obstacles. IEEE Trans Robot","DOI":"10.1109\/TRO.2023.3257549"},{"key":"5679_CR12","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.jmsy.2019.12.002","volume":"54","author":"M De Ryck","year":"2020","unstructured":"De Ryck M, Versteyhe M, Debrouwere F (2020) Automated guided vehicle systems, state-of-the-art control algorithms and techniques. J Manuf Syst 54:152\u2013173","journal-title":"J Manuf Syst"},{"key":"5679_CR13","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1007\/s10514-016-9557-1","volume":"41","author":"C Sprunk","year":"2017","unstructured":"Sprunk C, Lau B, Pfaff P et al (2017) An accurate and efficient navigation system for omnidirectional robots in industrial environments. Auton Robots 41:473\u2013493","journal-title":"Auton Robots"},{"key":"5679_CR14","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1016\/j.isatra.2021.05.018","volume":"123","author":"X Liu","year":"2022","unstructured":"Liu X, Wang W, Li X et al (2022) Mpc-based high-speed trajectory tracking for 4wis robot. ISA Trans 123:413\u2013424","journal-title":"ISA Trans"},{"issue":"5","key":"5679_CR15","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1109\/TITS.2016.2604240","volume":"18","author":"Y Rasekhipour","year":"2016","unstructured":"Rasekhipour Y, Khajepour A, Chen SK et al (2016) A potential field-based model predictive path-planning controller for autonomous road vehicles. IEEE Trans Intell Transp Syst 18(5):1255\u20131267","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"5679_CR16","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1016\/j.isatra.2022.09.018","volume":"135","author":"H Yang","year":"2023","unstructured":"Yang H, Wang Z, Xia Y et al (2023) Empc with adaptive apf of obstacle avoidance and trajectory tracking for autonomous electric vehicles. ISA Trans 135:438\u2013448","journal-title":"ISA Trans"},{"issue":"5","key":"5679_CR17","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1007\/s10514-022-10039-8","volume":"46","author":"X Xiao","year":"2022","unstructured":"Xiao X, Liu B, Warnell G et al (2022) Motion planning and control for mobile robot navigation using machine learning: a survey. Auton Robots 46(5):569\u2013597","journal-title":"Auton Robots"},{"key":"5679_CR18","doi-asserted-by":"crossref","unstructured":"Zhu Y, Mottaghi R, Kolve E et\u00a0al (2017) Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: 2017 IEEE international conference on robotics and automation (ICRA), IEEE, pp 3357\u20133364","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"5679_CR19","doi-asserted-by":"crossref","unstructured":"Yokoyama K, Morioka K (2020) Autonomous mobile robot with simple navigation system based on deep reinforcement learning and a monocular camera. In: 2020 IEEE\/SICE International Symposium on System Integration (SII), IEEE, pp 525\u2013530","DOI":"10.1109\/SII46433.2020.9025987"},{"issue":"13","key":"5679_CR20","doi-asserted-by":"publisher","first-page":"15600","DOI":"10.1007\/s10489-022-03191-2","volume":"52","author":"Z Zhou","year":"2022","unstructured":"Zhou Z, Zhu P, Zeng Z et al (2022) Robot navigation in a crowd by integrating deep reinforcement learning and online planning. Appl Intell 52(13):15600\u201315616","journal-title":"Appl Intell"},{"issue":"2","key":"5679_CR21","doi-asserted-by":"publisher","first-page":"2754","DOI":"10.1109\/LRA.2020.2972868","volume":"5","author":"Y Chen","year":"2020","unstructured":"Chen Y, Liu C, Shi BE et al (2020) Robot navigation in crowds by graph convolutional networks with attention learned from human gaze. IEEE Robot Autom Lett 5(2):2754\u20132761","journal-title":"IEEE Robot Autom Lett"},{"issue":"23","key":"5679_CR22","doi-asserted-by":"publisher","first-page":"4744","DOI":"10.3390\/electronics12234744","volume":"12","author":"X Sun","year":"2023","unstructured":"Sun X, Zhang Q, Wei Y et al (2023) Risk-aware deep reinforcement learning for robot crowd navigation. Electronics 12(23):4744","journal-title":"Electronics"},{"key":"5679_CR23","doi-asserted-by":"crossref","unstructured":"Liu L, Dugas D, Cesari G, et\u00a0al (2020) Robot navigation in crowded environments using deep reinforcement learning. In: 2020 IEEE\/RSJ International conference on intelligent robots and systems (IROS), IEEE, pp 5671\u20135677","DOI":"10.1109\/IROS45743.2020.9341540"},{"key":"5679_CR24","doi-asserted-by":"crossref","unstructured":"Pfeiffer M, Schaeuble M, Nieto J et\u00a0al (2017) From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots. In: 2017 IEEE international conference on robotics and automation (icra), IEEE, pp 1527\u20131533","DOI":"10.1109\/ICRA.2017.7989182"},{"issue":"4","key":"5679_CR25","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.1109\/TRO.2020.2975428","volume":"36","author":"A Francis","year":"2020","unstructured":"Francis A, Faust A, Chiang HTL et al (2020) Long-range indoor navigation with prm-rl. IEEE Trans Robot 36(4):1115\u20131134","journal-title":"IEEE Trans Robot"},{"issue":"4","key":"5679_CR26","doi-asserted-by":"publisher","first-page":"4423","DOI":"10.1109\/LRA.2018.2869644","volume":"3","author":"M Pfeiffer","year":"2018","unstructured":"Pfeiffer M, Shukla S, Turchetta M et al (2018) Reinforced imitation: sample efficient deep reinforcement learning for mapless navigation by leveraging prior demonstrations. IEEE Robot Autom Lett 3(4):4423\u20134430","journal-title":"IEEE Robot Autom Lett"},{"issue":"2","key":"5679_CR27","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1007\/s12555-021-0642-7","volume":"21","author":"W Li","year":"2023","unstructured":"Li W, Yue M, Shangguan J et al (2023) Navigation of mobile robots based on deep reinforcement learning: Reward function optimization and knowledge transfer. Int J Control Autom Syst 21(2):563\u2013574","journal-title":"Int J Control Autom Syst"},{"key":"5679_CR28","doi-asserted-by":"publisher","first-page":"106613","DOI":"10.1016\/j.engappai.2023.106613","volume":"124","author":"H Guo","year":"2023","unstructured":"Guo H, Ren Z, Lai J et al (2023) Optimal navigation for agvs: a soft actor-critic-based reinforcement learning approach with composite auxiliary rewards. Eng Appl Artif Intell 124:106613","journal-title":"Eng Appl Artif Intell"},{"key":"5679_CR29","doi-asserted-by":"crossref","unstructured":"Martinez-Baselga D, Riazuelo L, Montano L (2023) Improving robot navigation in crowded environments using intrinsic\u00a0rewards. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp 9428\u20139434","DOI":"10.1109\/ICRA48891.2023.10160876"},{"key":"5679_CR30","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.neucom.2022.06.102","volume":"503","author":"H Jiang","year":"2022","unstructured":"Jiang H, Esfahani MA, Wu K et al (2022) itd3-cln: Learn to navigate in dynamic scene through deep reinforcement learning. Neurocomputing 503:118\u2013128","journal-title":"Neurocomputing"},{"issue":"11","key":"5679_CR31","doi-asserted-by":"publisher","first-page":"11816","DOI":"10.1109\/TIE.2021.3118407","volume":"69","author":"Y Jang","year":"2021","unstructured":"Jang Y, Baek J, Han S (2021) Hindsight intermediate targets for mapless navigation with deep reinforcement learning. IEEE Trans Ind Electron 69(11):11816\u201311825","journal-title":"IEEE Trans Ind Electron"},{"issue":"5","key":"5679_CR32","doi-asserted-by":"publisher","first-page":"4962","DOI":"10.1109\/TIE.2022.3190850","volume":"70","author":"W Zhu","year":"2022","unstructured":"Zhu W, Hayashibe M (2022) A hierarchical deep reinforcement learning framework with high efficiency and generalization for fast and safe navigation. IEEE Trans Ind Electron 70(5):4962\u20134971","journal-title":"IEEE Trans Ind Electron"},{"key":"5679_CR33","doi-asserted-by":"crossref","unstructured":"Miranda VR, Neto AA, Freitas GM, et\u00a0al (2023) Generalization in deep reinforcement learning for robotic navigation by reward shaping. IEEE Trans Ind Electron","DOI":"10.1109\/TIE.2023.3290244"},{"issue":"7","key":"5679_CR34","doi-asserted-by":"publisher","first-page":"7073","DOI":"10.1109\/TIE.2022.3203761","volume":"70","author":"C Yan","year":"2022","unstructured":"Yan C, Qin J, Liu Q et al (2022) Mapless navigation with safety-enhanced imitation learning. IEEE Trans Ind Electron 70(7):7073\u20137081","journal-title":"IEEE Trans Ind Electron"},{"key":"5679_CR35","doi-asserted-by":"publisher","first-page":"102570","DOI":"10.1016\/j.rcim.2023.102570","volume":"83","author":"L Chang","year":"2023","unstructured":"Chang L, Shan L, Zhang W et al (2023) Hierarchical multi-robot navigation and formation in unknown environments via deep reinforcement learning and distributed optimization. Robot Comput-Integr Manuf 83:102570","journal-title":"Robot Comput-Integr Manuf"},{"issue":"4","key":"5679_CR36","doi-asserted-by":"publisher","first-page":"1739","DOI":"10.1109\/TMECH.2020.2993564","volume":"25","author":"J Lim","year":"2020","unstructured":"Lim J, Ha S, Choi J (2020) Prediction of reward functions for deep reinforcement learning via gaussian process regression. IEEE\/ASME Trans Mechatron 25(4):1739\u20131746. https:\/\/doi.org\/10.1109\/TMECH.2020.2993564","journal-title":"IEEE\/ASME Trans Mechatron"},{"issue":"2","key":"5679_CR37","doi-asserted-by":"publisher","first-page":"1918","DOI":"10.1109\/LRA.2021.3061305","volume":"6","author":"W Zhang","year":"2021","unstructured":"Zhang W, Liu N, Zhang Y (2021) Learn to navigate maplessly with varied lidar configurations: a support point-based approach. IEEE Robot Autom Lett 6(2):1918\u20131925. https:\/\/doi.org\/10.1109\/LRA.2021.3061305","journal-title":"IEEE Robot Autom Lett"},{"key":"5679_CR38","unstructured":"Haarnoja T, Zhou A, Abbeel P, et\u00a0al (2018) Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning, PMLR, pp 1861\u20131870"},{"issue":"5","key":"5679_CR39","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1007\/s11431-022-2292-3","volume":"66","author":"J Yang","year":"2023","unstructured":"Yang J, Lu S, Han M et al (2023) Mapless navigation for uavs via reinforcement learning from demonstrations. Sci China Technol Sci 66(5):1263\u20131270","journal-title":"Sci China Technol Sci"},{"key":"5679_CR40","doi-asserted-by":"crossref","unstructured":"Huang W, Zhou Y, He X, et\u00a0al (2023) Goal-guided transformer-enabled reinforcement learning for efficient autonomous navigation. IEEE Trans Intell Transp Syst","DOI":"10.1109\/TITS.2023.3312453"},{"issue":"6","key":"5679_CR41","doi-asserted-by":"publisher","first-page":"3675","DOI":"10.1109\/TSMC.2022.3230666","volume":"53","author":"X Gao","year":"2023","unstructured":"Gao X, Yan L, Li Z et al (2023) Improved deep deterministic policy gradient for dynamic obstacle avoidance of mobile robot. IEEE Trans Syst, Man, Cybern Syst 53(6):3675\u20133682","journal-title":"IEEE Trans Syst, Man, Cybern Syst"},{"key":"5679_CR42","doi-asserted-by":"crossref","unstructured":"Pathak D, Agrawal P, Efros AA et\u00a0al (2017) Curiosity-driven exploration by self-supervised prediction. In: International conference on machine learning, PMLR, pp 2778\u20132787","DOI":"10.1109\/CVPRW.2017.70"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05679-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05679-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05679-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T13:15:01Z","timestamp":1723727701000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05679-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,13]]},"references-count":42,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["5679"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05679-5","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,13]]},"assertion":[{"value":"5 July 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}