{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T16:24:24Z","timestamp":1759940664295,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T00:00:00Z","timestamp":1655337600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T00:00:00Z","timestamp":1655337600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"DOI":"10.1007\/s10489-022-03566-5","type":"journal-article","created":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T17:02:32Z","timestamp":1655398952000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Feature semantic space-based sim2real decision model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9009-0158","authenticated-orcid":false,"given":"Wenwen","family":"Xiao","sequence":"first","affiliation":[]},{"given":"Xiangfeng","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Shaorong","family":"Xie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,6,16]]},"reference":[{"issue":"1","key":"3566_CR1","first-page":"1","volume":"16","author":"BR Kiran","year":"2021","unstructured":"Kiran BR, Sobh I, Talpaert V, et al. (2021) Deep reinforcement learning for autonomous driving: A survey. IEEE Trans Intell Transp Syst 16(1):1\u201318","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"3566_CR2","unstructured":"Sallab AE, Abdou M, Perot E, Yogamani S (2016) End-to-end deep reinforcement learning for lane keeping assist. arXivpreprint arXiv:1612.04340"},{"issue":"2","key":"3566_CR3","doi-asserted-by":"publisher","first-page":"70","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023","volume":"36","author":"AE Sallab","year":"2017","unstructured":"Sallab AE, Abdou M, Perot E, Yogamani S (2017) Deep reinforcement learning framework for autonomous driving. Electron Imaging 36(2):70\u201376","journal-title":"Electron Imaging"},{"issue":"1","key":"3566_CR4","first-page":"28","volume":"11","author":"X Zong","year":"2018","unstructured":"Zong X, Xu G, Yu G, et al. (2018) Obstacle avoidance for self-driving vehicle with reinforcement learning. SAE Int J Passenger Cars Electron Electr Syst 11(1):28\u201337","journal-title":"SAE Int J Passenger Cars Electron Electr Syst"},{"key":"3566_CR5","doi-asserted-by":"crossref","unstructured":"Spryn M, Sharma A, Parkar D, et al. (2018) Distributed deep reinforcement learning on the cloud for autonomous driving. 2018 IEEE ACM 1st International Workshop on Software Engineering for AI in Autonomous Systems (SEFAIAS).IEEE Computer Society","DOI":"10.1145\/3194085.3194088"},{"key":"3566_CR6","unstructured":"Wang S, Jia D, Weng X (2016) Deep reinforcement learning for autonomous driving. Computer Vision and Pattern Recognition"},{"key":"3566_CR7","unstructured":"Xu N, Tan B, Kong B (2017) Autonomous driving in reality with reinforcement learning and image translation. arXiv:1801.05299"},{"key":"3566_CR8","doi-asserted-by":"crossref","unstructured":"Xiao C, Lu P, He Q (2021) Flying through a narrow gap using end-to-end deep reinforcement learning augmented with curriculum learning and sim2real. IEEE Transactions on Neural Networks and Learning Systems","DOI":"10.1109\/TNNLS.2021.3107742"},{"issue":"1","key":"3566_CR9","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/LRA.2021.3116700","volume":"7","author":"T Zhang","year":"2021","unstructured":"Zhang T, Zhang K, Lin J, Louie W-YG, Huang H (2021) Sim2real learning of obstacle avoidance for robotic manipulators in uncertain environments. IEEE Robot Autom Lett 7(1):65\u201372","journal-title":"IEEE Robot Autom Lett"},{"key":"3566_CR10","doi-asserted-by":"crossref","unstructured":"Kaspar M, Osorio JDM (2020) Sim2real transfer for reinforcement learning without dynamics randomization. In: 2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 4383\u20134388","DOI":"10.1109\/IROS45743.2020.9341260"},{"key":"3566_CR11","doi-asserted-by":"crossref","unstructured":"Zhao W, Queralta JP, Qingqing L, Westerlund T (2020) Towards closing the sim-to-real gap in collaborative multi-robot deep reinforcement learning. In: 2020 5th international conference on robotics and automation engineering (ICRAE), IEEE, pp 7\u201312","DOI":"10.1109\/ICRAE50850.2020.9310796"},{"key":"3566_CR12","unstructured":"Liu J, Shen H, Wang D, Kang Y, Tian Q (2021) Unsupervised domain adaptation with dynamics-aware rewards in reinforcement learning. arXiv preprint arXiv:2110.12997"},{"key":"3566_CR13","unstructured":"Jaunet T, Bono G, Vuillemot R, Wolf C (2021) Sim2realviz: Visualizing the sim2real gap in robot ego-pose estimation. arXiv preprint arXiv:2109.11801"},{"key":"3566_CR14","doi-asserted-by":"crossref","unstructured":"Gao H, Yang Z, Su X, Tan T, Chen F (2020) Adaptability preserving domain decomposition for stabilizing sim2real reinforcement learning. In: 2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS), IEEE, pp 4403\u2013 4410","DOI":"10.1109\/IROS45743.2020.9341124"},{"key":"3566_CR15","unstructured":"Blum T, Paillet G, Laine M, Yoshida K (2020) Rl star platform: Reinforcement learning for simulation based training of robots. arXiv preprint arXiv:2009.09595"},{"key":"3566_CR16","doi-asserted-by":"crossref","unstructured":"Li G, Yang Y, Li S, Qu X, Lyu N, Li SE (2021) Decision making of autonomous vehicles in lane change scenarios: Deep reinforcement learning approaches with risk awareness. Transportation Research Part C: Emerging Technologies, 103452","DOI":"10.1016\/j.trc.2021.103452"},{"key":"3566_CR17","doi-asserted-by":"crossref","unstructured":"Chen J, Li SE, Tomizuka M (2021) Interpretable end-to-end urban autonomous driving with latent deep reinforcement learning. IEEE Transactions on Intelligent Transportation Systems","DOI":"10.1109\/TITS.2020.3046646"},{"key":"3566_CR18","doi-asserted-by":"crossref","unstructured":"Zhang Q, Pan W, Reppa V (2021) Model-reference reinforcement learning for collision-free tracking control of autonomous surface vehicles. IEEE Transactions on Intelligent Transportation Systems","DOI":"10.1109\/TITS.2021.3086033"},{"key":"3566_CR19","unstructured":"Wang G, Niu H, Zhu D, Hu J, Zhan X, Zhou G (2021) Model: A modularized end-to-end reinforcement learning framework for autonomous driving. arXiv preprint arXiv:2110.11573"},{"issue":"3","key":"3566_CR20","first-page":"1556","volume":"42","author":"V Mnih","year":"2013","unstructured":"Mnih V, Kavukcuoglu K, Silver D, et al. (2013) Playing atari with deep reinforcement learning. Comput Sci 42(3):1556\u20131568","journal-title":"Comput Sci"},{"key":"3566_CR21","unstructured":"Mnih V, Badia AP, Mirza M, et al. (2017) Asynchronous methods for deep reinforcement learning"},{"issue":"1","key":"3566_CR22","first-page":"32","volume":"16","author":"TP Lillicrap","year":"2013","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, et al. (2013) Continuous control with deep reinforcement learning. computer science-learning statistics. Comput Sci Learn Stat Mach Learn 16(1):32\u201342","journal-title":"Comput Sci Learn Stat Mach Learn"},{"key":"3566_CR23","unstructured":"Schulman J, Levine S, Abbeel P, Jordan M, Moritz P (2015) Trust region policy optimization. In: International conference on machine learning, PMLR, pp 1889\u20131897"},{"key":"3566_CR24","unstructured":"Haarnoja T, Zhou A, Abbeel P, Levine S (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"},{"key":"3566_CR25","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347"},{"key":"3566_CR26","unstructured":"Vilas SC, KS, Vilas ST (2021) Autonomous racing using a hybrid imitation-reinforcement learning architecture. arXiveprints, 2110"},{"key":"3566_CR27","doi-asserted-by":"crossref","unstructured":"Niu H, Hu J, Cui Z, Zhang Y (2021) Dr2l: Surfacing corner cases to robustify autonomous driving via domain randomization reinforcement learning. In: The 5th international conference on computer science and application engineering, pp 1\u20138","DOI":"10.1145\/3487075.3487177"},{"key":"3566_CR28","doi-asserted-by":"crossref","unstructured":"Pan X, You Y, Wang Z, et al. (2017) Virtual to real reinforcement learning for autonomous driving. https:\/\/arxiv.org\/pdf\/1704.03952.pdf","DOI":"10.5244\/C.31.11"},{"issue":"1","key":"3566_CR29","first-page":"1","volume":"41","author":"Q Liu","year":"2018","unstructured":"Liu Q, Zhai JW, Zhang ZZ, et al. (2018) A survey on deep reinforcement learning. Chin J Comput 41(1):1\u201327","journal-title":"Chin J Comput"},{"issue":"2","key":"3566_CR30","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","volume":"30","author":"GJ Brostow","year":"2009","unstructured":"Brostow GJ, Fauqueur J, Cipolla R (2009) Semantic object classes in video: A high-definition ground truth database. Pattern Recogn Lett 30(2):88\u201397","journal-title":"Pattern Recogn Lett"},{"issue":"11","key":"3566_CR31","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: The kitti dataset. The International Journal of Robotics Research 32(11):1231\u20131237","journal-title":"The International Journal of Robotics Research"},{"key":"3566_CR32","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"key":"3566_CR33","unstructured":"M\u00fcller M, Dosovitskiy A, Ghanem B, Koltun V (2018) Driving policy transfer via modularity and abstraction. arXiv preprint arXiv:1804.09364"},{"key":"3566_CR34","unstructured":"Dosovitskiy A, Ros G, Codevilla F, Lopez A, Koltun V (2017) Carla: An open urban driving simulator. In: Conference on robot learning, PMLR, pp 1\u201316"},{"key":"3566_CR35","doi-asserted-by":"crossref","unstructured":"Xu H, Gao Y, Yu F, Darrell T (2017) End-to-end learning of driving models from large-scale video datasets. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2174\u20132182","DOI":"10.1109\/CVPR.2017.376"},{"key":"3566_CR36","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"},{"key":"3566_CR37","doi-asserted-by":"crossref","unstructured":"Bewley A, Rigley J, Liu Y, Hawke J, Shen R, Lam V-D, Kendall A (2019) Learning to drive from simulation without real world labels. In: 2019 international conference on robotics and automation (ICRA), IEEE, pp 4818\u20134824","DOI":"10.1109\/ICRA.2019.8793668"},{"key":"3566_CR38","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114"},{"key":"3566_CR39","unstructured":"Liu M. -Y., Breuel T, Kautz J (2017) Unsupervised image-to-image translation networks. In: Advances in neural information processing systems, pp 700\u2013708"},{"key":"3566_CR40","doi-asserted-by":"crossref","unstructured":"Yang L, Liang X, Wang T, Xing E (2018) Real-to-virtual domain unification for end-to-end autonomous driving. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 530\u2013545","DOI":"10.1007\/978-3-030-01225-0_33"},{"key":"3566_CR41","unstructured":"Loiacono D, Cardamone L, Lanzi PL (2013) Simulated car racing championship: Competition software manual Computer Science"},{"key":"3566_CR42","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03566-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-03566-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03566-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T17:04:58Z","timestamp":1655399098000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-03566-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,16]]},"references-count":42,"alternative-id":["3566"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-03566-5","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2022,6,16]]},"assertion":[{"value":"29 March 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}