{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T06:05:39Z","timestamp":1770530739533,"version":"3.49.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031301070","type":"print"},{"value":"9783031301087","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-30108-7_27","type":"book-chapter","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T04:03:04Z","timestamp":1681272184000},"page":"317-330","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Model-Based Reinforcement Learning with\u00a0Self-attention Mechanism for\u00a0Autonomous Driving in\u00a0Dense Traffic"],"prefix":"10.1007","author":[{"given":"Junjie","family":"Wen","sequence":"first","affiliation":[]},{"given":"Zuoquan","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jinqiang","family":"Cui","sequence":"additional","affiliation":[]},{"given":"Ben M.","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,13]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Alahi, A., Goel, K., Ramanathan, V., et al.: Social LSTM: human trajectory prediction in crowded spaces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013971 (2016)","DOI":"10.1109\/CVPR.2016.110"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Altch\u00e9, F., de La Fortelle, A.: An LSTM network for highway trajectory prediction. In: 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), pp. 353\u2013359. IEEE (2017)","DOI":"10.1109\/ITSC.2017.8317913"},{"key":"27_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Dankwa, S., Zheng, W.: Twin-delayed ddpg: a deep reinforcement learning technique to model a continuous movement of an intelligent robot agent. In: Proceedings of the 3rd International Conference on Vision, Image and Signal Processing, pp. 1\u20135 (2019)","DOI":"10.1145\/3387168.3387199"},{"key":"27_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"27_CR6","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, S., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"27_CR7","unstructured":"Eraqi, H.M., Moustafa, M.N., Honer, J.: End-to-end deep learning for steering autonomous vehicles considering temporal dependencies. arXiv preprint arXiv:1710.03804 (2017)"},{"issue":"10","key":"27_CR8","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1002\/rob.20266","volume":"25","author":"L Fletcher","year":"2008","unstructured":"Fletcher, L., Teller, S., Olson, E., et al.: The MIT-cornell collision and why it happened. J. Field Robot. 25(10), 775\u2013807 (2008)","journal-title":"J. Field Robot."},{"key":"27_CR9","unstructured":"Ha, D., Schmidhuber, J.: World models. arXiv preprint arXiv:1803.10122 (2018)"},{"issue":"8","key":"27_CR10","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Isele, D., Nakhaei, A., Fujimura, K.: Safe reinforcement learning on autonomous vehicles. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/IROS.2018.8593420"},{"key":"27_CR12","unstructured":"Kaiser, L., Babaeizadeh, M., Milos, P., et al.: Model-based reinforcement learning for atari. arXiv preprint arXiv:1903.00374 (2019)"},{"issue":"1928","key":"27_CR13","doi-asserted-by":"publisher","first-page":"4585","DOI":"10.1098\/rsta.2010.0084","volume":"368","author":"A Kesting","year":"2010","unstructured":"Kesting, A., Treiber, M., Helbing, D.: Enhanced intelligent driver model to access the impact of driving strategies on traffic capacity. Philos. Trans. R. Soc. A: Math. Phys. Eng. Sci. 368(1928), 4585\u20134605 (2010)","journal-title":"Philos. Trans. R. Soc. A: Math. Phys. Eng. Sci."},{"key":"27_CR14","first-page":"1008","volume":"12","author":"V Konda","year":"1999","unstructured":"Konda, V., Tsitsiklis, J.: Actor-critic algorithms. Adv. Neural Inf. Process. Syst. 12, 1008\u20131014 (1999)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"27_CR15","unstructured":"Leurent, E.: An environment for autonomous driving decision-making. GitHub (2018)"},{"key":"27_CR16","unstructured":"Leurent, E., Mercat, J.: Social attention for autonomous decision-making in dense traffic. arXiv preprint arXiv:1911.12250 (2019)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Ma, Y., Zhu, X., Zhang, S., et al.: Trafficpredict: trajectory prediction for heterogeneous traffic-agents. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 6120\u20136127 (2019)","DOI":"10.1609\/aaai.v33i01.33016120"},{"issue":"1","key":"27_CR19","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/S0001-4575(00)00019-1","volume":"33","author":"MM Minderhoud","year":"2001","unstructured":"Minderhoud, M.M., Bovy, P.H.: Extended time-to-collision measures for road traffic safety assessment. Accid. Anal. Prev. 33(1), 89\u201397 (2001)","journal-title":"Accid. Anal. Prev."},{"issue":"7540","key":"27_CR20","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., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"9","key":"27_CR21","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1002\/rob.20258","volume":"25","author":"M Montemerlo","year":"2008","unstructured":"Montemerlo, M., Becker, J., Bhat, S., et al.: Junior: the stanford entry in the urban challenge. J. Field Robot. 25(9), 569\u2013597 (2008)","journal-title":"J. Field Robot."},{"key":"27_CR22","unstructured":"Silver, D., Lever, G., Heess, N., et al.: Deterministic policy gradient algorithms. In: International Conference on Machine Learning, pp. 387\u2013395. PMLR (2014)"},{"issue":"4","key":"27_CR23","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1145\/122344.122377","volume":"2","author":"RS Sutton","year":"1991","unstructured":"Sutton, R.S.: Dyna, an integrated architecture for learning, planning, and reacting. ACM Sigart Bull. 2(4), 160\u2013163 (1991)","journal-title":"ACM Sigart Bull."},{"key":"27_CR24","first-page":"15424","volume":"32","author":"C Tang","year":"2019","unstructured":"Tang, C., Salakhutdinov, R.R.: Multiple futures prediction. Adv. Neural Inf. Process. Syst. 32, 15424\u201315434 (2019)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"8","key":"27_CR25","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1002\/rob.20255","volume":"25","author":"C Urmson","year":"2008","unstructured":"Urmson, C., Anhalt, J., Bagnell, D., et al.: Autonomous driving in urban environments: boss and the urban challenge. J. Field Robot. 25(8), 425\u2013466 (2008)","journal-title":"J. Field Robot."},{"key":"27_CR26","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Vemula, A., Muelling, K., Oh, J.: Social attention: modeling attention in human crowds. In: 2018 IEEE international Conference on Robotics and Automation (ICRA), pp. 4601\u20134607. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460504"},{"issue":"3\u20134","key":"27_CR28","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"issue":"3","key":"27_CR29","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Xu, H., Gao, Y., Yu, F., Darrell, T.: 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 (2017)","DOI":"10.1109\/CVPR.2017.376"},{"key":"27_CR31","unstructured":"Zhuo, X., Jianyu, C., Masayoshi, T.: Guided policy search model-based reinforcement learning for urban autonomous driving. arXiv preprint arXiv:2005.03076 (2020)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-30108-7_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T04:08:14Z","timestamp":1681272494000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-30108-7_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031301070","9783031301087"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-30108-7_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"13 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"359","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"44% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.65","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}