{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:22:33Z","timestamp":1782404553816,"version":"3.54.5"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031918124","type":"print"},{"value":"9783031918131","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-91813-1_16","type":"book-chapter","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:42:10Z","timestamp":1748090530000},"page":"244-263","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["MAPPO-PIS: A Multi-agent Proximal Policy Optimization Method with\u00a0Prior Intent Sharing for\u00a0CAVs\u2019 Cooperative Decision-Making"],"prefix":"10.1007","author":[{"given":"Yicheng","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongjie","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Hang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Aloufi, N., Chatterjee, A.: Autonomous vehicle scheduling at intersections based on production line technique. In: 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall), pp.\u00a01\u20135. IEEE (2018)","DOI":"10.1109\/VTCFall.2018.8690682"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Ayres, T., Li, L., Schleuning, D., Young, D.: Preferred time-headway of highway drivers. In: ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No. 01TH8585), pp. 826\u2013829. IEEE (2001)","DOI":"10.1109\/ITSC.2001.948767"},{"key":"16_CR3","doi-asserted-by":"publisher","first-page":"103216","DOI":"10.1016\/j.artint.2019.103216","volume":"280","author":"N Bard","year":"2020","unstructured":"Bard, N., et al.: The Hanabi challenge: a new frontier for AI research. Artif. Intell. 280, 103216 (2020)","journal-title":"Artif. Intell."},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Bouton, M., Nakhaei, A., Fujimura, K., Kochenderfer, M.J.: Cooperation-aware reinforcement learning for merging in dense traffic. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp. 3441\u20133447. IEEE (2019)","DOI":"10.1109\/ITSC.2019.8916924"},{"key":"16_CR5","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.conengprac.2014.10.005","volume":"34","author":"W Cao","year":"2015","unstructured":"Cao, W., Mukai, M., Kawabe, T., Nishira, H., Fujiki, N.: Cooperative vehicle path generation during merging using model predictive control with real-time optimization. Control. Eng. Pract. 34, 98\u2013105 (2015)","journal-title":"Control. Eng. Pract."},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Chandra, R., Bhattacharya, U., Mittal, T., Bera, A., Manocha, D.: CMetric: a driving behavior measure using centrality functions. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2035\u20132042. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341720"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Chandra, R., Bhattacharya, U., Mittal, T., Li, X., Bera, A., Manocha, D.: GraphRQI: classifying driver behaviors using graph spectrums. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 4350\u20134357. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196751"},{"issue":"11","key":"16_CR8","doi-asserted-by":"publisher","first-page":"11623","DOI":"10.1109\/TITS.2023.3285442","volume":"24","author":"D Chen","year":"2023","unstructured":"Chen, D., et al.: Deep multi-agent reinforcement learning for highway on-ramp merging in mixed traffic. IEEE Trans. Intell. Transp. Syst. 24(11), 11623\u201311638 (2023)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Q., Wang, H.: Traffic flow characteristics of ramp merging bottleneck on urban expressway. In: CICTP 2019, pp. 486\u2013497 (2019)","DOI":"10.1061\/9780784482292.045"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Choi, D., Min, K.: Hierarchical latent structure for multi-modal vehicle trajectory forecasting. In: European Conference on Computer Vision, pp. 129\u2013145. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_8"},{"key":"16_CR11","unstructured":"Clamann, M., Aubert, M., Cummings, M.L.: Evaluation of vehicle-to-pedestrian communication displays for autonomous vehicles. Technical report (2017)"},{"key":"16_CR12","unstructured":"Committee, O.R.A.D.O.: Sae j3216 standard: Taxonomy and definitions for terms related to cooperative driving automation for on-road motor vehicles. In SAE International (2020). https:\/\/www.sae.org\/standards\/content\/j3216\/"},{"key":"16_CR13","unstructured":"Dresner, K., Stone, P.: Multiagent traffic management: a reservation-based intersection control mechanism. In: Autonomous Agents and Multiagent Systems, International Joint Conference on, vol.\u00a03, pp. 530\u2013537. Citeseer (2004)"},{"key":"16_CR14","unstructured":"Hancock, M.W., Wright, B.: A policy on geometric design of highways and streets. Am. Assoc. State Highw. Transp. Officials: Washington, DC, USA 3 (2013)"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Hecker, S., Dai, D., Van\u00a0Gool, L.: End-to-end learning of driving models with surround-view cameras and route planners. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 435\u2013453 (2018)","DOI":"10.1007\/978-3-030-01234-2_27"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, L., Meng, D., Zhao, Q., Shan, S., Hauptmann, A.: Self-paced curriculum learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a029 (2015)","DOI":"10.1609\/aaai.v29i1.9608"},{"issue":"1","key":"16_CR17","doi-asserted-by":"publisher","first-page":"86","DOI":"10.3141\/1999-10","volume":"1999","author":"A Kesting","year":"2007","unstructured":"Kesting, A., Treiber, M., Helbing, D.: General lane-changing model MOBIL for car-following models. Transp. Res. Rec. 1999(1), 86\u201394 (2007)","journal-title":"Transp. Res. Rec."},{"key":"16_CR18","unstructured":"Kim, W., Park, J., Sung, Y.: Communication in multi-agent reinforcement learning: intention sharing. In: International Conference on Learning Representations (2020)"},{"key":"16_CR19","unstructured":"Leurent, E., et\u00a0al.: An environment for autonomous driving decision-making (2018)"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Liu, J., Hang, P., Na, X., Huang, C., Sun, J.: Cooperative decision-making for CAVs at unsignalized intersections: a marl approach with attention and hierarchical game priors. Authorea Preprints (2023)","DOI":"10.36227\/techrxiv.22817417.v1"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, Z., Hang, P., Sun, J.: Delay-aware multi-agent reinforcement learning for cooperative adaptive cruise control with model-based stability enhancement. arXiv preprint: arXiv:2404.15696 (2024)","DOI":"10.1109\/ITSC58415.2024.10919632"},{"key":"16_CR22","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter\u00a0Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"16_CR23","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.trc.2016.12.005","volume":"75","author":"Z Ma","year":"2017","unstructured":"Ma, Z., Sun, J., Wang, Y.: A two-dimensional simulation model for modelling turning vehicles at mixed-flow intersections. Transp. Res. Part C: Emerg. Technol. 75, 103\u2013119 (2017)","journal-title":"Transp. Res. Part C: Emerg. Technol."},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Mahadevan, K., Somanath, S., Sharlin, E.: Communicating awareness and intent in autonomous vehicle-pedestrian interaction. In: Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, pp. 1\u201312 (2018)","DOI":"10.1145\/3173574.3174003"},{"key":"16_CR25","unstructured":"Mahajan, N., Zhang, Q.: Intent-aware autonomous driving: a case study on highway merging scenarios. arXiv preprint: arXiv:2309.13206 (2023)"},{"key":"16_CR26","unstructured":"Matthews, M., Chowdhary, G., Kieson, E.: Intent communication between autonomous vehicles and pedestrians. arXiv preprint: arXiv:1708.07123 (2017)"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Ntousakis, I.A., Porfyri, K., Nikolos, I.K., Papageorgiou, M.: Assessing the impact of a cooperative merging system on highway traffic using a microscopic flow simulator. In: ASME International Mechanical Engineering Congress and Exposition, vol. 46613, p. V012T15A024. American Society of Mechanical Engineers (2014)","DOI":"10.1115\/IMECE2014-39850"},{"issue":"11","key":"16_CR28","doi-asserted-by":"publisher","first-page":"13677","DOI":"10.1007\/s10489-022-04105-y","volume":"53","author":"A Oroojlooy","year":"2023","unstructured":"Oroojlooy, A., Hajinezhad, D.: A review of cooperative multi-agent deep reinforcement learning. Appl. Intell. 53(11), 13677\u201313722 (2023)","journal-title":"Appl. Intell."},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Polack, P., Altch\u00e9, F., d\u2019Andr\u00e9a Novel, B., de\u00a0La\u00a0Fortelle, A.: The kinematic bicycle model: a consistent model for planning feasible trajectories for autonomous vehicles? In: 2017 IEEE Intelligent Vehicles Symposium (IV), pp. 812\u2013818. IEEE (2017)","DOI":"10.1109\/IVS.2017.7995816"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Qi, S., Zhu, S.C.: Intent-aware multi-agent reinforcement learning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 7533\u20137540. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463211"},{"key":"16_CR31","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint: arXiv:1707.06347 (2017)"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Spaan, M.T.: Partially observable Markov decision processes. In: Reinforcement Learning: State-of-The-Art, pp. 387\u2013414. Springer (2012)","DOI":"10.1007\/978-3-642-27645-3_12"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Tan, M.: Multi-agent reinforcement learning: Independent vs. cooperative agents. In: Proceedings of the Tenth International Conference On Machine Learning, pp. 330\u2013337 (1993)","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"16_CR34","unstructured":"Terry, J.K., Grammel, N., Son, S., Black, B., Agrawal, A.: Revisiting parameter sharing in multi-agent deep reinforcement learning. arXiv preprint: arXiv:2005.13625 (2020)"},{"issue":"1","key":"16_CR35","doi-asserted-by":"publisher","first-page":"90","DOI":"10.3141\/2088-10","volume":"2088","author":"C Thiemann","year":"2008","unstructured":"Thiemann, C., Treiber, M., Kesting, A.: Estimating acceleration and lane-changing dynamics from next generation simulation trajectory data. Transp. Res. Rec. 2088(1), 90\u2013101 (2008)","journal-title":"Transp. Res. Rec."},{"issue":"12","key":"16_CR36","doi-asserted-by":"publisher","first-page":"24791","DOI":"10.1109\/TITS.2022.3207872","volume":"23","author":"B Toghi","year":"2022","unstructured":"Toghi, B., Valiente, R., Sadigh, D., Pedarsani, R., Fallah, Y.P.: Social coordination and altruism in autonomous driving. IEEE Trans. Intell. Transp. Syst. 23(12), 24791\u201324804 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"2","key":"16_CR37","doi-asserted-by":"publisher","first-page":"1805","DOI":"10.1103\/PhysRevE.62.1805","volume":"62","author":"M Treiber","year":"2000","unstructured":"Treiber, M., Hennecke, A., Helbing, D.: Congested traffic states in empirical observations and microscopic simulations. Phys. Rev. E 62(2), 1805 (2000)","journal-title":"Phys. Rev. E"},{"issue":"3","key":"16_CR38","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1109\/JAS.2021.1004395","volume":"9","author":"J Wang","year":"2021","unstructured":"Wang, J., Zhang, Q., Zhao, D.: Highway lane change decision-making via attention-based deep reinforcement learning. IEEE\/CAA J. Automatica Sinica 9(3), 567\u2013569 (2021)","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"16_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/978-3-030-58536-5_36","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T-H Wang","year":"2020","unstructured":"Wang, T.-H., Manivasagam, S., Liang, M., Yang, B., Zeng, W., Urtasun, R.: V2VNet: vehicle-to-vehicle communication for joint perception and prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 605\u2013621. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_36"},{"key":"16_CR40","unstructured":"Wu, X., Chandra, R., Guan, T., Bedi, A.S., Manocha, D.: iPLAN: intent-aware planning in heterogeneous traffic via distributed multi-agent reinforcement learning. arXiv preprint: arXiv:2306.06236 (2023)"},{"key":"16_CR41","unstructured":"Wu, Y., Mansimov, E., Grosse, R.B., Liao, S., Ba, J.: Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Xu, R., Xiang, H., Tu, Z., Xia, X., Yang, M.H., Ma, J.: V2X-ViT: vehicle-to-everything cooperative perception with vision transformer. In: European Conference on Computer Vision, pp. 107\u2013124. Springer (2022)","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Xue, J., Li, B., Zhang, R.: Multi-agent reinforcement learning-based autonomous intersection management protocol with attention mechanism. In: 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD), pp. 1132\u20131137. IEEE (2022)","DOI":"10.1109\/CSCWD54268.2022.9776229"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Ye, Y., Sun, J., Jiang, S.: Modeling car-following behaviors on a merging section in an expressway on-ramp bottleneck. In: CICTP 2016, pp. 2348\u20132365 (2016)","DOI":"10.1061\/9780784479896.211"},{"key":"16_CR45","unstructured":"Yu, C., et al.: The surprising effectiveness of PPO in cooperative multi-agent games. In: Advances in Neural Information Processing Systems, vol. 35, pp. 24611\u201324624 (2022)"},{"key":"16_CR46","unstructured":"Zhang, C., Lesser, V., Shenoy, P.: A multi-agent learning approach to online distributed resource allocation. In: Twenty-First International Joint Conference on Artificial Intelligence (2009)"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: CityFlow: a multi-agent reinforcement learning environment for large scale city traffic scenario. In: The World Wide Web Conference, pp. 3620\u20133624 (2019)","DOI":"10.1145\/3308558.3314139"},{"issue":"1","key":"16_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s43684-022-00023-5","volume":"2","author":"W Zhou","year":"2022","unstructured":"Zhou, W., Chen, D., Yan, J., Li, Z., Yin, H., Ge, W.: Multi-agent reinforcement learning for cooperative lane changing of connected and autonomous vehicles in mixed traffic. Auton Intell. Syst. 2(1), 1\u201311 (2022). https:\/\/doi.org\/10.1007\/s43684-022-00023-5","journal-title":"Auton Intell. Syst."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91813-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:42:23Z","timestamp":1748090543000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91813-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031918124","9783031918131"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91813-1_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}