{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:45:14Z","timestamp":1773773114769,"version":"3.50.1"},"reference-count":70,"publisher":"SAGE Publications","issue":"5","license":[{"start":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T00:00:00Z","timestamp":1728432000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2153426"],"award-info":[{"award-number":["IIS-2153426"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","award":["GHP\/126\/21GD"],"award-info":[{"award-number":["GHP\/126\/21GD"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Grants Council","award":["17200924"],"award-info":[{"award-number":["17200924"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of Robotics Research"],"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:p>\n            Intersections are essential road infrastructures for traffic in modern metropolises. However, they can also be the bottleneck of traffic flows as a result of traffic incidents or the absence of traffic coordination mechanisms such as traffic lights. Recently, various control and coordination mechanisms that are beyond traditional control methods have been proposed to improve the efficiency of intersection traffic by leveraging the ability of autonomous vehicles. Among these methods, the control of foreseeable mixed traffic that consists of human-driven vehicles (HVs) and robot vehicles (RVs) has emerged. We propose a decentralized multi-agent reinforcement learning approach for the control and coordination of mixed traffic by RVs at real-world, complex intersections\u2014an open challenge to date. We design comprehensive experiments to evaluate the effectiveness, robustness, generalizablility, and adaptability of our approach. In particular, our method can prevent congestion formation via merely 5% RVs under a real-world traffic demand of 700 vehicles per hour. In contrast, without RVs, congestion will form when the traffic demand reaches as low as 200 vehicles per hour. Moreover, when the RV penetration rate exceeds 60%, our method starts to outperform traffic signal control in terms of the average waiting time of all vehicles. Our method is not only robust against blackout events, sudden RV percentage drops, and V2V communication error, but also enjoys excellent generalizablility, evidenced by its successful deployment in five unseen intersections. Lastly, our method performs well under various traffic rules, demonstrating its adaptability to diverse scenarios. Videos and code of our work are available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/sites.google.com\/view\/mixedtrafficcontrol\">https:\/\/sites.google.com\/view\/mixedtrafficcontrol<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1177\/02783649241284069","type":"journal-article","created":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T12:22:43Z","timestamp":1728562963000},"page":"805-825","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":13,"title":["Learning to control and coordinate mixed traffic through robot vehicles at complex and unsignalized intersections"],"prefix":"10.1177","volume":"44","author":[{"given":"Dawei","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Hong Kong, China"}]},{"given":"Weizi","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, The University of Tennessee, Knoxville, TN, USA"}]},{"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, The University of North Carolina at Charlotte, Charlotte, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9003-2054","authenticated-orcid":false,"given":"Jia","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Hong Kong, China"}]}],"member":"179","published-online":{"date-parts":[[2024,10,9]]},"reference":[{"key":"e_1_3_4_2_1","unstructured":"Alshiekh M Bloem R Ehlers R et al. (2018) Safe reinforcement learning via shielding. In: Proceedings of the thirty-second AAAI conference on artificial intelligence and thirtieth innovative applications of artificial intelligence conference and eighth AAAI symposium on educational advances in artificial intelligence AAAI\u201918\/IAAI\u201918\/EAAI\u201918 New Orleans LA 2\u20137 February 2018 2669\u20132678. AAAI Press."},{"key":"e_1_3_4_3_1","unstructured":"Bai L Yao L Li C et al (2020) Adaptive graph convolutional recurrent network for traffic forecasting. In: Proceedings of the 34th international conference on neural information processing systems NIPS\u2019 20 Vancouver BC 6-12 December 2020 17804\u201317815. Curran Associates Inc."},{"key":"e_1_3_4_4_1","unstructured":"Behrisch M Bieker L Erdmann J et al. (2011) Sumo\u2013simulation of urban mobility: an overview. In: Proceedings of international conference on advances in system simulation Barcelona Spain 23\u201329 October 2011 63\u201368. ThinkMind."},{"key":"e_1_3_4_5_1","doi-asserted-by":"crossref","unstructured":"Cai P Lee Y Luo Y et al. (2020) Summit: a simulator for urban driving in massive mixed traffic. In: IEEE international conference on robotics and automation (ICRA) Paris France 31 May 2020\u201331 August 2020 pp. 4023\u20134029.","DOI":"10.1109\/ICRA40945.2020.9197228"},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2022.127953"},{"key":"e_1_3_4_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2377074"},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919868290"},{"key":"e_1_3_4_9_1","volume-title":"Crash Factors in Intersection-Related Crashes: An On-Scene Perspective","author":"Choi EH","year":"2010","unstructured":"Choi EH (2010) Crash Factors in Intersection-Related Crashes: An On-Scene Perspective. Washington, DC: National Highway Traffic Safety Administration, U.S. Department of Transportation."},{"key":"e_1_3_4_10_1","unstructured":"Cui J Macke W Yedidsion H et al. (2021) Scalable multiagent driving policies for reducing traffic congestion. In: Proceedings of the 20th international conference on autonomous agents and multiagent systems (AAMAS) Online 3\u20137 May 2021 pp. 386\u2013394."},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2021.103859"},{"key":"e_1_3_4_12_1","first-page":"97888548415126","article-title":"Calibration and validation of micro-simulation of medium-size networks","volume":"24","author":"El Esawey M","year":"2011","unstructured":"El Esawey M, Sayed T (2011) Calibration and validation of micro-simulation of medium-size networks. Advances in Transportation Studies 24: 97888548415126.","journal-title":"Advances in Transportation Studies"},{"issue":"1","key":"e_1_3_4_13_1","first-page":"1","article-title":"Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment","volume":"12","author":"Feng S","year":"2021","unstructured":"Feng S, Yan X, Sun H, et al. (2021) Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment. Nature Communications 12(1): 1\u201314.","journal-title":"Nature Communications"},{"key":"e_1_3_4_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05732-2"},{"key":"e_1_3_4_15_1","doi-asserted-by":"publisher","DOI":"10.3390\/app10114011"},{"key":"e_1_3_4_16_1","doi-asserted-by":"crossref","unstructured":"Guo K Miao Z Jing W et al. (2024) Lasil: learner-aware supervised imitation learning for long-term microscopic traffic simulation. ArXiv preprint arXiv:2403.17601.","DOI":"10.1109\/CVPR52733.2024.01457"},{"key":"e_1_3_4_17_1","unstructured":"Haarnoja T Zhou A Abbeel P et al. (2018) Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning Stockholm Sweden 10\u201315 July 2018 1861\u20131870. PMLR."},{"key":"e_1_3_4_18_1","unstructured":"Hessel M Modayil J Van Hasselt H et al (2018) Rainbow: combining improvements in deep reinforcement learning. In: Proceedings of the AAAI conference on artificial intelligence New Orleans Louisiana USA February 2-7 2018 pp. 3215\u20133222."},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3262120"},{"key":"e_1_3_4_20_1","volume-title":"Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specifications: High-Speed Physical Layer in the 5 GHz Band","author":"IEEE Standards Association","year":"1999","unstructured":"IEEE Standards Association (1999) Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specifications: High-Speed Physical Layer in the 5 GHz Band. New York, NY: IEEE."},{"key":"e_1_3_4_21_1","doi-asserted-by":"crossref","unstructured":"J\u00e1come L Benavides L Jara D et al. (2018) A survey on intelligent traffic lights. In: 2018 IEEE international conference on automation\/XXIII congress of the Chilean association of automatic control (ICA-ACCA) Concepcion Chile 17\u201319 October 2018 1\u20136. IEEE.","DOI":"10.1109\/ICA-ACCA.2018.8609705"},{"key":"e_1_3_4_22_1","doi-asserted-by":"crossref","unstructured":"Jang K Vinitsky E Chalaki B et al. (2019) Simulation to scaled city: zero-shot policy transfer for traffic control via autonomous vehicles. In: ACM\/IEEE international conference on cyber-physical systems Montreal QC 16\u201318 April 2019 pp. 291\u2013300.","DOI":"10.1145\/3302509.3313784"},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102663"},{"key":"e_1_3_4_24_1","article-title":"Microscopic modeling of traffic flow: investigation of collision free vehicle dynamics","volume":"1998","author":"Krauss S","year":"1998","unstructured":"Krauss S (1998) Microscopic modeling of traffic flow: investigation of collision free vehicle dynamics. Research Report 98-08, German Aerospace Center 1998.","journal-title":"Research Report 98-08, German Aerospace Center"},{"key":"e_1_3_4_25_1","doi-asserted-by":"crossref","unstructured":"Leung K Veer S Schmerling E et al. (2023) Learning autonomous vehicle safety concepts from demonstrations. In: American control conference San Diego CA 31 May 2023\u201302 June 2023 pp. 3193\u20133200.","DOI":"10.23919\/ACC55779.2023.10156279"},{"key":"e_1_3_4_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3333838"},{"key":"e_1_3_4_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103933"},{"key":"e_1_3_4_28_1","doi-asserted-by":"crossref","unstructured":"Lu J Hossain S Sheng W et al. (2023) Cooperative driving in mixed traffic of manned and unmanned vehicles based on human driving behavior understanding. In: IEEE international conference on robotics and automation (ICRA) London UK 29 May 2023\u20132 June 2023. IEEE 3532\u20133538.","DOI":"10.1109\/ICRA48891.2023.10160282"},{"key":"e_1_3_4_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.03.056"},{"key":"e_1_3_4_30_1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231188740"},{"key":"e_1_3_4_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2921659"},{"key":"e_1_3_4_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.01.004"},{"key":"e_1_3_4_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"issue":"5","key":"e_1_3_4_34_1","doi-asserted-by":"crossref","first-page":"5355","DOI":"10.11591\/ijece.v12i5.pp5355-5363","article-title":"Traffic light control design approaches: a systematic literature review","volume":"12","author":"Mohamed NE","year":"2022","unstructured":"Mohamed NE, Radwan II (2022) Traffic light control design approaches: a systematic literature review. International Journal of Electrical and Computer Engineering 12(5): 5355\u20138708.","journal-title":"International Journal of Electrical and Computer Engineering"},{"key":"e_1_3_4_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3032227"},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0225-y"},{"key":"e_1_3_4_37_1","doi-asserted-by":"crossref","unstructured":"Poudel B Li W Heaslip K (2024) Endurl: enhancing safety stability and efficiency of mixed traffic under real-world perturbations via reinforcement learning. In: 2024 IEEE\/RSJ international conference on intelligent robots and systems (IROS) Abu Dhabi UAE 14\u201318 October 2024.","DOI":"10.1109\/IROS58592.2024.10802689"},{"key":"e_1_3_4_38_1","unstructured":"Press A (2022) Power still out to 50k customers days after memphis storm. https:\/\/www.usnews.com\/news\/best-states\/tennessee\/articles\/2022-02-07\/power-still-out-to-60k-customers-days-after-memphis-storm"},{"key":"e_1_3_4_39_1","unstructured":"Ramirez R (2022) Power outages are on the rise led by Texas Michigan and California. here\u2019s what\u2019s to blame. https:\/\/www.cnn.com\/2022\/09\/14\/us\/power-outages-rising-extreme-weather-climate\/index.html"},{"key":"e_1_3_4_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2600504"},{"key":"e_1_3_4_41_1","volume-title":"Urban Mobility Scorecard","author":"Schrank D","year":"2021","unstructured":"Schrank D, Eisele B, Lomax T, et al. (2021) Urban Mobility Scorecard. College Station, TX: Texas A&M Transportation Institute and INRIX."},{"key":"e_1_3_4_42_1","unstructured":"Schulman J Wolski F Dhariwal P et al. (2017) Proximal policy optimization algorithms. ArXiv preprint arXiv:1707.06347."},{"key":"e_1_3_4_43_1","unstructured":"Shao H Wang L Chen R et al. (2023) Safety-enhanced autonomous driving using interpretable sensor fusion transformer. In: Conference on robot learning Atlanta GA 6 November 2023 726\u2013737. PMLR."},{"key":"e_1_3_4_44_1","doi-asserted-by":"crossref","unstructured":"Sharon G Stone P (2017) A protocol for mixed autonomous and human-operated vehicles at intersections. In: International conference on autonomous agents and multiagent systems S\u00e3o Paulo Brazil 8\u201312 May 2017 pp. 151\u2013167.","DOI":"10.1007\/978-3-319-71682-4_10"},{"key":"e_1_3_4_45_1","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2022.2109416"},{"key":"e_1_3_4_46_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw1975"},{"key":"e_1_3_4_47_1","unstructured":"Timothy O Marzenna C (2005) Calibration and validation of a micro-simulation model in network analysis. In: Presentation at the TRB annual meeting and included in the compendium of papers CD-ROM 05-1938 Washington DC January 2005."},{"issue":"2","key":"e_1_3_4_48_1","first-page":"1805","article-title":"Congested traffic states in empirical observations and microscopic simulations","volume":"62","author":"Treiber M","year":"2000","unstructured":"Treiber M, Hennecke A, Helbing D (2000) Congested traffic states in empirical observations and microscopic simulations. Physical Review 62(2): 1805\u20131824.","journal-title":"Physical Review"},{"key":"e_1_3_4_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2008.34"},{"key":"e_1_3_4_50_1","doi-asserted-by":"crossref","unstructured":"Vegni AM Little TD (2010) A message propagation model for hybrid vehicular communication protocols. In: 2010 7th international symposium on communication systems networks & digital signal processing (CSNDSP 2010) Newcastle upon Tyne UK 21\u201323 July 2010 382\u2013386. IEEE.","DOI":"10.1109\/CSNDSP16145.2010.5580390"},{"key":"e_1_3_4_51_1","doi-asserted-by":"publisher","unstructured":"Villarreal M Poudel B Pan J et al. (2024) Mixed traffic control and coordination from pixels. In: 2024 IEEE international conference on robotics and automation (ICRA) Yokohama Japan 13\u201317 May 2024 pp. 4488\u20134494. DOI: 10.1109\/ICRA57147.2024.10610517.","DOI":"10.1109\/ICRA57147.2024.10610517"},{"key":"e_1_3_4_52_1","doi-asserted-by":"crossref","unstructured":"Vinitsky E Parvate K Kreidieh A et al. (2018) Lagrangian control through deep-rl: applications to bottleneck decongestion. In: IEEE international conference on intelligent transportation systems Edmonton AB 24\u201327 September 2024 pp. 759\u2013765.","DOI":"10.1109\/ITSC.2018.8569615"},{"key":"#cr-split#-e_1_3_4_53_1.1","doi-asserted-by":"crossref","unstructured":"Wang J Zheng Y Xu Q et al. (2019) Controllability analysis and optimal controller synthesis of mixed traffic systems. In: IEEE intelligent vehicles symposium","DOI":"10.1109\/IVS.2019.8813984"},{"key":"#cr-split#-e_1_3_4_53_1.2","unstructured":"(IV) Paris France 9-12 June 2019. IEEE 1041-1047."},{"key":"e_1_3_4_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3335292"},{"key":"e_1_3_4_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103967"},{"key":"e_1_3_4_56_1","unstructured":"Wei H Zheng G Gayah V et al. (2019) A survey on traffic signal control methods. ArXiv preprint arXiv:1904.08117."},{"key":"e_1_3_4_57_1","unstructured":"Winck B (2022) Get ready for blackouts from london to la as the global energy crisis overwhelms grids and sends energy prices skyrocketing. https:\/\/www.businessinsider.com\/global-europe-energy-crisis-power-electricity-outages-blackouts-energy-grid-2022-9?op=1"},{"key":"e_1_3_4_58_1","doi-asserted-by":"crossref","unstructured":"Wu C Bayen AM Mehta A (2018) Stabilizing traffic with autonomous vehicles. In: IEEE international conference on robotics and automation (ICRA) Brisbane QLD 21\u201325 May 2018 6012\u20136018. IEEE.","DOI":"10.1109\/ICRA.2018.8460567"},{"key":"e_1_3_4_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3087314"},{"key":"e_1_3_4_60_1","doi-asserted-by":"crossref","unstructured":"Wu X Wei Y Zou L (2023) Optimizing cooperative control algorithms for vehicles and roads at unsignalized intersections considering communication performance. In: International conference on robotics intelligent control and artificial intelligence (RICAI) Zhangjiajie China 24\u201326 November 2023. IEEE 423\u2013428.","DOI":"10.1109\/RICAI60863.2023.10489671"},{"key":"e_1_3_4_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3054649"},{"key":"e_1_3_4_62_1","doi-asserted-by":"crossref","unstructured":"Yan Z Wu C (2021) Reinforcement learning for mixed autonomy intersections. In: IEEE international intelligent transportation systems conference Indianapolis IN 19\u201322 September 2021 pp. 2089\u20132094.","DOI":"10.1109\/ITSC48978.2021.9565000"},{"key":"e_1_3_4_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3121807"},{"key":"e_1_3_4_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3168621"},{"key":"e_1_3_4_65_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0175"},{"key":"e_1_3_4_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2958859"},{"key":"e_1_3_4_67_1","first-page":"1","article-title":"Learning a robust multiagent driving policy for traffic congestion reduction","author":"Zhang Y","year":"2023","unstructured":"Zhang Y, Macke W, Cui J, et al. (2023) Learning a robust multiagent driving policy for traffic congestion reduction. Neural Computing & Applications, Special Issue on Adaptive and Learning Agents 2022 1\u201314.","journal-title":"Neural Computing & Applications, Special Issue on Adaptive and Learning Agents 2022"},{"key":"e_1_3_4_68_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.07.013"},{"key":"e_1_3_4_69_1","doi-asserted-by":"crossref","unstructured":"Zheng J Zhu K Wang R (2022) Deep reinforcement learning for autonomous vehicles collaboration at unsignalized intersections. In: IEEE global communications conference (GLOBECOM) Rio de Janeiro Brazil 4\u20138 December 2022 pp. 1115\u20131120.","DOI":"10.1109\/GLOBECOM48099.2022.10001133"},{"key":"e_1_3_4_70_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103610"}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649241284069","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/02783649241284069","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649241284069","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649241284069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T11:02:39Z","timestamp":1747738959000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/02783649241284069"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,9]]},"references-count":70,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["10.1177\/02783649241284069"],"URL":"https:\/\/doi.org\/10.1177\/02783649241284069","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"value":"0278-3649","type":"print"},{"value":"1741-3176","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,9]]}}}