{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:52:25Z","timestamp":1782762745160,"version":"3.54.5"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFB2505500"],"award-info":[{"award-number":["2024YFB2505500"]}]},{"name":"NSF China","award":["92582205"],"award-info":[{"award-number":["92582205"]}]},{"name":"Didi Voyager Labs"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3695533","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T19:45:35Z","timestamp":1779392735000},"page":"11578-11595","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced Integrated Decision and Control for High-Level Automated Vehicles and Its Experiment Verification"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0689-0510","authenticated-orcid":false,"given":"Yang","family":"Guan","sequence":"first","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liye","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1539-472X","authenticated-orcid":false,"given":"Yao","family":"Lyu","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4923-3633","authenticated-orcid":false,"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7222-0019","authenticated-orcid":false,"given":"Yujie","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kehua","family":"Sheng","sequence":"additional","affiliation":[{"name":"DiDi Autonomous Driving, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"DiDi Autonomous Driving, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0370-177X","authenticated-orcid":false,"given":"Lei","family":"He","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9333-7416","authenticated-orcid":false,"given":"Keqiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01713"},{"key":"ref3","article-title":"Sep.: Towards efficient scene representation learning for motion prediction","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Lan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21541-4_17"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/oca.2123"},{"key":"ref6","first-page":"11","article-title":"Diffusion-based planning for autonomous driving with flexible guidance","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Zheng"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00843"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611364"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01124"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3251376"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103489"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922100"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342038"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103662"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3163816"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2024.3399102"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103863"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2024.3393293"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0954407020906627"},{"key":"ref26","article-title":"Baidu Apollo EM motion planner","author":"Fan","year":"2018","journal-title":"arXiv:1807.08048"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2904385"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3633415"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3574262"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3196167"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2234\/1\/012015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3579573"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/int.22466"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995727"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.64"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3026111"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s42154-023-00260-1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3266277"},{"key":"ref40","first-page":"8234","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Buckman"},{"key":"ref41","first-page":"12498","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Janner"},{"key":"ref42","first-page":"8387","article-title":"Temporal difference learning for model predictive control","volume-title":"Proc. Int. Conf. Machin. Learn.","author":"Hansen"},{"key":"ref43","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Deisenroth"},{"key":"ref44","first-page":"2944","article-title":"Learning continuous control policies by stochastic value gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heess"},{"key":"ref45","first-page":"4062","article-title":"PIPPS: Flexible model-based policy search robust to the curse of chaos","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Parmas"},{"key":"ref46","first-page":"526","article-title":"Mastering diverse domains through world models","volume":"631","author":"Hafner","year":"2024","journal-title":"Nature"},{"key":"ref47","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref48","first-page":"15338","article-title":"First order constrained optimization in policy space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhang"},{"key":"ref49","first-page":"10","article-title":"Breaking safety paradox with feasible dual policy iteration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3136588"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0317"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569448"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3406507"},{"key":"ref56","article-title":"Mixed policy gradient: Off-policy reinforcement learning driven jointly by data and model","author":"Guan","year":"2021","journal-title":"arXiv:2102.11513"},{"key":"ref57","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1080\/10586458.2022.2061650"},{"key":"ref59","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"Fujimoto","year":"2019","journal-title":"arXiv:1910.01708"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IVWorkshops54471.2021.9669260"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2022.799893"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11533504.pdf?arnumber=11533504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:43:00Z","timestamp":1782762180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533504\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3695533","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}