{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T19:28:21Z","timestamp":1773775701973,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,2]]},"DOI":"10.1109\/iv55156.2024.10588479","type":"proceedings-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T17:19:28Z","timestamp":1721063968000},"page":"2383-2390","source":"Crossref","is-referenced-by-count":8,"title":["Pix2Planning: End-to-End Planning by Vision-language Model for Autonomous Driving on Carla Simulator"],"prefix":"10.1109","author":[{"given":"Xiangru","family":"Mu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Qin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunjing","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Technologies,IAS BU,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"End-to-end autonomous driving: Challenges and frontiers","author":"Chen","year":"2023"},{"key":"ref2","article-title":"Rethinking self-driving: Multi-task knowledge for better generalization and accident explanation ability","author":"Li","year":"2018"},{"key":"ref3","first-page":"3145","article-title":"Can autonomous vehicles identify, recover from, and adapt to distribution shifts?","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Filos"},{"key":"ref4","article-title":"Causal imitative model for autonomous driving","author":"Samsami","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAR.2019.8813431"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01550"},{"key":"ref9","first-page":"6119","article-title":"Trajectory-guided control prediction for end-to-end autonomous driving: A simple yet strong baseline","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Wu","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00754"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref12","first-page":"20703","article-title":"Model-based imitation learning for urban driving","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Hu","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01671"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.031"},{"key":"ref18","first-page":"66","article-title":"Learning by cheating","volume-title":"Proceedings of the Conference on Robot Learning","volume":"100","author":"Chen"},{"key":"ref19","first-page":"726","article-title":"Safety-enhanced autonomous driving using interpretable sensor fusion transformer","volume-title":"Proceedings of The 6th Conference on Robot Learning","volume":"205","author":"Shao"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02105"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01319"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00757"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref28","article-title":"Pix2seq: A language modeling framework for object detection","volume":"abs\/2109.10852","author":"Chen","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160614"},{"key":"ref30","first-page":"492","article-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proceedings of The 6th Conference on Robot Learning","volume":"205","author":"Shah"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160326"},{"key":"ref32","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Tan"},{"key":"ref33","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proceedings of the 1st Annual Conference on Robot Learning","volume":"78","author":"Dosovitskiy"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"event":{"name":"2024 IEEE Intelligent Vehicle Symposium (IV)","location":"Jeju Island, Korea, Republic of","start":{"date-parts":[[2024,6,2]]},"end":{"date-parts":[[2024,6,5]]}},"container-title":["2024 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10587320\/10588370\/10588479.pdf?arnumber=10588479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T04:51:44Z","timestamp":1721364704000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10588479\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,2]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iv55156.2024.10588479","relation":{},"subject":[],"published":{"date-parts":[[2024,6,2]]}}}