{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T07:25:35Z","timestamp":1787729135696,"version":"build-2784847793"},"reference-count":128,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100006360","name":"Bundesministerium f\u00fcr Wirtschaft und Energie","doi-asserted-by":"publisher","award":["19A19013O"],"award-info":[{"award-number":["19A19013O"]}],"id":[{"id":"10.13039\/501100006360","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BMBF: Tübingen AI Center","award":["01IS18039B"],"award-info":[{"award-number":["01IS18039B"]}]},{"name":"ERC","award":["LEGO-3D (850533)"],"award-info":[{"award-number":["LEGO-3D (850533)"]}]},{"name":"DFG EXC 2064\/1","award":["390727645"],"award-info":[{"award-number":["390727645"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,11,1]]},"DOI":"10.1109\/tpami.2022.3200245","type":"journal-article","created":{"date-parts":[[2022,8,19]],"date-time":"2022-08-19T15:36:55Z","timestamp":1660923415000},"page":"12878-12895","source":"Crossref","is-referenced-by-count":450,"title":["TransFuser: Imitation With Transformer-Based Sensor Fusion for Autonomous Driving"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3891-3230","authenticated-orcid":false,"given":"Kashyap","family":"Chitta","sequence":"first","affiliation":[{"name":"Autonomous Vision Group, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aditya","family":"Prakash","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernhard","family":"Jaeger","sequence":"additional","affiliation":[{"name":"Autonomous Vision Group, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehao","family":"Yu","sequence":"additional","affiliation":[{"name":"Autonomous Vision Group, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katrin","family":"Renz","sequence":"additional","affiliation":[{"name":"Autonomous Vision Group, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8151-3726","authenticated-orcid":false,"given":"Andreas","family":"Geiger","sequence":"additional","affiliation":[{"name":"Autonomous Vision Group, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep imitative models for flexible inference, planning, and control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rhinehart"},{"key":"ref2","first-page":"3145","article-title":"Can autonomous vehicles identify, recover from, and adapt to distribution shifts?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Filos"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_25"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01580"},{"key":"ref5","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Dosovitskiy"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.470"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.376"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1604.01685"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref12","article-title":"Waymo open dataset: An autonomous driving dataset","year":"2019"},{"key":"ref13","article-title":"BDD100 K: A. diverse driving video database with scalable annotation tooling","author":"Yu","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/wacv51458.2022.00335"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref16","first-page":"923","article-title":"End-to-end multi-view fusion for 3D object detection in lidar point clouds","volume-title":"Proc. Conf. Robot Learn.","author":"Zhou"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341450"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00918"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"ref21","article-title":"Pseudo-LiDAR: Accurate depth for 3D object detection in autonomous driving","volume-title":"Proc. Int. Conf. Learn. Representations","author":"You"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00752"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00162"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00376"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196697"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01157"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01136"},{"key":"ref28","first-page":"947","article-title":"Intentnet: Learning to predict intention from raw sensor data","volume-title":"Proc. Conf. Robot Learn.","author":"Casas"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/iv48863.2021.9575718"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2020.3047793"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341392"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341385"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00290"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01296"},{"key":"ref35","article-title":"End-to-end multi-modal sensors fusion system for urban automated driving","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshops","author":"Sobh"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01550"},{"key":"ref40","article-title":"Carla autonomous driving leaderboard","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2020.3013234"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340641"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw6661"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2022.3185303"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01671"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3070379"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00321"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00336"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/wevj12030139"},{"key":"ref52","article-title":"Investigating the effect of sensor modalities in multi-sensor detection-prediction models","author":"Mohta","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759048"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00033"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019267"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160968"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3123169"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3275954\/mm1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3228806"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00098"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968565"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2017.2717451"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_10"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00144"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00637"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00101"},{"key":"ref73","first-page":"137","article-title":"Social-BIGAT: Multimodal trajectory forecasting using bicycle-GAN and graph attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kosaraju"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00246"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561904"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00967"},{"key":"ref77","article-title":"Scene transformer: A unified architecture for predicting multiple agent trajectories","author":"Ngiam","year":"2021"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-04151-2"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811718"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01528"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00588"},{"key":"ref84","article-title":"M $^{2}$2 BEV: Multi-camera joint 3d detection and segmentation with unified birds-eye view representation","author":"Xie","year":"2022"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00291"},{"key":"ref87","first-page":"66","article-title":"Learning by cheating","volume-title":"Proc. Conf. Robot Learn.","author":"Chen"},{"key":"ref88","first-page":"739","article-title":"Off-road obstacle avoidance through end-to-end learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Muller"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967897"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.031"},{"key":"ref91","first-page":"2564","article-title":"Fighting copycat agents in behavioral cloning from observation histories","author":"Wen","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref92","first-page":"11123","article-title":"Keyframe-focused visual imitation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wen"},{"key":"ref93","volume-title":"Adaptive Control Processes - a Guided Tour","volume":"2045","author":"Bellman","year":"2015"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref95","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref96","article-title":"ImageBERT: Cross-modal pre-training with large-scale weak-supervised image-text data","author":"Qi","year":"2020"},{"key":"ref97","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9811576"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01131"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3003121"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/wacv48630.2021.00010"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_45"},{"key":"ref104","article-title":"Semantic-aware grad-GAN for virtual-to-real urban scene adaption","author":"Li","year":"2018"},{"key":"ref105","article-title":"Objects as points","author":"Zhou","year":"2019"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.597"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.430"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01530"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"ref112","article-title":"Affordance-based reinforcement learning for urban driving","author":"Agarwal","year":"2021"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref116","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.3390\/robotics12050127"},{"key":"ref118","article-title":"Large-scale visual active learning with deep probabilistic ensembles","author":"Chitta","year":"2018"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3133268"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304793"},{"key":"ref121","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01178"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00978"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01679"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_20"},{"key":"ref126","first-page":"156","article-title":"SAM: Squeeze-and-mimic networks for conditional visual driving policy learning","volume-title":"Proc. Conf. Robot Learn.","author":"Zhao"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_28"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10269680\/09863660.pdf?arnumber=9863660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T15:55:14Z","timestamp":1719330914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9863660\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":128,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3200245","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,1]]}}}