{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:11:25Z","timestamp":1780675885803,"version":"3.54.1"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611018","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"14093-14100","source":"Crossref","is-referenced-by-count":157,"title":["Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Long","family":"Chen","sequence":"first","affiliation":[{"name":"Wayve"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oleg","family":"Sinavski","sequence":"additional","affiliation":[{"name":"Wayve"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"H\u00fcnermann","sequence":"additional","affiliation":[{"name":"Wayve"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alice","family":"Karnsund","sequence":"additional","affiliation":[{"name":"Wayve"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew James","family":"Willmott","sequence":"additional","affiliation":[{"name":"Wayve"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danny","family":"Birch","sequence":"additional","affiliation":[{"name":"Wayve"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Maund","sequence":"additional","affiliation":[{"name":"Wayve"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamie","family":"Shotton","sequence":"additional","affiliation":[{"name":"Wayve"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","author":"Bubeck","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.550030"},{"key":"ref3","article-title":"Robot representation and reasoning with knowledge from reinforcement learning","author":"Lu","year":"2018"},{"key":"ref4","article-title":"Reimagining an autonomous vehicle","author":"Hawke","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561723"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"issue":"8","key":"ref7","first-page":"10 142","article-title":"Explanations in autonomous driving: A survey","volume-title":"IEEE Transactions on Intelligent Transportation Systems","volume":"23","author":"Omeiza","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1487"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1410-8"},{"key":"ref10","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.031"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"ref13","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume":"1","author":"Pomerleau","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"20 703","article-title":"Model-based imitation learning for urban driving","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Hu","year":"2022"},{"key":"ref15","first-page":"82","article-title":"Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai","volume-title":"Information Fusion","volume":"58","author":"Barredo Arrieta","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3434580"},{"key":"ref17","first-page":"13","volume-title":"Explainable AI Methods - A Brief Overview","author":"Holzinger","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3321\/j.issn:0529-6579.2007.z1.029"},{"key":"ref20","first-page":"3145","article-title":"Learning important features through propagating activation differences","volume-title":"International conference on machine learning","author":"Shrikumar"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref22","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan","year":"2013"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.320"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186611"},{"key":"ref27","article-title":"Attention is not explanation","author":"Jain","year":"2019"},{"key":"ref28","article-title":"Attcat: Explaining transformers via attentive class activation tokens","author":"Qiang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref30","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022"},{"key":"ref31","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref32","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"issue":"6","key":"ref34","article-title":"Sensor fusion in autonomous vehicle with traffic surveillance camera system: Detection, localization, and ai networking","volume-title":"Sensors","volume":"23","author":"Hasanujjaman","year":"2023"},{"key":"ref35","first-page":"540","article-title":"Conditional driving from natural language instructions","volume-title":"Conference on Robot Learning","author":"Roh"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00968"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160326"},{"key":"ref38","first-page":"1046","article-title":"Languagerefer: Spatial-language model for 3d visual grounding","volume-title":"Conference on Robot Learning","author":"Roh"},{"key":"ref39","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref41","article-title":"Plant: Explainable planning transformers via object-level representations","author":"Renz","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.33540\/2168"},{"key":"ref45","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.365"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.newsum-1.1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_15"},{"key":"ref50","article-title":"Exploring ai ethics of chatgpt: A diagnostic analysis","author":"Zhuo","year":"2023"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611018.pdf?arnumber=10611018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:23:19Z","timestamp":1723267399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611018","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}