{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T04:13:06Z","timestamp":1748664786747,"version":"3.41.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031945748","type":"print"},{"value":"9783031945755","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-94575-5_7","type":"book-chapter","created":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T02:15:02Z","timestamp":1748657702000},"page":"116-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting the\u00a0Road Ahead: A Knowledge Graph Based Foundation Model for\u00a0Scene Understanding in\u00a0Autonomous Driving"],"prefix":"10.1007","author":[{"given":"Hongkuan","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Schimid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yicong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lavdim","family":"Halilaj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangtong","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,1]]},"reference":[{"key":"7_CR1","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. CoRR abs\/2005.14165 (2020). https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuscenes: a multimodal dataset for autonomous driving. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, 13\u201319 June 2020, pp. 11618\u201311628. Computer Vision Foundation\/IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"7_CR3","doi-asserted-by":"publisher","unstructured":"Chen, L., et al.: Driving with LLMs: fusing object-level vector modality for explainable autonomous driving. In: IEEE International Conference on Robotics and Automation, ICRA 2024, Yokohama, Japan, 13\u201317 May 2024, pp. 14093\u201314100. IEEE (2024). https:\/\/doi.org\/10.1109\/ICRA57147.2024.10611018","DOI":"10.1109\/ICRA57147.2024.10611018"},{"issue":"11","key":"7_CR4","doi-asserted-by":"publisher","first-page":"12878","DOI":"10.1109\/TPAMI.2022.3200245","volume":"45","author":"K Chitta","year":"2023","unstructured":"Chitta, K., Prakash, A., Jaeger, B., Yu, Z., Renz, K., Geiger, A.: Transfuser: imitation with transformer-based sensor fusion for autonomous driving. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 12878\u201312895 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3200245","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR5","unstructured":"Chowdhery, A., et\u00a0al.: Palm: scaling language modeling with pathways. J. Mach. Learn. Res. 24, 240:1\u2013240:113 (2023)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Cui, C., et al.: A survey on multimodal large language models for autonomous driving. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, pp. 958\u2013979 (2024)","DOI":"10.1109\/WACVW60836.2024.00106"},{"issue":"1","key":"7_CR7","doi-asserted-by":"publisher","first-page":"1450","DOI":"10.1109\/TIV.2023.3327715","volume":"9","author":"Y Cui","year":"2024","unstructured":"Cui, Y., et al.: Drivellm: charting the path toward full autonomous driving with large language models. IEEE Trans. Intell. Veh. 9(1), 1450\u20131464 (2024). https:\/\/doi.org\/10.1109\/TIV.2023.3327715","journal-title":"IEEE Trans. Intell. Veh."},{"key":"7_CR8","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (1), pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"7_CR9","unstructured":"Ding, X., Han, J., Xu, H., Zhang, W., Li, X.: Hilm-d: towards high-resolution understanding in multimodal large language models for autonomous driving. arXiv preprint arXiv:2309.05186 (2023)"},{"key":"7_CR10","doi-asserted-by":"publisher","unstructured":"Gao, H., Li, Y., Long, K., Yang, M., Shen, Y.: A survey for foundation models in autonomous driving. CoRR abs\/2402.01105 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2402.01105","DOI":"10.48550\/ARXIV.2402.01105"},{"issue":"11","key":"7_CR11","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013). https:\/\/doi.org\/10.1177\/0278364913491297","journal-title":"Int. J. Robot. Res."},{"issue":"2","key":"7_CR12","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1142\/S1793351X23600048","volume":"17","author":"L Halilaj","year":"2023","unstructured":"Halilaj, L., Luettin, J., Monka, S., Schmid, S.: Knowledge graph-based integration of autonomous driving datasets. Int. J. Semant. Comput. 17(2), 249\u2013271 (2023)","journal-title":"Int. J. Semant. Comput."},{"key":"7_CR13","unstructured":"Hoffmann, J., et\u00a0al.: Training compute-optimal large language models. CoRR abs\/2203.15556 (2022)"},{"key":"7_CR14","doi-asserted-by":"publisher","unstructured":"Lin, X., et al.: Protokens: a machine-learned language for compact and informative encoding of protein 3D structures. bioRxiv (2023). https:\/\/doi.org\/10.1101\/2023.11.27.568722. https:\/\/www.biorxiv.org\/content\/early\/2023\/11\/28\/2023.11.27.568722. https:\/\/www.biorxiv.org\/content\/early\/2023\/11\/28\/2023.11.27.568722.full.pdf","DOI":"10.1101\/2023.11.27.568722"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Luettin, J., Monka, S., Henson, C.A., Halilaj, L.: A survey on knowledge graph-based methods for automated driving. In: KGSWC. Communications in Computer and Information Science, vol.\u00a01686, pp. 16\u201331. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-21422-6_2"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Mlodzian, L., et al.: nuscenes knowledge graph - a comprehensive semantic representation of traffic scenes for trajectory prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops, pp. 42\u201352 (2023)","DOI":"10.1109\/ICCVW60793.2023.00011"},{"key":"7_CR17","doi-asserted-by":"publisher","unstructured":"Peters, M.E., et al.: Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 2227\u20132237. Association for Computational Linguistics, New Orleans, Louisiana (2018). https:\/\/doi.org\/10.18653\/v1\/N18-1202","DOI":"10.18653\/v1\/N18-1202"},{"issue":"8","key":"7_CR18","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"7_CR19","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1\u2013140:67 (2020)"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Seff, A., et al.: Motionlm: multi-agent motion forecasting as language modeling. CoRR abs\/2309.16534 (2023)","DOI":"10.1109\/ICCV51070.2023.00788"},{"issue":"9","key":"7_CR21","doi-asserted-by":"publisher","first-page":"7381","DOI":"10.1109\/LRA.2024.3426386","volume":"9","author":"Z Sun","year":"2024","unstructured":"Sun, Z., Wang, Z., Halilaj, L., Luettin, J.: Semanticformer: holistic and semantic traffic scene representation for trajectory prediction using knowledge graphs. IEEE Robot. Autom. Lett. 9(9), 7381\u20137388 (2024)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"7_CR22","unstructured":"Tian, R., et al.: Tokenize the world into object-level knowledge to address long-tail events in autonomous driving. CoRR abs\/2407.00959 (2024)"},{"key":"7_CR23","doi-asserted-by":"publisher","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. CoRR abs\/2302.13971 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2302.13971","DOI":"10.48550\/ARXIV.2302.13971"},{"key":"7_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"7_CR25","unstructured":"Wang, G., et al.: Voyager: an open-ended embodied agent with large language models. Trans. Mach. Learn. Res. 2024 (2024). https:\/\/openreview.net\/forum?id=ehfRiF0R3a"},{"key":"7_CR26","unstructured":"Wang, W., et\u00a0al.: Drivemlm: aligning multi-modal large language models with behavioral planning states for autonomous driving. arXiv preprint arXiv:2312.09245 (2023)"},{"key":"7_CR27","unstructured":"Wang, Z., Sun, Z., Luettin, J., Halilaj, L.: Socialformer: social interaction modeling with edge-enhanced heterogeneous graph transformers for trajectory prediction. CoRR abs\/2405.03809 (2024)"},{"key":"7_CR28","unstructured":"Wen, L., et al.: Dilu: a knowledge-driven approach to autonomous driving with large language models. arXiv preprint arXiv:2309.16292 (2023)"},{"issue":"10","key":"7_CR29","doi-asserted-by":"publisher","first-page":"8186","DOI":"10.1109\/LRA.2024.3440097","volume":"9","author":"Z Xu","year":"2024","unstructured":"Xu, Z., et al.: Drivegpt 4: interpretable end-to-end autonomous driving via large language model. IEEE Robot. Autom. Lett. 9(10), 8186\u20138193 (2024)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"7_CR30","unstructured":"Zheng, Y., et\u00a0al.: Planagent: a multi-modal large language agent for closed-loop vehicle motion planning. arXiv preprint arXiv:2406.01587 (2024)"},{"key":"7_CR31","doi-asserted-by":"publisher","unstructured":"Zhou, H., et al.: Visual representation learning guided by multi-modal prior knowledge. CoRR abs\/2410.15981 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2410.15981","DOI":"10.48550\/ARXIV.2410.15981"},{"key":"7_CR32","unstructured":"Zhou, H., Sui, A., Cao, W., Shi, L.: What matters to enhance traffic rule compliance of imitation learning for automated driving. arXiv preprint arXiv:2309.07808 (2023)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, H., Sui, A., Shi, L., Li, Y.: Penalty-based imitation learning with cross semantics generation sensor fusion for autonomous driving. In: ITSC, pp. 1876\u20131883. IEEE (2023)","DOI":"10.1109\/ITSC57777.2023.10422239"},{"key":"7_CR34","unstructured":"Zhou, H., et al.: Bridging language and action: a survey of language-conditioned robot manipulation. CoRR abs\/2312.10807 (2023). https:\/\/doi.org\/10.48550\/arXiv.2312.10807"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: Embodied understanding of driving scenarios. In: ECCV (62). Lecture Notes in Computer Science, vol. 15120, pp. 129\u2013148. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-73033-7_8"}],"container-title":["Lecture Notes in Computer Science","The Semantic Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-94575-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T02:15:15Z","timestamp":1748657715000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-94575-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031945748","9783031945755"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-94575-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ESWC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Semantic Web Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portoroz","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"esws2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025.eswc-conferences.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}