{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:09:23Z","timestamp":1777655363880,"version":"3.51.4"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727634","type":"print"},{"value":"9783031727641","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"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\/978-3-031-72764-1_5","type":"book-chapter","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T14:03:10Z","timestamp":1729778590000},"page":"73-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Making Large Language Models Better Planners with\u00a0Reasoning-Decision Alignment"],"prefix":"10.1007","author":[{"given":"Zhijian","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoxiang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sihao","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zequn","family":"Jie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangrun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,25]]},"reference":[{"key":"5_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Aggarwal, S., Mandowara, D., Agrawal, V., Khandelwal, D., Singla, P., Garg, D.: Explanations for commonsenseQA: new dataset and models. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 3050\u20133065 (2021)","DOI":"10.18653\/v1\/2021.acl-long.238"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"5_CR4","unstructured":"Chen, S., et al.: VADv2: end-to-end vectorized autonomous driving via probabilistic planning. arXiv preprint arXiv:2402.13243 (2024)"},{"key":"5_CR5","unstructured":"Cobbe, K., et\u00a0al.: Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Cui, C., Ma, Y., Cao, X., Ye, W., Wang, Z.: Drive as you speak: enabling human-like interaction with large language models in autonomous vehicles. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 902\u2013909 (2024)","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"5_CR7","unstructured":"Cui, C., Yang, Z., Zhou, Y., Ma, Y., Lu, J., Wang, Z.: Large language models for autonomous driving: real-world experiments. arXiv preprint arXiv:2312.09397 (2023)"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Da, F., Zhang, Y.: Path-aware graph attention for HD maps in motion prediction. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 6430\u20136436. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812100"},{"key":"5_CR9","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: an open urban driving simulator. In: Conference on Robot Learning, pp. 1\u201316. PMLR (2017)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Gao, J., et al.: VectorNet: encoding HD maps and agent dynamics from vectorized representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11525\u201311533 (2020)","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Gao, L., et al.: Cola-HRL: continuous-lattice hierarchical reinforcement learning for autonomous driving. In: 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 13143\u201313150. IEEE (2022)","DOI":"10.1109\/IROS47612.2022.9982041"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Gu, J., et al.: ViP3D: end-to-end visual trajectory prediction via 3D agent queries. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5496\u20135506 (2023)","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"5_CR13","unstructured":"Han, W., Guo, D., Xu, C.Z., Shen, J.: DME-driver: integrating human decision logic and 3d scene perception in autonomous driving. arXiv preprint arXiv:2401.03641 (2024)"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Hu, P., Huang, A., Dolan, J., Held, D., Ramanan, D.: Safe local motion planning with self-supervised freespace forecasting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12732\u201312741 (2021)","DOI":"10.1109\/CVPR46437.2021.01254"},{"key":"5_CR15","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/978-3-031-19839-7_31","volume-title":"ECCV 2022","author":"S Hu","year":"2022","unstructured":"Hu, S., Chen, L., Wu, P., Li, H., Yan, J., Tao, D.: ST-P3: end-to-end vision-based autonomous driving via spatial-temporal feature learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13698, pp. 533\u2013549. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_31"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Hu, Y., et\u00a0al.: Planning-oriented autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17853\u201317862 (2023)","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"5_CR17","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: BEVDet: high-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, B., et al.: VAD: vectorized scene representation for efficient autonomous driving. arXiv preprint arXiv:2303.12077 (2023)","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"5_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1007\/978-3-031-19839-7_21","volume-title":"ECCV 2022","author":"T Khurana","year":"2022","unstructured":"Khurana, T., Hu, P., Dave, A., Ziglar, J., Held, D., Ramanan, D.: Differentiable raycasting for self-supervised occupancy forecasting. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13698, pp. 353\u2013369. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_21"},{"key":"5_CR20","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"5_CR21","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20077-9_1","volume-title":"ECCV 2022","author":"Z Li","year":"2022","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Is ego status all you need for open-loop end-to-end autonomous driving? arXiv preprint arXiv:2312.03031 (2023)","DOI":"10.1109\/CVPR52733.2024.01408"},{"key":"5_CR23","first-page":"10421","volume":"35","author":"T Liang","year":"2022","unstructured":"Liang, T., et al.: BEVFusion: a simple and robust lidar-camera fusion framework. Adv. Neural. Inf. Process. Syst. 35, 10421\u201310434 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR24","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: BEVFusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 2774\u20132781. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"5_CR26","unstructured":"Mao, J., Qian, Y., Zhao, H., Wang, Y.: GPT-driver: learning to drive with GPT. arXiv preprint arXiv:2310.01415 (2023)"},{"key":"5_CR27","unstructured":"Mao, J., Ye, J., Qian, Y., Pavone, M., Wang, Y.: A language agent for autonomous driving. arXiv preprint arXiv:2311.10813 (2023)"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Nie, M., et al.: Reason2drive: towards interpretable and chain-based reasoning for autonomous driving. arXiv preprint arXiv:2312.03661 (2023)","DOI":"10.1007\/978-3-031-73347-5_17"},{"key":"5_CR29","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., Ray, A., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Pan, C., et al.: VLP: vision language planning for autonomous driving. arXiv preprint arXiv:2401.05577 (2024)","DOI":"10.1109\/CVPR52733.2024.01398"},{"key":"5_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-58568-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Philion","year":"2020","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XIV. LNCS, vol. 12359, pp. 194\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12"},{"key":"5_CR32","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"5_CR33","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: Your language model is secretly a reward model. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"5_CR34","unstructured":"Ramamurthy, R., et al.: Is reinforcement learning (not) for natural language processing?: Benchmarks, baselines, and building blocks for natural language policy optimization. arXiv preprint arXiv:2210.01241 (2022)"},{"key":"5_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1007\/978-3-030-58592-1_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Sadat","year":"2020","unstructured":"Sadat, A., Casas, S., Ren, M., Wu, X., Dhawan, P., Urtasun, R.: Perceive, predict, and plan: safe motion planning through interpretable semantic representations. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XXIII. LNCS, vol. 12368, pp. 414\u2013430. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_25"},{"key":"5_CR36","unstructured":"Scheel, O., Bergamini, L., Wolczyk, M., Osi\u0144ski, B., Ondruska, P.: Urban driver: learning to drive from real-world demonstrations using policy gradients. In: Conference on Robot Learning, pp. 718\u2013728. PMLR (2022)"},{"key":"5_CR37","unstructured":"Sha, H., et al.: LanguageMPC: large language models as decision makers for autonomous driving. arXiv preprint arXiv:2310.03026 (2023)"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Shao, H., Hu, Y., Wang, L., Waslander, S.L., Liu, Y., Li, H.: LMDrive: closed-loop end-to-end driving with large language models. arXiv preprint arXiv:2312.07488 (2023)","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Sima, C., et al.: DriveLM: driving with graph visual question answering. arXiv preprint arXiv:2312.14150 (2023)","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"5_CR40","unstructured":"Tian, X., et al.: DriveVLM: the convergence of autonomous driving and large vision-language models. arXiv preprint arXiv:2402.12289 (2024)"},{"key":"5_CR41","unstructured":"Touvron, H., et\u00a0al.: LLaMa: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"5_CR42","unstructured":"Wang, P., et al.: Making large language models better reasoners with alignment. arXiv preprint arXiv:2309.02144 (2023)"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Wang, P., et al.: BEVGPT: generative pre-trained large model for autonomous driving prediction, decision-making, and planning. arXiv preprint arXiv:2310.10357 (2023)","DOI":"10.1109\/TIV.2024.3449278"},{"key":"5_CR44","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":"5_CR45","unstructured":"Wang, Y., et al.: Empowering autonomous driving with large language models: a safety perspective. arXiv preprint arXiv:2312.00812 (2023)"},{"key":"5_CR46","unstructured":"Wen, L., et al.: DiLu: a knowledge-driven approach to autonomous driving with large language models. arXiv preprint arXiv:2309.16292 (2023)"},{"key":"5_CR47","unstructured":"Wen, L., et\u00a0al.: On the road with GPT-4V(ision): early explorations of visual-language model on autonomous driving. arXiv preprint arXiv:2311.05332 (2023)"},{"key":"5_CR48","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: DriveGPT4: interpretable end-to-end autonomous driving via large language model. arXiv preprint arXiv:2310.01412 (2023)","DOI":"10.1109\/LRA.2024.3440097"},{"key":"5_CR49","unstructured":"Yuan, Z., Yuan, H., Tan, C., Wang, W., Huang, S., Huang, F.: RRHF: rank responses to align language models with human feedback without tears. arXiv preprint arXiv:2304.05302 (2023)"},{"key":"5_CR50","doi-asserted-by":"crossref","unstructured":"Zeng, W., et.: End-to-end interpretable neural motion planner. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8660\u20138669 (2019)","DOI":"10.1109\/CVPR.2019.00886"},{"key":"5_CR51","unstructured":"Zhai, J.T., et al.: Rethinking the open-loop evaluation of end-to-end autonomous driving in nuScenes. arXiv preprint arXiv:2305.10430 (2023)"},{"key":"5_CR52","unstructured":"Zhao, Y., Joshi, R., Liu, T., Khalman, M., Saleh, M., Liu, P.J.: SLIC-HF: sequence likelihood calibration with human feedback. arXiv preprint arXiv:2305.10425 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72764-1_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T06:28:09Z","timestamp":1732948089000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72764-1_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"ISBN":["9783031727634","9783031727641"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72764-1_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,25]]},"assertion":[{"value":"25 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}