Abstract
The quest for fully autonomous vehicles (AVs) capable of navigating complex real-world scenarios with human-like understanding and responsiveness. In this paper, we introduce Dolphins, a novel vision-language model architected to imbibe human-like abilities as a conversational driving assistant. Dolphins is adept at processing multimodal inputs comprising video (or image) data, text instructions, and historical control signals to generate informed outputs corresponding to the provided instructions. Building upon the open-sourced pretrained Vision-Language Model, OpenFlamingo, we first enhance Dolphins’s reasoning capabilities through an innovative Grounded Chain of Thought (GCoT) process in the general domain. Then we tailored Dolphins to the driving domain by constructing driving-specific instruction data and conducting instruction tuning. Through the utilization of the BDD-X dataset, we designed and consolidated four distinct AV tasks into Dolphins to foster a holistic understanding of intricate driving scenarios. As a result, the distinctive features of Dolphins are characterised into two dimensions: (1) the ability to provide a comprehensive understanding of complex and long-tailed open-world driving scenarios and solve a spectrum of AV tasks, and (2) the emergence of human-like capabilities including gradient-free instant adaptation via in-context learning and error recovery via reflection. The anonymous demo is available at https://vlm-driver.github.io/.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Openai chat. https://chat.openai.com. Accessed 20 Oct 2023
Openai chat. https://openai.com/research/gpt-4v-system-card. Accessed 20 Oct 2023
TinyChat: large language model on the edge. https://hanlab.mit.edu/blog/tinychat. Accessed 20 Oct 2023
What are embeddings? https://platform.openai.com/docs/guides/embeddings/what-are-embeddings. Accessed 20 Oct 2023
Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. ArXiv preprint arxiv: abs/2204.14198 (2022), https://api.semanticscholar.org/CorpusID:248476411
Awadalla, A., et al.: OpenFlamingo: an open-source framework for training large autoregressive vision-language models. ArXiv abs/2308.01390 (2023), https://api.semanticscholar.org/CorpusID:261043320
Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pp. 65–72 (2005)
Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. arXiv preprint arXiv:1903.11027 (2019)
Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal LLM’s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)
Chen, L., Wu, P., Chitta, K., Jaeger, B., Geiger, A., Li, H.: End-to-end autonomous driving: challenges and frontiers. arXiv preprint arXiv:2306.16927 (2023)
Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* chatGPT quality (March 2023). https://lmsys.org/blog/2023-03-30-vicuna/
Coelho, D., Oliveira, M.: A review of end-to-end autonomous driving in urban environments. IEEE Access 10, 75296–75311 (2022)
Contributors, D.: DriveLM: drive on language. https://github.com/OpenDriveLab/DriveLM (2023)
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, pp. 958–979 (2024)
Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. ArXiv preprint arxiv: abs/2305.06500 (2023). https://api.semanticscholar.org/CorpusID:258615266
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)
Ding, X., Han, J., Xu, H., Liang, X., Zhang, W., Li, X.: Holistic autonomous driving understanding by bird’s-eye-view injected multi-modal large models. arXiv preprint arXiv:2401.00988 (2024)
Fu, D., et al.: Drive like a human: rethinking autonomous driving with large language models. arXiv preprint arXiv:2307.07162 (2023)
Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904–6913 (2017)
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)
Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700–6709 (2019)
Jain, A., Del Pero, L., Grimmett, H., Ondruska, P.: Autonomy 2.0: why is self-driving always 5 years away? arXiv preprint arXiv:2107.08142 (2021)
Jin, B., et al.: Adapt: action-aware driving caption transformer. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 7554–7561 (2023). https://api.semanticscholar.org/CorpusID:256459842
Jin, Y., et al.: SurrealDriver: designing generative driver agent simulation framework in urban contexts based on large language model. arXiv preprint arXiv:2309.13193 (2023)
Jordan, M.I., Mitchell, T.M.: Machine learning: trends, perspectives, and prospects. Science 349(6245), 255–260 (2015)
Kafle, K., Kanan, C.: An analysis of visual question answering algorithms. In: Proceedings of the IEEE international conference on computer vision. pp. 1965–1973 (2017)
Kim, J., Rohrbach, A., Darrell, T., Canny, J., Akata, Z.: Textual explanations for self-driving vehicles. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 563–578 (2018)
Kim, J., Rohrbach, A., Darrell, T., Canny, J.F., Akata, Z.: Textual explanations for self-driving vehicles. In: European Conference on Computer Vision (2018). https://api.semanticscholar.org/CorpusID:51887402
Li, B., et al.: Mimic-it: multi-modal in-context instruction tuning. arXiv preprint arxiv: abs/2306.05425 (2023). https://api.semanticscholar.org/CorpusID:259108295
Li, B., Zhang, Y., Chen, L., Wang, J., Yang, J., Liu, Z.: Otter: a multi-modal model with in-context instruction tuning. arXiv preprint arxiv: abs/2305.03726 (2023). https://api.semanticscholar.org/CorpusID:258547300
Li, C., et al.: LLaVA-med: training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890 (2023)
Li, J., Li, D., Savarese, S., Hoi, S.C.H.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arxiv: abs/2301.12597 (2023). https://api.semanticscholar.org/CorpusID:256390509
Li, W., et al.: AADS: augmented autonomous driving simulation using data-driven algorithms. Sci. robot. 4(28), eaaw0863 (2019)
Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arxiv:abs/2304.08485 (2023). https://api.semanticscholar.org/CorpusID:258179774
Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)
Liu, L., et al.: Computing systems for autonomous driving: state of the art and challenges. IEEE Internet Things J. 8(8), 6469–6486 (2020)
Liu, Z., et al.: Video swin transformer. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202–3211 (2022)
Luo, R., et al.: Valley: video assistant with large language model enhanced ability. arXiv preprint arxiv: abs/2306.07207 (2023). https://api.semanticscholar.org/CorpusID:259138706
Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-chatGPT: towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 (2023)
Mao, J., Qian, Y., Zhao, H., Wang, Y.: GPT-driver: learning to drive with GPT. arXiv preprint arxiv: abs/2310.01415 (2023). https://api.semanticscholar.org/CorpusID:263605637
Mao, J., Ye, J., Qian, Y., Pavone, M., Wang, Y.: A language agent for autonomous driving. arXiv preprint arXiv:2311.10813 (2023)
Marcu, A.M., et al.: LingoQA: video question answering for autonomous driving. arXiv preprint arXiv:2312.14115 (2023)
Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Ok-VQA: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE/cvf Conference on Computer Vision and Pattern Recognition, pp. 3195–3204 (2019)
Mom, G.: The Evolution of Automotive Technology: A Handbook. SAE International (2023)
Mu, Y., et al.: EmbodiedGPT: vision-language pre-training via embodied chain of thought. arXiv preprint arXiv:2305.15021 (2023)
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311–318 (2002)
Rubin, O., Herzig, J., Berant, J.: Learning to retrieve prompts for in-context learning. arXiv preprint arXiv:2112.08633 (2021)
Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. arXiv preprint arxiv: abs/2210.08402 (2022). https://api.semanticscholar.org/CorpusID:252917726
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)
Soori, M., Arezoo, B., Dastres, R.: Artificial intelligence, machine learning and deep learning in advanced robotics, a review. Cognitive Robot. 3, 54–70 (2023)
Tampuu, A., Matiisen, T., Semikin, M., Fishman, D., Muhammad, N.: A survey of end-to-end driving: architectures and training methods. IEEE Trans. Neural Netw. Learn. Syst. 33(4), 1364–1384 (2020)
Team, M.N.: Introducing MPT-7B: a new standard for open-source, commercially usable LLMs (2023). www.mosaicml.com/blog/mpt-7b. Accessed 05 May 2023
Tian, X., et al.: DriveVLM: the convergence of autonomous driving and large vision-language models. arXiv preprint arXiv:2402.12289 (2024)
Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv preprint arxiv: abs/2302.13971 (2023). https://api.semanticscholar.org/CorpusID:257219404
Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)
Touvron, H., et al.: LLaMA 2: open foundation and fine-tuned chat models. ArXiv abs/2307.09288 (2023). https://api.semanticscholar.org/CorpusID:259950998
Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566–4575 (2015)
Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence-video to text. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4534–4542 (2015)
Wang, W., et al.: DriveMLM: aligning multi-modal large language models with behavioral planning states for autonomous driving. arXiv preprint arXiv:2312.09245 (2023)
Wong, K., Gu, Y., Kamijo, S.: Mapping for autonomous driving: opportunities and challenges. IEEE Intell. Transp. Syst. Mag. 13(1), 91–106 (2020)
Wu, D., Han, W., Wang, T., Liu, Y.H., Zhang, X., Shen, J.: Language prompt for autonomous driving. arXiv preprint arxiv: abs/2309.04379 (2023). https://api.semanticscholar.org/CorpusID:261660217
Xu, Z., et al.: DriveGPT4: interpretable end-to-end autonomous driving via large language model. arXiv preprint arxiv: abs/2310.01412 (2023). https://api.semanticscholar.org/CorpusID:263605524
Yang, S., et al.: LiDAR-LLM: exploring the potential of large language models for 3D lidar understanding. arXiv preprint arXiv:2312.14074 (2023)
Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2636–2645 (2020)
Yuan, J., Sun, S., Omeiza, D., Zhao, B., Newman, P., Kunze, L., Gadd, M.: RAG-driver: generalisable driving explanations with retrieval-augmented in-context learning in multi-modal large language model. arXiv preprint arXiv:2402.10828 (2024)
Yuan, W., Pang, R.Y., Cho, K., Sukhbaatar, S., Xu, J., Weston, J.: Self-rewarding language models. arXiv preprint arXiv:2401.10020 (2024)
Zhang, H., Li, X., Bing, L.: Video-LLaMA: an instruction-tuned audio-visual language model for video understanding. arXiv preprint arxiv: abs/2306.02858 (2023). https://api.semanticscholar.org/CorpusID:259075356
Zhang, S., et al.: GPT4RoI: instruction tuning large language model on region-of-interest. arXiv preprint arXiv:2307.03601 (2023)
Zhao, B., Wu, B., Huang, T.: SVIT: scaling up visual instruction tuning. arXiv preprint arXiv:2307.04087 (2023)
Zhao, H., et al.: MMICL: empowering vision-language model with multi-modal in-context learning. arXiv preprint arXiv:2309.07915 (2023)
Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arxiv: abs/2304.10592 (2023). https://api.semanticscholar.org/CorpusID:258291930
Zhu, W., et al.: Multimodal c4: An open, billion-scale corpus of images interleaved with text. arXiv preprint arxiv: abs/2304.06939 (2023). https://api.semanticscholar.org/CorpusID:258170467
Acknowledgements
We sincerely appreciate the reviewers’ insightful comments and valuable feedback, which have greatly enhanced the quality of our manuscript.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, Y., Cao, Y., Sun, J., Pavone, M., Xiao, C. (2025). Dolphins: Multimodal Language Model for Driving. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15103. Springer, Cham. https://doi.org/10.1007/978-3-031-72995-9_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-72995-9_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-72994-2
Online ISBN: 978-3-031-72995-9
eBook Packages: Computer ScienceComputer Science (R0)