EUVIMEDEUVIMED entdecken
Crossref

CoT-VLNBench: A Benchmark for Visual Chain-of-Thought Reasoning in Vision-Language-Navigation Robots

Xiao Zhao, Chang Liu, Ruiteng Ji, Zheyuan Zhang, Mingxu Zhu, Linna Song, Zhe Ren, Luo Qingliang, YuHang Gao, Zhaolong Du, Chufan Guo, Kuifeng Su

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (43) · 36573-36581

DOI: 10.1609/aaai.v40i43.40980 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xiao Zhao und 11 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in vision language models (VLMs) have demonstrated remarkable potential in embodied navigation tasks. However, existing robot-centric datasets primarily focus on traditional 3D tasks such as perception and prediction, lacking adequate support for vision-language tasks. Vision-language-navigation (VLN) is a key capability for achieving human-like and interpretable navigation in complex environments. In this study, we present CoT-VLNBench, the first large-scale benchmark and dataset designed for chain-of-thought (CoT) reasoning in quadruped robot navigation. Our dataset encompasses a diverse range of indoor and outdoor scenes, multi-step navigation trajectories, and rich natural language instructions, all annotated with fine-grained CoT reasoning traces. Specifically, it contains 175K frames, 5.25M 3D bounding boxes, and 875K vision–question–answer (VQA) pairs. This comprehensive resource enables thorough evaluation of embodied agents’ perceptual and step-by-step reasoning abilities. Furthermore, we propose a novel CoT-VLN model, a state-of-the-art 7B VLN model that integrates visual, linguistic, and reasoning modules, to facilitate interpretable and effective navigation. Extensive experiments demonstrate that our approach significantly outperforms existing non-VLMs baselines on the new benchmark, underscoring the importance of CoT-VLN in embodied navigation. We hope that CoT-VLNBench will serve as a valuable resource to advance research at the intersection of robotics, vision, language, and reasoning.

Zitieren

APA

Zhao, X., Liu, C., Ji, R., Zhang, Z., Zhu, M., Song, L., Ren, Z., Qingliang, L., Gao, Y., Du, Z., Guo, C., & Su, K. (2026). CoT-VLNBench: A Benchmark for Visual Chain-of-Thought Reasoning in Vision-Language-Navigation Robots. Proceedings of the AAAI Conference on Artificial Intelligence, 40(43), 36573-36581. https://doi.org/10.1609/aaai.v40i43.40980

Vancouver

Zhao X, Liu C, Ji R, Zhang Z, Zhu M, Song L, et al. CoT-VLNBench: A Benchmark for Visual Chain-of-Thought Reasoning in Vision-Language-Navigation Robots. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(43):36573-36581. doi:10.1609/aaai.v40i43.40980

BibTeX
@article{Zhao2026,
  author = {Zhao, Xiao and Liu, Chang and Ji, Ruiteng and Zhang, Zheyuan and Zhu, Mingxu and Song, Linna and Ren, Zhe and Qingliang, Luo and Gao, YuHang and Du, Zhaolong and Guo, Chufan and Su, Kuifeng},
  title = {CoT-VLNBench: A Benchmark for Visual Chain-of-Thought Reasoning in Vision-Language-Navigation Robots},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {43},
  pages = {36573--36581},
  doi = {10.1609/aaai.v40i43.40980}
}
Kostenlos starten →