EUVIMEDEUVIMED entdecken
Crossref

DA-Nav: Direction-Aware City-Scale Vision-Language Navigation

Ye Yuan, Kehan Chen, Xinqiang Yu, Wentao Xu, Heng Wang, Libo Huang, Chuanguang Yang, Yan Huang, Jiawei He, Zhulin An

IEEE Robotics and Automation Letters · 2026-12 · 11 (12) · 14308-14315

DOI: 10.1109/lra.2026.3746066 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Robotics and Automation Letters, 2026-12. Verfasst von Ye Yuan und 9 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation, Youth Key Project of the Chinese Academy of Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

City-scale outdoor navigation is currently hindered by the heavy reliance on dense maps or costly navigation supervision. In this work, we introduce a novel paradigm for leveraging directional instructions from commercial navigation tools (e.g., Google Maps). To bridge the gap between commercial instructions and executable navigation actions, while mitigating long-horizon error accumulation through robust trajectory recovery, we propose DA-Nav, a Direction-Aware vision-language Navigation framework that reformulates navigation as a discrete spatial grounding problem on the egocentric 2D image plane. To achieve trajectory recovery, DA-Nav employs a Chain-of-Thought (CoT) reasoning process encompassing deviation assessment, action prediction, and target grid selection. We further introduce ReDA, a dataset that provides direction-aware instructions and recovery trajectories to enhance spatial grounding and support CoT recovery reasoning. Extensive experiments in CARLA demonstrate that DA-Nav achieves a high success rate of 56.16% in unseen urban environments, outperforming existing State-of-The-Art (SoTA) methods while maintaining a substantially stronger recovery capability. Furthermore, without fine-tuning, DA-Nav seamlessly adapts to both quadruped and humanoid robots, enabling stable kilometer-scale closed-loop outdoor navigation in complex real world environments.

Förderung

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation
  • Youth Key Project of the Chinese Academy of Sciences

Zitieren

APA

Yuan, Y., Chen, K., Yu, X., Xu, W., Wang, H., Huang, L., Yang, C., Huang, Y., He, J., & An, Z. (2026). DA-Nav: Direction-Aware City-Scale Vision-Language Navigation. IEEE Robotics and Automation Letters, 11(12), 14308-14315. https://doi.org/10.1109/lra.2026.3746066

Vancouver

Yuan Y, Chen K, Yu X, Xu W, Wang H, Huang L, et al. DA-Nav: Direction-Aware City-Scale Vision-Language Navigation. IEEE Robotics and Automation Letters. 2026;11(12):14308-14315. doi:10.1109/lra.2026.3746066

BibTeX
@article{Yuan2026,
  author = {Yuan, Ye and Chen, Kehan and Yu, Xinqiang and Xu, Wentao and Wang, Heng and Huang, Libo and Yang, Chuanguang and Huang, Yan and He, Jiawei and An, Zhulin},
  title = {DA-Nav: Direction-Aware City-Scale Vision-Language Navigation},
  journal = {IEEE Robotics and Automation Letters},
  year = {2026},
  volume = {11},
  number = {12},
  pages = {14308--14315},
  doi = {10.1109/lra.2026.3746066}
}
Kostenlos starten →