EUVIMEDEUVIMED entdecken
Crossref

Traversability-Aware Legged Navigation by Learning From Real-World Visual Data

Hongbo Zhang, Zhongyu Li, Xuanqi Zeng, Laura Smith, Kyle Stachowicz, Dhruv Shah, Linzhu Yue, Zhitao Song, Weipeng Xia, Sergey Levine, Koushil Sreenath, Yun-hui Liu

IEEE Transactions on Robotics · 2026 · 42 · 400-417

DOI: 10.1109/tro.2025.3645885 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Robotics, 2026. Verfasst von Hongbo Zhang und 11 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: InnoHK initiative of the Innovation and Technology Commission of the Hong Kong Special Administrative Region Government.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The enhanced mobility brought by legged locomotion empowers quadrupedal robots to navigate through complex and unstructured environments. However, optimizing agile locomotion while accounting for the varying energy costs of traversing different terrains remains an open challenge. Most previous work focuses on planning trajectories with traversability cost estimation based on human-labeled environmental features. This human-centric approach is insufficient because it does not account for the varying capabilities of the robot locomotion controllers over challenging terrains. To address this, we introduce a novel real-world learning pipeline that unifies offline demonstrations, online reinforcement learning, and multimodal perception to achieve robust legged navigation. The framework employs multiple training stages to develop a planner that guides the robot in avoiding obstacles and hard-to-traverse terrains while reaching its goals. We first develop a novel traversability estimator in a robot-centric manner. The training of the navigation planner is directly performed in the real world using a sample efficient reinforcement learning method. With the proposed method, a quadrupedal robot learns to perform traversability-aware navigation through real-world interactions in diverse offroad and unstructured environments. Moreover, the robot demonstrates the ability to generalize the learned navigation skills to unseen scenarios.

Förderung

  • InnoHK initiative of the Innovation and Technology Commission of the Hong Kong Special Administrative Region Government

Zitieren

APA

Zhang, H., Li, Z., Zeng, X., Smith, L., Stachowicz, K., Shah, D., Yue, L., Song, Z., Xia, W., Levine, S., Sreenath, K., & Liu, Y. (2026). Traversability-Aware Legged Navigation by Learning From Real-World Visual Data. IEEE Transactions on Robotics, 42, 400-417. https://doi.org/10.1109/tro.2025.3645885

Vancouver

Zhang H, Li Z, Zeng X, Smith L, Stachowicz K, Shah D, et al. Traversability-Aware Legged Navigation by Learning From Real-World Visual Data. IEEE Transactions on Robotics. 2026;42:400-417. doi:10.1109/tro.2025.3645885

BibTeX
@article{Zhang2026,
  author = {Zhang, Hongbo and Li, Zhongyu and Zeng, Xuanqi and Smith, Laura and Stachowicz, Kyle and Shah, Dhruv and Yue, Linzhu and Song, Zhitao and Xia, Weipeng and Levine, Sergey and Sreenath, Koushil and Liu, Yun-hui},
  title = {Traversability-Aware Legged Navigation by Learning From Real-World Visual Data},
  journal = {IEEE Transactions on Robotics},
  year = {2026},
  volume = {42},
  pages = {400--417},
  doi = {10.1109/tro.2025.3645885}
}
Kostenlos starten →