PanoVLN beats VLN SOTA by 11.9% success rate using panoramic views, tested on a quadruped robot

ZhejiangUniversity · hf · 2026-09-30

Zhejiang University's PanoVLN uses panoramic observations for vision-and-language navigation, with confidence-guided execution for longer action sequences, branch-heavy training routes for route-choice supervision, and combined semantic-geometric RGB features. With a 4B backbone and RGB-only input it surpasses prior SOTA by 11.9% and 8.7% success rate on R2R-CE and RxR-CE Val-Unseen, and navigates faster with fewer pauses on a real quadruped robot.

Original post →

More from Embodied

Embodied channel →