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.
More from Embodied
- DIY open-source driving mods: Tesla owner runs Sunnypilot on Model Y with $1,000 Comma Four kit, alarming experts — science · 2026-09-30
- Call for physical AI founders: actuators, dexterous hands, robot foundation models and more — Sethwinterroth · 2026-09-30
- EVO-WAM self-verifies video-action rollouts, real-world long-horizon success 20%→76.7% — hitsz123 · 2026-09-30
- WorldLine: 10k-hour video-trained action simulator lifts robot policy success up to 21.4 pts — hongkongust · 2026-09-30
- Agile Robots ships humanoid robots daily from German factory, partners with DeepMind — CyberRobooo · 2026-09-30
- Real2Gym Turns Videos Into Interactive Robot Gyms, Beating GPT-6 Direct Mode by 33% on Real Robots — Shanghai-AI-Laboratory · 2026-09-30