NavVerse benchmark tests robots on indoor-to-outdoor navigation across 200 scenes and 10K episodes
GhaffariMaani · x · 2026-10-02
A team unveiled NavVerse, a physics-based simulation benchmark for continuous indoor-to-outdoor embodied navigation, tackling the real challenge of asking a robot to 'find a place to get burgers and fries' — requiring building exit, outdoor transition, and place understanding.
Key points:
- 200 indoor, outdoor, and connected scenes with 10K episodes
- Tasks include ObjNav, VLN, and a new PlaceNav setting
- Provides executable robot rollouts
- Paper, project page, and code are publicly available
The authors note that completing tasks across environment transitions remains a real challenge for today's navigation agents.
More from Embodied
- Robotics papers on arXiv hit 210 per day, up from 20-30 four years ago — DJiafei · 2026-10-02
- Kaigen dev confirms its AI 3D demos run entirely inside the Unity engine — gdechichi · 2026-10-02
- Cartwheel teases kinematics data breakthrough with a wink — andrew_n_carr · 2026-10-02
- Teleop a humanoid just by wearing glasses, and it sees through them too — danfei_xu · 2026-10-02
- One policy for millions of robots: team builds generalist motor control policy trained on 200+ real robot models — breadli428 · 2026-10-02
- Clone Robotics shows off Torso 3 humanoid hand, betting on an unconventional design path — MarwaEldiwiny · 2026-10-02