Single RGB Camera Embodied Navigation Model Hits SOTA
sophiamyang · x · 2026-07-08
Achieving SOTA on the R2R-CE validation set (79.4% success in seen scenes, 76.6% in unseen), this model relies solely on a single RGB camera without LiDAR or depth sensors. The 8B model is trained entirely in simulation and runs across wheeled, legged, and aerial robots of varying sizes, while remaining robust to different camera intrinsics.
Related event: Mistral Unveils Robostral, an 8B Embodied Navigation Model(12 posts)→
More from Embodied
- Inside Ant Group's play at WAIC-style expo: AI and hardware vendors settle into new division of labor — 智东西 · 2026-09-11
- Amazon and Google sold 600M+ smart speakers, so why no AGI-era successor? — julianlehr · 2026-09-11
- ECCV26 Oral: Flow Matching Enables Single-Stage Multi-View Point Cloud Registration — ducha_aiki · 2026-09-11
- Polish developers build iPhone app that detects nearby Meta smart glasses — Low-Honeydew6483 · 2026-09-11
- Ant's Afu health AI hits 150M users, unveils AI+hardware health alliance at Bund Summit — APPSO · 2026-09-11
- Johns Hopkins Launches Full-Stack Hands-on Robot Learning Class with SO-101 Arm Kits — _krishna_murthy · 2026-09-11