100k Hours of Real-World Data Yields Only 57% Success in Robotics
eigenron · x · 2026-08-06
A recent test on the RoboCasa365 benchmark revealed that training with 100,000 hours of real-world trajectories (equivalent to 11.4 years) only achieved a 57% success rate. This stark data point has sparked reflections among practitioners about the current bottlenecks in embodied AI, suggesting the field is still in its infancy.
More from Embodied
- CoRL 2026 Opens Call for Demos with New Fast Track for Accepted Papers — GeorgiaChal · 2026-08-06
- 51WORLD to Unveil Physical AI Master Plan 2030 on August 18 — rsasaki0109 · 2026-08-06
- Developer Shows Sneak Peek of New Vibescape Environment for Apple Vision Pro — dreamwieber · 2026-08-06
- Dongfang Starlink Launches AI Hyperspectral Satellites, Plans 2M Lunar Robots for Data Center — 新智元 · 2026-08-06
- USTC Study: AI Agents Achieve Only 3.3% Zero-Intervention Execution in Robot Labs — 新智元 · 2026-08-06
- Ego2Robot: Synthesizing 18,500+ Hours of Robot Training Data from Egocentric Videos — Ye Wang · 2026-08-06