Why Robotics AI Needs Data: Expert Says Deployment Skills Require Real Data
m_wulfmeier · x · 2026-08-04
Commenting on the performance of models like Gemini-Robotics-ER-2 and GPT-5.6-Sol in robotics benchmarks, a researcher points out that while these models show impressive accuracy and robustness, the core of robotics advancement still lies in data.
Just as models cannot learn to code without coding data, robotics AI cannot improve its deployment capabilities without real-world deployment data.
More from Embodied
- Berkeley researchers sample humanoid robot policies directly from weight space with diffusion — berkeley_ai · 2026-10-16
- OneWM: unified causal training shows world and action modeling improve each other — IAAI233 · 2026-10-16
- Tesla's hover car isn't a flying car — compressed air can't sustain flight — tinyfool · 2026-10-16
- Scobleizer relays claim that Optimus demo will be even more mind-blowing than the road-flipping Roadster — Scobleizer · 2026-10-16
- Indie dev's AI PASSPORT wearable firmware hits 1,200+ downloads in days — ezshine · 2026-10-16
- 1X Opens California Factory for Mass Production of NEO Humanoid Robots — emmanuelvivier · 2026-10-16