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.

Related event: GPT-5.6 and Gemini Robotics Models Show Promise but Lack Real-World Generalization(3 posts)→

Original post →

More from Embodied

Embodied channel →