Nvidia · NVIDIA Blog
Skild AI Taps NVIDIA Physical AI to Teach Robots New Tasks From a Single Video
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
Manufacturing floors, warehouses and production lines rarely stay fixed, tasks change, layouts shift and new products arrive, and most robots can’t keep up without significant reprogramming.
Key facts
- The launch comes as the company reached a $100 million annual revenue run rate 10 months after its first commercial deployment
- In Skild’s tests on new, multistep tasks, its S1 robot succeeded about 66% of the time at each step, compared with 9% for a similar AI system, a more than sevenfold improvement
- In one plant-potting test, the Skild AI team moved from recording the demonstration to autonomous execution on hardware in 11 minutes
- Learning by experience, and not preprogramming, is the step change that has happened in robotics,” said Deepak Pathak, cofounder and CEO of Skild AI
Summary
Skild AI’s new S1 robot foundation model helps address this, designed to learn previously unseen, long-horizon tasks from a single video demonstration. Skild built S1 and conducted the research on NVIDIA AI infrastructure, part of a broader collaboration spanning synthetic data generation, model training, simulation and real-world physical AI deployment. “Learning by experience, and not preprogramming, is the step change that has happened in robotics,” said Deepak Pathak, cofounder and CEO of Skild AI. The launch comes as the company reached a $100 million annual revenue run rate 10 months after its first commercial deployment.