Today we are announcing a partnership with Universal Robots (UR), a Teradyne Robotics subsidiary, to integrate Scale software with UR’s industrial robots. This collaboration, unveiled today at NVIDIA GTC, embeds Scale’s flagship Physical AI Data Engine in the UR AI Trainer, enabling physical AI applications to be deployed in challenging real-world environments.

Most of the data used to train robotics AI today is collected on research robots and not designed for production settings. These systems are effective at training Physical AI models, but lack the power and reliability for long-term real-world deployment.

By enabling data collection directly on production robots and incorporating force feedback with visual data, our solution with UR allows developers to train models on robust hardware used in more than 100,000 industrial deployments. UR’s global footprint provides an ideal foundation for scalable data capture and real-world AI deployment.

“Scale shares our belief that the future of robotics AI will be shaped as much by data quality as by model architecture. Together, we’re creating a foundation where imitation learning can move beyond isolated research projects and become a scalable, industrial capability. That’s an important step for customers who want AI systems they can actually deploy and rely on” – James Davidson, Chief AI Officer, Teradyne Robotics.

Later this year, Scale and UR will release a large-scale industrial robotics dataset that captures economically useful work across a wide range of industrial and commercial environments. This will serve as robust pre-training data for customers who will train on UR’s robots. In addition, Scale’s software will be embedded in the UR AI Trainer for on-the-edge capture of fine-tuning data and real-world rollout data to improve models over time.

Read the full press release from Universal Robots.

If you're building Physical AI systems and want to learn more about how Scale can accelerate your development, get in touch via physical-ai@scale.com.