Latest News

Design multimodal robot data workflows that align joint states, RGB-D video, actions, timestamps, and metadata for reliable physical AI training.

Explore behavior cloning robotics, from recording clean teleoperation demonstrations to validating learned policies and deploying them on real hardware.

Compare machine learning robot arm platforms across hardware, cameras, teleoperation, data, compute, inference, documentation, and scale for physical AI.

Collecting handheld demonstrations is only half the job. The other half is robotics data annotation: turning hours of raw episodes into multimodal training data a team can actually search, review, and train on. Our partners at DecisionFacts just showed what that second half can look like. They built a pipeline that takes episodes captured on TRumi, Trossen Robotics' handheld data collection device, and turns them into annotated, synchronized files that open directly in Foxglo

Explore robot arm for machine learning requirements, from mechanics and sensing to control, compute, datasets, and deployment planning.