Data infrastructure for Real World Robot Training
Robots fail outside the lab because their training data doesn’t transfer. We’re building a data infrastructure platform that converts real-world human demonstrations into reusable robot training data using consumer AR/VR headsets and guided capture workflows. Each demonstration is validated and enriched in a closed loop with action annotations, occlusion handling, and simulation-based verification. Instead of storing isolated trajectories, we decompose demonstrations into spatially and temporally structured atomic actions — reusable skill patterns that generalize across tasks and robots. The resulting skills are exported in industry-standard formats (LeRobot, ManiSkill, Isaac Sim) and can be retargeted across robot embodiments without custom engineering. Because XR devices are widely available, data collection can scale beyond robotics labs to everyday users.
Category tags:Additional links:
.png&w=96&q=75){kind=small}
.png&w=96&q=75){kind=small}
For Innovators & Creators