Noitom Robotics releases HiPHI dataset for humanoid robot training
Noitom Robotics has published a white paper introducing HiPHI, a large-scale motion capture dataset designed to address data limitations in humanoid robot learning. The dataset contains 617.5 hours of whole-body human motion recorded with optical motion capture at sub-millimeter accuracy. It specifically includes 245.7 hours of human-object interaction data, featuring synchronized object…
Key points
- HiPHI is a 617.5-hour dataset with sub-millimeter accuracy for humanoid robot training.
- It includes 245.7 hours of human-object interaction with synchronized object trajectories.
- Policies trained on HiPHI transfer successfully to a physical Unitree G1 robot.
The story so far
2 episodes →- Noitom Robotics releases HiPHI dataset for humanoid robot trainingthis story
HiPHI: A Large-Scale Benchmark for High-Precision Human Motion and Object Interaction
IEEE Spectrum Robotics · 7 October 2026
Loading the full article…
This text was published by IEEE Spectrum Robotics and written by Noitom Robotics. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Robotics & Physical AI
All →- UCLA builds PhoneBot humanoid from smartphone and $400 hardware · 1 src
- Atomic Machines raises $250M to build tiny machines from code with AI · 1 src
- Minerva unveils VR-controlled humanoid Roger for bomb disposal with $10M funding · 1 src
- Microsoft launches Xbox Labs to explore AI-powered game mods · 2 src
- Simbe Robotics completes 3,000 Tally robot rollout at Groceryshop 2026 · 1 src
Comments
via GitHub Discussions