NVIDIA Releases SOMA Retargeter for Humanoid Motion Mapping
In short: NVIDIA has launched v0.2 of the SOMA Retargeter, an open-source tool designed to adapt human motion data for humanoid robot platforms. It processes motion sources—such as mocap, video reconstruction, or generative models—and aligns them with specific robot anatomy using inverse kinematics.
This summary was generated automatically by AI from NVIDIA Developer's publication. It is our own text, not a copy of the original — facts, figures and quotes belong to the source, linked above and below.
What changed?
- 1Introduced v0.2 with support for five humanoid robots including Unitree G1 and AgiBot X2 Ultra.
- 2Added Robot Configurator for aligning reference poses and mapping skeletons.
- 3Integrated inverse kinematics solver built on NVIDIA Warp.
- 4Enabled export of retargeted trajectories as CSV files for downstream policy training.
Why it matters
This pipeline streamlines the creation of motion libraries for robotics training. By converting human-centric animation into robot-compatible joint movements, it accelerates the development of physically plausible behaviors in humanoid simulation and deployment.
Sources
- NVIDIA DeveloperOfficialPrimary sourceOriginal article →„Adapt Human Motion for Robots with NVIDIA SOMA Retargeter“13 Nov 2026, 19:00
- Published by source
- 13 Nov 2026, 19:00
- Found by our system
- 13 Nov 2026, 19:19
- Summary generated
- 13 Nov 2026, 19:20
This article was written by AI from the original source. Facts, numbers and prices come from the source; missing values are marked “Not specified”. Legal notice, copyright and privacy