dex-retargeting
- Software
- Humanoids and robot learning
- Library
A Python library that retargets human hand motion onto robot hands using several optimization methods. It is aimed at teleoperation and post-processing human hand data for robot imitation.
- Stale
Made by dexsuite.
Source on GitHub: github.com/dexsuite/dex-retargeting (opens in a new tab). Facts read at commit 3f56141 (opens in a new tab).
Licenses
- Code
- MIT (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit 3f56141 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
Labels
- StaleNo commit in 12 months: the newest is from 5 Apr 2025.
What it does
- Provides multiple retargeting optimizers that map human hand poses to robot hand joint positions.
- Supports retargeting from human hand video, for example for teleoperation.
- Supports retargeting from hand-object pose datasets, for use in robot imitation learning.
- Includes a helper for mapping retargeted joint positions onto simulator joint orders using joint names.
- Robot hand models come from the dex-urdf project and kinematics are based on pinocchio.
- Installable with pip; an optional extra adds dependencies for the examples.
Written by Robotheca from the project's README (opens in a new tab) at commit 3f56141.
Getting started
- Difficulty
- Intermediate
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Stale: no commit in 12 months
- Newest commit
- 5 Apr 2025 on main
- Latest release
- None published on GitHub
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.