MultiDex
GenDexGrasp research team
Synthetic grasp configurations for multiple hand embodiments, used by GenDexGrasp.
What you can explore
Compare contact representations across EZGripper, Barrett, Robotiq 3-Finger, Allegro and Shadow examples.
Before you use it
Simulation-based grasp labels are not physical success measurements. Check access and per-model permissions at the original project.
Original contributors
Puhao Li, Tengyu Liu and GenDexGrasp collaborators
License / access: Check original code, model and data terms before reuse
Keep exploring
GenDexGrasp
Contact-map-based grasp synthesis designed to generalize across robotic hand embodiments.
RobotFingerPrint
A common-coordinate representation for transferring grasp information across different robot hands.
DexGraspNet
Synthetic dexterous grasp configurations generated for a Shadow Hand and validated in simulation.
Editorial reference · checked 2026-09-22