MultiGrasp
MultiGrasp
Dexterous grasp generation and execution research for holding multiple objects in one hand.
What you can explore
Inspect the representation and simulation pipeline for multi-object grasp configurations.
Before you use it
A multi-object simulation benchmark does not establish physical reliability. Contact, friction and object geometry must be validated for a real hand.
Original contributors
Yuyang Li and MultiGrasp 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.
DexGraspNet
Synthetic dexterous grasp configurations generated for a Shadow Hand and validated in simulation.
Dexonomy
Contact templates and a grasp taxonomy for synthesizing human-like dexterous grasp configurations.
Editorial reference · checked 2026-09-22