Reproduce “Geometry Matching for Multi-Embodiment Grasping” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Maria Attarian, Muhammad Adil Asif, Jingzhou Liu, Ruthrash Hari, Animesh Garg, Igor Gilitschenski, Jonathan Tompson
GeoMatch predicts grasp contacts by encoding object and hand geometry together, then selecting object-surface contacts for hand keypoints one at a time. In Isaac Gym simulation, on 10 unseen objects, its mean success rate across ezgripper, barrett, and shadowhand was 79.17%, versus 72.38% for DFC. This result covers three tested hands; GeoMatch did not lead on Shadowhand.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.