Reproduce “Functional Eigen-Grasping Using Approach Heatmaps” 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

Malek Aburub, Kazuki Higashi, Weiwei Wan, Kensuke Harada

The authors present a method for planning tool grasps that leave a finger able to reach a button or trigger. It maps palm positions using kinematics and directional manipulability, then plans a grasp around the finger. In simulation, five-attempt consistency averaged 82.86% for Shadow Hand Lite across seven objects and 86.67% for Barrett Hand across six; physical tests covered Shadow Hand Lite.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.