Reproduce “Data-Driven Grasp Synthesis - A Survey” 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

Jeannette Bohg, Antonio Morales, Tamim Asfour, Danica Kragic

The authors survey data-driven robotic grasp synthesis, organizing methods by whether objects are known, familiar, or unknown. Systems retrieve stored grasps, transfer experience by similarity, or generate candidates from sensed features or shape. The survey notes one physical-robot study found 91% success for human-planned grasps versus 77% for GraspIt! grasps, not evidence that a category generally performs best.

Summary by alphaXiv.

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