SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.00938 · CVPR · 2023

UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy

Hao Shen, Haoran Liu, Tengyu Liu, Li Yi, He Wang, Jiayi Chen, Yijia Weng, Weikang Wan, Zikang Shan, Jialiang Zhang, Haoran Geng, Yinzhen Xu, and 1 more

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Figure 1. UniDexGrasp via grasp proposal generation and goal-conditioned execution. Left (grasp proposals): each figure demonstrates two or three diverse and high-quality grasp proposals that vary greatly in rotation, translation, and joint angles; right (grasp execution): given a grasp goal pose, our highly generalizable goal-conditioned grasping policy can grasp the object in the way specified by the goal, as shown in the green and blue trajectories and their corresponding goals.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.00938")
get_code_for_paper("2303.00938")
have("2303.00938")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.00938.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.00938.svg)](https://syntology.ai/paper/2303.00938)

Connect an agent — have() is free.