Popular GitHub Repositories for Grasping

Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.

Summary of key papers and blogs about diffusion models to learn about the topic. Detailed list of all published diffusion robotics papers.

A curated list of 3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs, inspired by awesome-computer-vision, including papers, codes, and related websites

Detect 6-DOF grasp poses in point clouds

Deep Reinforcement Learning for Robotic Grasping from Octrees

A comprehensive list of papers about Robot Manipulation, including papers, codes, and related websites.

Python module for GQ-CNN training and deployment with ROS integration.

Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home

MIT-Princeton Vision Toolbox for Robotic Pick-and-Place at the Amazon Robotics Challenge 2017 - Robotic Grasping and One-shot Recognition of Novel Objects with Deep Learning.

GrabNet: A Generative model to generate realistic 3D hands grasping unseen objects (ECCV2020)

This is a repository for GraspXL, which can generate objective-drive grasping motions for 500k+ objects with different dexterous hands.

Simple and unified interface to zero-shot computer vision models curated for robotics use cases.

Reinforcement Learning Experiments using PyBullet

Deep learning for grasp detection within MoveIt.

Isaaclab-based grasp learning test bench

"Good Robot! Now Watch This!": Repurposing Reinforcement Learning for Task-to-Task Transfer; and “Good Robot!”: Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer

6-Dof Grasping Policy from Point Clouds

This is a repository for RobustDexGrasp, which achieves robust grasping of 500+ unseen objects from single-view perception.

ContactGen: Generative Contact Modeling for Grasp Generation (ICCV 2023)

Integrating learning and task planning for robots with Keras, including simulation, real robot, and multiple dataset support.