Robotic Grasp Synthesis ML Frameworks

ML frameworks and tools for detecting, predicting, and generating robotic grasps from visual or point cloud data. Includes grasp detection networks, grasp pose synthesis, and integration with robot control systems. Does NOT include general robotic manipulation, motion planning, or non-grasp-specific robot learning.

There are 11 robotic grasp synthesis frameworks tracked. The highest-rated is BerkeleyAutomation/gqcnn at 44/100 with 339 stars.

Get all 11 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=robotic-grasp-synthesis&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

# Framework Score Tier
1 BerkeleyAutomation/gqcnn

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

44
Emerging
2 skumra/robotic-grasping

Antipodal Robotic Grasping using GR-ConvNet. IROS 2020.

44
Emerging
3 andyzeng/visual-pushing-grasping

Train robotic agents to learn to plan pushing and grasping actions for...

44
Emerging
4 google-research/ravens

Train robotic agents to learn pick and place with deep learning for...

41
Emerging
5 shadow-robot/smart_grasping_sandbox

A public sandbox for Shadow's Smart Grasping System

38
Emerging
6 huangwl18/geometry-dex

PyTorch Code for "Generalization in Dexterous Manipulation via...

32
Emerging
7 sebbyjp/dgl_ros

Deep grasp library for ROS2

30
Emerging
8 antoalli/L2G

End-to-End Learning to Grasp from Object Point Clouds

23
Experimental
9 MAYANK12-WQ/Vision-Guided-Robot-Grasping

Deep learning grasp detection network with simulation integration for...

22
Experimental
10 hsp-iit/byogg

[ICRA 2025] Bring Your Own Grasp Generator: Leveraging Robot Grasp...

13
Experimental
11 RhizomaticRobin/DexiGrab-Robot-Hand

LibreGrabbe 16-DOF Robot Hand

12
Experimental