BerkeleyAutomation/gqcnn
Python module for GQ-CNN training and deployment with ROS integration.
This tool helps robotics researchers and engineers train and analyze Grasp Quality Convolutional Neural Networks (GQ-CNNs). It takes in datasets of robotic grasps and outputs trained models that can predict the quality of a potential grasp, which is crucial for autonomous robotic manipulation. The primary users are those developing and refining robotic systems for grasping.
339 stars. No commits in the last 6 months.
Use this if you are developing robotic systems and need to train models to accurately predict the success or quality of a robot's grasp on objects.
Not ideal if you are looking for an out-of-the-box solution for robot control without needing to train custom grasp quality models.
Stars
339
Forks
152
Language
Python
License
—
Category
Last pushed
Apr 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BerkeleyAutomation/gqcnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
skumra/robotic-grasping
Antipodal Robotic Grasping using GR-ConvNet. IROS 2020.
andyzeng/visual-pushing-grasping
Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep...
google-research/ravens
Train robotic agents to learn pick and place with deep learning for vision-based manipulation in...
shadow-robot/smart_grasping_sandbox
A public sandbox for Shadow's Smart Grasping System
huangwl18/geometry-dex
PyTorch Code for "Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning"