skumra/robotic-grasping
Antipodal Robotic Grasping using GR-ConvNet. IROS 2020.
This project helps industrial automation engineers or robotics researchers equip their robotic arms with the ability to reliably pick up various objects. It takes camera images of objects within the robot's reach and identifies the best spots and angles for the robot's gripper to firmly grasp them. The output is precise instructions that guide the robot in performing effective 'antipodal' grasps, where two opposing forces hold the object securely.
633 stars. No commits in the last 6 months.
Use this if you need to train a robotic system to autonomously pick up a variety of objects with a two-fingered gripper, improving efficiency in tasks like sorting, assembly, or packaging.
Not ideal if your robotic application involves specialized gripping mechanisms (e.g., suction cups, multi-fingered hands) or if you only need to pick up a limited set of pre-defined objects with known positions.
Stars
633
Forks
144
Language
Python
License
—
Category
Last pushed
Nov 09, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/skumra/robotic-grasping"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
andyzeng/visual-pushing-grasping
Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep...
BerkeleyAutomation/gqcnn
Python module for GQ-CNN training and deployment with ROS integration.
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"