graspnet/graspnet-baseline
Baseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020)
This project helps robotics engineers and researchers design and test robotic systems that need to pick up a variety of objects. You provide 3D sensor data (RGB-D images) of an object, and the system outputs potential stable grasp configurations. It enables efficient exploration of how a robot gripper can best interact with different items.
893 stars. No commits in the last 6 months.
Use this if you are developing or evaluating robotic grasping strategies and need to identify effective ways for a robot to pick up objects based on visual sensor data.
Not ideal if you need a plug-and-play solution for an existing robot arm without any development or integration work, or if you don't have RGB-D sensor data.
Stars
893
Forks
211
Language
Python
License
—
Category
Last pushed
Feb 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/graspnet/graspnet-baseline"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
andyzeng/arc-robot-vision
MIT-Princeton Vision Toolbox for Robotic Pick-and-Place at the Amazon Robotics Challenge 2017 -...
dougsm/ggcnn
Generative Grasping CNN from "Closing the Loop for Robotic Grasping: A Real-time, Generative...
NVIDIA-ISAAC-ROS/isaac_ros_dnn_stereo_depth
NVIDIA-accelerated, deep learned stereo disparity estimation
PickNikRobotics/deep_grasp_demo
Deep learning for grasp detection within MoveIt.
wkentaro/reorientbot
ReorientBot: Learning Object Reorientation for Specific-Posed Placement, ICRA 2022