PickNikRobotics/deep_grasp_demo
Deep learning for grasp detection within MoveIt.
This project helps roboticists and automation engineers design and implement robotic pick-and-place tasks more efficiently. It takes 3D point cloud data or depth images of objects and outputs precise robotic grasp poses. The primary users are researchers and practitioners working with industrial robots, particularly those using the MoveIt motion planning framework.
137 stars. No commits in the last 6 months.
Use this if you need to integrate advanced deep learning models to enable robots to reliably grasp unknown objects from camera data within a MoveIt task sequence.
Not ideal if you are looking for a plug-and-play solution for a fully contained, off-the-shelf robot system without needing deep integration or customization.
Stars
137
Forks
54
Language
C++
License
—
Category
Last pushed
Jun 18, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/PickNikRobotics/deep_grasp_demo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...
graspnet/graspnet-baseline
Baseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020)
NVIDIA-ISAAC-ROS/isaac_ros_dnn_stereo_depth
NVIDIA-accelerated, deep learned stereo disparity estimation
wkentaro/reorientbot
ReorientBot: Learning Object Reorientation for Specific-Posed Placement, ICRA 2022