dougsm/ggcnn
Generative Grasping CNN from "Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach" (RSS 2018)
This project helps industrial automation specialists and robotics engineers train robotic arms to pick up objects reliably, even when items shift unexpectedly. By taking a depth image of a scene, it quickly determines the best way for a robot gripper to grasp an object, providing the quality and precise pose of potential grasps. This ensures smoother operation in dynamic environments like assembly lines or logistics hubs.
613 stars. No commits in the last 6 months.
Use this if you need to enable real-time, closed-loop grasping control for a robotic arm using a lightweight vision system.
Not ideal if you're looking for a solution that uses standard RGB images rather than depth data, or if your application doesn't involve robotic manipulation.
Stars
613
Forks
153
Language
Python
License
BSD-3-Clause
Category
Last pushed
Jul 21, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/dougsm/ggcnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
andyzeng/arc-robot-vision
MIT-Princeton Vision Toolbox for Robotic Pick-and-Place at the Amazon Robotics Challenge 2017 -...
skumra/robotic-grasping
Antipodal Robotic Grasping using GR-ConvNet. IROS 2020.
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
PickNikRobotics/deep_grasp_demo
Deep learning for grasp detection within MoveIt.