wkentaro/reorientbot
ReorientBot: Learning Object Reorientation for Specific-Posed Placement, ICRA 2022
This project helps industrial automation engineers program robotic arms to pick up objects and place them in a very specific orientation, such as storing items on a shelf or packing a box neatly. It takes in visual data of objects in a pile and outputs precise instructions for a robot to grasp, reorient, and place them correctly. It's designed for robotics engineers and automation specialists working with robotic manipulators.
No commits in the last 6 months.
Use this if you need to automate precise object reorientation and placement tasks using a robotic arm, especially when objects start in arbitrary positions.
Not ideal if your robotic tasks involve simple pick-and-place without the need for complex object reorientation or if you're not working with a Panda robot or ROS environment.
Stars
57
Forks
5
Language
Python
License
—
Category
Last pushed
Mar 16, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/wkentaro/reorientbot"
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
PickNikRobotics/deep_grasp_demo
Deep learning for grasp detection within MoveIt.