Unity-Technologies/Robotics-Object-Pose-Estimation
A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.
This project helps robotics engineers and researchers simulate and develop robotic pick-and-place tasks. It takes simulated camera images and object configurations from a Unity environment and produces a deep learning model that can estimate the object's position and orientation. The output is a robot arm performing a pick-and-place action based on the vision model.
338 stars. No commits in the last 6 months.
Use this if you need to train a robot vision system for object manipulation using synthetic data generated in a simulated environment.
Not ideal if you primarily work with physical robots and real-world data collection, or if you are not using Unity for simulation.
Stars
338
Forks
82
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 13, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Unity-Technologies/Robotics-Object-Pose-Estimation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DeepLabCut/DeepLabCut
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with...
openpifpaf/openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and...
lambdaloop/anipose
🐜🐀🐒🚶 A toolkit for robust markerless 3D pose estimation
DIYer22/bpycv
Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
NeLy-EPFL/DeepFly3D
Motion capture (markerless 3D pose estimation) pipeline and helper GUI for tethered Drosophila.