PietroVitiello/ActionRepresentation

MSc Project aimed at finding an alternative way of representing robot actions. We evaluate several machine learning models to control a simulated 7-joint robotic arm using solely a wrist mounted camera as input.

19
/ 100
Experimental

This project offers a new way for engineers and researchers to train robotic arms using visual input. It takes camera images from a robot's wrist and outputs instructions for the arm to perform actions like grasping objects. The intended users are robotics engineers and AI researchers focused on robot learning and automation.

No commits in the last 6 months.

Use this if you are exploring novel visual-based control methods for robotic arms, especially in simulated environments, and want to experiment with different action representations.

Not ideal if you need to deploy solutions directly onto physical robots or require real-time control in complex, unstructured industrial settings.

robotics-research robot-learning imitation-learning robotic-arm-control computer-vision-for-robotics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

13

Forks

1

Language

Python

License

Last pushed

Sep 09, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PietroVitiello/ActionRepresentation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.