etriantafyllidis/ROMAN

The RObotic MAnipulation Network

40
/ 100
Emerging

This project helps robotics engineers and researchers simulate and train robotic arms for complex, sequential manipulation tasks. It takes human demonstrations or defined training scenarios as input and outputs trained neural network models that can control robotic grippers to perform actions like picking and placing objects. It's designed for those developing or evaluating robotic manipulation systems.

No commits in the last 6 months.

Use this if you need to simulate, validate, or train a robotic arm, specifically a Franka Panda, to perform a series of coordinated actions within a controlled environment.

Not ideal if you are looking for a plug-and-play solution for a physical robot or do not have experience with Unity3D and reinforcement learning concepts.

robotics-simulation robotic-manipulation industrial-automation robot-training end-effector-control
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

40

Forks

8

Language

C#

License

GPL-3.0

Last pushed

Jun 20, 2023

Commits (30d)

0

Get this data via API

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

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