paulvantieghem/curla

CURLA: CURL x CARLA -- Robust end-to-end Autonomous Driving by combining Contrastive Learning and Reinforcement Learning

35
/ 100
Emerging

This project helps autonomous vehicle researchers develop and test robust self-driving car agents. It takes visual data from a simulated driving environment (CARLA) and applies advanced reinforcement learning techniques to train a virtual car. The output is a highly capable autonomous driving model that can navigate complex scenarios, ideal for those researching the next generation of AI drivers.

No commits in the last 6 months.

Use this if you are an autonomous driving researcher looking to train more robust and generalizable end-to-end self-driving agents using simulated visual data.

Not ideal if you need a plug-and-play solution for real-world autonomous driving or if you don't have experience with deep reinforcement learning and simulation environments.

autonomous-driving robotics-simulation reinforcement-learning-research vehicle-control-systems AI-training-environments
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

17

Forks

3

Language

Python

License

MIT

Last pushed

Feb 06, 2024

Commits (30d)

0

Get this data via API

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

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