marcpinet/neat-cars

🚗 Draw a circuit and watch self-driving cars evolve thanks to the NEAT evolutionary algorithm.

27
/ 100
Experimental

This project allows you to design custom car racetracks and observe how virtual self-driving cars learn to navigate them through an evolutionary process. You draw the track, and the system shows cars constantly improving their driving skills based on sensor input, eventually mastering the course. This tool is ideal for anyone interested in visualizing or demonstrating how genetic algorithms and neural networks can learn complex tasks like autonomous driving.

No commits in the last 6 months.

Use this if you want to visually understand and experiment with how AI, specifically neuroevolution, can be used to teach vehicles to drive themselves on custom-designed tracks.

Not ideal if you're looking for a tool to develop or test production-ready autonomous driving systems, or if you need to simulate realistic physics or complex urban environments.

AI-learning-visualization evolutionary-algorithms neural-network-simulation autonomous-driving-demonstration educational-AI-tool
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

15

Forks

1

Language

Python

License

MIT

Last pushed

Feb 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/marcpinet/neat-cars"

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