necrashter/driven-to-evolve

Teach AI to drive, one crash at a time. Evolve, upgrade, and turn failure into progress.

27
/ 100
Experimental

This project helps you teach AI cars to drive through simulated environments. You design or select initial AI drivers, observe their performance, and then use their 'failures' (crashes) to automatically improve the next generation of drivers. It's for anyone interested in exploring how evolutionary algorithms can be used to train intelligent agents in a visual, interactive way.

No commits in the last 6 months.

Use this if you want to experiment with genetic algorithms to evolve driving behaviors in a simulated car race, turning every crash into a learning opportunity.

Not ideal if you're looking for a production-ready autonomous driving system or a deep learning framework for complex real-world sensor data.

AI-training-simulation evolutionary-computation-demo genetic-algorithm-visualization autonomous-agent-experimentation neural-network-gaming
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 4 / 25

How are scores calculated?

Stars

22

Forks

1

Language

GDScript

License

MIT

Last pushed

Jun 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/necrashter/driven-to-evolve"

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