Self-Parking Car Evolved in 500 Lines of Code
Self-parking car using genetic algorithm (2021)
This project uses a genetic algorithm to train a car to park itself. Starting with random genomes, the cars gradually learn over about 40 generations. The car has sensors as eyes, muscles for movement, and a brain made of two linear polynomials. The entire algorithm is implemented in TypeScript in just 500 lines, and a browser-based simulator lets you watch the evolution or try parking manually.
Yeah-yeah, the cars are hitting some other cars along the way, and also are not perfectly fitting the parking spot, but this is only the 40th generation since the creation of the world for them, so be merciful and give the cars some space to grow :D