Skip to content

Self-driving car AI trained in simulations with randomly generated highways and parking lots ๐Ÿš—

License

Notifications You must be signed in to change notification settings

Defaultin/car-autopilot

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

Project Description

This project presents methods for training Autonomous Driving Models using NeuroEvolution of Augmenting Topologies and Deep Learning and their implementation in 2D and 3D simulations.

#1 - Self-driving 2D

Training an autopilot model using genetic algorithm for the generation of evolving artificial neural networks on randomly generated highways in a 2D simulation.

#2 - Self-parking 2D

Training an autopilot model using genetic algorithm for the generation of evolving artificial neural networks on randomly generated parking lot in a 2D simulation.

#3 - Self-driving 3D

Training an autopilot deep learning model based on behavioral cloning metodology using Udacity's self driving car 3D simulator.