Behaviorial Cloning

Track 1

Track 2

Teaching a car to drive

Project Overview

This project contains the results from completing Project 3 of the Udacity Self-Driving Car Engineer Nanodegree. The goal of this project is to teach a convolutional neural net to drive a car, using only video of humans driving as input. All driving was recorded with Udacity's driving simulator.

Files in the repository

• The code for the model and training procedure - model.py
• A trained model - model.h5
• The code that makes the driver drive - drive.py
• The videos recording autonomous laps around track 1 and track 2
• A writeup detailing the results of the project

Running the code

This project was developed using Python 3.5. The project depends on the NumPY, OpenCV, Keras and TensorFlow libraries.