ken-power/selfdrivingcarnd-behavioralcloning

Use convolutional neural networks (CNNs) to clone driving behavior and train a self-driving car to autonomously navigate a track.

Project: Behavioral Cloning

This project is part of Udacity's Self-driving Car Engineer Nanodegree program. The goal of this project is to clone driving behavior using convolutional neural networks (CNNs).

The Project

This project has the following requirements:

• Use a simulator to collect data of good driving behavior
• Design, train and validate a model that predicts a steering angle from image data
• Use the model to drive the vehicle autonomously around the first track in the simulator. The vehicle should remain on the road for an entire loop around the track.
• Summarize the results with a written report

The written report is in the file writeup.md.

The video (uploaded to YouTube) was created from the center camera perspective:

This animated GIF shows an extract of the car driving autonomously around the track. Videos of the car completing a full lap are below.

This video (hosted on YouTube) is sped up 30x and shows the car driving autonomously for a full lap around the track:

This is the same video (hosted on YouTube) at normal speed: