Page 65 - Data Science Algorithms in a Week

In: Artificial Intelligence ISBN: 978-1-53612-677-8
Editors: L. Rabelo, S. Bhide and E. Gutierrez © 2018 Nova Science Publishers, Inc.

Chapter 3

MACHINE LEARNING APPLIED

TO AUTONOMOUS VEHICLES

*
Olmer Garcia, PhD and Cesar Diaz, PhD
School of Engineering, Universidad Jorge Tadeo Lozano, Bogotá, Colombia

ABSTRACT

This article presents an overview of machine learning in general and deep learning in
particular applied to autonomous vehicles. The characteristics of the data from the noise
and small size viewpoints made this problem intractable for other methods. The use of
machine learning for this project required two hardware/software systems: one for
training in the cloud and the other one in the autonomous vehicle. The main conclusion is
that deep learning can create sophisticated models which are able to generalize with
relatively small datasets. In addition, autonomous vehicles are a good example of a
multiclass classification problem.

Keywords: perception, deep learning, autonomous vehicles

INTRODUCTION

According to data published by the United Nations, more than 1.2 million people die
on roads around the world every year, and as many as 50 million are injured. Over 90%
of these deaths occur in low- and middle-income countries. Brazil is among the countries

* Corresponding Author Email: olmer.garciab@utadeo.edu.co.