Introduction to Self-Driving Vehicle Technology

Hanky Sjafrie

• Publisher: Chapman and Hall/CRC
• Year: 2019
• ISBN:
  9781000712070
• Edition: 1
• Topic: Computer Science
• Subtopic: Computer Science General
• Index: Computer Science

This book aims to teach the core concepts that make Self-driving vehicles (SDVs) possible. It is aimed at people who want to get their teeth into self-driving vehicle technology, by providing genuine technical insights where other books just skim the surface. The book tackles everything from sensors and perception to functional safety and cybersecurity. It also passes on some practical know-how and discusses concrete SDV applications, along with a discussion of where this technology is heading. It will serve as a good starting point for software developers or professional engineers who are eager to pursue a career in this exciting field and want to learn more about the basics of SDV algorithms. Likewise, academic researchers, technology enthusiasts, and journalists will also find the book useful.

Key Features:

• Offers a comprehensive technological walk-through of what really matters in SDV development: from hardware, software, to functional safety and cybersecurity
• Written by an active practitioner with extensive experience in series development and research in the fields of Advanced Driver Assistance Systems (ADAS) and Autonomous Driving
• Covers theoretical fundamentals of state-of-the-art SLAM, multi-sensor data fusion, and other SDV algorithms.
• Includes practical information and hands-on material with Robot Operating System (ROS) and Open Source Car Control (OSCC).
• Provides an overview of the strategies, trends, and applications which companies are pursuing in this field at present as well as other technical insights from the industry.

Chapter 1

Introduction

For centuries, people dreamed of flying to the moon. But it wasn‘t until the Cold War that the two Space Race rivals, the US and the USSR, finally developed the aerospace capabilities to make this dream a reality.

The concept of self-driving vehicles, or SDVs, also stretches back a long time, first appearing in historical records around 1478. In the six centuries since then, the idea of autonomous vehicles has been regularly dismissed as absurd by some, and cherished as a dream by others. But now the momentum for SDVs is building, following a similar trajectory to that of space travel in the late 1950s. Things that once seemed impossible are coming within reach at astonishing speed.

Mention self-driving vehicles, and most people immediately think of autonomous cars. The idea of a car that drives itself has captured the popular imagination. Huge efforts are being made to lay the groundwork for the era of fully autonomous vehicles and hardly a day goes by without automakers, tech companies, policymakers, insurance brokers, or infrastructure firms unveiling the latest new development.

This book tackles the subject of SDVs from a technical perspective. It explains the big picture of what SDVs are and how they are developed, while offering plenty of in-depth engineering insights along the way.

1.1 Brief history of SDV technology

The concept of a self-driving vehicle may seem like a purely modern invention, but a sketch made by Leonardo da Vinci over 500 years ago suggests otherwise. The drawing shows a self-propelled cart powered by coiled springs and featuring programmable steering based on an arrangement of wooden pegs. In 2004, Paolo Galluzzi, director of the Institute and Museum of the History of Science in Florence, oversaw a project to build a working model based on the design created by da Vinci around 1478. A video shows their painstakingly crafted machine in action [3]. Often cited as the first example of a self-propelled vehicle and programmable machine, the design could also be regarded as the world‘s first robot vehicle, since it had no driver.

The idea of SDVs resurfaced at the 1939 New York World‘s Fair in the Futurama exhibit sponsored by the General Motors Corporation. The installation captured the public‘s imagination with its vision of the world 20 years into the future, showing self-driving cars operating on an automated highway system. Sixteen years later, General Motors expanded on the themes of smart roads and driverless cars in its musical short titled, ”Key to the Future.” The film of a relentlessly cheerful family enjoying the wonders of autopilot was exhibited at its 1956 Motorama auto show, which was attended by over 2.2 million visitors in various locations around the US [7].

Fast forward another half a century, and the development of autonomous vehicles gained significant momentum with the DARPA Grand Challenge competition held by the US Department of Defense in 2005, and the DARPA Urban Challenge in 2007. In each case, the participating teams were required to build a driverless vehicle, and complete a course within a specified timeframe. This provided a major boost to technologies such as vehicle software and robotics development and marked a tipping point for technological progress in the field of SDVs. Since then, BMW, Audi, Daimler, Google, Tesla, Uber, Baidu, and many other companies have continued to advance autonomous vehicle technology in various ways.

Meanwhile, policymakers in many countries have begun preparing new regulations for the future of autonomous vehicles. From insurance and standards to infrastructure and enabling technologies, the entire automotive ecosystem is playing an active role in embracing the changes that lie ahead.

1.2 What is an SDV?

Describe a vehicle as self-driving, autonomous or driverless, and different people will picture very different things. Some may interpret it as a vehicle that travels completely independently, without requiring a driver at all. Others may imagine a vehicle that travels on its own making autonomous decisions, but that still requires a human driver sitting behind the wheel ready to act in the event of an emergency.

The whole concept of a car driving on its own may seem extraordinarily complex, but the idea behind it is quite simple and lies well within the remit of current technology. Consider, for a moment, the processes involved in driving a vehicle. To begin with, you choose your destination and decide how to get there from your starting point. Then you start driving, keeping an eye on your surroundings at all times. These include static objects such as buildings, trees, road signs, and parked cars, as well as dynamic objects, such as pedestrians, moving cars, and animals. Every now and then, one of these objects may block the road, which will require you to react in one way or another. In the meantime, you, as the driver, are using all the available mechanisms within the vehicle to propel it in the required direction, while obeying the rules of the road.

Described in this way, it seems feasible that some of these steps could be performed without human intervention, and indeed many of the vehicles around us today are automated to a certain degree. Airplanes, trains, and ships all exhibit some degree of autonomy. By applying the computing power we already have at our disposal, and combining it with reliable sensors, intelligent algorithms as well as other components, it is possible to replicate the act of driving.

To provide clarity and a level playing field in the SDV industry, bodies such as the US Department of Transportation‘s National Highway Traffic Safety Administration (NHTSA) and the German Federal Highway Research Institute (BASt) have published definitions of SDVs based on their degree of automation. One of the most widely used references is the J3016 Driving Automation Taxonomy [4] published by Society for Automotive Engineers (SAE) International, which describes six levels of autonomous vehicles ranging from no automation to full automation as summarized in Table 1.1.

Table 1.1 SAE Levels of Driving...

Table of contents

• Cover
• Half Title
• Series Page
• Title Page
• Copyright Page
• Dedication
• Contents
• Preface
• Author
• Acknowledgment
• 1. Introduction
• 2. Hardware
• 3. Perception
• 4. Architecture
• 5. Putting it all together
• 6. Other technology aspects
• 7. Applications and outlook
• Final words
• Index