IEEE Robotics & Automation Magazine - December 2018 - 106

INDUSTRY TUTORIAL

Highly Automated Vehicles
and Self-Driving Cars
By Árpád Takács, Imre Rudas, Dominik Bösl, and Tamás Haidegger

S

elf-driving cars have, in recent
years, clearly become among
the most actively discussed
and researched topics. By all
definitions, these systems, as a third
robotic revolution, belong to the
robotics field, despite the fact that
people generally assign them to a
specific domain of the automotive
industry [1]. Replicating the complex
task of human driving by an auton omous system poses countless en gineering challenges, involving the
wider field of robotics, including environment perception, decision making,
and control.
Whereas most of today's prototypes
are able to achieve certain functionalities, self-driving vehicles-as consumer
products-are still several years away
from mass production, primarily due to
the strict and constantly evolving regulations and testing protocols required of
traditional automotive companies. Until
then, new functionalities will continue
to be introduced to vehicles gradually,
requiring human supervision and effective human-robot cooperation through
sophisticated interfaces.
There are many predictions about
how self-driving cars will change our
lives, based approaches from both the
philosophical and scientific points of
view. Contemporary society is characterized by mobility, with cars playing a
significant role; approximately 1 billion
units are in use worldwide. According to
experts, equipping these vehicles with

Digital Object Identifier 10.1109/MRA.2018.2874301
Date of publication: 12 December 2018

106

*

IEEE ROBOTICS & AUTOMATION MAGAZINE

*

Industry Tutorials-Why Should You Care?
The Industrial Activities Board of the IEEE Robotics and Automation Society has
established an industry tutorial column in IEEE Robotics and Automation Magazine,
where key topical areas of robotics are introduced to the community in a practical
manner. Articles focus on the history, achievements, and future potential of the
fields of robotics, including business aspects and the standardization landscape.
These short articles aim to provide a better understanding of the rapidly evolving
ecosystem, starting with autonomous vehicles and medical robotics, and moving
on to rescue robotics, autonomous underwater vehicles, and unmanned aerial
vehicles. If you have any comments or are willing to contribute, let us know at
ras-iab@ieee.org.

intelligent driver assistance or completely autonomous functionalities will ultimately lead to a 90% drop in road
accident rates, a 60% reduction of carbon-dioxide emissions (due to efficient
trajectory planning), and savings of
more than 1 billion h per day for commuters around the world [2].
Brief History of Self-Driving
The first concept of self-driving cars
was introduced in the 1920s; instead of
computer-controlled vehicles, however,
the Pontiac Phantom cars were remotely controlled, demonstrating the power
of radio communication. A self-driving
concept car, a General Motors Firebird
IV, was presented at the 1964 New York
World's Fair. The first computer-controlled self-driving vehicle-created by
Carnegie Mellon University (CMU)
and introduced in the mid-1980s under
the name Navlab 1-was capable of
routing and obstacle avoidance.
The first pan-European initiative for
self-driving development was carried
out within the scope of the Eureka Programme for a European Traffic of Highest Efficiency and Unprecedented Safety

december 2018

Project, an eight-year-long joint effort
involving universities and auto manufacturers to define state-of-the-art selfdriving functionalities. The project was
successfully concluded in 1995, and the
prototype cars demonstrated lane keeping, cooperative driving, automated
intelligent cruise control, and enhanced
vision capabilities- functionalities we
find in today's production vehicles.
The industry has quickly recognized
the potential of automated systems in
logistics, and automated guided vehicles
first appeared in well-controlled factory
environments in the 1950s. Given these
environments, with known pathways
and clear ground, a US$2 billion global
business has developed that grows 10%
annually. The technology received considerable public attention when Amazon began using machines made by
Kiva, the robotics company it acquired
for US$775 million in 2012. Today, systems like KUKA's KMP 1500 freely
roam the shop floor, relying on omnidirectional drive technologies with mecanum wheels and positioning payloads
up to 1,500 kg with millimeter accuracy.
The largest autonomous platforms (e.g.,
IEEE Robotics & Automation Magazine - December 2018

Table of Contents for the Digital Edition of IEEE Robotics & Automation Magazine - December 2018
