Home / Features / Milestones in the Development of Autonomous Driving

Milestones in the Development of Autonomous Driving

Bosch automated driving

With technology advancements, autonomous driving concept took centre stage of automotive industry in recent years across the world. Interestingly, the developments in this area are not new at all.

Like every other automotive innovation, this technology as well, took a long time to evolve where it stands today.

In fact, the driverless vehicles were deployed way back in the US military and concept of driverless cars, which ultimately led to more developed advanced driver assistance systems today, started a long back.

From cruise control to ABS and from airbags to today’s advanced emergency braking (AEB), autonomous vehicle concept is a product of hardcore efforts by several research and educational institutes as well as automakers and legislators. These milestones are depicted below.

Milestones

The technological advancement right from da Vinci’s Self-Propelled Cart to  today’s Autopilot has been astonishing. It got a grip from the DARPA challenge a decade back when manufacturers collaborated with technological partners and research institutes. Many developments post DARPA Challenge were made by the people and scholars who were actually a part of DARPA, and were hired by top manufacturers and technology companies later to drive their own self-driving technology programs.

The milestones of autonomous driving technology are shown below which gives a rough idea not only about how and where it started but also how these are connected to the future autonomous driving at large.

 Sixty-five years of Automotive baby steps, Source: Philip Ross, 2014, p. 62
Sixty-five years of Automotive baby steps, Source: Philip Ross, 2014, p. 62

da Vinci’s Self-Propelled Cart (ca. 1500)

Leonardo da Vinci, centuries before the invention of the automobile, designed a cart that could move without being pushed or pulled.

da Vinci’s Self Propelled Cart
da Vinci’s Self Propelled Cart

A distant forerunner to the car, the device is also considered to be the world’s first ever robot. The cart could move along the predetermined path using the power of high tension springs.

 

Antilock Braking System (ABS) (1936)

German auto technology major Bosch had filed a patent application for an “Apparatus for preventing lock-braking of the wheels of a motor vehicle” as early as 1936. Though it was first invented by a French company for an aircraft as it could help the landing process by reducing stopping distance without skidding, it was later tested for motorcycles by Royal Enfield Super Meteor motorcycles in the late 1950s. Due to its unreliability and expensiveness, the system saw a limited use in the 1960s in Ferguson P99 racing car and Jensen FF. In 1978 Bosch was the world’s first automotive supplier to present an ABS system ready for mass production.

“Futurama: Highways & Horizons” (1939)

“Futurama: Highways and Horizons”, The New York World’s fair (1939), Source: GM
“Futurama: Highways and Horizons”, The New York World’s fair (1939), Source: GM

The central theme of the New York World’s fair in 1939-40 was “The World of Tomorrow”. The General Motors sponsored event caught widespread attention. The most advanced technology posted was the automated highway system. Later in the 1960s, General Motors built a working prototype.

Teetor Cruise Control (1945)

A blind engineer named Ralph Teetor, invented one of the first cruise control systems to smooth out the ride. One day, while he was driving with his attorney who was driving the vehicle, used to slow down while speaking and speed up while listening. This rocking motion annoyed Mr. Teetor and eventually ended up inventing cruise control system using a throttle to set the speed of the vehicle. His invention commercialized in 1958.

Stanford Cart (1961)

Stanford Cart, Source: Stanford
Stanford Cart, Source: Stanford

Back then the space race was very competitive, researchers started various programs to land vehicles on the moon. The idea of a remote-control lunar rover was conceived by a Stanford engineering graduate student called James Adams. He faced a delay of 2.5 seconds between the signal sent from the earth and received by the rover on the moon. He wanted to control the rover from the earth itself. The solution ultimately led to the development of the world’s first truly self-driving wheeled vehicle. The Cart was eventually outfitted with cameras and programmed to detect and autonomously follow a solid white line on the ground. Today, successor technologies using cameras remain a vital element of autonomous vehicles.

Electronic Cruise Control (1968)

An engineer named as Daniel Aaron Wisner, invented the Automotive Electronic Cruise Control. This was the first electronic device for controlling a car. With this device, drivers can now maintain the speed of the vehicle without manual input – i.e. using automated systems. It is considered as a milestone in ADAS (Advanced Driver Assistance System).

Vienna Convention (1968)

The convention on road traffic was formed by United Nations Economic Commission for Europe (UNECE) at Vienna on November 8th 1968. The Vienna Convention was an international treaty that saw the establishment of important road traffic safety regulations and principles. One such a principle was that the driver is always fully in control of and responsible for the behavior of the vehicle in traffic.

The Contidrom (1969)

The Continental developed automated car in 1969 to standardize testing. They modified a passenger car which was able to follow the circular path via embedded cable. And it did not need a human driver to drive it. It discontinued in mid-70s, as it was not made for commercial use.

Tsukuba Mechanical Engineering (1977)

As the car could process images of the road ahead, it was called the first truly autonomous car. It was unveiled in 1977 by S. Tsugawa and his colleagues at Tsukuba Mechanical Engineering Lab, Japan. This car used analog computer technology for signal processing and had two cameras. The computerized car could achieve a speed of 30 km/h by tracking white street markers on the road.

Ernst Dickmanns’ VaMoRs (1986-1995)

A very important step forward in autonomous technology came from a German engineer Ernst Dickmanns, who equipped a sedan with two cameras and eight 16-bit Intel microprocessors and a host of other sensors and software, to detect objects on the road. It drove more than 90 km/h for roughly 20 km. Dickmanns’ key innovation was ‘dynamic vision’, allowing the imaging system to filter out extraneous noise and focus only on relevant objects.

 Ernst Dickmanns’ VaMoRs Mercedes Van, Busndeswehr University, Munich
Ernst Dickmanns’ VaMoRs Mercedes Van, Busndeswehr University, Munich

The EUREKA PROMETHEUS project (1987-1994)

The Program for European Traffic of Highest Efficiency and Unprecedented Safety was funded by European research initiative EUREKA. It was the largest project, till date, on Autonomous Driving involving 749 million Euro. Developed with inputs from Ernst Dickmanns at Bundeswehr University, it produced an automated van called VaMP.

VaMP was produced seven years after VaMoRs, with its two cameras processing 320 by 240 pixels per image at a range of 100 meters, could recognize road markings, its relative position in the lane and the presence of other vehicles. In a test drive near Paris, the car drove at up at 130 km/h in simulated traffic, even judging whether it was safe to change lanes. The next year, Dickmanns’ team piloted a Mercedes S-Class from Munich to Denmark, a trip of more than 1,600 kilometers at a maximum speed of 180 km/h with, as Dickmanns notes, “about 95% of the distance…traveled fully automatically.”

Mercedes-Benz Vario based VITA Autonomous prototype, Source: Diamler AG (VITA: Vision Information Technology Application)
Mercedes-Benz Vario based VITA Autonomous prototype, Source: Diamler AG
(VITA: Vision Information Technology Application)

Ernst Dickmanns’ 4D approach helped him and his team to achieve a speed of 96 km/h in 1987 itself while testing vehicles on the German Autobahn. He used conventional microprocessors and achieved 0.1 seconds per image time (10 images a second) whereas other participants could achieve 1 second to 10 seconds per image rate. In the DARPA Challenge in 2003, participants like the ALV and the NAVlab could achieve merely 2, 3, 5 kilometers per hour of speed. No wonder they literally crawled during the DARPA challenge. This very project which includes other teams from various German universities developed more seriousness into autonomous driving.

Lane Departure Warning System (1992)

The lane keeping technology was first introduced by Mitsubishi in the early 1990s with Mitsubishi Debonair. Later in the 2000s, other automakers including Toyota, Nissan, and Honda adopted it. This technology basically helps the driver to keep the vehicle in its lane, and would warn the driver when it moves out. It typically uses different sets of cameras and sensors. The technology senses the vehicle moving out of its lane and warns the driver using sounds and/or vibrations.

First Self-Parking car (2003)

In September 2003, Toyota started selling its new Prius hybrid gasoline-electric sedan in Japan with an automatic parallel parking capability. It was first commercial vehicle of its kind. The car could park itself without any intervention by the driver. It was demonstrated by then President of Toyota Motor Corp Fujio Cho. This intelligent park assists system was offered as an option with an additional cost of 230,000 yen (appx. 2000 Euro).

DARPA Grand Challenge (2004 – 2007)

Announced on 30 July 2002, the first DARPA (Defense Advanced Research Projects Agency) Grand Challenge held in Mojave Desert in the United States, mandated by the US Congress, had $1 Million of prize aimed to unman one-third of Armed Forces’ ground combat vehicles by 2015. It was an autonomous robotic ground vehicle competition with 150 miles of length. However, none of the vehicles travelled the whole length, the Red Team of Carnegie Mellon University travelled farthest completing 11.9 km. Hence, no team could claim the prize as they could barely reach 5% of the total distance.

picture_8
Red Team of Carnegie Mellon University, Source: DARPA website archived from 2004

The same year in June 2004, DARPA announced second grand challenge with 150 miles (212 km) off-road course with $2 million prize, double than the previous one. With lessons learned and improved vehicles, 23 final participants performed in October 2005. It was a challenging run that included three tunnels, more than 100 turns and navigating a steep pass with sharp drop-offs. The Stanford Racing Team won $2 million prize with the winning time 6 hours and 53 minutes followed by the Red Team of Carnegie Mellon University. Total five teams completed the competition.

This competition was said to be one of the founding stone in the development of autonomous driving as the goal of the competition was to make vehicles which could sense upcoming obstacles and follow the GPS waypoints. This advancement spurred interest and innovation, and results were encouraging enough to announce next challenge.

The Urban Challenge, the third installment in the series of the competition launched by Defense, was announced in May 2006 and was held on November 3, 2007, at the Former George AFB Victorville, California. Building on the success of the 2004 and 2005 Grand Challenges, this event aimed to build a vehicle which is capable of driving without a human driver in traffic, maneuvering complex situations like parking, passing, and negotiating intersections. This event was unique and truly groundbreaking as the first time autonomous vehicles have interacted with both, highly automated and conventional cars, in the traffic of an urban environment.

The competition was tougher this time with 60 miles (97 km) of urban course. It was won by “Boss” of Tartan Racing of Carnegie Mellon University with the average speed of 22.5 km/hr with a complex urban environment and driving time limited to a total of six hours. The DARPA director Mr. Tony Tether felt that autonomous driving technologies are robust and will ultimately save human lives in battlefields and on the roads as well. The big automotive and technology giants such as GM, VW, Caterpiller, Continental AG, Intel, Google etc. had sponsored participants’ teams.

The VisLab Intercontinental Autonomous Challenge (2010)

The university of Parma’s VisLab undertook the most daunting autonomous car journey started on 20th July 2010 from Parma and concluded on 28th October 2010 in Shanghai, crossing nine countries over 100 days and covering 15,926 km, known to be the first intercontinental driving test route.

Google’s Self-Driving Car Project (2009)

 Google’s Self-driving car, source: Google
Google’s Self-driving car, source: Google

This software giant launched its self-driving project in 2009 and has covered more than 2.1 million miles (3.38 million km), according to Google’s September 2016 report. The project was led by Sebastian Thrun, former director of Stanford Artificial Intelligence Laboratory and co-inventor of Google street view. Back in 2005, he and his team-mates helped Stanford to win $2 million DARPA challenge. However, Sebastian Thrun left the company to start his own ventures, his successor Chris Urmson lead the team later. Mr. Urmson, too, has left the project in August 2016.

Google’s driverless car uses data from Google Street View coupled with data from cameras, LIDAR and radar to determine the position of the car. The biggest edge that Google has on its competitors is, its street view mapping establishment. However, Google has been working on this project since last seven years and not been able to launch its final product yet. It seems it will take quite some time for Google to launch its driverless car commercially but it is not possible until 2020.

About Jayantraj Bhagyawant

Jayantraj Bhagyawant
Jayantraj Bhagyawant from Maharashtra is an independent researcher in the field of autonomous driving. He pursued higher education in Business Administration and Engineering (MBA&E) from University of Applied Science, Berlin. He has been living in Germany since five years and has worked in various companies including Audi. Being a mechanical engineer himself, his diverse technical and business expertise along with varied work and cultural experiences strengthened his competencies further.

Check Also

Autonomous Driving to drive Insurance Industry to plan in different mode

National Highway Traffic Safety Administration (NHTSA) say humans are the reason behind 90 percent of …

Leave a Reply