THE AUTONOMOUS FUTURE
DRIVERLESS MOBILITY
"The Anecdote Of Self-Driving Cars"
A journey covering a brief history of self-driving cars right from the first self-driving car to modern-day autonomous shuttles.
Not long ago, the word ‘Self-driving car’ seemed to be a Sci-Fi buzzword which when heard by commoners and even prominent techies, had a very similar response: “Interesting, but Impossible.” With advancements in Artificial Intelligence and machine learning techniques, the dream of driverless cars came closer to reality, with the response now changing to “Possible, But extremely difficult.”
With deep learning and computer vision revolution (The ImageNet challenge, 2011), the era of Self-driving cars had also begun. Fast forward to 2019… you will find Autonomous shuttles and Self-driving car services a common thing in cities like Palo Alto, Miami, Shanghai, Beijing, etc. prominently in countries like U.S., China, Singapore, etc.
With these technological revolutions, the number of companies working on self-driving cars and related services has also increased enormously. From Google’s self-driving car company Waymo, to big names like Uber, Intel, AMD, Baidu, IBM, Tesla, etc. are hustling hard in the field of self-driving cars.
Startups specifically targeting self-driving cars like Cruise, Zoox, Aptiv, etc. have emerged which spend their days and nights testing their technology and are continuously racing ahead in this competition.
The main motivation behind this development in which billions of dollars are invested is the promise of making driving safer and easier, to make travelling more productive and possible for people with physical disabilities, to increase profitability in shared mobility services thereby also reducing pollution, traffic jams and fuel consumption.
So although a driverless future seems just around the corner, it has been a long and arduous journey to arrive at this point. The dream of self-driving cars is almost as old as the automobile itself.
As early as 1925, Francis Udina demonstrated a remote control car called the ‘American Wonder’, which drove through the streets of Manhattan frightening passers by with an empty driver’s seat.
The dream was then kept alive with some early advances in Europe in the 1980s. Pioneers had been working on self-driving technology for over 40 years, with early vehicles mostly partially autonomous and operating at low speeds. In 1986, Ernst Dickens and his team from the University of Munich pioneered a robotic van that could drive fully autonomously without traffic, and in 1987, it drove at speeds up to 60 kilometres per hour.
In the year 1990...
So it was during the early 1990s, this same team contributed significantly to the Eureka Prometheus project, and developed an autonomous Daimler Benz using psychotic computer vision that focused on points of interest in the environment. They had over 50 transporters, the latest microprocessors of the day and used the same probabilistic approaches used throughout robotics, where it collected on-board sensor inputs and reacted to road situations in real time using that data.
Ultimately, the Daimler Benz drove 1,600 kilometers in traffic from Munich to Copenhagen with a mean human intervention distance of only 9 kilometers.
At the same time, Institutes like Carnegie Mellon, UC Berkeley were developing prototypes which could operate on road as well as off road, covering large distances with more than 98% of autonomous driving.
Turning Point in History
But the turning point in history is the year 2005, when Stanford’s Stanley, a self-driving car that was developed by Sebastian Thrun and team, successfully completed the DARPA grand challenge where the vehicle had to navigate 140 miles in a desert terrain autonomously, competing among 23 other teams.
Eureka Prometheus
Not long after that in the year 2007, Carnegie Mellon and General motor’s Self-driving car “BOSS” won the Darpa Urban challenge, which required the vehicles to carry out manoeuvres in an artificial urban environment.
These grand challenges were truly a watershed moment in the development of self-driving cars, changing the way the public and more importantly the tech and automotive industries thought about the feasibility of full vehicle autonomy.
Standford’s Stanley
Google then immediately bought the team leads from both Carnegie Mellon and Stanford, Chris Thompson, and Mike Monte-Carlo to push their designs onto public roads.
By 2010, Google's car had logged over 140 thousand miles in California and later wrote in a blog post how they were confident on cutting the number of traffic deaths by half.
Standford’s Stanley
Their pursuit of this ambitious goal continues to this day with the team having logged over 10 million miles as of October of 2018. Companies like GM’s Cruise, Zoox, Lyft continue to test their vehicles on public roads, with an aim to develop Fully Autonomous Ride. In Spite of this progress, there is a long way ahead for self-driving cars to fully gain people’s trust and to be at a technological level where they can function in any type of environment and in any condition.
The technology is still quite expensive, but the prices will fall quickly as economies of scale takeover. So much still needs to be done to bring about the transformational changes we expect driverless cars to bring to our society.
The industry requires outstanding engineers to produce innovative solutions, thereby creating an Autonomous future.
Mechatronics Engineer, Mumbai, India