New study uses mathematical analysis of walking patterns for early detection of Parkinson’s disorder.

What Drives Uber’s Self Driving Taxis?

December 10,2016
Read time: 6 mins

Photo: Siddharth Kankaria/ Research Matters

Imagine you call a taxi using one of the numerous cab aggregating apps and you find a “ghost” driver - well actually, no driver at all! If you think it is a page out of a science fiction, think again as Autonomous Vehicles (AV) or self-driving vehicles are already in operation in some cities of the world on a small scale. Nutonomy, a Singapore-based startup, became the world’s first company to test a self-driving taxi service in Singapore on August 25, 2016. Just a few weeks later, on September 14, 2016, Uber, the biggest cab aggregator service, launched its first self-driving taxi fleet in Pittsburgh, Pennsylvania, USA. You will hear more such news in the days to come as AVs are expected to replace conventional driver-driven vehicles by 2020 or sooner. A study by Business Insider estimates about 10 million self-driving cars to be on roads by 2020.

The market for AV is big and presently has automobile giants like BMW, Volkswagen, Daimler, Toyota and Tesla racing against each other to transfer the driving control from humans to computers. Google’s ambitious Self Driving Car project developed in collaboration with Stanford University was a game changer and won the US Defense Advanced Research Projects Agency (DARPA) Grand challenge in 2006. Today, Google's self-driving cars are found on the roads of California and Nevada and have logged 700,000 miles of accident-free autonomous driving. While companies like Tesla are developing a computer-based driver assistance system to help drivers avoid accidents, others are relying on the concept of a fully automated car, removing the need for a driver. Though this approach may take longer, this is considered a solid one on maturity. 

The quest for Autonomous Vehicles started with the need to fix the least reliable part of the car - the driver. Engineers around the world have built cars that are stronger than ever, and have equipped it with the best safety features - seat belts and airbags. Now, they are turning their attention to the most probable point of failure - the driver. A look at the statistics can emphasise the need for this - over 1.4 lakh people are killed in road accidents every year in India and about 93% of these accidents are caused due to human error. Computers, unlike humans, are near perfect drivers who do not doze off, never get drunk, are not fatigued and respond quickly.

Various experiments have been conducted on automating cars since the 1920s and the first truly autonomous car was realized in the 1980s at the Carnegie Mellon University's Navlab. Research picked up pace in the recent decade with the advent of improved machine learning techniques, better computing hardware and software, and more accurate sensor technologies. However, there are reports of collisions of such cars that have been termed as either a software failure or a misunderstanding. Google has confirmed that there have been 12 collisions of its self-driving cars as of 2015 with just one resulting in injuries to passengers in the car. On 14 February, 2016, a Google self-driving car struck a bus when it attempted to avoid sandbags blocking its path. Such crashes have been termed as “learning experience” by companies.

So, what “actually” drives these cars? The brain of the AVs is the algorithms that are programmed to function in a specific way based on Artificial Intelligence and Machine Learning. These algorithms, much like our brain, react based on the surrounding conditions. A self-driving car uses a GPS to know its location, a RADAR to detect obstacles, a laser ranging system to map the three-dimensional surrounding and a camera to identify traffic lights and signs, recognize pedestrians and monitor other vehicles on the road. There are also sensors that track weather and road conditions. All the data collected from the cameras, GPS, RADARs and sensors are fed to an on-board computer with a processing power equivalent to several desktop units, which maneuvers the car to its destination, avoiding people and other vehicles on the way. However, for rare events like a plastic bag blowing down the road or a ball bouncing on the road, the computer has to rely on the “knowledge” developed through millions of kilometres of test drives. This is where the learning part comes into play. Based on the inputs and the learning history, the computer decides the course of action thus, making the ride safe and reliable.

The advantages of AVs do not stop at that. AVs can then be sold as a service, just like cabs on the road, and no one would ever want to own a car of their own! This translates to reduced parking hassles and unnecessary garage space. In addition, we could use all the time spent on driving a car and waiting at the traffic lights, for doing what we actually want to do. This takes away the commute time from our lives and gives back free time to pursue hobbies or go outdoors for a sunset. These futuristic vehicles will also be eco-friendly with a 5%-15% reduction in fuel consumption and a comparable reduction in CO2 emissions.

However, not everything is rosy at the moment with self-driving vehicles. Though there is a push by several governments and industries for these vehicles, there are some ethical, legal and security issues that need to be addressed before we see a high adoption. Situations where a car has to decide between the lives of passengers and the person who is in front, are still unresolved and need a widespread debate among policy makers. Legal issues concerning accidents involving AVs as who should be blamed by law - the manufacturers, the passengers or the programmers, need to be charted out. As a ray of hope, some of these steps are in the right direction with the US Federal government drafting guidelines for automated vehicles and mulling a “pre-approval” for such cars. There is also a widespread skepticism about hackers taking over the control of the vehicle while someone is on board, literally hijacking the ride. Some anthropological studies have shown that some people attach certain emotions to their car and driving, some consider that a personal car symbolises status and driving gives them a sense of freedom, which cannot be fulfilled by autonomous cars.

At this point, not everyone might know how AVs might change their life, but there is a sense of excitement all around. Companies are busy conducting one trial run after another and refining the technology to get a buy-in from the masses. Policy makers are realizing that roads will be safer with computers driving us around rather than humans. But can a computer compete against humans? Only time can tell!