Autonomous Cars and Artificial Intelligence (AI)

On a daily basis, people worldwide spend a big portion of their day moving from one place to another. Shouldn’t it be easier and safer to go wherever we want to go? In the last decade or so, researchers, scientists, and tech companies have put in so much effort to develop fully self driving technology. This technology has also been tested on real streets in real cities.

Self driving cars aren’t a science fiction anymore. Companies like Toyota and Ford have dedicated billions of dollars in Research and Development for this technology. Services like Uber and Lyft, who currently pay humans to drive, would soon deploy an entire fleet of self driving cars. In a few years, we would see self driving cars being sold to regular consumers. But there is still a fear surrounding it. Perhaps it's because most people don't know how they work. So let's start there!

How do they work ?

When we humans are in the driver’s seat, we are observing our environment by simultaneously receiving an input of our surroundings and processing it in order to make a decision on which way to turn the steering wheel and when to step on the brake. A self driving car is usually outfitted with GPS Unit, an inertial navigation system, and a range of sensors. It uses the positional information from GPS and navigation system to localize itself and the sensor data to build an internal map of its environment. Once it has its position on the internal map of the world down, it can then use that map to find the optimal path, which would avoid all kinds of obstacles, to its destination. What I just described is a very high level description of how self driving cars work.

Why Self Driving Cars at all ?

There are couple of reasons for their existence, let us take a look at each of the reasons:

1. Economics:

Utilization:

Cars are seriously underutilized. In most cases, a car is only utilized 4% of the time, while the rest of the 96%, it is parked in parking lot. A car is one the biggest investments people make but still, it is underutilized. So, we have a very expensive equipment available to us that is underutilized most of the time.

Cost:

If we look at services that offers mobility on demand, such as Uber, Lyft, etc., and analyse the cost per kilometer, the driver makes up for 50% of the cost. If you remove the driver out of the loop and if you move to electric fuel as well, the cost per kilometer reduces significantly.

2. Add On Services :

There is also another dimension to it that pulls tech companies into it. Since most cars have passengers in it that are not engaged in driving, you can start thinking about sending them contents. You have sensors in the car, which can track what you are talking about and can talk back to you. It can send you suggestions like where you have have a good coffee or some good food on your route, or it can show you discount offers on items being sold in shops on that route etc. Tech companies can provide multiple similar services and derive an economic value out of it while collecting data about the passengers.

3. Artificial Intelligence (AI) :

There is a consensus amongst most technological players in the world that artificial intelligence, AI, is going to have a very major impact on the economy in the near future, roughly 5 to 10 years from now. It is agreed that there is a need for companies to invest a lot more in developing AI, but the ultimate question is: What would the business model for AI look like? Robotics is one thing that comes to mind, but its market is not big enough to justify such a big investment. Chatbots may be another market, yet again, it’s not a big enough market to justify these big investments (which can run into billions of dollars to develop). But when we think about cars, it has a huge market and caters to virtually any human being. It is an ideal platform for AI because if you want to have a self driving car, you would need sensors that understand the world at perception levels that are very close to that of humans and understand driving negotiations as to how we merge into traffic. In short, we would need a car that can be considered a competitor to human intelligence. So, here we are, figuring out serious artificial intelligence use cases along with the business model. Since we now have a business model that may attract billions of dollars annually, worldwide, it makes total sense to develop AI.

That is why self driving car is becoming such a huge industry. It makes mobility on demand very attractive. Any organization that is into software development, be it startups, companies like Uber, Google, Tesla, Apple, or any company in the automobile industry, has started working towards positioning itself as a player in the self driving cars segment.

Artificial Intelligence in Self Driving Cars:

Lets us try to understand what is the kind of AI that we need when it comes to self driving cars and why it is exciting from a technological point of view. In order to enable a car to drive on its own, we need to cover three technological pillars:

1. Sensing:

Let's start with humans: We all have senses such as seeing, hearing, and touching, all of which collects signal, which are then sent to the brain and directs our bodies to take certain actions. In the same way, we need to enable self driving cars to have sensors that cover 360 degrees using cameras and sensors for redundancy like radar scanners. The laser scanners then take the data from all these sensors and go through a very powerful high-performing computing device in order to build an environmental model that can:

• tell where all the entities around the car are, such as pedestrians, cyclists, road turns, signals, symbols, barriers, etc.
• tell what these entities are doing or what their statuses are,
• tell about the path, such as if this path is a highway.

Sensing is a complicated area but it is still the easiest of the three.

2. Mapping:

Mapping should not be confused with navigational map (Google map). Instead, they are maps that are high definition and are very detailed. Once you position your vehicle inside this map at a very high accuracy (in the range of 10 cm), you know everything about the roadway, the drivable paths, the delimiter, etc., the only thing that you don’t know about is where the road users are. That data is provided by sensing. So, how do you create and update these maps in efficient and cost effective ways? These maps should reflect reality in a very short time, which means, the moment these environments change, the map must be updated immediately – today's maps are not updated at such a fast rate. This brings up the topic of using crowdsourcing to build maps. This is a very hard thing to do, but it's very much necessary. Without these detailed maps, you cannot reliably propel a self driving car.

3. Driving Policy:

This is where serious intelligence needs to be embedded into the driving platform. The car must be able to tell what pedestrians and other vehicles look like and what they're doing. Not only so, self driving car must understand driving policy, which is mostly about negotiation. It is all about building a strategy as to when we can merge into traffic lanes. Mind you, this skill does not come naturally to us — it often takes both driving lessons and driving experiences. This is a sophisticated negotiation and since it is already difficult for humans, it is going to be even more difficult for computers, because we are talking about broad intelligence which involves understanding which vehicles to give way to, which vehicles to take the way from, what roads are often used to merge into traffic. Also, driving policy changes according to locations because traffic negotiation differs from city to city. This has to be taken into consideration when the driving policy is being fed to the system.

Self Driving as Multi Agent System:

Self Driving can be thought of as a multi agent system. It's actually like a game because we are strategizing, making decisions that are potentially rewarding – just like playing chess, we can sacrifice a point knowing few steps later, we will take the queen.

Evolution of Self Driving Cars Industry:

The period from 2015 to 2017, Driving Assist have been used. Driving Assist is a technology used to prevent accidents. This technology has been used to help a hands-free vehicle stay in lane. With this technology, the driver still needs to stay alert. It is not really autonomous driving because the system can make mistakes. It doesn’t have 360 degree awareness. It doesn’t see everything. It is not designed to add all possible crash situations, which is why the driver needs to stay alert.

Starting from 2018, we will be talking about Highly Autonomous Driving. These are real hands-free driving with limited scenarios, where it only works on major highways. Highly autonomous driving means that the driver does not have to have his or her eye on the road. The system will provide a grace period, between 10 to 30 seconds, for the driver to take over – if the driver doesn't, the system will know how to safely move the car aside and stop it.

The real action starts in 2021. What we'll be seeing is the so called Fully Autonomous Driving. It is also know as "level 4 autonomy," where cars can drive in cities and provide mobility on demand, kind of like Uber without a human driver.

Hope this article gives you a basic understanding of how self driving cars work and how artificial intelligence is opening more doors of opportunities for developers to build add-on applications around autonomous cars.