Why 5G and Edge Computing will Boost the Development of Autonomous Cars

The automobile industry is experiencing exponential growth of self-driving features, and this trend is expected to continue. 5G network connections will have a major influence on the development of self-driving cars, making them faster, smarter, and safer.

The momentum for the realization of autonomous vehicles in mainstream use is reaching critical mass. Companies such as Tesla and Toyota are now testing self-driving vehicles on the roads in places like Pittsburgh, Boston, and Phoenix. And the same is happening in Europe, where Zenuity, the joint venture of Volvo and Veoneer, has been granted permission to test its self-driving systems on the public roads in Sweden.

With self-driving features already in widespread use, it stands to reason that fully autonomous cars will be appearing on our roads, and perhaps sooner than people realize. Even more surprising, they will also be considered much safer than human-controlled vehicles.

Vehicle-to-everything

The telecoms industry envisions autonomous cars equipped with hundreds of sensors collecting and receiving information all at once over a network. This concept is called "Vehicle-to-everything" (V2X), a developing communication platform that leverages LTE and, in the future, 5G communications.

To achieve this, the car needs to detect blind spots and avoid collisions with people, animals or other vehicles on the road. As the car drives, its sensors will also pick up information about weather, accidents, road conditions, etc.

Once this information is gathered, either an on-board computer will make an instant decision or the data may be sent into the cloud to be processed, and then a decision would be sent back to the vehicle.

A truly automated car that can communicate instantaneously with its surroundings is still a prospect for the future, but to get a better understanding of the road to true vehicle automation, the US engineering organisation SAE International has set out six categories:

• Level Zero: not automated at all
• Level One: some driver assist features
• Level Two: car can accelerate and steer by itself, but driver must pay attention
• Level Three: car can drive by itself on safe road conditions under 37 mph or 60 km/h, but driver is still needed
• Level Four: car can drive completely by itself, but only within a well-mapped area
• Level Five: car can drive completely by itself, over any terrain, anywhere in the world

Research firm Gartner expects Level Three and Level Four autonomous vehicles to gain a foothold during 2019 in very small numbers, and by 2025, it expects that there will be more than 600,000 autonomous vehicles on the roads worldwide.

How will 5G support autonomous cars?

Self-driving cars use hundreds of sensors to make vehicles faster and smarter. These sensors generate unprecedented amounts of data, much more than any other IoT application would. Handling, processing, and analysing this amount of data requires a much faster network than the existing 4G technology.

However, the fifth-generation of wireless technology is expected to connect almost everything around us with an ultra-fast, highly reliable, and fully responsive network. 5G will allow us to leverage the full potential of advanced technologies such as artificial intelligence, virtual reality and the Internet of Things (IoT).

While wireless devices and smartphones will receive most of the attention when it comes to developing 5G, the communication protocols for vehicles will be impacted significantly and usher in a new era of car-to-car communications.

When it comes to autonomous vehicles, the speeds and data processing capabilities needed to mimic the timing of human reflexes (2 milliseconds) are incredible. Experts also believe the future self-driving car will generate approximately two petabits of data – the equivalent of two-million gigabits. Even with an advanced Wi-Fi connection, it would take 230 days to transfer a week’s-worth of data from a self-driving car. That is why ultrafast 5G networks will be crucial to continuously process these huge amounts of data at an split-second pace.

Driverless cars are just one of the many incredible technologies that are likely to be ushered in with 5G. It will present exciting possibilities for the automobile industry used for vehicle-to-vehicle (V2V) and vehicle-to-everything (V2X) connectivity. Furthermore, the technology’s low latency will make these vehicles extraordinarily safe and reliable on the roads – safer than vehicles today that are operated by people.

Driving on the Edge

Along with 5G, edge computing will push the development of automated vehicles and allow for faster response times (thanks to the lower latency), the ability to offload computing tasks (which in turn reduces energy consumption) and better location awareness, among other benefits.

Offering a range of advantages, edge computing is recognized by many experts as one of the latest significant enterprise trends. Edge computing helps automated vehicles achieve situational awareness. It improves reliability, availability and quick recall of data – which can be challenging with centralized cloud processing, and further worsened through clogged or erratic networks. Multiple smaller processors spread throughout the vehicle handle the inputs from various systems such as video stream data, and categorise information and behaviour from metadata and context.

Then, encrypted text is used to detail the object and coordinates and sends it wirelessly or via secure physical connection to the computer, which can make higher level decisions. But a delay in the transmission, analysis or relay of a decision back to the vehicle can have grave consequences. This is the reason why edge and 5G need to be mutually dependant of each other to make significant headway for automated technologies in cars.

With the advent of autonomous cars comes the responsibility of managing the infrastructure which processes massive amounts of unstructured data and provides privacy protection when collecting sensitive data at the edge. Edge computing will allow lightning-fast response time because of 5G’s promise of lower latency and ability to offload computing tasks and better location awareness.

Part of a bigger picture

If you are concerned about driverless cars on the road, think about the evolution of smartphone devices over the past few decades. At one point, you probably couldn’t fathom being able to make a call to someone on the other side of the world from a pocket-sized device. Today, you can’t imagine a day without the ability to connect to friends, family, and colleagues around the world using your mobile phone.

Technology and network evolution bring incredible and useful advancements to society. 5G’s promises to usher in safer and smarter self-driving cars will be one of the most remarkable developments of our time. Virtual reality, smart cities and artificial intelligence all sit on the cusp of major breakthroughs—they just need the data networks to catch up.