Level 3 Autonomous Vehicles Will Soon Be on the Roads
Have you ever dreamed about driving to your destination while watching a movie? How about texting your coworkers on your daily commute to work? Thanks to the latest developments in autonomous driving, this is no longer a fantasy. According to the latest reports, Mercedes-Benz is the first automaker to be allowed to legally build and sell such a vehicle. Let’s take a closer look at this exciting news since it brings us one step closer to fully autonomous vehicles on the road.
What Will the Newest Cars Be Able to Do?
According to Germany’s Federal Motor Transport Authority granted approval to Mercedes-Benz to become the world’s first automaker to have the right to enable Level 3 self-driving. The system is not yet used for driving in heavy traffic. Level 3 is known as conditional driving automation. It uses various driver assistance systems and artificial intelligence to make decisions based on changing driving situations around the vehicle. People inside the vehicle do not need to supervise the technology, which means they can engage in other activities. However, a human driver must be present, alert, and able to take control of the vehicle at any time, especially in the case of an emergency due to system failure.
Before we celebrate, let’s make two big footnotes to this story. Drive Pilot’s speed on the Autobahn is limited to 37 mph (60 km / h), so you can only use it in traffic jams. In addition, this feature only works in areas selected by Mercedes-Benz and the German government. (These geofenced areas are about 8,080 miles, or 13,000 kilometers.)
Thus, you cannot use speakerphone while driving on the Autobahn at 80 miles per hour. But you can get your hands off the wheel and play on your phone or make a sandwich in tight traffic. And this is very important – not only because sitting in traffic sucks, but also because it is a relatively safe and consistent environment for automakers to collect real-world data on autonomous driving.
Markus Schäfer, Member of the Board of Management of Daimler AG and Mercedes-Benz AG, explains how the manufacturer achieved this:
“For many years, we have been working to realise our vision of automated driving. With this LiDAR based system, we have developed an innovative technology for our vehicles that offers customers a unique, luxurious driving experience and gives them what matters most: time.”
Since LiDAR played an important role in allowing Mercedes-Benz to achieve such a high level of automation, let’s take a closer look at how this technology works.
What is LiDAR and How Does it Work?
LiDAR is an acronym for “light detection and ranging.” It is sometimes called “laser scanning” or “3D scanning.” The technology uses eye-safe laser beams to create a 3D representation of the surveyed environment. Basically, the laser beams that are sent out bounce off various objects and then return back to the LiDAR, which determines the distance between the object and the LiDAR. All of this creates a 3D Point Cloud, which is a digital representation of how the vehicle sees the physical world.
To better understand 3D Point Clouds, let’s take a look at the image below:
The above image is not only a 3D Point Cloud, but also includes point characterization. What this means is that the objects or areas closest to the car will be in blue, because this color has a short wavelength and objects that are far away will be in red, because it has a long wavelength. Such 3D Point Clouds need to be annotated with methods like semantic segmentation, labeling 2D/3D boxes so the AI system understands the world around it.
In addition to 3D Point Cloud Annotation, autonomous vehicles manufacturers need to annotate large quantities of images and many hours of videos to train machine learning algorithms. Mindy Support is one of the leading European vendors for data annotation and business process outsourcing, trusted by several Fortune 500 and GAFAM companies, as well as innovative startups. With 9 years of experience under our belt and 10 locations in Cyprus, Poland, Ukraine, and other geographies globally, Mindy Support’s team now stands strong with 2000+ professionals helping companies with their most advanced data annotation challenges. Contact us today to learn more about how we can help you.
January 27th, 2022 Mindy News Blog
Talk to our experts about your AI/ML projectContact us