| A + T |
Settled in Silicon Valley, an office unit houses the BMW Group Technology Office. Like many technology companies, it neighbors one of the biggest names in town, Google, in Mountain View.
It's no coincidence that BMW has an office in California. Not only does the State of California allow the testing of autonomous vehicles on the road, but many of the technology partners that BMW might look to work with are also located in California.
The aim of the Technology Office is to research and develop technologies, before passing them back to Munich for wider roll-out into BMW's future cars. One such example is the development of wireless Apple CarPlay which made its introduction on the BMW 5 Series in 2016.
Klaus Fröhlich, member of the BMW Board of Management responsible for development, has stated on several occasions that BMW's autonomous technology will be ready by 2021, there's a lot happening in this BMW's tech research office.
The R&D team in BMW's California office is utilizing a BMW 7 Series to perform their research; loaded with eight cameras, five Lidar systems and other sensors, with the boot/trunk of the car loaded with hardware to capture and process the information that the car collects.
The Lidar and camera systems mean that the car can see the environment it is travelling through. It can identify and track the motion of other vehicles and map the 3D world around it, so it knows where it is, where it's going and where everything else is going too.
Not only does the vehicle have all the wiring and sensors that the regular 7 Series would offer, but it has the full rig for BMW iNext, characterizing it for autonomous driving.
There are roughly 80 engineering test cars around the globe, gathering data on the roads and learning about driving in different locations. With so many sensors gathering data, it comes in at "a couple of terabytes per hour per car". But it's data that's essential for developing an autonomous driving policy and its data that informs the algorithm that will ultimately see the car making decisions.
THE HUMAN & AI INTERACTION
Much of what BMW is undertaking to develop its autonomous driving policy starts with simulation. You can't just have sentient cars careening all over the place learning by trial and error, so much of the work comes from a simulator. That gives BMW the opportunity to see what the car does when left to its own devices.
Essentially, driving the car is easy and many of those technologies are well established and available through existing systems like adaptive cruise control, lane guidance or automatic parking. However, when you get to level 3 autonomy, the car becomes "highly autonomous", in that it can basically do everything for you, which means negotiating things like junctions, overtaking, and changing lanes safely.
For these tasks, the vehicle needs to monitor all the other cars around it and be able to make predictions about what those vehicles will do. Inspecting the data captured from the vehicle, the potential routes that other cars could make are displayed, changing, in real time, when negotiating a junction. That's something the human driver does by scanning the mirrors and developing a sense through experience for how a driver might behave, before making a decision on what action to take.
This is where the data collected from those test cars becomes very important. Putting a human driver into the car in everyday situations means that "normal" driving behavior can be analyzed and compared to what the AI would do under the same conditions. Once there's alignment between the human driver and the AI simulation you're closer to a driving policy that will see autonomous cars behaving in a "normal" manner and that forms the basis for the self-driving algorithm.
In addition, autonomous cars will have to make decisions on the road. While there's a system of rules for driving on the road very often other drivers do unpredictable maneuvers, like pull an illegal u-turn or suddenly change speed or direction with no warning. These are challenges autonomous vehicles will need to deal with to be able to drive safely.
Machine learning means that cars could, potentially, learn for themselves but there's always the risk that a vehicle could learn bad behaviors. For this reason, data must be processed by BMW central before an algorithm change gets pushed out to the fleet, and this is how autonomous vehicles will get smarter, as behaviors and responses get increasingly refined.
Consequently, if you spot test cars out on the road they aren't necessarily driving autonomously waiting for human intervention, instead they are capturing the human driver's data to learn from decisions being made.
Although the development group is in California, its intensely aware that driving conditions aren't all the same. For instance, the four-way stop is characteristic of the US, while the roundabout is more common on European roads, for example. With test vehicles in several different locations, BMW is developing a solution that's aware of driving differences across the globe.
BMW iNext LAUNCHING 2021
Level 2 autonomy is getting relatively common. Tesla's Autopilot is typical of level 2, taking some of the load off the driver but legally one still always needs to be in control of the vehicle.
Level 3 autonomy is a concept that is very near. The Society of Automotive Engineers (SAE International) proposes that level 3 autonomy is "eyes-off" driving, suggesting you still must be in the driving seat, but not necessarily paying attention all the time.
There is a lot of research and development going across the industry. Hence, it’s one of the reasons BMW is open to the idea of collaboration and partnerships. Currently, Fiat Chrysler Automobiles (FCA) is the only vehicle partner that BMW has (granting that covers a lot of brands, from Fiat to Maserati).
This advocates the possibility that BMW's research won't be limited to the luxury cars that it's known for, but might one day be taking the weight off someone who drives a Fiat 500. BMW is open to wider collaboration, but there's yet to be further announcements.
It’s certain BMW's launch plan for level 3 autonomy is through iNext as it has repeatedly expressed to be ready in 2021. Whether we'll see it introduced through one new vehicle or across the whole group remains to be seen, but before we can let these vehicles drive themselves there will need to be local regulations established.
While there is confidence the technology will be in place within the next few years, the legal framework will be an entirely different aspect.
Tags: Autonomous Technology
