BMW’s road map for autonomous driving

BMW plans to introduce a package for highly automated driving on motorways from 2021. The driver will only need to be able to take over control quickly if the system reports a problem.
“BMW’s autonomous test vehicles are already in action around the world. A fleet of 40 BMW 7 Series will be on the roads in Munich, California and Israel. Partially-automated systems are already installed in our vehicles today. In the BMW 5 Series, you can already take your hands off the wheel for a defined period of time. We are rolling these functions out across the fleet,” said Harald Kruger, Chairman of the Board of Management of BMW AG in a December 2017 release.
He added: “Autonomous driving will take the mobility experience to a whole new level. The display and operating concept with personalized information will play an important role. We launched the first ConnectedDrive services in the late 90s. We now have 10 million connected vehicles on the road. As of November, our customers can use Skype for Business and starting this December BMW Connected will also be integrated with the Google Assistant.”
Autonomous driving is graded from Level 0 to Level 5. At Level 0 the driver controls the car without any support from a driver assistance system, while at Level 5 all occupants are passengers and there are no controls. Level 3 “Highly Automated Driving”, level 4 “Fully Automated Driving” and level 5 “Full Automation” are still in the testing phase. BMW’s Personal CoPilot driver assistance system provides Level 2 support for drivers.
“Examples of this include the Active Cruise Control with Stop&Go function, which independently adjusts the distance to the car in front. There is also collision and pedestrian warning with city brake activation, which prevents collisions via automatic braking. The safety-auditing institute Euro NCAP honored this BMW feature as a ground-breaking innovation in the area of accident prevention and passenger protection by giving it the Euro NCAP Advanced Award,” says the company. Other semi-autonomous driving assistance systems already in the market include BMW’s steering and Lane Control Assistant and Traffic Jam Assistant. They can brake automatically, accelerate and, unlike Level 1, take over steering. Some models can park themselves. Level 4 is considered to be fully autonomous driving, although a human driver can still request control. The car can handle the majority of driving situations independently.
The technology in level 4 is developed to the point that a car can handle highly complex urban driving situations, such as the appearance of roadworks, without any driver intervention. The driver, however, must remain fit to drive and capable of taking over control if needed, but does not need to keep their eyes on the road at all times. BMW says that, unlike levels 3 and 4, the “Full Automation” of level 5 is where true autonomous driving becomes a reality: Drivers don’t need to have a license. The car performs any and all driving tasks – there is no steering wheel or controls. Cars at this level will clearly need to meet stringent safety demands, and will initially only drive at relatively low speeds within populated areas.
BMW, Intel, Mobileye and Fiat Chrysler Automobiles have formed an alliance to develop an autonomous driving platform for global deployment. The development partners intend to leverage each other’s individual strengths, capabilities and resources to enhance the platform’s technology, increase development efficiency and reduce time to market.
BMW, Intel and Mobileye formed the alliance in 2016 with the objective of bringing automated driving (Level 3) and fully automated driving (Level 4/5) into production by 2021. Since then, they have been designing and developing a scalable architecture that can be used by multiple automakers around the world, while at the same time maintaining each automaker’s brand identity. “The two factors that remain key to the success of the cooperation are uncompromising excellence in development, and the scalability of our autonomous driving platform,” said Kruger, in an August 2017 press release. Autonomous vehicles use a combination of technologies in order to steer and navigate. The foundation is laid by maps. BMW’s HERE mapping technology provides the high-precision digital road maps needed for autonomous driving. “Vision, although our most dominant sense, has its limits,” says Sanjay Sood, Head of Highly Automated Driving at HERE. “That cannot be the case with self-driving vehicles, however, which need to see through buildings, around corners and 20 miles in advance to maneuver safely.”
Autonomous cars “see” using a number of technologies, starting with optical cameras that provide information about the driving environment and traffic. They also recognize road signs and traffic lights. Radar and ultrasound that measure distances to other vehicles and objects in the vicinity. They are augmented by lidar, which creates a 3D image of the vehicle’s surroundings. Lidar also works in the dark and extremely bright light. The data from the three technologies is compared with the information stored in HD maps, which provide the car with pre-recorded details about the environment, including information outside the vehicle’s sensor range.
Maps are expected to retain their importance even as sensors become more powerful and intelligent. Road markings may become obscured, or a traffic sign may be covered or bent.
“We see the map as a sort of additional sensor,” says Klaus Buttner, BMW Group’s Vice President Projects Autonomous Driving. Buttner’s focus is on making vehicles so intelligent that, in automated mode, they behave correctly in every traffic situation. “We’re working with reinforcement learning. In other words, we play as many traffic situations as possible to the computer together with an assessment of those situations. Gradually, it develops its own understanding of which driving strategies are most suitable.” According to the experts at BMW, the algorithm is being trained. Maps will be updated in real-time with the assistance of Mobileye which is a global leader in vision-based advanced driver-assistance systems.
The idea is for BMW to provide realtime, camera-based information on the driving environment. The data is then aggregated at the back end and used to update the highly precise digital map. Crowdsourcing on the road would have huge advantages – as soon as the critical mass of vehicles with on-board sensors is reached, it will be possible to keep the map material up-to-date at all times. In other words, the map will achieve real-time capability.
But, despite the advances, driver controls are not due to go the way of the buggy whip any time soon. “Steering wheels will be around for a long time to come,” predicts Buttner. He also steers away from seeing the car of the future as a computer on wheels. Cars will still need to be robust machines that are safe and reliable even when they are not connected. “Cars will assist us on routes that we are not interested in experiencing as drivers. At first on motorways, then in urban rush hour traffic. But steering wheels will be around for a long time to come,” says Buttner.

r.

Hands-free driving behind the wheel of a BMW.

BMW’s Personal CoPilot driver assistance system provides Level 2 support for drivers.