Bosch and Volkswagen have come together to harvest real-time information for high-resolution maps. A continuous and seamless flow of information from real road traffic ensures map layers are always up-to-date and at present VW Golf 8s on Europe’s roads are helping create the Bosch road signature.
If cars are to drive on their own in the future, they will need highly accurate digital maps – and to know precisely where they are on those maps. Bosch says this is what its road signature offers: using information from radar and video sensors, as well as vehicle motion data, it augments common navigation maps with additional layers for vehicle localisation and control. These additional layers are compatible with typical map formats. Data is currently being generated to set up the road signature.
Starting in 2023, vehicles will feature the signature along with an initial number of services. Bosch plans to use current data to continuously expand the signature and keep it up to date. While the other map levels truly unfold their full potential especially in vehicles featuring Level 2 hands-free functions and higher, they also offer advantages at lower levels. “The more vehicles that provide information now and in the future, the larger and more robust the database will be for automated and assisted driving,” says Dr. Mathias Pillin, president of the Bosch Cross-Domain Computing Solutions division.
Digital twin of vehicle environment
Volkswagen is leading the way with the high-volume Golf 8 in Europe, with other vehicles to follow. While on the road, the vehicle fleet uses surround sensors to generate information about landmarks such as road signs, guardrails, curbs, and lane markings. The vehicles send the data completely anonymously via the VW cloud to the Bosch cloud. Furthermore, only the information that is required for the map layers is transmitted. The road signature is created in the Bosch cloud on this basis, producing a kind of digital twin of the real environment.
Thanks to the Bosch road signature, vehicles can determine their position with a high degree of accuracy: in real time, each vehicle compares the information currently provided by its surround sensors with that of its digital twin. This comparison enables the cars to accurately determine their position in the lane down to a few decimetres relative to the highly accurate map. The use of radar means that localisation works reliably even in adverse weather conditions such as fog, rain, and snow – conditions which make it difficult, if not impossible, for a camera to perceive its surroundings.
Natural driving behaviour of automated vehicles
In addition, the road signature enables safer and more convenient lateral and longitudinal guidance of automated vehicles, as it contains information not only about landmarks, but also about road geometry, lane layout, road signs, and speed limits. It even includes typical driving behaviour at specific locations: for instance, how do human drivers approach a curve? When do they step on the brakes before an intersection? What do they do when they change lanes prior to making a turn? To answer such questions, the service uses motion data such as speed, steering angle, and wheel speed. In the future, the road signature will provide vehicles with this information – and thus help make automated driving an experience that is as natural, comfortable, and safe as possible.