How traffic data will enable new mobility services
To warn of dangerous situations, avoid traffic jams, make autonomous vehicles more intelligent, and analyze traffic: These are just some of the reasons why we need traffic data. It lays the foundation for new intelligent services.
Digital twins require enormous amounts of data. Whether digital information stems from radar, lidar, or camera systems: The position and speed of trucks, cars, and motorcycles are stored in the digital twin and can be anonymously retrieved and analyzed at any time. Service development is not about monitoring individuals, but rather about analyzing the overall situation, in which many vehicles and the stationary systems along the road communicate with each other and exchange data. The Providentia researchers have new services, application scenarios, and business models in mind. Drivers, highway operators, scientists, and car manufacturers all stand to benefit equally from these services in the future.
Here are some possible value-added services:
1. Warning of risk of collision and looking ahead
Providentia++ extends the capability of in-vehicle sensors through external information from sensor stations equipped with cameras, radars, and, in the future, lidars. This will enable drivers to react to traffic situations earlier than before. The more the infrastructure is expanded, the more predictable traffic will become.
2. Improving traffic flow
Connected vehicles are able to “understand” the current traffic situation and anticipate how traffic will develop. This also has consequences for conventional vehicles that are not yet equipped with sensor technology and do not have access to external traffic data through Providentia++. In the future, this connectivity can lead to autonomous vehicles on the highway changing lanes earlier when there are indications of slower traffic, and beginning to slow down even before the traffic volume increases. Taken as a whole, autonomous vehicles will therefore contribute to better traffic flow and ultimately enable more vehicles to travel along the highway in a given period of time. This increases the “throughput,” which is particularly relevant for highway operators.
3. Controlling traffic with autonomous vehicles
The observation of traffic between the overhead highway signs on the A9 generates a great deal of current movement and position data, which can be analyzed with the help of artificial intelligence (AI). From the behavior of the vehicles, the system learns which driving style is best for ensuring smooth traffic flow or avoiding accidents. The aim of the scientists is to find out how vehicles should be controlled in so-called mixed traffic, that is, in traffic with both conventional and autonomous vehicles.
4. Exchanging real-time data between vehicle and infrastructure
Vehicles, cameras, and radar systems all collect data on the highway. Taken together, this data provides a good picture of the current traffic situation. Car manufacturers and suppliers can use the data from the digital twin in their vehicles to conduct so-called real-world tests.
5. Analyzing traffic with autonomous vehicles
Because autonomous vehicles have an overview of the entire traffic situation and can react proactively, they change the traffic. This leads other drivers to adapt – to avoid frequent lane changes, for example, and to drive more slowly in order to stay in their lane.
FURTHER CURRENT TOPICS
Expanding the A9 test field: Improvisation required
Expanding the A9 test section for autonomous and connected driving required a great deal of research and pragmatic decision-making. Now that it has been accomplished and the scientists are at work, we look back at eight challenges and their solutions.
Connected car services with great potential
Vehicle connectivity and automation is becoming increasingly important in the automotive industry. Particularly high growth potential is expected for connected car services, according to a recent study by IW Consult and Fraunhofer IAO.
Predicting movements by autonomous agents
To predict movements, many trajectory options must be taken into consideration and prioritized. The FloMo model works with probabilities and has been trained on the basis of three datasets. Its performance is improved by a proposed method of stabilizing training flows.