How 'swarm' data generates live maps to improve safety | Automotive News Europe

RENNINGEN, Germany -- Connected map services are helping automakers to enrich in-car mapping using sensors and “swarm” data. This data is then transferred into the clouds of software-defined vehicles (SDVs) to provide real-time driving information and increase safety and drivability.

“Connected maps are an extremely important part of the swarm data concept,” Pedro Pacheco, vice president of research at Gartner, said in an interview. “This kind of concept is definitely the future. It will bring major benefits” for automakers, he said.

Such vehicle intelligence starts with swarm data collection – in other words, crowdsourcing data from as many vehicles on the road as possible. The data extracts insights, which go to the cloud to enhance vehicles’ intelligence. These insights enhance the performance of various systems, such as ADAS or navigation.

Volkswagen is among automakers using swarm data for ADAS systems. The automaker's Travel Assist ADAS system, introduced in 2022, positions the vehicle in its lane and maintains speed, using such data if available.

Creating a virtual sensor

Connected maps provide the cornerstone of swarm vehicle intelligence. For example, Bosch’s connected map services use swarm data in combination with other data sources from a vehicle’s infrastructure to provide a virtual sensor for use in driver assistance systems. The map sensor aggregates real-time data on to four different map layers, which provide information to connected vehicles.

“We are generating live maps using the car’s intelligence and this is really revolutionary,” Thomas Classen, project leader, Bosch Automated Driving Alliance, said at a recent Tech Day at the company headquarters in Renningen, Germany. “The car sees what is around it and gives a very precise localization.”

The four map layers include a planning area layer, with road line geometry and info-like traffic lights, as well as a behavioral map layer with swarm trajectories, showing the optimal driving speed. “This answers the question how a human would behave in any certain situation,” Classen said.

Key benefits include a reliable map sensor in all weather conditions. This looks ahead far beyond the sensor range and compensates for a driver’s obstructed line of sight.

Multiple carmakers, which Bosch would not identify, supply the data, allowing the German supplier to move closer an open map ecosystem. So far, two billion kilometers’ worth of data has been harvested since January 2021.

The map to the future

Enabling vehicles to collect data to automatically update maps is “a powerful concept that can even lead to many more things,” Pacheco said.

For example, standard navigation systems provide traffic updates to let drivers know if there is a traffic jam or an accident up ahead. But the information often arrives too late to change course. However, if for example there is an accident on the motorway, then a car driving in the opposite direction can capture that accident with its cameras and share that insight with the rest of the fleet so that a driver has more time to avoid that stretch of road.

Likewise, if a road surface has become dangerous due to bad weather, then a vehicle can share this insight to provide a real-time update. These insights are all linked to a map’s location.

While some automakers are now starting with basic swarm data collection, others already have “a good grip on this,” Pacheco said. They include Tesla, which is skilled at using computer vision to identify situations using a vehicle’s cameras.

“In short, this is an area where OEMs have in general already realized there is potential,” Pacheco said.

Please enter a valid email address.

Please enter your email address.

Please verify captcha.

Please select at least one newsletter to subscribe.

You can unsubscribe at any time through links in these emails. For more information, see our Privacy Policy.