How connected cars can make urban traffic safer and more efficient
Results of LUKAS research project presented

Ulm University
  • Bosch presents LUKAS project results together with Mercedes-Benz, Nokia, IT-Designers, InMach, Ulm University and the University of Duisburg-Essen
  • Cooperative behaviour planning increases safety and efficiency of automated driving in mixed traffic
  • Edge servers and sensors on street lights support cooperative behaviour in urban traffic

Stuttgart – There are many challenges currently facing the mobility sector: digital transformation, increasing urbanisation and automation, and the need for greater energy efficiency and climate protection. In the three-year research project LUKAS (acronym for “Lokales Umfeldmodell für das cooperative, automatisierte Fahren in komplexen Verkehrssituationen”, or “local environment model for cooperative automated driving in complex traffic situations”), the partners Bosch, InMach, IT-Designers, Mercedes-Benz, Nokia, Ulm University and the University of Duisburg-Essen are researching how to improve traffic efficiency and safety in future mixed traffic scenarios in urban environments. Here, reliable communication between automated and non-automated road users and the infrastructure plays a key role. This project was funded by the German Federal Ministry for Economic Affairs and Climate Action (Bundesministerium für Wirtschaft und Klimaschutz, BMWK) with 5.2 million euros within the scope of its programme for new vehicle and systems technologies.

Using data from the local environment to increase safety and efficiency

The LUKAS research project draws upon all the information available within the local environment to increase traffic efficiency and safety in future mixed traffic scenarios in urban environments. This includes information from infrastructure sensors and connected cars and commercial vehicles, but also from mobile devices such as smartphones used by passing pedestrians or cyclists. This concept delivers anonymised data from road users and stationary objects, such as position, dimensions, travel speed and direction of movement. The pre-processed sensor information is relayed to an edge server, which is directly connected to the 5G network near the intersection and provides data transmission with minimal delays.

A fusion algorithm on the edge server is able to create a comprehensive model of the local environment and use this as a basis for planning manoeuvres for connected road users. Object information from the server environment model is fed back to the road users. This expands their overview to include areas that they cannot themselves see. “The edge server calculates an optimised, cooperative manoeuvre using artificial intelligence, among other methods, and then sends instructions to the connected road users. This approach makes it possible to increase the overall energy efficiency of a traffic scenario as well as the safety of road users, in particular those who are vulnerable”, explains Dr Rüdiger Walter Henn, head of the LUKAS project at Bosch, the consortium leader.

LUKAS pilot station in Ulm suburb of Lehr

To run the trials, which took place in a public space in the Ulm suburb of Lehr, the consortium used a pilot station supported by the City of Ulm and operated by Ulm University. The designated area is comprised of an intersection with a right-of-way street turning off and side street leading in. The buildings in the area obscure the view of the right-of-way street, which makes this traffic situation particularly interesting for real traffic scenarios.  “This station provides us with outstanding opportunities to test the approaches we have researched and developed in real traffic situations, so that we can very quickly draw conclusions about their suitability for practical use”, explains Priv-Doz Dr-Ing Michael Buchholz, who heads the Electromobility and Connected Driving/Connected Infrastructure research teams at the Institute of Measurement, Control and Microtechnology at Ulm University. Dr Buchholz is also responsible for the pilot station.

The lampposts near the intersection are equipped with video, lidar and radar sensors to detect and classify the moving traffic. The object information is sent to the edge server via a 5G network operated by Nokia. For data protection reasons, people and vehicles cannot be identified. The edge server hosts the global environment model, several tested variations of cooperative manoeuvre planning and a warning module for pedestrians and cyclists.

Safer and more efficient on the road thanks to connectivity

To depict cooperative use cases in mixed traffic, Bosch, Mercedes-Benz and Ulm University are providing connected and partially automated passenger cars. InMach is contributing a connected prototype of a street sweeper. Special smartphone apps from IT-Designers GmbH and Nokia make it possible to connect pedestrians and cyclists with the edge server. IT-Designers collects data with a video drone to assist in the simulation of the traffic scenarios, and the University of Duisburg-Essen is supporting the project with traffic flow simulations.

All tested use cases verified the benefits of the LUKAS approach in terms of increasing traffic efficiency and safety.

Simulation results from AI-based planning algorithms lead the researchers to expect a significant increase in the flow of traffic. Studies by the partner Mercedes-Benz show a substantial reduction in fuel consumption as well as a reduction in the time required to pass through the intersection compared to conventional driving. Delaying oncoming traffic for cooperative behaviour ensures more safety when passing stationary vehicles or when vulnerable road users cross the street in areas with limited visibility. Thanks to the new technology and cooperative scenario planning, road users recognise early on which driving strategy will enable them to behave safely and efficiently.

The LUKAS project has made it possible for the consortium partners to gain insightful experience concerning connected, cooperative driving and incorporate this into the development of new products. The approach developed in the LUKAS project can help to make automated driving in mixed urban traffic settings safer and more efficient for all road users.

Press contact:
Jennifer Kallweit, Bosch spokesperson for automated driving, assistance and safety systems, brake and steering systems

Cyclist and commercial vehicle at the LUKAS project pilot station. Both are participating in a cooperative overtaking manoeuvre at the test intersection (Photo: Bosch)
Perspective from the interior of an automated vehicle at the LUKAS project pilot station. Also pictured are two other automated vehicles that are participating in a cooperative turning manoeuvre at the test intersection (Photo: Bosch)
Visualisation of some data from the automated vehicle. Light blue area: extremely precise map; cloud of white spots: measuring points from the lidar sensor; blue boxes: object information that is either self-detected or received via 5G; spheres in various shades of blue: marking the connected road users to distinguish them from non-connected users (Image: Bosch)