Blog

In the first week of July, the University of Tartu Autonomous Driving Lab took part of the FOSS4G conference in Tartu. During the conference, Tambet Matiisen presented "Tartu: Pioneering the Future of Self-Driving Technology with Open Source and Open Data."

Self-driving vehicles promise safer, more affordable transportation. While driverless taxis operate in San Francisco, their global rollout faces significant challenges. Tartu, Estonia, is stepping up as Europe’s premier testing ground for autonomous vehicles, leveraging open-source software and open data to tackle legal and technological hurdles.

Estonia’s diverse seasonal conditions, adaptive legislation, and robust ecosystem of autonomous technology companies—such as Starship, AuveTech, Clevon, and Milrem Robotics—make Tartu an ideal testing hub. The University of Tartu's Autonomous Driving Lab is central to this effort.

Autonomous Driving Lab's vision for Tartu includes several key components:

• Designated testing zones for autonomous vehicles, encompassing both specialized closed areas and marked public city spaces.
• A comprehensive high-definition map of Tartu, featuring a detailed spatial point cloud and lane-level road network.
  
• A digital twin, or simulation, of Tartu, facilitating pre-arrival testing.
  
• Machine-readable traffic lights throughout Tartu, enhancing autonomous system safety beyond traditional light signals.

Open-source tools like QGIS, Shapely, Blender, and the CARLA simulator, along with datasets from the Estonian Land Board and the City of Tartu, are crucial for achieving high precision in high-definition map and digital twin, with decimeter-level accuracy.

The talk outlines how Tartu utilizes these open-source resources to become a leader in self-driving technology. You can watch the talk in this video; Tambet's presentation starts at 10:44.

Moreover, during the FOSS4G conference, the Autonomous Driving Lab set up an expo area where attendees could try driving in a Digital Twin of Tartu!