The joint project “Artificial Intelligence for selective near-real-time recordings of scenario and manoeuvre data in testing highly automated vehicles” (short: KisSME) investigates how artificial intelligence can bundle data for automated driving.
Large amounts of data are generated when testing highly automated vehicles. Equipped with various sensors, the vehicles record constantly while driving information about the own driving status, the environment, or the road. Based on this information, automated vehicles must be able to make reliable driving decisions in the shortest possible time.
The approach of the joint project KIsSME is to reduce and condense the accumulating data volumes with the help of AI-based algorithms to save storage space, electricity, and evaluation effort.
The aim of the joint project is to create catalogues of driving scenarios and to classify new scenarios that arise during vehicle testing. This means recording only those data during driving that actually add value.
In the joint project the Karlsruhe Institute of Technology (KIT) provides data from road trials and simulations carried out on the test area autonomous driving Baden-Württemberg among others.
The KIsSME-project is funded by the Federal Ministry for Economic Affairs and Energy with a total of 6,5 million €.
The Cluster Electric Mobility South-West, coordinated by the state agency e-mobil BW GmbH, supports the project as an associated partner and is pleased about the participation of numerous cluster members.
Project term:
Affiliated partners:
Associated partners: