Autonomous Driving in the Smart City

Whenever complex situations arise, the autonomous vehicles of the near future will still require occasional human support. In such cases, remote assistance can be used: The staff of control centers will remotely help the autonomous vehicle with the next actions to be taken. In the closing event of the research project the real-time capable connection of autonomous vehicles to a remote point of support was demonstrated. The assistance of autonomous vehicles via a control center can be required in certain cases, for example to ensure the continuous availability of a vehicle fleet. A prerequisite for this assistance is however the transmission of high sensor data volumes from the vehicles and, if applicable, from the infrastructure sensors. In order to ensure this transmission also in a future smart city with a high number of connected units and thus a high communication traffic load, the FZI Research Center for Information Technology investigated and developed in its KIGLIS project various methods dedicated to autonomous driving. This includes AI-based compression methods for LiDAR and camera data. In combination with the network infrastructure of the project partners it was possible to give a successful demonstration of the explored methods on the Test Area Autonomous Driving. Furthermore, the FZI Research Center for Information Technology investigated methods for the detection of so-called corner cases, rarely occurring traffic situations with a need for remote assistance.