AI-SEE will develop a novel sensing technology with associated AI enabling automated driving in all relevant weather and lighting conditions (e.g. snow, heavy rain or fog) in a 24h/365-day mode. Thereby, AI-SEE will extend the Operational Design Domain (ODD) of automated vehicles and extend the technology from today’s SAE level 3 (conditional automation) to SAE level 4 (high automation) where vehicles can drive themselves with no human interaction in almost any circumstances.

In the research project KI Wissen, methods for integrating existing knowledge into the data-driven AI functions of autonomous vehicles are being developed and investigated. 
By combining conventional data-based AI methods with the knowledge-based methods developed in the project, the basis for training and validating AI functions is completely redefined.

The VVM project is instrumental for the implementation of autonomous driving. Its success will have a decisive influence on the further development of this pioneering technology.

The project will develop methods to safeguard autonomous driving functions, and for the first time it will allow a quantitative assessment of the safety of these functions.

The work will use a modular approach which aims at making it possible to exchange individual components of the driving function without additional testing. On the one hand, the project therefore contributes to helping the general public better understand and accept autonomous driving and, on the other hand, it makes its implementation more easily manageable for the automotive industry.
 

The project KI Delta Learning aims to develop methods and tools for the efficient extension and adaptation of existing AI modules for autonomous vehicles. The developed methods will allow for the transfer of prior knowledge to new domains or more complex scenarios. Only additional requirements, the so-called deltas, are then to be learned with minimal development effort.