Artificial Intelligence


(ROOM: Business Stage)

Validation of AI and AI for validation

In the form of machine learning, AI presents the indispensable technology for the development of autonomous driving functions. The validation and successful implementation therefore hinges on the availability of training data and the effectiveness of the training depends on both the quantity and the quality, i.e. diversity, of test scenarios. To validate AI-based functions, and to thereby reach the necessary safety levels that can foster user acceptance, practical driving experience must be supplemented with driving simulations. The availability of training data can be greatly improved through active data exchange or the use of shared and open platforms.
In the preparation/extraction of these training sets and scenarios, AI techniques are also required for the analysis of collected and shared Big Data, e.g. for the annotation of raw data.


Arpad Takacs, AImotive
Philipp Slusallek, DFKi


Hala Elrofai, TNO


Print Friendly, PDF & Email

By continuing to use the site, you agree to the use of cookies. more information

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.