Subproject 1

AI Function

State-of-the-art algorithms for pedestrian detection will be developed, trained with synthetic data and made available to the other subprojects for the development and investigation of safety validation methods.

Subproject 2

Synthetic Data

A tool chain for the production of synthetic data is being developed that AI modules are trained and tested with. A prototypical data set is developed that allows for statements about the suitability of synthetic data as a substitute for real data.

Subproject 3

Methods and measures

Methods and measures to determine and reduce systematic insufficiencies of the AI function are developed, combined and evaluated with regard to their effectiveness on safety. Efficacy and safety metrics for AI algorithms are derived from these.

Subproject 4

Assurance Strategy

Formulation of a safety argumentation and exemplary demonstration and implementation of a methodology for the validation of the technical safety requirements and the sufficient mitigation of systematic insufficiencies of the AI function.

Subproject 5

Project Management

In addition to organizing the project and disseminating the results, the results will also be used in the exchange with standardization bodies to support the development of a standard for safeguarding AI-based function modules.

Facts and figures

Dr. Stephan Scholz
Volkswagen AG
Project coordinator
PD Dr. Michael Mock
Frauenhofer IAIS
Scientific coordinator and consortium co-lead
36 Monate
Project runtime
01 July 2019 to 30 June 2022
Project budget: €41 M
Funding budget: €19.2 M
24 project partners
4 external partners