KIZAM – Artificial Intelligence in Target and Requirements Management

In the vehicle development process, requirements form the basis for all subsequent stages. The quality of the requirements in terms of unambiguity, completeness, and freedom from redundancy is crucial for the efficiency of the following steps of the development process. Increasing requirements due to new forms of drive or regulations lead to a disproportionate increase in the complexity of requirements management since each new requirement must be checked for interactions with the already large number of existing requirements. Classical requirements management methods are increasingly reaching their limits, which is why future development processes in vehicle construction can only be designed efficiently if demanding tasks are automated and time-consuming manual checks are reduced.

The aim of the KIZAM research project is to research the use of AI methods in requirements management. Firstly, this should make machine-readable, optimized, and consistent requirements available for digital vehicle development. In addition, AI enables fast and efficient matching of all relevant requirements data and recognizes interactions across requirements levels, process interfaces, and system boundaries, which can significantly increase the quality of the requirements catalog. The use of AI in requirements management is expected to accelerate the vehicle development process overall.