Search Results

Prevailing automotive development focus shifts towards passenger-centric development of vehicle systems. Comparative to autonomous driving development, the challenge evolves to describe all relevant driving situations with the necessary information and context to be able to develop and optimize vehicle systems to actual driving situations. The situational description or scenario, i.e., context or ambiance in which a vehicle is located, represents a fundamental factor in consideration of system behavior and respective system optimization opportunities. The challenge to solve the respective automotive engineering problems for nonlinear multidimensional parameter spaces or mixed integer classification problems is to describe and limit the possible solution space by suitable methodologies. Conventional methods prove inadequate solution as they can only be applied with significant financial resources and engineering time efforts, as known by autonomous driving system development.

Modern automotive development evolves beyond artificial intelligence for highly automated driving, and toward an interconnected manifold of data-driven development processes. Widely used analytical system modelling struggles with rising system complexity, invoking approaches through data-driven system models. We consider these as key enablers for further improvements in accuracy and development efficiency. However, literature and industry have yet to thoroughly discuss the relevance and methods along the vehicle development cycle. We emphasize the importance of data-driven system models in their distinct types and applications along the developing process, from pre-development to fleet operation. Data-driven models have proven in other works to be fast approximators, of high accuracy and adaptive, in contrast to physics-based analytical approaches across domains.