Multi-Fidelity Surrogate Model for Representing Hierarchical and Conflicting Databases to Approximate Human-Seat Interaction

It has been shown that working with databases from heterogeneous sources of varying fidelity can be leveraged in multi-fidelity surrogate models to enhance the high-fidelity prediction accuracy or, equivalently, to reduce the amount of high-fidelity data and thus computational effort required while maintaining accuracy. In contrast, this contribution leverages low-fidelity data queried on a larger feature space to realize data-driven multi-fidelity surrogate models with a fallback option in regimes where high-fidelity data is unavailable. Accordingly, methodologies are introduced to fulfill this task and effectively resolve the contradictions, that inherently arise in multi-fidelity databases. In particular, the databases considered in this contribution feature two levels of fidelity with a defined hierarchy, where data from a high-fidelity source is, when available, prioritized over low-fidelity data. The proposed surrogate model architectures are illustrated first with a toy problem and further examined in the context of an engineering use case in autonomous driving, where the human-seat interaction is evaluated using a data-driven surrogate model, that is trained through an active learning approach. It is shown, that two proposed architectures achieve an improvement in accuracy on high-fidelity data while simultaneously performing well where high-fidelity data is unavailable compared to a naive approach.