It is no exaggeration to say that intelligent systems are rapidly changing the world how we know it. Particularly for image data, machine learning (ML) can handle high variability in high-dimensional data, leading to significant breakthroughs. In many commercial applications of ML, such as photo tagging and machine translation, errors can be tolerated. In contrast, applications in which flaws can have disastrous consequences, such as medical imaging and autonomous driving, have not yet been transformed by artificial intelligence.
Much research is focusing on using either machine learning or estimation. The aim of this group is to consider the bigger picture and focus on the more promising approach in the considered scenario. Further, we also consider combinations of learning-based methods and classical estimators to combine the adaptability and versatility of machine learning with the ease of modeling and low data requirements of classical estimators.
Projects
Role | Project Name | Funding Agency |
---|---|---|
Principal Investigator | Helmholtz AI Project 2019 ULearn4Mobility – Ubiquitous Spatio-Temporal Learning for Future Mobility. In cooperation with DLR Oberpfaffenhofen. |
Helmholtz Artificial Intelligence Cooperation Unit |
Member of the Technical Scientific Committee and the Scientific Steering Board | CC-King – Competence Center Karlsruhe for AI Systems Engineering AP 1.1 Safety of AI/ML-based Systems In cooperation with Fraunhofer IOSB and Forschungszentrum Informatik. |
Ministerium für Wirtschaft, Arbeit und Wohnungsbau Baden-Württemberg |
Co-author of the proposal and co-leader | Innovation competition "KI für KMU" Embedded AI in a Box In cooperation with Knowtion UG and Endiio Engineering GmbH |
Ministerium für Wirtschaft, Arbeit und Tourismus Baden-Württemberg |
Project leader | IGF project of the GVT e. V. IGF-Vorhaben Optische Schüttgutsortierer im dynamischen Einsatz. (Optical Belt Sorters for Dynamic Applications) |
Bundesministerium für Wirtschaft und Klimaschutz |
Researcher | IGF-Vorhaben der GVT e. V. Verbesserung optischer Schüttgutsortierung durch simulationsgestützte Entwicklung von Trackingverfahren. (Improving Belt Sorting Using Simulation-Driven Development of Tracking Algrotihms) |
Bundesministerium für Wirtschaft und Klimaschutz |