Our research primarily focuses on integrating machine learning (ML) into safety-critical applications and advancing MLOps (Machine Learning Operations), which encompasses the development, deployment, and operation of ML systems. This approach facilitates data-driven innovation by leveraging standardized development processes and automated quality assurance mechanisms. Furthermore, we place particular emphasis on validating ML and generative AI (GenAI) solutions to mitigate risks such as limited robustness, hallucinations, or unethical outputs. These challenges are addressed through systematic risk analyses, targeted countermeasures, and the implementation of robust safety architectures.
Our team specialises in defining architectures, communication infrastructures, exchange formats and processes for the automotive and rail industry, in particular using the AUTOSAR standard. In combination with model-based development, we use innovative methods that promote both efficiency and quality. These approaches allow for the precise validation and verification of safety-critical software and contribute to compliance with international standards and best practices in functional safety.
Another focus is on supporting software development with generative AI. With the help of AI-supported tools, we automate development and testing processes, increase efficiency and facilitate the handling of complex systems. This enables our customers to concentrate on creative and strategic tasks while recurring tasks are optimised by generative AI.
With many years of experience in standardisation, particularly in AUTOSAR and ETSI, as well as in the implementation of standards and certification processes, we support our customers throughout the entire development cycle. Our projects always operate at the interface between industry-oriented research and practical application in order to achieve the best possible results for companies.