Deutsch
English
Modern software and system engineering is facing challenges due to increasing complexity and long project lifecycles. The integration of AI offers transformative opportunities to optimize processes and manage data. Our research group "AI for Software and Systems Engineering" focuses on the use of machine learning and Large Language Models (LLMs) to improve the development of embedded systems and software.
To ensure the safety and reliability of embedded safety-critical systems, innovative approaches are required to perform the validation process comprehensively and efficiently. Our research investigates the role of AI approaches in optimizing traditional test methods for hardware-in-the-loop (HIL) systems. Specifically, we develop ML and DL models to improve testing activities during real-time HIL validation in terms of test case generation, execution and evaluation. By combining innovative AI solutions with HIL testing during the development process, our research aims to improve the safety and robustness of these systems, taking into account the requirements of the ISO 26262 standard.
Our software engineering research focuses on the application of AI in the requirements analysis and architectural design of information systems. The integration of AI language models, i.e. LLMs, into the different phases of the development of software-intensive systems is a growing area of research and offers great potential to support developers in their tasks. The combination of AI techniques and formal methods creates a more systematic and automated approach that significantly improves the quality, efficiency and effectiveness of software development. The aim of research in this area is to develop innovative, practical and scalable solutions that change the entire software development process.
Our research group addresses the following research questions:
- How can AI-driven methods improve the efficiency and scope of the validation process for embedded safety-related systems in the context of ISO 26262?
- How does the combination of AI language models and formal methods improve the architectural design of information systems in terms of quality, efficiency and scalability?
By exploring innovative AI models and strategies to improve development workflows, our group aims to pave the way for smarter, more agile software and system development methods.
