The newly founded chair of Artificial Intelligence and Formal Methods (headed by Prof. Dr. Nils Jansen) has a mission: Increasing the trustworthiness of Artificial Intelligence (AI).
We conduct broad foundational and application-driven research. Our vision of neurosymbolic AI brings together the areas of machine learning and formal methods, in particular, formal verification. We tackle problems that are inspired by autonomous systems, industrial projects, and planning problems in robotics.
The following goals are central to our efforts:
- Increase the dependability of AI in safety-critical environments.
- Render AI models robust against uncertain knowledge about their environment.
- Enhance the capabilities of formal verification to handle real-world problems using learning techniques.
We are interested in various aspects of dependability and safety in AI, intelligent decision-making under uncertainty, and safe reinforcement Learning. A key aspect of our research is a thorough understanding of the (epistemic or aleatoric) uncertainty that may occur when AI systems operate in the real world.
Another main focal point is research within the chair’s ERC Starting Grant Project "DEUCE: Data-Driven Verification and Learning Under Uncertainty". There will be freedom to shape the chair in an excellent research environment in close collaboration with Radboud University, Nijmegen, RWTH Aachen University, The University of Oxford, and The University of Texas at Austin. We publish regularly in the top venues and journals of Artificial Intelligence (AAAI, IJCAI, ICLR, NeurIPS, JAIR), Formal Methods (CAV, TACAS) and Control Theory (Transactions on Automatic Control). Our latest results can be found at https://nilsjansen.org/publications/.