Nils Jansen.
I am a Full Professor of Artificial Intelligence and Formal Methods at Ruhr University Bochum, Germany, and Professor of Safe and Dependable AI at Radboud University Nijmegen, The Netherlands. My research focuses on AI safety, trustworthy and reliable autonomous systems, and formal verification for machine learning.
My research sits at the intersection of AI safety, trustworthy AI, formal verification, and autonomous systems. As head of the Chair of Artificial Intelligence and Formal Methods, my mission is:
Increase the trustworthiness of Artificial Intelligence (AI).
We conduct broad foundational and application-driven research on neurosymbolic AI, combining machine learning with formal methods — with a particular focus on formal verification — to make AI systems safe, robust, and dependable. Our work is inspired by real-world challenges in autonomous systems, robotics, and planning under uncertainty.
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 work on safe reinforcement learning and decision-making under uncertainty (including POMDPs and MDPs). A key aspect of our research is a thorough understanding of the epistemic and aleatoric uncertainty that may occur when AI systems operate in the real world.
Read more at the webpage of my group(s), or at the official website of our chair at Ruhr University.