Nils Jansen’s research has a clear vision: Increase the trustworthiness of Artificial Intelligence (AI). Jansen’s research group conducts broad foundational and application-driven research. Their vision of neurosymbolic Artificial Intelligence combines the field of machine learning and formal methods, with a particular focus on formal verification. The team group tackles problems that are inspired by autonomous systems and planning problems in robotics. The following goals are central to Jansen’s group’s 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.
Jansen is interested in various aspects of dependability and safety in AI, intelligent decision-making under uncertainty, and safe reinforcement learning. A key aspect of Jansen’s research is a thorough understanding of the (epistemic or aleatoric) uncertainty that may occur when AI systems operate in the real world.
About Nils Jansen
Prof. Dr. Nils Jansen (1982, Simmerath, Germany) began his academic career at RWTH Aachen University, where he obtained a diploma in Computer Science. He continued his studies at RWTH Aachen University, where he obtained his PhD summa cum laude. He completed his PhD thesis Counterexamples in Probabilistic Verification, on finding bugs in systems that exhibit probabilistic behaviour, in 2015.
After obtaining his PhD in Aachen, Jansen moved to the United States to work as a postdoctoral researcher. Jansen spent just over a year at the University of Texas in Austin, before he started his tenure track position as an assistant professor at Radboud University. He worked at Radboud University full time for more than 6 years before he assumed his position as full professor at Ruhr University Bochum in Germany, where he also holds the position of chair of AI and Formal Methods. Additionally, he is a fellow of the European Laboratory for Learning and Intelligent Systems (ELLIS).
Nils Jansen holds several grants in academic and industrial settings, including an ERC starting grant titled Data-Driven Verification and Learning Under Uncertainty (DEUCE) and the NWA project Predictive Maintenance For Very Effective Asset Management (PrimaVera). Jansen has also organised numerous scientific events, including several Dagstuhl and Lorentz seminars, and he was program or area chair for several conferences both from the formal methods and AI community.