Verifiable and Safe AI for Autonomous Systems

The rapidly growing application of machine learning techniques in cyber-physical systems leads to better solutions and products in terms of adaptability, performance, efficiency, functionality and usability.
However, cyber-physical systems are often safety critical, e.g., self-driving cars or medical devices, and the need for verification against potentially fatal accidents is of key importance.
Together with industrial partners, this project aims to develop methods and tools that will enable industry to automatically synthesize correct-by-construction and near-optimal controllers for safety critical systems within a variety of domains.