DSAI seminar with Hazem Torfah

Abstract

AI-based autonomous systems are increasingly relying on machine learning (ML) components to perform a variety of complex tasks in perception, prediction, and control. The use of ML components is projected to grow and with it the concern of using these components in systems that operate in safety-critical settings. To guarantee a safe operation of autonomous systems, it is important to run an ML component in its operational design domain (ODD), i.e., the conditions under which using the component does not endanger the safety of the system. Building safe and reliable autonomous systems which may use machine-learning-based components, calls therefore for automated techniques that allow to systematically capture the ODD of systems.

In this talk, we present a framework for learning runtime monitors that capture the ODDs of black-box systems. A runtime monitor of an ODD predicts based on a sequence of monitorable observations whether the system is about to exit the ODD. We discuss different methods for learning optimal ODD monitors, particularly the role of ensemble methods in reducing the bound on the misclassification risk of these monitors. We evaluate the applicability of our approach in a case study from the domain of autonomous driving.

About the speaker

Hazem Torfah is an Assistant Professor in the Computing Science Division at Chalmers University of Technology. He leads the lab on Safe and Trustworthy Autonomous Reasoning, supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP). Previously, he was a postdoctoral researcher in the EECS Department at UC Berkeley, USA. He received his doctoral degree in Computer Science in December 2019 from Saarland University, Germany. His research interests are the formal specification, verification, and synthesis of cyber-physical systems. He is one of the developers of the RTLola monitoring framework, which has been integrated into the ARTIS fleet of unmanned aerial vehicles in close collaboration with the German Aerospace Center (DLR). Hazem’s current focus is the development of quantitative methods for the explainability and runtime assurance of AI-based autonomous systems.

This is a seminar from the DSAI seminars series usually held every Monday at 14:00 by the Data Science and AI division. The seminars are usually hybrid. No registration is required.