The usage of deep neural networks in safety-critical systems is limited by our ability to
guarantee their correct behavior. Runtime monitors are components aiming to identify …

Deep Reinforcement Learning (DRL) has made significant advancements in various fields,
such as autonomous driving, healthcare, and robotics, by enabling agents to learn optimal …

To certify UAV operations in populated areas, risk mitigation strategies-such as Emergency
Landing (EL)-must be in place to account for potential failures. EL aims at reducing ground …

With the increasing use of Machine Learning (ML) in critical autonomous systems, runtime
monitors have been developed to detect prediction errors and keep the system in a safe …

The behavior of neural networks (NNs) on previously unseen types of data (out-of-
distribution or OOD) is typically unpredictable. This can be dangerous if the network's output …

Deep neural networks (DNN) are increasingly used as components of larger software
systems that need to process complex data, such as images, written texts, audio/video …

Autonomous Driving Systems (ADSs) are complex Cyber-Physical Systems (CPSs) that
must ensure safety even in uncertain conditions. Modern ADSs often employ Deep Neural …

Failures of the vehicle camera may compromise the correct acquisition of frames, that are
subsequently used by autonomous driving tasks. A clear understanding of the behavior of …

Autonomous Driving Systems (ADSs) are complex Cyber-Physical Systems (CPSs) that
must ensure safety even in uncertain conditions. Modern ADSs often employ Deep Neural …

This paper explores the role and challenges of Artificial Intelligence (AI) algorithms,
specifically AI-based software elements, in autonomous driving systems. These AI systems …