Self-driving vehicles (SDVs)–above the SAE automation level 4–are designed to operate
without human intervention [1]. Due to the expected advantages attributed to SDVs, such as …

This work gives a logical characterization of the (ethical and social) obligations of an agent
trained with Reinforcement Learning (RL). An RL agent takes actions by following a utility …

Deep neural networks exhibit excellent performance in computer vision tasks, but their
vulnerability to real-world adversarial attacks, achieved through physical objects that can …

Ensuring ethical behavior in Artificial Intelligence (AI) systems amidst their increasing
ubiquity and influence is a major concern the world over. The use of formal methods in AI …

This paper provides a set of cut-free complete sequent-style calculi for deontic STIT ('See To
It That') logics used to formally reason about choice-making, obligations, and norms in a …

Due to unavoidable accident risks, decisions in the motion planning of autonomous vehicles
have a complex moral component. Decisions previously made by humans will be executed …

In this dissertation we investigate how to reason about an autonomous system's obligations.
In particular, we explore how to verify, elicit, and enforce rules about how a system should …

We present an initial proposal for a testing framework for ethical decisions in autonomous
agents, based on the well-known perception-action model. We identify three main …

A Complete Bibliography of ACM Transactions on Cyber-Physical Systems (TCPS) Page 1
A Complete Bibliography of ACM Transactions on Cyber-Physical Systems (TCPS) Nelson …

As autonomous systems become more ubiquitous, the ability to represent and reason about
their behaviors becomes more important. Normative autonomous systems are those systems …