相关论文: Who is Responsible? Explaining Safety Violations i…

As aircraft systems become increasingly autonomous, the human-machine role allocation changes and opportunities for new failure modes arise. This necessitates an approach to identify the safety requirements for the increasingly autonomous…

Computer-use agents have rapidly improved on real-world tasks such as web navigation, desktop automation, and software interaction, in some cases surpassing human performance. Yet even when the task and model are unchanged, an agent that…

As AI agents become more widely deployed, we are likely to see an increasing number of incidents: events involving AI agent use that directly or indirectly cause harm. For example, agents could be prompt-injected to exfiltrate private…

Reinforcement learning (RL) is an effective approach to motion planning in autonomous driving, where an optimal driving policy can be automatically learned using the interaction data with the environment. Nevertheless, the reward function…

Preventing collisions in multi-robot navigation is crucial for deployment. This requirement hinders the use of learning-based approaches, such as multi-agent reinforcement learning (MARL), on their own due to their lack of safety…

The Robot Operating System (ROS) is a widely used framework for building robotic systems. It offers a wide variety of reusable packages and a pattern for new developments. It is up to developers how to combine these elements and integrate…

Robotic systems are more present in our society everyday. In human-robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To increase action…

Generating safe behaviors for autonomous systems is important as they continue to be deployed in the real world, especially around people. In this work, we focus on developing a novel safe controller for systems where there are multiple…

Causal models of agents have been used to analyse the safety aspects of machine learning systems. But identifying agents is non-trivial -- often the causal model is just assumed by the modeler without much justification -- and modelling…

We provide a formal definition of blameworthiness in settings where multiple agents can collaborate to avoid a negative outcome. We first provide a method for ascribing blameworthiness to groups relative to an epistemic state (a…

Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations, including evaluator bias and detection failures arising from model homogeneity, which collectively undermine the robustness of risk…

Ethical dilemmas are a common challenge in everyday driving, requiring human drivers to balance competing priorities such as safety, efficiency, and rule compliance. However, much of the existing research in automated vehicles (AVs) has…

Autonomous cyber and cyber-physical systems need to perform decision-making, learning, and control in unknown environments. Such decision-making can be sensitive to multiple factors, including modeling errors, changes in costs, and impacts…

A central challenge for autonomous vehicles is coordinating with humans. Therefore, incorporating realistic human agents is essential for scalable training and evaluation of autonomous driving systems in simulation. Simulation agents are…

A significant amount of people die in road accidents due to driver errors. To reduce fatalities, developing intelligent driving systems assisting drivers to identify potential risks is in an urgent need. Risky situations are generally…

An open question in autonomous driving is how best to use simulation to validate the safety of autonomous vehicles. Existing techniques rely on simulated rollouts, which can be inefficient for finding rare failure events, while other…

Autonomous systems often operate in environments where the behavior of multiple agents is coordinated by a shared global state. Reliable estimation of the global state is thus critical for successfully operating in a multi-agent setting. We…

Autonomous multi-agent systems (MAS) are useful for automating complex tasks but raise trust concerns due to risks such as miscoordination or goal misalignment. Explainability is vital for users' trust calibration, but explainable MAS face…

We present a methodology for estimating collision risk from counterfactual simulated scenarios built on sensor data from automated driving systems (ADS) or naturalistic driving databases. Two-agent conflicts are assessed by detecting and…

There are many artificial intelligence algorithms for autonomous driving, but directly installing these algorithms on vehicles is unrealistic and expensive. At the same time, many of these algorithms need an environment to train and…