相关论文: The Perceived Danger (PD) Scale: Development and V…

The field of AI Control seeks to develop robust control protocols, deployment safeguards for untrusted AI which may be intentionally subversive. However, existing protocols that rely on weaker monitors to detect unsafe behavior often fail…

Robots have gained relevance in society, increasingly performing critical tasks. Nonetheless, robot security is being underestimated. Robotics security is a complex landscape, which often requires a cross-disciplinar perspective to which…

To design trustworthy robots, we need to understand the impact factors of trust: people's attitudes, experience, and characteristics; the robot's physical design, reliability, and performance; a task's specification and the circumstances…

Better methods to detect insider threats need new anticipatory analytics to capture risky behavior prior to losing data. In search of the best overall classifier, this work empirically scores 88 machine learning algorithms in 16 major…

Safety and performance are key enablers for autonomous driving: on the one hand we want our autonomous vehicles (AVs) to be safe, while at the same time their performance (e.g., comfort or progression) is key to adoption. To effectively…

Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider…

Drivers' perception of risk determines their acceptance, trust, and use of the Automated Driving Systems (ADSs). However, perceived risk is subjective and difficult to evaluate using existing methods. To address this issue, a driver's…

The predictive functions that permit humans to infer their body state by sensorimotor integration are critical to perform safe interaction in complex environments. These functions are adaptive and robust to non-linear actuators and noisy…

Deployment in hazardous environments requires robots to understand the risks associated with their actions and movements to prevent accidents. Despite its importance, these risks are not explicitly modeled by currently deployed locomotion…

We introduce a novel simulation-based approach to identify hazards that result from unexpected worker behavior in human-robot collaboration. Simulation-based safety testing must take into account the fact that human behavior is variable and…

Machine Learning (ML) models, such as deep neural networks, are widely applied in autonomous systems to perform complex perception tasks. New dependability challenges arise when ML predictions are used in safety-critical applications, like…

In this paper, we consider the problem of designing collision-free, dynamically feasible, and socially-aware trajectories for robots operating in environments populated by humans. We define trajectories to be social-aware if they do not…

As these attacks become more and more difficult to see, the need for the great hi-tech models that detect them is undeniable. This paper examines and compares various machine learning as well as deep learning models to choose the most…

Suicide is a critical global health issue that requires urgent attention. Even though prior work has revealed valuable insights into detecting current suicide risk on social media, little attention has been paid to developing models that…

The integration of foundation models (FMs) into robotics has accelerated real-world deployment, while introducing new safety challenges arising from open-ended semantic reasoning and embodied physical action. These challenges require safety…

Intelligent devices for supporting persons with vision impairment are becoming more widespread, but they are lacking behind the advancements in intelligent driver assistant system. To make a first step forward, this work discusses the…

Safe human-to-robot handovers of unknown objects require accurate estimation of hand poses and object properties, such as shape, trajectory, and weight. Accurately estimating these properties requires the use of scanned 3D object models or…

As the use of autonomous robots expands in tasks that are complex and challenging to model, the demand for robust data-driven control methods that can certify safety and stability in uncertain conditions is increasing. However, the…

Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges. Among the challenges, it is known that a rigorous, yet practical, way of achieving…

Robots must balance compliance with safety and social expectations as blind obedience can cause harm, while over-refusal erodes trust. Existing safe reinforcement learning (RL) benchmarks emphasize physical hazards, while human-robot…