Related papers: Hazard Analysis for Self-Adaptive Systems Using Sy…

Autonomous emergency steering (AES) systems have the promising potential to further reduce traffic fatalities with other (potentially vulnerable) traffic participants by using relatively small lateral deviations to realize collision-free…

Testing autonomous driving systems for safety and reliability is extremely complex. A primary challenge is identifying the relevant test scenarios, especially the critical ones that may expose hazards or risks of harm to autonomous vehicles…

Cyber Physical Systems (CPS) enable new kinds of applications as well as significant improvements of existing ones in numerous different application domains. A major trait of upcoming CPS is an increasing degree of automation up to the…

This paper concerns the risk-aware control of stochastic systems with temporal logic specifications dynamically assigned during runtime. Conventional risk-aware control typically assumes that all specifications are predefined and remain…

Hamilton-Jacobi (HJ) reachability analysis is a powerful tool for analyzing the safety of autonomous systems. However, the provided safety assurances are often predicated on the assumption that once deployed, the system or its environment…

This paper targets control problems that exhibit specific safety and performance requirements. In particular, the aim is to ensure that an agent, operating under uncertainty, will at runtime strictly adhere to such requirements. Previous…

This work addresses the question whether it is possible to design a computer-vision based automatic threat recognition (ATR) system so that it can adapt to changing specifications of a threat without having to create a new ATR each time.…

Each new concept of operation and equipment generation in aviation becomes more automated, integrated and interconnected. In the case of Unmanned Aircraft Systems (UAS), this evolution allows drastically decreasing aircraft weight and…

Runtime uncertainty such as unpredictable resource unavailability, changing environmental conditions and user needs, as well as system intrusions or faults represents one of the main current challenges of self-adaptive systems. Moreover,…

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a…

Self-adaptive robotic systems operate autonomously in dynamic and uncertain environments, requiring robust real-time monitoring and adaptive behaviour. Unlike traditional robotic software with predefined logic, self-adaptive robots exploit…

Fault detection is essential in complex industrial systems to prevent failures and optimize performance by distinguishing abnormal from normal operating conditions. With the growing availability of condition monitoring data, data-driven…

We present a novel technique for solving the problem of safe control for a general class of nonlinear, control-affine systems subject to parametric model uncertainty. Invoking Lyapunov analysis and the notion of fixed-time stability (FxTS),…

Test-time adaptation (TTA) has emerged as a promising solution to tackle the continual domain shift in machine learning by allowing model parameters to change at test time, via self-supervised learning on unlabeled testing data. At the same…

A runtime assurance system (RTA) for a given plant enables the exercise of an untrusted or experimental controller while assuring safety with a backup (or safety) controller. The relevant computational design problem is to create a logic…

Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely heavily on heuristic and empirical studies. To advance TTA under…

Safe navigation in real-time is challenging because engineers need to work with uncertain vehicle dynamics, variable external disturbances, and imperfect controllers. A common safety strategy is to inflate obstacles by hand-defined margins.…

The analysis of configurable systems, i.e., systems those behaviors depend on parameters or support various features, is challenging due to the exponential blowup arising in the number of configuration options. This volume contains the…

Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision. Yet, current methods are usually evaluated on benchmarks that are only a…

The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes, depending on the familiarity of the agent with its environment. This is especially important in safety-critical…