Time-series data vary widely across domains, making a universal anomaly detector impractical. Methods that perform well on one dataset often fail to transfer because what counts as an anomaly is context dependent. The key challenge is to design a method that performs well in specific contexts while remaining adaptable across domains with varying data complexities. We present the Robust and Adaptive Model Selection for Time-Series Anomaly Detection RAMSeS framework. RAMSeS comprises two branches: (i) a stacking ensemble optimized with a genetic algorithm to leverage complementary detectors. (ii) An adaptive model-selection branch identifies the best single detector using techniques including Thompson sampling, robustness testing with generative adversarial networks, and Monte Carlo simulations. This dual strategy exploits the collective strength of multiple models and adapts to dataset-specific characteristics. We evaluate RAMSeS and show that it outperforms prior methods on F1.

This paper builds on our Uncertainty-Guided Live Measurement Sequencing (UGLMS) method. UGLMS is a closedloop test strategy that adaptively selects SAR ADC code edges based on model uncertainty and refines a behavioral mismatch model in real time via an Extended Kalman Filter (EKF), eliminating full-range sweeps and offline post-processing. We introduce an enhanced UGLMS that delivers significantly faster test runtimes while maintaining estimation accuracy. First, a rank-1 EKF update replaces costly matrix inversions with efficient vector operations, and a measurement-aligned covarianceinflation strategy accelerates convergence under unexpected innovations. Second, we extend the static mismatch model with a low-order carrier polynomial to capture systematic nonlinearities beyond pure capacitor mismatch. Third, a trace-based termination adapts test length to convergence, preventing premature stops and redundant iterations. Simulations show the enhanced UGLMS reconstructs full Integral- and Differential-Non-Linearity (INL/DNL) in just 36 ms for 16-bit and under $\mathbf{7 0 ~ m s}$ for 18-bit ADCs ($\mathbf{1 2 0 ~ m s}$ with the polynomial extension). Combining the faster convergence from covariance inflation with reduced per-iteration runtime from the rank-1 EKF update, the method reaches equal accuracy $8 \times$ faster for 16 -bit ADCs. These improvements enable real-time, production-ready SAR ADC linearity testing.

This paper introduces a novel closed-loop testing methodology for efficient linearity testing of high-resolution Successive Approximation Register (SAR) Analog-to-Digital Converters (ADCs). Existing test strategies, including histogram-based approaches, sine wave testing, and model-driven reconstruction, often rely on dense data acquisition followed by offline post-processing, which increases overall test time and complexity. To overcome these limitations, we propose an adaptive approach that utilizes an iterative behavioral model refined by an Extended Kalman Filter (EKF) in real time, enabling direct estimation of capacitor mismatch parameters that determine INL behavior. Our algorithm dynamically selects measurement points based on current model uncertainty, maximizing information gain with respect to parameter confidence and narrowing sampling intervals as estimation progresses. By providing immediate feedback and adaptive targeting, the proposed method eliminates the need for large-scale data collection and post-measurement analysis. Experimental results demonstrate substantial reductions in total test time and computational overhead, highlighting the method’s suitability for integration in production environments.

AI-controlled robotic systems can introduce significant risks to both humans and the environment. Traditional reliability assessment methods fall short in addressing the complexities of these systems, particularly when dealing with black-box or dynamically changing control policies. The traditional approaches are applied manually and do not consider frequent software updates. In this paper, we present RelAIBotiX, a new methodology that enables dynamic and continuous reliability assessment, specifically tailored for robotic systems controlled by AI algorithms. RelAIBotiX combines four methods: (i) Skill Detection that automatically identifies executed skills using deep learning techniques, (ii) Behavioral Analysis that creates an operational profile of the robotic system containing information about the skill execution sequence, active components for each skill, and their utilization intensity that influence their failure rate, (iii) Reliability Model Generation that automatically transforms the operational profile and reliability data of robotic hardware components into quantitative hybrid reliability models, and (iv) Reliability Model Solver for the numerical evaluation of the generated reliability models. Our evaluation included computing the reliability of the system, the probability of failure of individual skills, and component sensitivity analysis. We validated the applicability of the proposed framework across five simulative and real-world setups.

Safety is a critical concern in human-robot collaboration (HRC). As collaborative robots take on increasingly complex tasks in human environments, their systems have become more sophisticated through the integration of multimodal sensors, including force-torque sensors, cameras, LiDARs, and IMUs. However, existing studies on HRC safety primarily focus on ensuring safety under normal operating conditions, overlooking scenarios where internal sensor faults occur.While anomaly detection modules can help identify sensor errors and mitigate hazards, two key challenges remain: (1) no anomaly detector is flawless, and (2) not all sensor malfunctions directly threaten human safety. Relying solely on anomaly detection can lead to missed errors or excessive false alarms.To enhance safety in real-world HRC applications, this paper introduces a deep learning-based method that proactively predicts hazards following the detection of sensory anomalies. We simulate two common types of faults—bias and noise—affecting joint sensors and monitor abnormal manipulator behaviors that could pose risks in fenceless HRC environments. A dataset of 2,400 real-world samples is collected to train the proposed hazard prediction model.The approach leverages multimodal inputs, including RGB-D images, human pose, joint states, and planned robot paths, to assess whether sensor malfunctions could lead to hazardous events. Experimental results show that the proposed method outperforms state-of-the-art models, while offering faster inference speed. Additionally, cross-scenario testing confirms its strong generalization capabilities.The code and datasets are available at: DL-based-Hazard-Prediction.

We present LiHRA, a novel dataset designed to facilitate the development of automated, learning-based, or classical risk monitoring (RM) methods for Human-Robot Interaction (HRI) scenarios. The growing prevalence of collaborative robots in industrial environments has increased the need for reliable safety systems. However, the lack of high-quality datasets that capture realistic human-robot interactions, including potentially dangerous events, slows development. LiHRA addresses this challenge by providing a comprehensive, multi-modal dataset combining 3D LiDAR point clouds, human body keypoints, and robot joint states, capturing the complete spatial and dynamic context of human-robot collaboration. This combination of modalities allows for precise tracking of human movement, robot actions, and environmental conditions, enabling accurate RM during collaborative tasks. The LiHRA dataset covers six representative HRI scenarios involving collaborative and coexistent tasks, object handovers, and surface polishing, with safe and hazardous versions of each scenario. In total, the data set includes 4,431 labeled point clouds recorded at 10 Hz, providing a rich resource for training and benchmarking classical and AI-driven RM algorithms. Finally, to demonstrate LiHRA’s utility, we introduce an RM method that quantifies the risk level in each scenario over time. This method leverages contextual information, including robot states and the dynamic model of the robot. With its combination of high-resolution LiDAR data, precise human tracking, robot state data, and realistic collision events, LiHRA offers an essential foundation for future research into real-time RM and adaptive safety strategies in human-robot workspaces.

Due to the increasing behavioral and structural complexity of robots, it is challenging to predict the execution outcome after error detection. Anomaly detection methods can help detect errors and prevent potential failures. However, not every fault leads to a failure due to the system’s fault tolerance or unintended error masking. In practical applications, a robotic system should have a potential failure evaluation module to estimate the probability of failures when receiving an error alert. Subsequently, a decision-making mechanism should help to take the next action, e.g., terminate, degrade performance, or continue the execution of the task. This paper proposes a multimodal method for failure prediction for vision-based manipulation systems that suffer from potential camera faults. We inject faults into images (e.g., noise and blur) and observe manipulation failure scenarios (e.g., pick failure, place failure, and collision) that can occur during the task. Through extensive fault injection experiments, we created a FAULT-to-FAILURE dataset containing 4000 real-world manipulation samples. The dataset is subsequently used to train the failure predictor. Our approach processes the combination of RGB images, masked images, and planned paths to effectively evaluate whether a certain faulty image could potentially lead to a manipulation failure. Results demonstrate that the proposed method outperforms state-of-the-art models in terms of overall performance, requires fewer sensors, and achieves faster inference speeds. The analytical software prototype and dataset are available at Github: MultimodalFailurePrediction.

The cyber-physical systems (CPS) are characterized by a high degree of complexity due to the presence of networked heterogeneous components. This complexity makes it crucial to prevent error propagation in the system. Therefore, error detection and mitigation are necessary requirements in CPS. Recently, DL-based techniques have emerged as popular solutions for error detection in CPS. However, the main concern of DL-based error detection models in power constrained CPS is the trade-off between accuracy and speed. This leads to the necessity of designing optimized, accurate, and lightweight models.This paper proposes an optimized lightweight error detection model based on prediction approach. The paper addresses the limitations of conventional DL-based approaches in error detection for hardware-constrained CPS, particularly an exoskeleton system. The model adopted state-of-the-art efficient architecture that comprises in parallel CNN and LSTM layers, which is then transformed into a lightweight network through data quantization and network pruning techniques. The effectiveness of the proposed method is demonstrated through its application in error detection of the exoskeleton system’s data.

Modern Cyber-Physical Systems are characterized by dynamic and complex structure. They are facing factors such as erroneous software update, Artificial Intelligence components, reconfigurable structure, etc. Because of that, they are prone to latent or dormant faults. With the growth of data that needs to be processed, traditional error-handling mechanisms are failing to be efficient enough. For this reason, Deep Learning methods come into play. Application of such methods for detection and handling of error is nowadays a vastly used approach. However, the development of Deep Learning-based error detectors is time-consuming because there is no general approach to automatically exploit the specifics of the given system. In order to effectively address this issue, we propose a new hybrid deep learning-based methodology called Remedy. It comprises three steps: (1) identification of critical fault parameters, (2) automatic search for efficient access points for training data generation, and (3) deployment of deep learning-based error detector. To illustrate the effectiveness of this methodology, we present an implementation example on a classical Simulink model. Comparing the results with the corresponding baseline, the authors discuss the advantages and disadvantages of the proposed method.

Since the introduction of the term Cyber-Physical Systems (CPS) in 2006, they came to a long way. CPS are now autonomous and networked systems of systems with state-space exceeding the capabilities of conventional risk analysis methods. Model-based fault injection methods allow assessment of a system’s fault tolerance not only during its design phase but also in the course of operation. This allows the evaluation of updates and new modules before deploying such changes to a real system. Such operational model-based fault injection on a system’s digital twin can ensure continuous safety throughout all system life cycles.Modern risk analysis tools and Machine Learning-based safety methods require vast amounts of representative input and training data. Such methods not only will require mountains of erroneous time-series data from a myriad of operational cycles, but also corresponding fault parameter labels. As the state space of the system component explodes in complexity, it becomes problematic to cover all possible component fault combinations. As such, only those faults that could lead to potential failures or increased risk scenarios are of interest for automated safety assessment methodologies. It is clear that an intelligent and effective model-based fault injection method is required for the operational safety assessment of industrial CPS.Recently we introduced a new model-based fault injection method implemented as a highly customizable Simulink block called FIBlock. It supports the model-based injection of typical faults of CPS components such as sensors, software, computing, and network hardware. In this paper, we proposed a Deep Learning-based approach for model-based fault injection called FIDGET. It extends the FIBlock with Deep Reinforcement Learning capabilities. We employed a Deep Deterministic Policy Gradient algorithm with Long Short-Term Memory (LSTM) architecture to train the Reinforcement Learning agent to per-form the automated search of fault parameters that yield the biggest system response. It allows automatic generation of labeled training data for further use in risk analysis tools or to train fault classifiers. The generated training data consists of errors that lead to the biggest response (i.e., disturbance) of the system.

The current trend in production systems development is shifted towards the software part. This is emphasized by the concepts of digital twins and Software-Defined Manufacturing (SDM). These software-intensive and safety-critical systems have more frequent software updates to address higher system flexibility and adjustable production processes. SDM-systems bring new challenges to the reliability assessment. Each update can change the system behavior significantly. This leads to the necessity to reconduct reliability assessment automatically before each software update.In this paper, we introduce the concept of an automated model-based reliability assessment method sensible to the software update. The paper describes the key idea of the method and demonstrates its application on a model of a robotic manipulator.

Increasing complexity and heterogeneity of modern safety-critical systems require advanced tools for quantitative reliability analysis. Most of the available analytical software exploits classical methods such as event trees, static and dynamic fault trees, reliability block diagrams, simple Bayesian networks, and Markov chains. First, these methods fail to adequately model complex interaction of software, hardware, physical components, dynamic feedback loops, propagation of data errors, nontrivial failure scenarios, sophisticated fault tolerance, and resilience mechanisms. Second, these methods are limited to the evaluation of the fixed set of traditional reliability metrics such as the probability of generic system failure, failure rate, MTTF, MTBF, and MTTR. More flexible models, such as the Dual-graph Error Propagation Model (DEPM) can overcome these limitations but have no available tools. This paper introduces the first open-source DEPM-based analytical software tool OpenErrorPro. The DEPM is a formal stochastic model that captures control and data flow structures and reliability-related properties of executable system components. The numerical analysis in OpenErrorPro is based on the automatic generation of Markov chain models and the utilization of modern Probabilistic Model Checking (PMC) techniques. The PMC enables the analysis of highly-customizable resilience metrics, e.g. "the probability of system recovery after a specified system failure during the defined time interval", in addition to the traditional reliability metrics. DEPMs can be automatically generated from Simulink/Stateflow, UML/SysML, and AADL models, as well as source code of software components using LLVM. This allows not only the automated model-based evaluation but also the analysis of systems developed using the combination of several modeling paradigms. The key purpose of the tool is to close the gap between the conventional system design models and advanced analytical methods in order to give system reliability engineers easy and automated access to the full potential of PMC techniques. Finally, OpenErrorPro enables the application of several effective optimizations against the state space explosion of underlying Markov models already in the DEPM level where the system semantics such as control and data flow structures are accessible.

Model-based design of embedded control systems becomes more and more popular. Control engineers prefer to use MATLAB Simulink and suitable automatic code generators for the development and deployment of the software. Simulink provides a vast variety of functionally equivalent design solutions. For instance, a proportional-integral-derivative (PID) controller can be implemented in Simulink using i) separate blocks for the P, I, D terms, ii) a dedicated Discrete PID Controller block, iii) a Discrete Transfer Function block, or iv) a Discrete State-Space block. However, these functionally equivalent implementations of the PID controller show completely different reliability properties. This article introduces a new analytical method for the overall system reliability evaluation under data errors occurred in RAM and CPU. The method is based on a stochastic dual-graph error propagation model that captures control and data flow structures of the assembly code and allows the computation of system level reliability metrics in critical system outputs for specified faults probabilities. The analytical method enables an early system reliability evaluation. Also, application of this analytical method to possible implementations of the particular control algorithm helps to select the most reliable one.