23 results
Now showing1 - 10 of 23
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Simulation-only training for real-world localization integrity monitoring(IEEE, 2026-09); ; ; ; Reliable self-localization is a prerequisite for the safe operation of autonomous mobile robots. Particle-filter-based methods such as adaptive Monte Carlo localization (AMCL) may silently fail under dynamic disturbances, map ambiguities, or motion uncertainty. This paper presents a data-driven localization monitoring framework that detects localization failures using Light Detection and Ranging (LiDAR) scans, occupancy maps, and particle filter statistics. The monitoring model is trained exclusively in simulation using randomized environments, without real-world training data. Gradient-boosting models are employed to capture nonlinear consistency relations, and temporal feature aggregation is introduced to model failure dynamics over time. Experiments in simulation and on real robotic platforms demonstrate reliable failure detection and generalization to unseen environments and motion uncertainty levels. Cross-platform transfer to a different robot is evaluated and identified as a limitation. Simulation-only training with domain randomization achieves an F1 score of 0.86 on real-world data.Publicationtype: Conference Paper7 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Learnability of models for cyber-physical systems — a reviewThe complexity of Cyber-Physical Systems (CPS) emerges from a tight integration of numerous digital and physical components. Recent powerful machine learning algorithms are increasingly applied to learn models of CPS from data. However, theoretical limitations of such a pragmatic approach are often left aside. In this paper, we review the learnability of such data-driven models for CPS. Learnability is a key aspect in all parts of the model learning process which seeks for guarantees and preconditions for formal properties of a learned model such as accuracy, robustness, and interpretability. We review the state-of-the-art in model learning for CPS that focuses on these learnability aspects. We arrange and discuss this state-of-the-art alongside the steps of the model learning process, being (1) data quality assurance, (2) model learning, (3) model evaluation, and (4) model refinement. Additionally, we analyze the involvement of prior knowledge and its influence on model learnability. Finally, we discuss the implications of our findings for the development of models for CPS and identify directions for future research, e.g., incorporating prior knowledge more deeply into the model learning process.Publicationtype: Book Part14 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Data-driven identification of models for discrete and hybrid systems(2026); This thesis addresses the challenge of identifying interpretable models for cyber-physical systems. Data-driven identification leverages observed data to automatically construct models that capture the underlying behavior of systems. The work explores a progression of methods, ranging from classical automata learning and extensions of decision trees, to novel algorithms for hybrid automata learning. Empirical evaluations demonstrate the effectiveness and complementarity of the proposed methods, showcasing their ability to address a wide range of modeling challenges in discrete and hybrid systems.Publicationtype: Doctoral Thesis47 38 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Identification of hybrid systems with dynamics-based modeling through symbolic regression(Elsevier, 2026-01); ; ; ; Hybrid systems combine both continuous and discrete behavior. These systems serve as models in many fields, including control systems, robotics, and industrial processes. However, due to their complexity, finding an accurate model is a challenge. This paper presents a holistic approach to learning models of hybrid systems using symbolic regression. Our method leverages symbolic regression to automatically discover accurate and interpretable mathematical models in the form of hybrid systems from observed data. An advantage of our algorithm is that it detects transitions between different behavioral modes of a system based on the inherent dynamics. From learned expressions for the dynamical behavior of a system, we form a hybrid system by combining the learned expressions with a decision tree determining the current behavioral mode from data. This hybrid decision tree serves regression, prediction, and further related tasks. Our results demonstrate that symbolic regression can effectively identify the underlying dynamics of a real hybrid system and predict output signals on new input data with high accuracy.Publicationtype: Journal Article16 43 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , One-shot learning in hybrid system identification: a new modular paradigm(2025-10-11); ; ; Identification of hybrid systems requires learning models that capture both discrete transitions and continuous dynamics from observational data. Traditional approaches follow a stepwise process, separating trace segmentation and mode-specific regression, which often leads to inconsistencies due to unmodeled interdependencies. In this paper, we propose a new iterative learning paradigm that jointly optimizes segmentation and flow function identification. The method incrementally constructs a hybrid model by evaluating and expanding candidate flow functions over observed traces, introducing new modes only when existing ones fail to explain the data. The approach is modular and agnostic to the choice of the regression technique, allowing the identification of hybrid systems with varying levels of complexity. Empirical results on benchmark examples demonstrate that the proposed method produces more compact models compared to traditional techniques, while supporting flexible integration of different regression methods. By favoring fewer, more generalizable modes, the resulting models are not only likely to reduce complexity but also simplify diagnostic reasoning, improve fault isolation, and enhance robustness by avoiding overfitting to spurious mode changes.Publicationtype: Conference Paper33 13 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Data-driven probabilistic evaluation of logic properties with PAC-confidence on Mealy machinesCyber-Physical Systems (CPS) are complex systems that require powerful models for tasks like verification, diagnosis, or debugging. Often, suitable models are not available and manual extraction is difficult. Data-driven approaches then provide a solution to, e.g., diagnosis tasks and verification problems based on data collected from the system. In this paper, we consider CPS with a discrete abstraction in the form of a Mealy machine. We propose a data-driven approach to determine the safety probability of the system on a finite horizon of n time steps. The approach is based on the Probably Approximately Correct (PAC) learning paradigm. Thus, we elaborate a connection between discrete logic and probabilistic reachability analysis of systems, especially providing an additional confidence on the determined probability. The learning process follows an active learning paradigm, where new learning data is sampled in a guided way after an initial learning set is collected. We validate the approach with a case study on an automated lane-keeping system.Publicationtype: Conference Paper7 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Usability of Symbolic Regression for Hybrid System Identification - System Classes and Parameters(2024-11-26); ; ; 13 17 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Dynamics-based identification of hybrid systems using symbolic regression(IEEE, 2024-08); ; ; ; Travé-Massuyès, LouiseSymbolic regression has shown potential in the identification of physical systems. Hybrid systems, which combine both continuous and discrete behavior, are a relevant extension of purely physical systems, used in many fields, including robotics, biological systems, and control systems. However, due to their complexity, finding an accurate model is a challenge. This paper presents a novel approach to learning models of hybrid systems using symbolic regression. Our method leverages the power of genetic programming to automatically discover accurate and interpretable mathematical models in the form of hybrid systems from observed data. Symbolic regression detects transitions between different continuous behavior of a system directly based on the dynamics, instead of pure distances of observed trajectories. Furthermore, models generated by symbolic regression can be used to predict future system behavior, detect anomalies, and identify the underlying dynamics of the system while providing a human-readable representation. Our results demonstrate that symbolic regression can effectively identify the underlying dynamics of a real system represented in a hybrid model, providing a valuable tool for system identification and diagnosis.Publicationtype: Conference Paper21 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , FaMoS– Fast Model Learning for Hybrid Cyber-Physical Systems using Decision Trees(Association for Computing Machinery (ACM), 2024-05-14); ; ; In the domain of cyber-physical systems, there is an increasing relevance of data-driven approaches for the learning of hybrid system dynamics. In particular, accurate models have been successfully abstracted from continuous (real-valued) traces and applied for various goals. However, industrial applications involving online modeling or rapid prototyping have two additional requirements: 1) runtime efficiency and 2) the interpretability of the approach and results. This work adopts a common break down of this learning problem into four steps: 1) trace segmentation, 2) segment clustering, 3) characterization of the dynamics for each cluster (mode) and 4) learning of the overall model of mode transitions. Correspondingly, the bottlenecks in the state-of-the-art approaches are identified and discussed. Then, in a heuristic manner, interpretable and time-efficient algorithms for each of the steps are proposed giving a novel approach named FaMoS. The accuracy and runtime efficiency of the approach are evaluated for several system examples. FaMoS shows very short learning time, while the model’s predictions of system dynamics are close to the ground truth behavior.Publicationtype: Conference Paper46 98 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Towards robustness evaluation of models for cyber-physical systems extended abstractThis paper presents a novel approach to evaluate robustness of models for Cyber-Physical Systems (CPS). We consider a CPS to be a hybrid system and learn models from data using decision tree regressors. We define robustness as the capability of the learned model to maintain its performance under varying unseen conditions. By systematically incorporating a perturbation process and calculating key statistical measures on the differences in model predictions, our method provides a comprehensive evaluation framework when modeling CPS. This approach enhances our understanding of a model’s robustness in the face of uncertainties, ultimately contributing to the development of more robust models for CPS. We demonstrate the application of our method for a simulated temperature control system.Publicationtype: Conference Paper56