arXiv subjects

Thao Dang

Publications and source records attributed to Thao Dang.

18 recordsLinked to original sources

arXiv2026

Beam-Wise Statistical Background Subtraction for Static Roadside LiDAR: A Cross-Sensor Benchmark Study

Background subtraction is a key preprocessing step for infrastructure-based LiDAR perception, enabling efficient isolation of dynamic traffic participants without semantic annotations. However, systematic cross-sensor evaluations and reproducible studies for static roadside LiDAR are missing. This paper presents a comparative benchmark of beam-wise statistical background subtraction for statically mounted LiDAR sensors. We formulate background estimation as a per-beam temporal modeling problem and investigate complementary statistical strategies that capture dominant as well as multi-modal background structures, combined with spatial filtering in the angular and 3D domain. To enable reproducible evaluation, we introduce HighwayScene, a new multi-LiDAR dataset recorded in a static roadside setup, and extend the public CoopScenes dataset with static/dynamic point-wise annotations. Across multiple scenes and heterogeneous sensing technologies, we demonstrate that beam-wise statistical modeling provides a robust and transferable solution. Combining lightweight per-beam models with spatial consistency filtering substantially improves precision while maintaining high recall and real-time capability. All datasets, annotations, and implementations are publicly released.

cs.CV↗

arXiv2026

On Tackling Complex Tasks with Reward Machines and Signal Temporal Logics

We propose a Reinforcement Learning (RL) based control design framework for handling complex tasks. The approach extends the concept of Reward Machines (RM) with Signal Temporal Logic (STL) formulas that can be used for event generation. The use of STL allows not only a more efficient representation of rewards for complex tasks but also guiding the training process to converge towards behaviors satisfying specified requirements. We also propose an implementation of the framework that leverages the STL online monitoring algorithms. We illustrate the framework with three case studies (minigrid, cart-pole and high-way environments) with non-trivial tasks.

cs.AI↗

arXiv2025

Beyond Features: How Dataset Design Influences Multi-Agent Trajectory Prediction Performance

Accurate trajectory prediction is critical for safe autonomous navigation, yet the impact of dataset design on model performance remains understudied. This work systematically examines how feature selection, cross-dataset transfer, and geographic diversity influence trajectory prediction accuracy in multi-agent settings. We evaluate a state-of-the-art model using our novel L4 Motion Forecasting dataset based on our own data recordings in Germany and the US. This includes enhanced map and agent features. We compare our dataset to the US-centric Argoverse 2 benchmark. First, we find that incorporating supplementary map and agent features unique to our dataset, yields no measurable improvement over baseline features, demonstrating that modern architectures do not need extensive feature sets for optimal performance. The limited features of public datasets are sufficient to capture convoluted interactions without added complexity. Second, we perform cross-dataset experiments to evaluate how effective domain knowledge can be transferred between datasets. Third, we group our dataset by country and check the knowledge transfer between different driving cultures.

cs.RO↗

arXiv2025

CoopScenes: Multi-Scene Infrastructure and Vehicle Data for Advancing Collective Perception in Autonomous Driving

The increasing complexity of urban environments has underscored the potential of effective collective perception systems. To address these challenges, we present the CoopScenes dataset, a large-scale, multi-scene dataset that provides synchronized sensor data from both the ego-vehicle and the supporting infrastructure.The dataset provides 104 minutes of spatially and temporally synchronized data at 10 Hz, resulting in 62,000 frames. It achieves competitive synchronization with a mean deviation of only 2.3 ms. Additionally the dataset includes a novel procedure for precise registration of point cloud data from the ego-vehicle and infrastructure sensors, automated annotation pipelines, and an open-source anonymization pipeline for faces and license plates. Covering nine diverse scenes with 100 maneuvers, the dataset features scenarios such as public transport hubs, city construction sites, and high-speed rural roads across three cities in the Stuttgart region, Germany. The full dataset amounts to 527 GB of data and is provided in the .4mse format, making it easily accessible through our comprehensive development kit. By providing precise, large-scale data, CoopScenes facilitates research in collective perception, real-time sensor registration, and cooperative intelligent systems for urban mobility, including machine learning-based approaches.

cs.RO↗

arXiv2025

Dynamic Intent Queries for Motion Transformer-based Trajectory Prediction

In autonomous driving, accurately predicting the movements of other traffic participants is crucial, as it significantly influences a vehicle's planning processes. Modern trajectory prediction models strive to interpret complex patterns and dependencies from agent and map data. The Motion Transformer (MTR) architecture and subsequent work define the most accurate methods in common benchmarks such as the Waymo Open Motion Benchmark. The MTR model employs pre-generated static intention points as initial goal points for trajectory prediction. However, the static nature of these points frequently leads to misalignment with map data in specific traffic scenarios, resulting in unfeasible or unrealistic goal points. Our research addresses this limitation by integrating scene-specific dynamic intention points into the MTR model. This adaptation of the MTR model was trained and evaluated on the Waymo Open Motion Dataset. Our findings demonstrate that incorporating dynamic intention points has a significant positive impact on trajectory prediction accuracy, especially for predictions over long time horizons. Furthermore, we analyze the impact on ground truth trajectories which are not compliant with the map data or are illegal maneuvers.

cs.RO↗

arXiv2024

Towards Consistent and Explainable Motion Prediction using Heterogeneous Graph Attention

In autonomous driving, accurately interpreting the movements of other road users and leveraging this knowledge to forecast future trajectories is crucial. This is typically achieved through the integration of map data and tracked trajectories of various agents. Numerous methodologies combine this information into a singular embedding for each agent, which is then utilized to predict future behavior. However, these approaches have a notable drawback in that they may lose exact location information during the encoding process. The encoding still includes general map information. However, the generation of valid and consistent trajectories is not guaranteed. This can cause the predicted trajectories to stray from the actual lanes. This paper introduces a new refinement module designed to project the predicted trajectories back onto the actual map, rectifying these discrepancies and leading towards more consistent predictions. This versatile module can be readily incorporated into a wide range of architectures. Additionally, we propose a novel scene encoder that handles all relations between agents and their environment in a single unified heterogeneous graph attention network. By analyzing the attention values on the different edges in this graph, we can gain unique insights into the neural network's inner workings leading towards a more explainable prediction.

cs.RO↗

arXiv2024

Counter-example guided Imitation Learning of Feedback Controllers from Temporal Logic Specifications

We present a novel method for imitation learning for control requirements expressed using Signal Temporal Logic (STL). More concretely we focus on the problem of training a neural network to imitate a complex controller. The learning process is guided by efficient data aggregation based on counter-examples and a coverage measure. Moreover, we introduce a method to evaluate the performance of the learned controller via parameterization and parameter estimation of the STL requirements. We demonstrate our approach with a flying robot case study.

cs.RO↗

arXiv2023

Automated Multi-Drugs Administration During Total Intravenous Anesthesia Using Multi-Model Predictive Control

In this paper, a multi-model predictive control approach is used to automate the co-administration of propofol and remifentanil from bispectral index measurement during general anesthesia. To handle the parameter uncertainties in the non-linear output function, multiple Extended Kalman Filters are used to estimate the state of the system in parallel. The best model is chosen using a model-matching criterion and used in a non-linear MPC to compute the next drug rates. The method is compared with a conventional non-linear MPC approach and a PID from the literature. The robustness of the controller is evaluated using Monte-Carlo simulations on a wide population introducing uncertainties in the models. Both simulation setup and controller codes are accessible in open source for further use. Our preliminary results show the potential interest in using a multi-model method to handle parameter uncertainties.

eess.SY↗

arXiv2022

Towards Efficient Active Learning of PDFA

We propose a new active learning algorithm for PDFA based on three main aspects: a congruence over states which takes into account next-symbol probability distributions, a quantization that copes with differences in distributions, and an efficient tree-based data structure. Experiments showed significant performance gains with respect to reference implementations.

cs.FL↗

arXiv2022

Identifying Scenarios in Field Data to Enable Validation of Highly Automated Driving Systems

Scenario-based approaches for the validation of highly automated driving functions are based on the search for safety-critical characteristics of driving scenarios using software-in-the-loop simulations. This search requires information about the shape and probability of scenarios in real-world traffic. The scope of this work is to develop a method that identifies redefined logical driving scenarios in field data, so that this information can be derived subsequently. More precisely, a suitable approach is developed, implemented and validated using a traffic scenario as an example. The presented methodology is based on qualitative modelling of scenarios, which can be detected in abstracted field data. The abstraction is achieved by using universal elements of an ontology represented by a domain model. Already published approaches for such an abstraction are discussed and concretised with regard to the given application. By examining a first set of test data, it is shown that the developed method is a suitable approach for the identification of further driving scenarios.

cs.RO↗

arXiv2021

Sampling of Shape Expressions

Cyber-physical systems (CPS) are increasingly becoming driven by data, using multiple types of sensors to capture huge amounts of data. Extraction and characterization of useful information from big streams of data is a challenging problem. Shape expressions facilitate formal specification of rich temporal patterns encountered in time series as well as in behaviors of CPS. In this paper, we introduce a method for systematically sampling shape expressions. The proposed approach combines methods for uniform sampling of automata (for exploring qualitative shapes) with hit-and-run Monte Carlo sampling procedures (for exploring multi-dimensional parameter spaces defined by sets of possibly non-linear constraints). We study and implement several possible solutions and evaluate them in the context of visualization and testing applications.

cs.CY↗

arXiv2021

Proceedings 6th International Workshop on Symbolic-Numeric methods for Reasoning about CPS and IoT

The proceedings of the 6th International Workshop on Symbolic-Numeric Methods for Reasoning about CPS and IoT (SNR 2020) contains papers underlying talks presented at the workshop. SNR focuses on the combination of symbolic and numeric methods for reasoning about Cyber-Physical Systems and the Internet of Things to facilitate model identification, specification, verification, and control synthesis for these systems.

cs.LO↗

arXiv2018

Certified Roundoff Error Bounds using Bernstein Expansions and Sparse Krivine-Stengle Representations

Floating point error is a drawback of embedded systems implementation that is difficult to avoid. Computing rigorous upper bounds of roundoff errors is absolutely necessary for the validation of critical software. This problem of computing rigorous upper bounds is even more challenging when addressing non-linear programs. In this paper, we propose and compare two new algorithms based on Bernstein expansions and sparse Krivine-Stengle representations, adapted from the field of the global optimization, to compute upper bounds of roundoff errors for programs implementing polynomial and rational functions. We also provide the convergence rate of these two algorithms. We release two related software package FPBern and FPKriSten, and compare them with the state-of-the-art tools. We show that these two methods achieve competitive performance, while providing accurate upper bounds by comparison with the other tools.

math.NA↗

arXiv2017

Occupation measure methods for modelling and analysis of biological hybrid automata

Mechanistic models in biology often involve numerous parameters about which we do not have direct experimental information. The traditional approach is to fit these parameters using extensive numerical simulations (e.g. by the Monte-Carlo method), and eventually revising the model if the predictions do not correspond to the actual measurements. In this work we propose a methodology for hybrid automaton model revision, when new type of functions are needed to capture time varying parameters. To this end, we formulate a hybrid optimal control problem with intermediate points as successive infinite-dimensional linear programs (LP) on occupation measures. Then, these infinite-dimensional LPs are solved using a hierarchy of semidefinite relaxations. The whole procedure is exposed on a recent model for haemoglobin production in erythrocytes.

eess.SY↗

arXiv2016

Certified Roundoff Error Bounds using Bernstein Expansions and Sparse Krivine-Stengle Representations

Floating point error is an inevitable drawback of embedded systems implementation. Computing rigorous upper bounds of roundoff errors is absolutely necessary to the validation of critical software. This problem is even more challenging when addressing non-linear programs. In this paper, we propose and compare two new methods based on Bernstein expansions and sparse Krivine-Stengle representations, adapted from the field of the global optimization to compute upper bounds of roundoff errors for programs implementing polynomial functions. We release two related software package FPBern and FPKiSten, and compare them with state of the art tools. We show that these two methods achieve competitive performance, while computing accurate upper bounds by comparison with other tools.

math.NA↗

arXiv2013

Falsifying Oscillation Properties of Parametric Biological Models

We propose an approach to falsification of oscillation properties of parametric biological models, based on the recently developed techniques for testing continuous and hybrid systems. In this approach, an oscillation property can be specified using a hybrid automaton, which is then used to guide the exploration in the state and input spaces to search for the behaviors that do not satisfy the property. We illustrate the approach with the Laub-Loomis model for spontaneous oscillations during the aggregation stage of Dictyostelium.

cs.LO↗

arXiv2013

Proceedings Second International Workshop on Hybrid Systems and Biology

This volume contains the proceedings of the Second International Workshop Hybrid Systems and Biology (HSB 2013) held in Taormina (Italy), on September 2th, 2013. The workshop is affiliated to the 12th European Conference on Artificial Life (ECAL 2013). Systems biology aims at providing a system-level understanding of biological systems by unveiling their structure, dynamics and control methods. Due to the intrinsic multi-scale nature of these systems in space, in organization levels and in time, it is extremely difficult to model them in a uniform way, e.g., by means of differential equations or discrete stochastic processes. Furthermore, such models are often not easily amenable to formal analysis, and their simulations at the organ or even at the cell levels are frequently impractical. Indeed, an important open problem is finding appropriate computational models that scale well for both simulation and formal analysis of biological processes. Hybrid modeling techniques, combining discrete and continuous processes, are gaining more and more attention in such a context, and they have been successfully applied to capture the behavior of many biological complex systems, ranging from genetic networks, biochemical reactions, signaling pathways, cardiac tissues electro-physiology, and tumor genesis. This workshop aims at bringing together researchers in computer science, mathematics, and life sciences, interested in the opportunities and the challenges of hybrid modeling applied to systems biology. The workshop programme included the keynote presentation of Alessandro Astolfi (Imperial College of London, UK) on Immune response enhancement via hybrid control. Furthermore, 8 papers were selected out of 13 submissions by the Program Committee of HSB 2013. The papers in this volume address the hybrid modeling of a number important biological processes (iron homeostasis network, mammalian cell cycle, vascular endothelial growth factor (VEGF), genetic regulatory network in mammalian sclera) and, the formalisms and techniques for specifying and validating properties of biological systems (such as, robustness, oscillations).

cs.CE↗

arXiv2012

Analysis of parametric biological models with non-linear dynamics

In this paper we present recent results on parametric analysis of biological models. The underlying method is based on the algorithms for computing trajectory sets of hybrid systems with polynomial dynamics. The method is then applied to two case studies of biological systems: one is a cardiac cell model for studying the conditions for cardiac abnormalities, and the second is a model of insect nest-site choice.

cs.CE↗