@inproceedings{Krueger2025, author = {Kr{\"u}ger, Max}, title = {ChatGPT as a Subject Matter Expert in the Parameterization of Bayesian Network Classifiers}, booktitle = {Proceedings of the 2025 28th International Conference on Information Fusion (FUSION 2025)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-0370-5623-9}, doi = {https://doi.org/10.23919/FUSION65864.2025.11124000}, year = {2025}, language = {en} } @article{HennighausenYarzaNavarroSchaerEller2025, author = {Hennighausen, Christine and Yarza Navarro-Sch{\"a}r, Vanessa Gabriela and Eller, Eric}, title = {AI-Mediated Communication in E-Commerce: Implications for Customer Trust}, volume = {49}, pages = {e70111}, journal = {International Journal of Consumer Studies}, number = {5}, publisher = {Wiley}, address = {Oxford}, issn = {1470-6431}, doi = {https://doi.org/10.1111/ijcs.70111}, year = {2025}, abstract = {Generative artificial intelligence (AI) technologies offer new potential for marketing and customer operations, such as automation and personalization of customer service. However, more must be understood about how AI-mediated communication (AI-MC) affects customer trust. We conducted an online experiment to investigate the impact of AI-MC on customer trust in an online retail context. We presented N = 294 participants with two email scenarios describing a product return context, labeled as written by either (a) a service employee, (b) a service employee assisted by AI, or (c) AI on behalf of the service employee. We further varied levels of service criticality to consider customers' perception of vulnerability. Our findings revealed higher customer trust ratings in the online retailer when the email communications were written by the service employee, compared to those written by the service employee assisted by AI. When analyzing the different components of trust, it was found that communications written by the service employee assisted by AI reduced perceptions of both the online retailer's benevolence and integrity, while communications written by AI on behalf of the employee led to lower perceived integrity of the online retailer. Surprisingly, service criticality did not affect trust ratings. We discuss the managerial implications of integrating generative AI into customer service in the context of the EU AI Act, which came into force on 1 August 2024.}, language = {en} } @unpublished{PandeyMohdVeettiletal.2025, author = {Pandey, Amit and Mohd, Zubair Akhtar and Veettil, Nandana Kappuva and Wunderle, Bernhard and Elger, Gordon}, title = {Quantitative Kernel Estimation from Traffic Signs using Slanted Edge Spatial Frequency Response as a Sharpness Metric}, titleParent = {Research Square}, publisher = {Research Square}, address = {Durham}, doi = {https://doi.org/10.21203/rs.3.rs-6725582/v1}, year = {2025}, abstract = {The sharpness is a critical optical property of automotive cameras, measured by the Spatial Frequency Response (SFR) within the end of line (EOL) test after manufacturing. This work presents a method to estimate the blurring kernel of automotive camera for state monitoring. To achieve this, Principal Component Analysis (PCA) is performed, using synthetic kernels generated by Zemax. The PCA model is built with approximately 1300 base kernels representing spatially variant point spread functions (PSFs). This model generates kernel samples during the estimation process. Synthetic images are created by convolving the synthetic kernels with reference traffic sign images and compared with real-life data captured by an automotive camera. These synthetic data are utilized for algorithm development, and later on validation is performed on real-life data. The algorithm extracts two 45 x 45 pixels regions of interest (ROIs) containing slanted edges from the blurred image and crops matching ROIs from a reference sharp image. Each candidate kernel blurs the reference ROIs, and the resulting Spatial Frequency Response (SFR) is compared with the blurred ROIs' SFR. Differential evolution optimization minimizes the SFR difference, selecting the kernel that best matches the observed blur. The final kernel is evaluated against the true kernel for accuracy. Structural similarity index measure (SSIM) between the original and estimated blurred ROIs ranges from 0.808 to 0.945. For true vs. estimated kernels, SSIM varies from 0.92 to 0.98. Pearson correlation coefficients range from 0.84 to 0.99, Cosine similarity from 0.86 to 0.98, and mean squared error (MSE) from 1.1 x 10-5 to 8.3 x 10-5. Validation on real-life camera images shows that the SSIM between estimated ROI is 0.82 indicating a sufficient level of accuracy in kernel estimation to detect potential degradation of the camera.}, language = {en} } @inproceedings{NietoOtaeguiPanouetal.2025, author = {Nieto, Marcos and Otaegui, Oihana and Panou, Maria and Birkner, Christian and Vaculin, Ondrej and Rodr{\´i}guez, Ariadna}, title = {AWARE2ALL: Human Centric Interaction and Safety Systems for Increasing the Share of Automated Vehicles}, booktitle = {Transport Transitions: Advancing Sustainable and Inclusive Mobility, Proceedings of the 10th TRA Conference, 2024, Dublin, Ireland-Volume 1: Safe and Equitable Transport}, editor = {McNally, Ciaran and Carroll, P{\´a}raic and Martinez-Pastor, Beatriz and Ghosh, Bidisha and Efthymiou, Marina and Valantasis-Kanellos, Nikolaos}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-88974-5}, doi = {https://doi.org/10.1007/978-3-031-88974-5_112}, pages = {779 -- 785}, year = {2025}, abstract = {The AWARE2ALL project is designed to address the new challenges of Highly Automated Vehicles (HAVs) from a human-centric perspective. These vehicles will allow occupants to engage in non-driving activities, rising research questions about occupant behavior, activities, and Human-Machine Interfaces (HMI) to keep them aware of the situation and the automation mode. The project aims to ensure safe operation of HAVs by developing safety and HMI systems that provide a holistic understanding of the scene. This includes continuous monitoring of the interior situation and advanced passive safety systems for occupant safety, as well as a surround perception system and external HMI for the safety of Human Road Users (HRUs). AWARE2ALL is paving the way for HAV deployment by effectively addressing changes in road safety and interactions between different road users caused by the emergence of HAVs. It is developing innovative technologies, assessment tools, and methodologies to adapt to new scenarios in mixed traffic. The project builds on previous research and aims to mitigate new safety risks associated with the introduction of HAVs.}, language = {en} } @unpublished{BattahiChbaniNiederlaenderetal.2025, author = {Battahi, Fouad and Chbani, Zaki and Niederl{\"a}nder, Simon and Riahi, Hassan}, title = {Asymptotic behavior of the Arrow-Hurwicz differential system with Tikhonov regularization}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2411.17656}, year = {2025}, abstract = {In a real Hilbert space setting, we investigate the asymptotic behavior of the solutions of the classical Arrow-Hurwicz differential system combined with Tikhonov regularizing terms. Under some newly proposed conditions on the Tikhonov terms involved, we show that the solutions of the regularized Arrow-Hurwicz differential system strongly converge toward the element of least norm within its set of zeros. Moreover, we provide fast asymptotic decay rate estimates for the so-called primal-dual gap function and the norm of the solutions' velocity. If, in addition, the Tikhonov regularizing terms are decreasing, we provide some refined estimates in the sense of an exponentially weighted moving average. Under the additional assumption that the governing operator of the Arrow-Hurwicz differential system satisfies a reverse Lipschitz condition, we further provide a fast rate of strong convergence of the solutions toward the unique zero. We conclude our study by deriving the corresponding decay rate estimates with respect to the so-called viscosity curve. Numerical experiments illustrate our theoretical findings.}, language = {en} } @unpublished{KernTolksdorfBirkner2025, author = {Kern, Tobias and Tolksdorf, Leon and Birkner, Christian}, title = {Comparison of Localization Algorithms between Reduced-Scale and Real-Sized Vehicles Using Visual and Inertial Sensors}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2507.11241}, year = {2025}, language = {en} } @inproceedings{RauscherBraunHiemeretal.2025, author = {Rauscher, Andreas and Braun, Julian and Hiemer, Rainer and Heldwein, Marcelo Lobo and Endisch, Christian}, title = {Convolutional Neural Networks and Thresholding Approaches for Single and Multi-Sensor Detection of Partial Discharges in Electrical Machine Stators}, booktitle = {Proceedings of the 15th International 2025 IEEE Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives (SDEMPED)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-8820-6}, doi = {https://doi.org/10.1109/SDEMPED53223.2025.11153974}, year = {2025}, language = {en} } @article{NikoloskiBotzenTalevietal.2025, author = {Nikoloski, Marjan and Botzen, Wouter and Talevi, Marta and Blasch, Julia and Banerjee, Sanchayan and Cazenave, M. P.}, title = {Methods to Tailor Behavioural Interventions: A Systematic Review of Categorisation Approaches in (Energy) Economics}, volume = {19}, journal = {International Review of Environmental and Resource Economics}, number = {2}, publisher = {Now Publishers}, address = {Boston}, issn = {1932-1473}, doi = {https://doi.org/10.1561/101.00000175}, pages = {117 -- 158}, year = {2025}, language = {en} } @article{ChoeDongBoschetal.2025, author = {Choe, Mungyeong and Dong, Jiayuan and Bosch, Esther and Alvarez, Ignacio and Oehl, Michael and Jallais, Christophe and Alsaid, Areen and Jeon, Myounghoon}, title = {Driving with Empathy: Workshop Report on AI-driven In-vehicle Empathic Agent Design for Automated Vehicles}, volume = {69}, journal = {Proceedings of the Human Factors and Ergonomics Society Annual Meeting}, number = {1}, publisher = {Sage}, address = {London}, issn = {1071-1813}, doi = {https://doi.org/10.1177/10711813251369800}, pages = {1770 -- 1775}, year = {2025}, language = {en} } @inproceedings{PeintnerMalveSadeghianetal.2025, author = {Peintner, Jakob and Malve, Bhavana and Sadeghian, Shadan and Riener, Andreas}, title = {Driving Together: An Analysis of Passengers' Needs and Desire for Cooperative Control in Automated Vehicles}, booktitle = {MuC´25: Proceedings of the 2025 Conference on Mensch und Computer}, publisher = {ACM}, address = {New York}, isbn = {979-8-4007-1582-2}, doi = {https://doi.org/10.1145/3743049.3743061}, pages = {333 -- 344}, year = {2025}, abstract = {Driving automation aims to enhance comfort, safety, and traffic flow by removing the human driver from the control loop. However, the human experience of commuting involves more than just reaching a destination or assuming the role of a driver. Factors like personal driving style and courtesy towards fellow road users are integral to the driving experience but often overlooked in the development of driving algorithms for automated vehicles. In this study, we explored the needs of passengers in highly automated vehicles. A qualitative use case analysis was conducted (N=16). In a second study, N=15 participants experienced the resulting use cases in an automated vehicle. In these scenarios, they were able to interact with the automation through a cooperation HMI. Results indicate that most participants expressed a desire for cooperative driving, albeit varying with the driving situation. Moreover, allowing cooperation improves passengers' overall experience by satisfying psychological needs for autonomy, security, competence, and relatedness.}, language = {en} } @article{Klages2025, author = {Klages, Anna-Lisa}, title = {Andreas Schadauer: Wissen in Zahlen? Zur Herstellung quantitativen Wissens in der Sozialwissenschaft. Bielefeld: transcript 2022, 254 S., ISBN 978-3-8376-6398-3, 45,00 €}, volume = {26}, journal = {ZQF - Zeitschrift f{\"u}r Qualitative Forschung}, number = {1-2025}, publisher = {Verlag Barbara Budrich}, address = {Leverkusen}, issn = {2196-2138}, doi = {https://doi.org/10.3224/zqf.v26i1.09}, pages = {116 -- 120}, year = {2025}, abstract = {Mit der auf seiner Dissertation aufbauenden Monografie Wissen in Zahlen? Zur Herstellung quantitativen Wissens in der Sozialwissenschaft, zeigt Andreas Schadauer anhand von zwei empirischen Fallstudien auf, wie Umfragedaten zun{\"a}chst zu Zahlen und Statistiken werden, denen im weiteren Verlauf der Rezeption ein nahezu faktischer Status der Objektivit{\"a}t zugeschriebenwird. Daf{\"u}r zeichnet er in der ersten Fallstudie den Weg der Daten nach, die im Rahmen der Household Finance and Consumption Survey (HFCS) der {\"O}sterreichischen Nationalbank (OeNB) zwischen 2010-2011 generiert wurden. Als zweite Fallstudie w{\"a}hlt er die {\"o}sterreichische Immobilienverm{\"o}genserhebung von 2008, die zum Zeitpunkt der Feldforschung bereits abgeschlossen war. Beide Datens{\"a}tze wurden mit dem Anspruch an Repr{\"a}sentativit{\"a}t generiert und stellen in der {\"o}sterreichischen Debatte um die nationale Verm{\"o}gensverteilung wichtige Referenzen dar. Mit den „multi-sited" (S. 19, 59 ff., Hervorh. i. Orig.) Fallstudien verfolgt Schadauer zwei Ziele: Zum einen hinterfragt er ein in vielen Gesellschaftsteilen vorherrschendes normativ-positivistisches Wissenschaftsverst{\"a}ndnis, welches er als elementar f{\"u}r die unkritische Rezeption von Statistiken als die Abbildung von Realit{\"a}t im Singular sieht. Zum anderen stellt er sich „gegen die Vorstellung, Wissenschaft werde von der Gesellschaft determiniert und Erfolg h{\"a}nge dann davon ab, was gesellschaftlich vorgegeben und akzeptiert wird (vgl. z. B. Bloor, 1991)" (S. 16). Um sich diesen Zielen anzun{\"a}hern, geht er der Frage nach, wie Zahlen und Statistiken so wichtig werden, dass sie mediale wie politische Diskurse formen, gar f{\"u}r Gesellschaftsgruppen beziehungsweise eine ganze Nation sprechen k{\"o}nnen.}, language = {de} } @article{KuthOberbergerKawalaetal.2025, author = {Kuth, Bastian and Oberberger, Max and Kawala, Felix and Reitter, Sander and Michel, Sebastian and Chajdas, Matth{\"a}us and Meyer, Quirin}, title = {Real-time meshlet decompression}, volume = {2025}, pages = {104292}, journal = {Computers \& Graphics}, number = {131}, publisher = {Elsevier}, address = {Amsterdam}, issn = {1873-7684}, doi = {https://doi.org/10.1016/j.cag.2025.104292}, year = {2025}, language = {en} } @inproceedings{DietlFacchi2025, author = {Dietl, Laura and Facchi, Christian}, title = {A Glimpse into the Future: An Inverse Soft Q-Learning's Soft Actor-Critic Approach for Pedestrian Path Prediction}, booktitle = {2025 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3315-3803-3}, doi = {https://doi.org/10.1109/IV64158.2025.11097431}, pages = {111 -- 118}, year = {2025}, language = {en} } @inproceedings{RothUlreichEbert2025, author = {Roth, Carla and Ulreich, Fabian and Ebert, Martin}, title = {Domain Awareness via Spectral-normalized Neural Gaussian Processes for E2E Autonomous Vehicle Control}, booktitle = {2025 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3315-3803-3}, doi = {https://doi.org/10.1109/IV64158.2025.11097444}, pages = {1668 -- 1673}, year = {2025}, language = {en} } @inproceedings{DietlFacchi2025, author = {Dietl, Laura and Facchi, Christian}, title = {Really, Pedestrian Trajectories: How Realistic are the Datasets?}, booktitle = {2025 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3315-3803-3}, doi = {https://doi.org/10.1109/IV64158.2025.11097441}, pages = {301 -- 308}, year = {2025}, language = {en} } @inproceedings{JagtapSongSadashivaiahetal.2025, author = {Jagtap, Abhishek Dinkar and Song, Rui and Sadashivaiah, Sanath Tiptur and Festag, Andreas}, title = {V2X-Gaussians: Gaussian Splatting for Multi-Agent Cooperative Dynamic Scene Reconstruction}, booktitle = {2025 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3315-3803-3}, doi = {https://doi.org/10.1109/IV64158.2025.11097436}, pages = {1033 -- 1039}, year = {2025}, language = {en} } @inproceedings{MosaferchiRienerNajafiGhobadietal.2025, author = {Mosaferchi, Saeedeh and Riener, Andreas and Najafi-Ghobadi, Khadijeh and Li, Tingnan and Naddeo, Alessandro}, title = {Shaping Affective Trust in Automated Vehicles: The Interplay of Initial Trust, Gender, and Biophilic Design}, booktitle = {2025 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3315-3803-3}, doi = {https://doi.org/10.1109/IV64158.2025.11097605}, pages = {1293 -- 1298}, year = {2025}, language = {en} } @inproceedings{EscherHerdeNikolaietal.2025, author = {Escher, Bengt and Herde, Jonas and Nikolai, Florian and Riener, Andreas}, title = {Regulating Teleoperation on Public Roads: Key Takeaways From an Expert Workshop}, booktitle = {2025 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3315-3803-3}, doi = {https://doi.org/10.1109/IV64158.2025.11097504}, pages = {2601 -- 2606}, year = {2025}, language = {en} } @unpublished{BhanderiAgrawalElger2025, author = {Bhanderi, Savankumar and Agrawal, Shiva and Elger, Gordon}, title = {Deep Segmentation of 3+1D Radar Point Cloud for Real-Time Roadside Traffic User Detection}, titleParent = {Research Square}, publisher = {Research Square}, address = {Durham}, doi = {https://doi.org/10.21203/rs.3.rs-7222130/v1}, year = {2025}, abstract = {Smart cities rely on intelligent infrastructure to enhance road safety, optimize traffic flow, and enable vehicle-to-infrastructure (V2I) communication. A key component of such infrastructure is an efficient and real-time perception system that accurately detects diverse traffic participants. Among various sensing modalities, automotive radar is one of the best choices due to its robust performance in adverse weather and low-light conditions. However, due to low spatial resolution, traditional clustering-based approaches for radar object detection often struggle with vulnerable road user detection and nearby object separation. Hence, this paper proposes a deep learning-based 3+1D radar point cloud clustering methodology tailored for smart infrastructure-based perception applications. This approach first performs semantic segmentation of the radar point cloud, followed by instance segmentation to generate well-formed clusters with class labels using a deep neural network. It also detects single-point objects that conventional methods often miss. The described approach is developed and experimented using a smart infrastructure-based sensor setup and it performs segmentation of the point cloud in real-time. Experimental results demonstrate 95.35\% F1-macro score for semantic segmentation and 91.03\% mean average precision (mAP) at an intersection over union (IoU) threshold of 0.5 for instance segmentation. Further, the complete pipeline operates at 43.61 frames per second with a memory requirement of less than 0.7 MB on the edge device (Nvidia Jetson AGX Orin).}, language = {en} } @article{WeihmayrBirknerMarzbanietal.2025, author = {Weihmayr, Daniel and Birkner, Christian and Marzbani, Hormoz and Jazar, Reza}, title = {Data-Driven Vehicle Dynamics: Lever-Aging SINDy for Optimization-Based Vehicular Motion Planning}, volume = {13}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2025.3594892}, pages = {136584 -- 136597}, year = {2025}, abstract = {Motion planning remains a crucial challenge for the widespread adoption of autonomous vehicles. This paper presents a novel approach that integrates an empirical plant model within an optimization-based motion planning architecture. The model prioritizes performance and efficiency while maintaining interpretability. We introduce a methodology that utilizes a data-driven approach to derive an interpretable description of the evolution of vehicle states over time using sparse regression. This method allows effective learning from limited datasets, eliminating the need for extensive and expensive data collection. Our approach addresses the trade-off between performance and accuracy, enabling adaptation to diverse driving scenarios. We affirm the efficacy of our methodology via an extensive analysis, evaluating the independent prediction performance across diverse metrics. Additionally, we examine the overall tracking performance when incorporated into an optimization-based framework. Finally, we present a comparative analysis and discuss the subsequent impact on overall motion planning and decision-making in relation to a state-of-the-art single-track model.}, language = {en} }