TY - JOUR A1 - Schmid, Maximilian A1 - Zippelius, Andreas A1 - Hanß, Alexander A1 - Böckhorst, Stephan A1 - Elger, Gordon T1 - Investigations on High-Power LEDs and Solder Interconnects in Automotive Application: Part II - Reliability JF - IEEE Transactions on Device and Materials Reliability UR - https://doi.org/10.1109/TDMR.2023.3300355 KW - LED KW - non-destructive testing KW - reliability KW - solder KW - scanning acoustic microscopy (SAM) KW - thermal impedance (Zth) KW - thermal resistant (Rth) KW - X-ray KW - transient thermal analysis (TTA) Y1 - 2023 UR - https://doi.org/10.1109/TDMR.2023.3300355 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-39651 SN - 1558-2574 SN - 1530-4388 VL - 23 IS - 3 SP - 419 EP - 429 PB - IEEE CY - New York ER - TY - JOUR A1 - Schmid, Maximilian A1 - Zippelius, Andreas A1 - Hanss, Alexander A1 - Böckhorst, Stephan A1 - Elger, Gordon T1 - Investigations on High-Power LEDs and Solder Interconnects in Automotive Application: Part I - Initial Characterization JF - IEEE Transactions on Device and Materials Reliability N2 - Thermo-mechanical reliability is one major issue in solid-state lighting. Mismatches in the coefficients of thermal expansion (CTE) between high-power LED packages and substrates paired with temperature changes induce mechanical stress. This leads to a thermal degradation of LED modules by crack formation in the solder interconnect and/or delamination in the substrate, which in turn increases junction temperature and thus decreases light output and reduces lifetime. To investigate degradation and understand influence of LED package design and solder material, a reliability study with a total of 1800 samples − segmented in nine LED types and five solder pastes − is performed. First of all, in this paper a state-of-the-art review of high-power LED packages is performed by analyzing and categorizing the packaging technologies. Second, the quality inspection after assembly is realized by transient thermal analysis (TTA), scanning acoustic microscopy (SAM) and X-ray. For TTA, a new method is introduced to separate the thermal resistance of the LED package from solder interconnect and substrate by applying the transient dual interface method (TDI) on samples with different solder interconnect void ratios. Further measurement effort is not required. The datasheet values for thermal resistance are verified and the different LED package types are benchmarked. The void ratio of the solder interconnects is determined by X-ray inspection combined with an algorithm to suppress disruptive internal LED package structures. TTA and TDI revealed that initial thermal performance is independent of solder paste type and that voiding is more critical to smaller LED packages. In addition, lower silver proportion in the paste is found to increase voiding. SAM is less sensitive for initial void detection than X-ray, but it’s applied to monitor crack propagation while aging in combination with TTA. The results of the reliability study, i.e., the crack growth under temperature shock test for the different SAC solders, will be presented in a second independent paper. UR - https://doi.org/10.1109/TDMR.2022.3152590 KW - LED KW - non-destructive testing KW - reliability KW - solder KW - scanning acoustic microscopy (SAM) KW - thermal impedance (Zth) KW - thermal resistant (Rth) KW - transient thermal analysis (TTA) KW - X-ray Y1 - 2022 UR - https://doi.org/10.1109/TDMR.2022.3152590 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-28799 SN - 1530-4388 SN - 1558-2574 VL - 22 IS - 2 SP - 175 EP - 186 PB - IEEE CY - New York ER - TY - JOUR A1 - Mohd, Zubair Akhtar A1 - Schmid, Maximilian A1 - Zippelius, Andreas A1 - Elger, Gordon T1 - Solder joint lifetime model using AI framework operating on FEA data JF - Engineering Failure Analysis N2 - The thermo-mechanical reliability of electronic systems is often limited by the crack growth within the solder joints. Addressing this issue requires careful consideration of the design of the package and solder pads. Finite Element Analysis (FEA) is widely used to predict crack growth and to model their lifetime. Traditionally, FEA post-processing methods rely on human expertise to select appropriate regions for evaluating plastic and creep strain at critical locations and correlating these values with experimental data using the Coffin-Manson equation, which predicts fatigue lifetime based on cyclic plastic strain. This study introduces a novel method for FEA post-processing of surface-mounted devices (SMD) on printed circuit boards (PCB) using artificial intelligence. The method transforms the FEA data into a 2D grid map of creep strain values and employs a Convolutional Neural Network (CNN) for automatic feature extraction. Afterwards, a fully connected layer correlates the extracted features with the experimental measured solder joint lifetime, effectively capturing nonlinear relationships. The study focuses on the development of the concept of crack formation in the solder interconnects of ceramic based high-power LED packages used in the automotive industry for headlights. The validated FEA model is based on an extensive data set of 1800 LED packages including seven different ceramic-based LED packages and five different solders. The design of the ceramic LED package covers two-pad and three-pad footprint for soldering and thin film and thick film metallized ceramic carriers. Results show a strong agreement (R2 Score is 99.867 %) between simulations and experimental data for ceramic LED packages. This automatic feature extraction from FEA data sets a new benchmark for improving solder reliability predictions, and it has proved to be better than established methods for lifetime prediction of solder joints. UR - https://doi.org/10.1016/j.engfailanal.2024.109032 Y1 - 2024 UR - https://doi.org/10.1016/j.engfailanal.2024.109032 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53803 SN - 1350-6307 VL - 2025 IS - 167, Part B PB - Elsevier CY - Oxford ER - TY - CHAP A1 - Mohd, Zubair Akhtar A1 - Kreiner, Christian A1 - Schmid, Maximilian A1 - Zippelius, Andreas A1 - Tetzlaff, Ulrich A1 - Elger, Gordon T1 - Fully Connected Neural Network (FCNN) Based Validation Framework for FEA Post Processing to Improve SAC Solder Reliability Analysis T2 - 2024 IEEE 10th Electronics System-Integration Technology Conference (ESTC), Proceedings UR - https://doi.org/10.1109/ESTC60143.2024.10712023 Y1 - 2024 UR - https://doi.org/10.1109/ESTC60143.2024.10712023 SN - 979-8-3503-9036-0 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Mohd, Zubair Akhtar A1 - Schmid, Maximilian A1 - Zippelius, Andreas A1 - Elger, Gordon T1 - LEDs Lifetime Prediction Modeling: Thermomechanical Simulation for SAC305 and SAC105 T2 - 2024 25th International Conference on Thermal, Mechanical and Multi-Physics Simulation and Experiments in Microelectronics and Microsystems (EuroSimE) UR - https://doi.org/10.1109/EuroSimE60745.2024.10491530 Y1 - 2024 UR - https://doi.org/10.1109/EuroSimE60745.2024.10491530 SN - 979-8-3503-9363-7 PB - IEEE CY - Piscataway ER - TY - JOUR A1 - Mohd, Zubair Akhtar A1 - Schmid, Maximilian A1 - Elger, Gordon T1 - AI-driven point cloud framework for predicting solder joint reliability using 3D FEA data JF - Scientific Reports N2 - Crack propagation in solder joints remains a major challenge impacting the thermo-mechanical reliability of electronic devices, underscoring the importance of optimizing package and solder pad designs. Traditional Finite Element Analysis (FEA) techniques for predicting solder joint lifespan often rely on manual post-processing to identify high-risk regions for plastic strain accumulation. However, this manual process can fail to detect complex and subtle failure mechanisms and purely based on averaging the creep strain and correlating it to lifetime values collected from experiments using Coffin Manson equation. To address these limitations, this study presents an Artificial Intelligence (AI) framework designed for automated 3D FEA post-processing of surface-mounted devices (SMDs) assembled to Printed Circuit Board (PCB). This framework integrates 3D Convolutional Neural Networks (CNNs) and PointNet architectures to automatically extract complex spatial features from 3D FEA data. These learned features are then linked to experimentally measured solder joint lifetimes through fully connected neural network layers, allowing the model to capture complex and nonlinear failure behaviours. The research specifically targets crack development in solder joints of ceramic-based high-power LED packages used in automotive lighting systems. This dataset included variations in two-pad and three-pad configurations, as well as thin and thick film metallized ceramic substrates. Results from the study demonstrate that the PointNet model outperforms the 3D CNN, achieving a high correlation with experimental data (R2 = 99.91%). This AI-driven, automated feature extraction approach significantly improves the accuracy and provide the more reliable models for solder joint lifetime predictions, offering a substantial improvement over traditional method. UR - https://doi.org/10.1038/s41598-025-06902-0 Y1 - 2025 UR - https://doi.org/10.1038/s41598-025-06902-0 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-60961 SN - 2045-2322 VL - 15 PB - Springer Nature CY - London ER - TY - INPR A1 - Mohd, Zubair Akhtar A1 - Schmid, Maximilian A1 - Elger, Gordon T1 - AI-Driven Point Cloud Framework for Predicting Solder Joint Reliability using 3D FEA Data T2 - Research Square N2 - Crack propagation in solder joints remains a critical challenge affecting the thermo-mechanical reliability of electronic devices, emphasizing the need for optimized package and solder pad designs. Traditional Finite Element Analysis (FEA) methods for predicting solder joint lifespan rely heavily on manual post-processing, where high-risk regions for plastic strain accumulation are identified. However, these approaches often overlook intricate failure mechanisms, as they primarily average creep strain and correlate it with experimental lifetime data using the Coffin-Manson equation, limiting their predictive accuracy. To overcome these limitations, this study introduces a novel AI-driven framework that automates 3D FEA post-processing for surface-mounted devices (SMDs) connected to printed circuit boards (PCBs). Unlike traditional methods, this framework leverages deep learning architectures—specifically, 3D Convolutional Neural Networks (CNNs) and PointNet—to extract complex spatial features directly from 3D FEA data, eliminating the need for manual interpretation. These learned features are then mapped to experimentally measured solder joint lifetimes through fully connected neural network layers, allowing the model to capture nonlinear failure behaviours that conventional methods fail to recognize. The research focuses on crack propagation in ceramic-based high-power LED packages used in automotive lighting systems, incorporating variations in two-pad and three-pad configurations, as well as thin and thick film metallized ceramic substrates with validated FEA models. Comparative analysis shows that PointNet significantly outperforms 3D CNNs, achieving an exceptionally high correlation with experimental data (R² = 99.99%). This AI-driven automated feature extraction and lifetime prediction approach marks a major advancement over traditional FEA-based methods, offering superior accuracy, reliability, and scalability for predicting solder joint reliability in microelectronics. UR - https://doi.org/10.21203/rs.3.rs-6173485/v1 Y1 - 2025 UR - https://doi.org/10.21203/rs.3.rs-6173485/v1 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58308 SN - 2693-5015 PB - Research Square CY - Durham ER - TY - CHAP A1 - Liu, E A1 - Mohd, Zubair Akhtar A1 - Steinberger, Fabian A1 - Wunderle, Bernhard A1 - Elger, Gordon T1 - Using µ-RAMAN Spectroscopy to Inspect Sintered Interconnects T2 - 2024 IEEE 10th Electronics System-Integration Technology Conference (ESTC), Proceedings UR - https://doi.org10.1109/ESTC60143.2024.10712149 Y1 - 2024 UR - https://doi.org10.1109/ESTC60143.2024.10712149 SN - 979-8-3503-9036-0 PB - IEEE CY - Piscataway ER - TY - JOUR A1 - Zippelius, Andreas A1 - Mohd, Zubair Akhtar A1 - Schmid, Maximilian A1 - Elger, Gordon T1 - Comparison of different Input data for the prediction of LED solder joints using Artificial Neural Networks JF - IEEE Transactions on Device and Materials Reliability N2 - Scarcity of raw data is a major issue for applying data driven methods to reliability prediction, so making the best use of what is available is critical. This paper studies how different aspects of measurement data can be used best. Specifically, the reliability of the solder joint of LED packages is predicted based on Transient Thermal Analysis and Scanning Acoustic Microscopy data from a large measurement campaign. The impact of using full temporal information vs measurements at individual datapoints is investigated as well as the benefit of including the SAM data, and different ways of presenting the TTA information, either as a full curve or as expert-selected features. The impact of formatting categorical information of solder and LED package type as one-hot encoding or using embeddings is considered. Finally, the performance for Pass/Fail predictions of the best identified model with a model architecture developed on a similar dataset is compared. We identified the most relevant sources of information for predicting the behavior and the best format for the data, which helps guide the choice for future model architectures. UR - https://doi.org/10.1109/TDMR.2025.3633876 Y1 - 2025 UR - https://doi.org/10.1109/TDMR.2025.3633876 SN - 1558-2574 PB - IEEE CY - New York ER - TY - JOUR A1 - Xu, Wenguang A1 - Membarth, Richard T1 - Exploration of Efficient Computation for Trajectory Planning via Fixed-Point Arithmetic JF - PARS-Mitteilungen 2025 Y1 - 2025 UR - https://dl.gi.de/items/6b2c0546-1081-40ab-b97b-052b60b8374f SN - 0177-0454 VL - 37 SP - 51 EP - 61 PB - Gesellschaft für Informatik CY - Bonn ER - TY - JOUR A1 - Meess, Henri A1 - Gerner, Jeremias A1 - Hein, Daniel A1 - Schmidtner, Stefanie A1 - Elger, Gordon A1 - Bogenberger, Klaus T1 - First steps towards real-world traffic signal control optimisation by reinforcement learning JF - Journal of Simulation N2 - Enhancing traffic signal optimisation has the potential to improve urban traffic flow without the need for expensive infrastructure modifications. While reinforcement learning (RL) techniques have demonstrated their effectiveness in simulations, their real-world implementation is still a challenge. Real-world systems need to be developed that guarantee a deployable action definition for real traffic systems while prioritising safety constraints and robust policies. This paper introduces a method to overcome this challenge by introducing a novel action definition that optimises parameter-level control programmes designed by traffic engineers. The complete proposed framework consists of a traffic situation estimation, a feature extractor, and a system that enables training on estimates of real-world traffic situations. Further multimodal optimisation, scalability, and continuous training after deployment could be achieved. The first simulative tests using this action definition show an average improvement of more than 20% in traffic flow compared to the baseline – the corresponding pre-optimised real-world control. UR - https://doi.org/10.1080/17477778.2024.2364715 Y1 - 2024 UR - https://doi.org/10.1080/17477778.2024.2364715 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-48585 SN - 1747-7778 VL - 18 IS - 6 SP - 957 EP - 972 PB - Taylor & Francis CY - London ER - TY - JOUR A1 - Wan, Lei A1 - Zhao, Jianxin A1 - Wiedholz, Andreas A1 - Bied, Manuel A1 - Martinez de Lucena, Mateus A1 - Jagtap, Abhishek Dinkar A1 - Festag, Andreas A1 - Fröhlich, Antônio A1 - Keen, Hannan Ejaz A1 - Vinel, Alexey T1 - A Systematic Literature Review on Vehicular Collaborative Perception—A Computer Vision Perspective JF - IEEE Transactions on Intelligent Transportation Systems N2 - The effectiveness of autonomous vehicles relies on reliable perception capabilities. Despite significant advancements in artificial intelligence and sensor fusion technologies, current single-vehicle perception systems continue to encounter limitations, notably visual occlusions and limited long-range detection capabilities. Collaborative Perception (CP), enabled by Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication, has emerged as a promising solution to mitigate these issues and enhance the reliability of autonomous systems. Beyond advancements in communication, the computer vision community is increasingly focusing on improving vehicular perception through collaborative approaches. However, a systematic literature review that thoroughly examines existing work and reduces subjective bias is still lacking. Such a systematic approach helps identify research gaps, recognize common trends across studies, and inform future research directions. In response, this study follows the PRISMA 2020 guidelines and includes 106 peer-reviewed articles. These publications are analyzed based on modalities, collaboration schemes, and key perception tasks. Through a comparative analysis, this review illustrates how different methods address practical issues such as pose errors, temporal latency, communication constraints, domain shifts, heterogeneity, and adversarial attacks. Furthermore, it critically examines evaluation methodologies, highlighting a misalignment between current metrics and CP’s fundamental objectives. By delving into all relevant topics in-depth, this review offers valuable insights into challenges, opportunities, and risks, serving as a reference for advancing research in vehicular collaborative perception. UR - https://doi.org/10.1109/TITS.2025.3631141 Y1 - 2025 UR - https://doi.org/10.1109/TITS.2025.3631141 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-64708 SN - 1558-0016 VL - 27 IS - 1 SP - 81 EP - 118 PB - IEEE CY - New York ER - TY - JOUR A1 - Gregor, Markus A1 - Bauder, Maximilian A1 - Kirsten Vidal de Oliveira, Aline A1 - Mast, Pascal A1 - Rüther, Ricardo A1 - Schweiger, Hans-Georg T1 - Approaches for Lifetime Prediction of Vehicle Traction Battery Systems During a Technical Inspection: A Systematic Review JF - World Electric Vehicle Journal N2 - Creating trust in society for new technologies, such as a new types of powertrains, and making them marketable requires transparent, neutral, and independent technical verification. This is crucial for the acceptance and success of electrified vehicles in the used car markets. A key component of electric vehicles is the traction battery, whose current and future condition, particularly regarding aging, determines its residual value and safe operation. This review aims to identify and evaluate methods for predicting the lifetime of onboard traction batteries, focusing on their applicability in technical inspections. A systematic literature and patent review was conducted using targeted keywords, yielding 22 patents and 633 publications. From these, 150 distinct lifetime prediction methods were extracted and categorized into a four-level mind map. These methods are summarized, cited, and structured in detailed tables. The relationships between approaches are explained to clarify the current research landscape. Long Short-Term Memory, Convolutional Neural Networks, and Particle Filters were identified as the most frequently used techniques. However, no methods were found suitable for predicting the lifetime of traction batteries during technical vehicle inspections, which operate under short test durations, limited data access, and diverse real-world operating conditions. Most studies focused on cell-level testing and did not address complete battery systems in operational vehicles. This gap highlights the need for applied research and the development of practical methods to support battery assessment in real-world conditions. Advancing this field is essential to foster confidence in battery systems and enable a sustainable transition to electromobility. UR - https://doi.org/10.3390/wevj17010003 Y1 - 2025 UR - https://doi.org/10.3390/wevj17010003 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-65631 SN - 2032-6653 VL - 17 IS - 1 PB - MDPI CY - Basel ER - TY - CHAP A1 - Gerner, Jeremias A1 - Bogenberger, Klaus A1 - Schmidtner, Stefanie T1 - Investigating Floating Car Observers for Traffic State Estimation through Co-Simulation T2 - MFTS: The 5th Symposium on Management of Future Motorway and Urban Traffic System 2024 Y1 - 2024 PB - Technion CY - Haifa ER - TY - THES A1 - Iberl, Andreas Benedikt T1 - Numerische Untersuchungen des kapillaren Aufstiegs und der Validität des Berechnungsverfahrens mit interFoam N2 - Diese Arbeit liefert einen Beitrag zur Beschreibung des kapillaren Aufstiegs zwischen zwei parallelen Platten und innerhalb eines kreisrunden zylindrischen Rohrs mit Methoden aus dem Bereich der numerischen Strömungsmechanik. Dabei wird mit dem Gleichungslöser interFoam aus dem Softwarepaket OpenFOAM gearbeitet und verschiedene Studien vorgestellt. Zunächst werden die Grundlagen aus dem Bereich der Strömungsmechanik und der Strömungssimulation erklärt, bevor einige Ergebnisse aus der Literatur analysiert werden. Daraufhin werden eigene Resultate aus unterschiedlichen numerischen Untersuchungen gezeigt, wobei keine endgültige Netzunabhängigkeit erreicht wird. Wichtig ist die Erkenntnis, dass der Kompressionsfaktor aus dem MULES-Algorithmus für eine korrekte Abbildung des kapillaren Aufstiegs null sein muss, da ansonsten die Phasengrenzfläche komprimiert wird und der stationäre Wert nicht erreicht wird. Mit Implementierung einer Schlupfrandbedingung wird außerdem eine gute Übereinstimmung mit numerischen Werten aus der Literatur erzielt, wobei die Größe der Schlupflänge noch näher untersucht werden sollte. Innerhalb dieser Arbeit wird eine vom Netz unabhängige stationäre Steighöhe erreicht, die auch mit einem relativ groben Netz berechnet werden kann. Eine Annäherung des berechneten Kapillardrucks und des Kontaktwinkels an analytisch ermittelte Werte konnte ebenfalls verwirklicht werden. Y1 - 2022 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-35403 CY - Ingolstadt ER - TY - INPR A1 - Haryanto, Aditya A1 - Vaculin, Ondrej T1 - YoFlow Method for Scenario Based Automatic Accident Detection N2 - Recent advances in sensor and computing technologies have enabled roadside units (RSUs) to not only monitor traffic flow but also process data in real time to improve road safety. However, leveraging RSUs for proactive accident detection remains a challenging and underexplored task, partly due to the lack of diverse accident data. To address this, this study proposes two key contributions: (i) a scenario based synthetic data generation framework, and (ii) YoFlow, a novel system for vehicle-to-vehicle accident detection from a simulated RSU camera perspective. The proposed framework leverages the PEGASUS methodology and the BeamNG.tech simulation platform to create the SB-SIF dataset, which includes five representative intersection crash scenarios derived from German accident data. SB-SIF dataset contains 914 crash videos, 123 near-miss events, and 924 normal traffic instances and is publicly available at: https://doi.org/10.5281/zenodo.15267252. The proposed YoFlow system identifies accidents by analyzing temporal variations in vehicle speed vectors, using YOLO for vehicle classification and CUDA-accelerated dense optical flow to capture abrupt motion changes. Extracted features are processed and classified using an XGBoost model, achieving 94% recall and 90% precision in accident detection. UR - https://doi.org/10.36227/techrxiv.175099959.99453472/v1 Y1 - 2025 UR - https://doi.org/10.36227/techrxiv.175099959.99453472/v1 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-60556 PB - TechRxiv CY - Piscataway ER - TY - THES A1 - Klaumann Gubert, Gabriel Vitor T1 - Evaluation of the impact of the posit quantization on the inference performance of a deep learning neural network for 3D object detection and classification with RADAR and camera N2 - The evolution of autonomous driving is influenced by the convergence of technologies shaping the capabilities of perception systems. This study reflects the interaction between deep learning, specialized hardware accelerators, and advanced numerical representations, specifically Posits, in the context of CenterFusion - a middle-fusion method for fusing radar and camera data designed for autonomous vehicles. In order to optimize the CenterFusion for embedded systems, a parameter quantization and hardware inference technique using Posit numbers was developed, named Posits4Torch and Posits4TorcHA. Posit is a type of floating-point numerical representation and arithmetic whose fields have variable sizes, resulting in non-uniform precision. The main objective of this study is to evaluate the reduction in memory usage, processing speed gain, and degradation of CenterFusion performance, when subjected to Posit quantization, in terms of the average errors and the NuScenes Detection Score. The results demonstrate that the inference errors for both the Deep PeNSieve-emulated model on an AMD EPYC 7413 24-Core CPU and the Posits4TorcHA-based model on an AMD Kria KV260 Vision Starter Kit FPGA were identical. The FPGA-based model's inference time of 3,49 seconds was nearly 1000 times lower than the 3194,69 seconds of the CPU model but 300 times higher than the PyTorch GPU model, which ran on a NVIDIA GeForce RTX 3090. Moreover, FPGA implementation metrics for the 2D 8x8 Posit MAC Unit Array on the AMD Kria KV260 showed a power consumption of 2,939 W, 3,033 W, and 3,090 W for Posit precisions of 6, 7, and 8 bits, respectively, highlighting the approach's resource efficiency. When quantizing CenterFusion's regression heads, an 8-bit Posit precision for Posit-as-Storage (PaS) resulted in a degradation in the Mean Average Precision (mAP) and NuScenes Detection Score (NDS) of, respectively, 0,7% and 0,5%. For Posit-as-Arithmetic (PaA) on the FPGA, certain metrics like Mean Average Velocity Error (mAVE) and Mean Average Translation Error (mATE) were more affected, with 8-bit precision leading to degradations in mAP and NDS by 9,8% and 7,7%, respectively, which can be improved by training the model with a higher Posit precision and subsequently quantizing to a lower Posit precision using Posits4Torch. This approach presents a promising perspective for optimizing neural network performance in perception and sensor fusion systems for autonomous vehicles. By improving efficiency using lower bit-widths without compromising too much accuracy, this research contributes to the development of more energy-efficient high-speed AI solutions for autonomous vehicle's embedded systems, demonstrating ongoing progress in the field of autonomous driving technology. Key-words: posit, autonomous driving, hardware acceleration. Y1 - 2024 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-50204 CY - Ingolstadt ER - TY - THES A1 - Ravichandran, Sai Sharan T1 - Transparent rating of multivariate time series classification using explainable AI N2 - Validation of virtual simulation models, particularly for crash tests and occupant safety, is crucial. Traditionally, experts manually validate these models. In the arTIco project by Applus+ IDIADA and C-ISAFE at Technische Hochschule Ingolstadt, an AI model was developed to classify correlation ratings of digital twins into "Good," "Acceptable," "Marginal," or "Poor" based on expert-labeled data. Although these AI models show high accuracy, their decision-making processes are not easily understood. This master's thesis aims to use Explainable AI (XAI) algorithms to interpret the AI model used in arTIco, focusing on understanding the model's decisions and learned patterns. Model-agnostic SHAP methods, including kernelSHAP, deepSHAP, and windowSHAP, are employed to identify key feature points influencing decisions. These are compared with expert criteria to ensure alignment. The study also addresses challenges and limitations of using Shapley values for multivariate time series data. Y1 - 2024 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-50106 CY - Ingolstadt ER - TY - THES A1 - dos Santos Silva, Jaqueline T1 - Prediction of communication signal strength with UAVs using artificial neural networks N2 - Recognizing the growing importance of unmanned aerial vehicles, notably drones, in the surveillance of urban traffic operations, this research initiative seeks to address the challenges associated with wireless communication in signal-interference-prone environments. It proposes the formulation of a specialized artificial neural network designed to predict the Wi-Fi signal strength during drone flights, thereby providing support in emergency scenarios that involve rescue operations at traffic accident sites. The developed algorithm is a multilayer perceptron with one hidden layer and the following input features: altitude, elevation angle, type of terrain, the distance between the drone and its controller, velocity, and battery percent. To validate the reliability of the proposed solution, outcomes derived from the neural network were juxtaposed with drone flight simulations using the Longley-Rice model conducted in Radio Mobile, a software extensively utilized for the planning and modeling of wireless communication networks. For the rural region, the perceptron multilayer achieved an RMSE of 1.95 dB, while the Longley-Rice model showed a significantly higher RMSE of 8.23 dB. In the suburban region, the perceptron multilayer presented an RMSE of 2.93 dB, compared to the Longley-Rice model's RMSE of 10.88 dB. In the urban region, the perceptron multilayer had an RMSE of 2.39 dB, whereas the Longley-Rice model exhibited the RMSE of 12.84 dB. These findings highlight the perceptron multilayer as a promising alternative for signal intensity prediction in areas with different levels of urbanization. Y1 - 2024 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-50193 CY - Ingolstadt ER - TY - THES A1 - Patel, Chintan Tinesh T1 - Implementation of dynamic trajectory control for an industrial robot by external dSPACE real-time system using the KUKA RSI interface N2 - This master's thesis focuses on developing a solution to avoid kinematic singularities in six axis serial industrial robots by employing alternative path planning strategies near the singularity. The proposed solution involves implementing a sample-based path searching algorithm that enables the robot to temporarily deviate from its original path, thereby avoiding the singularity and ensuring continuous, smooth motion. Y1 - 2024 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-49987 CY - Ingolstadt ER - TY - THES A1 - Vyas, Meet Hitendrabhai T1 - Centralized traffic signal control for critical crossing scenarios N2 - Efficient traffic signal control is crucial for optimizing urban mobility, reducing congestion, and enhancing road safety. This thesis explores a centralized approach to control traffic signals, specifically tailored for critical crossing scenarios where traditional decentralized systems often fail to adapt dynamically to fluctuating traffic conditions. The study develops and evaluates a centralized traffic signal control algorithm that leverages data including vehicle counts from the virtual environment. By integrating CARLA's API (Application Programming Interface), the proposed system anticipates traffic flow variations and adjusts signal timings accordingly to minimize delays and enhance the throughput of intersections. The productiveness of the centralized control strategy is demonstrated through a series of simulations and virtual-world trials, highlighting significant improvements in average wait times and overall traffic efficiency compared to conventional and existing methods. With this approach, an improvised version of the Traffic manager controls the traffic lights based on the different situations to avoid traffic jams compared to the existing traffic manager in CARLA. This research contributes to the field of traffic management by providing a framework for centralized control in complex traffic environments, paving the way for smarter and more responsive urban infrastructure. Y1 - 2024 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-51341 CY - Ingolstadt ER - TY - THES A1 - Kern, Tobias T1 - Loss optimisation in the drive train with PMSM taking into account the interaction of the switching frequency and behavior of SiC mosfets N2 - For electric vehicles, the range becomes more and more relevant. Adding more battery weight will add additional drivable range at the cost of increased energy consumption of the vehicles. Therefore this work aims to minimize the traction system losses by investigating inverters switching frequency. Mathematical descriptions of the losses were implemented, and simulation models were set up based on the reviewed literature. These models were validated against the mathematical description and the manufacturer's online tool. This work results in a mathematical approach to determine the efficiency optimal switching frequency. The derived behavior could also be reproduced by simulation. Due to the unavailability of hardware, the models are not checked against the real world. When the hardware is available, the validation will be completed. Y1 - 2022 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-34833 CY - Ingolstadt ER - TY - CHAP A1 - Rauscher, Andreas A1 - Braun, Julian A1 - Hiemer, Rainer A1 - Heldwein, Marcelo Lobo A1 - Endisch, Christian T1 - Convolutional Neural Networks and Thresholding Approaches for Single and Multi-Sensor Detection of Partial Discharges in Electrical Machine Stators T2 - Proceedings of the 15th International 2025 IEEE Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives (SDEMPED) UR - https://doi.org/10.1109/SDEMPED53223.2025.11153974 Y1 - 2025 UR - https://doi.org/10.1109/SDEMPED53223.2025.11153974 SN - 979-8-3503-8820-6 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Hoppe, Frederik A1 - Verdun, Claudio Mayrink A1 - Krahmer, Felix A1 - Menzel, Marion Irene A1 - Rauhut, Holger T1 - With or Without Replacement? Improving Confidence in Fourier Imaging T2 - 2024 International Workshop on the Theory of Computational Sensing and its Applications to Radar, Multimodal Sensing and Imaging (CoSeRa) UR - https://doi.org/10.1109/CoSeRa60846.2024.10720357 Y1 - 2024 UR - https://doi.org/10.1109/CoSeRa60846.2024.10720357 SN - 979-8-3503-6550-4 SP - 66 EP - 70 PB - IEEE CY - Piscataway ER - TY - JOUR A1 - Haryanto, Aditya A1 - Vaculin, Ondrej T1 - YoFlow Method for Scenario Based Automatic Accident Detection JF - IEEE Open Journal of Intelligent Transportation Systems N2 - Recent advances in sensor and computing technologies have enabled road side units (RSUs) to not only monitor traffic flow but also process data in real time to improve road safety. However, leveraging RSUs for proactive accident detection remains a challenging and underexplored task, partly due to the lack of diverse accident data. To address this, this study proposes two key contributions: (i) a scenario-based synthetic data generation framework, and (ii) YoFlow, a novel system for vehicle-tovehicle accident detection from a simulated RSU camera perspective. The proposed framework leverages the PEGASUS method for scenario generation strategy and BeamNG.tech for generating synthetic traffic videos. This approach led to the development of the SB-SIF dataset, which includes five representative intersection crash scenarios derived from German accident data. The SB-SIF dataset contains 914 crash videos, 123 near-miss events, and 924 normal traffic instances and is publicly available at: https://doi.org/10.5281/zenodo.15267252. The proposed YoFlow system identifies accidents by analyzing temporal variations in vehicle speed vectors, using YOLO for vehicle classification and CUDA-accelerated dense optical flow to capture abrupt motion changes. The extracted features are processed and classified using an XGBoost model, achieving 94% recall and 90% precision in accident detection. UR - https://doi.org/10.1109/OJITS.2025.3639557 KW - accident detection KW - traffic accident KW - surveillance camera KW - optical flow KW - traffic scenarios Y1 - 2025 UR - https://doi.org/10.1109/OJITS.2025.3639557 SN - 2687-7813 VL - 7 SP - 61 EP - 73 PB - IEEE CY - New York ER - TY - JOUR A1 - Geisbauer, Christian A1 - Wöhrl, Katharina A1 - Lott, Susanne A1 - Nebl, Christoph A1 - Schweiger, Hans-Georg A1 - Goertz, Roland A1 - Kubjatko, Tibor T1 - Scenarios involving accident-damaged electric vehicles JF - Transportation Research Procedia N2 - Electrically propelled cars will play a major role on the streets, not only in the far, but also in the near future. In this work, an overview on the possible risks arising from electric vehicles is given that involves electrical, chemical and thermal hazards. Additionally, an analysis on different scenarios involving damaged electric vehicles, the involved parties, as well as their risk assessment in terms of hazard rating is presented. Furthermore, two scenarios are explained and addressed with more detail. With the derived risks of the battery and with possible crash scenarios presented, the still existing uncertainties for handling damaged electric vehicles are addressed, followed by a discussion on ways to overcome this problem. UR - https://doi.org/10.1016/j.trpro.2021.07.136 KW - electromobility KW - batteries KW - lithium ion KW - electric vehicle KW - accident KW - rescue service KW - recycling Y1 - 2021 UR - https://doi.org/10.1016/j.trpro.2021.07.136 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-13130 SN - 2352-1465 VL - 2021 IS - 55 SP - 1484 EP - 1489 PB - Elsevier CY - Amsterdam ER - TY - CHAP A1 - Paula, Daniel A1 - Bauder, Maximilian A1 - König, Thomas A1 - Dengler, Yannick A1 - Böhm, Klaus A1 - Kubjatko, Tibor A1 - Schweiger, Hans-Georg T1 - Impact of vehicle electrification on fundamental accident reconstruction parameters T2 - Proceedings of the 30th Annual Congress of the EVU Y1 - 2022 SP - 34 EP - 41 PB - EVU CY - Berlin ER - TY - CHAP A1 - Paula, Daniel A1 - Bauder, Maximilian A1 - König, Thomas A1 - Kubjatko, Tibor A1 - Schweiger, Hans-Georg T1 - Systematic investigation of influences on advanced driver assistance systems for accident reconstruction T2 - Proceedings of the 31st Annual Congress of the EVU Y1 - 2023 SP - 253 EP - 261 PB - EVU CY - Berlin ER - TY - CHAP A1 - Bauder, Maximilian A1 - Paula, Daniel A1 - Böhm, Klaus A1 - Kubjatko, Tibor A1 - Wech, Lothar A1 - Schweiger, Hans-Georg T1 - Opportunities and challenges of cooperative intelligent transportation systems on accident analysis T2 - Proceedings of the 30th Annual Congress of the EVU Y1 - 2022 PB - EVU CY - Berlin ER - TY - JOUR A1 - Graf, Michael A1 - Steinhauser, Dagmar A1 - Vaculin, Ondrej A1 - Brandmeier, Thomas T1 - Impact of Adverse Weather on Road Safety: A Survey of Test Methods for Enhancing Safety of Automated Vehicles and Sensor Robustness in Challenging Environmental Conditions JF - IEEE Access N2 - Adverse weather conditions can significantly affect environmental sensors and reduce the ability of automated vehicles to interpret the environment. This can lead to the failure of driving and safety functions. To validate and increase the robustness of these, several adverse weather test methods have been introduced in recent years. The survey first gives an overview of the current traffic and accident analysis with a focus on adverse weather influences to assess the most relevant weather phenomena. Overall, rain and glare are the statistically most important adverse weather phenomena in terms of accidents. Heavy fog is rare but can cause very serious accidents. In a second step, meteorological knowledge is incorporated and the key environmental indicators for the respective weather conditions are determined, particularly taking the environmental sensor characteristics into account. Both sets of information are then utilized to provide a qualified overview of simulative and physical test methods used to reproduce critical adverse weather situations. These methods are employed to investigate the disturbance effects of inclement weather on sensors and to test the robustness of automated vehicles. The paper reveals that various approaches are used to reproduce weather effects and that test methods, each with different advantages and disadvantages, have been developed to varying degrees depending on the type of the weather phenomena. Overall, this review integrates perspectives from road safety research, meteorology, and testing methodologies to provide new insights into the validation of automated driving systems in challenging weather conditions. UR - https://doi.org/10.1109/ACCESS.2025.3622501 Y1 - 2025 UR - https://doi.org/10.1109/ACCESS.2025.3622501 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-63190 SN - 2169-3536 VL - 13 SP - 179817 EP - 179838 PB - IEEE CY - New York ER - TY - JOUR A1 - König, Thomas A1 - Paula, Daniel A1 - Quaschner, Stefan A1 - Schweiger, Hans-Georg T1 - Influence of Blind Spot Assistance Systems in Heavy Commercial Vehicles on Accident Reconstruction JF - Sensors N2 - Accidents between right-turning commercial vehicles and crossing vulnerable road users (VRUs) in urban environments often lead to serious or fatal injuries and therefore play a significant role in forensic accident analysis. To reduce the risk of accidents, blind spot assistance systems have been installed in commercial vehicles for several years, among other things, to detect VRUs and warn the driver in time. However, since such systems cannot reliably prevent all turning accidents, an investigation by experts must clarify how the accident occurred and to what extent the blind spot assistance system influenced the course of the accident. The occurrence of the acoustic warning message can be defined as an objective reaction prompt for the driver, so that the blind spot assistance system can significantly influence the avoidability assessment. In order to be able to integrate the system into forensic accident analysis, a precise knowledge of how the system works and its limitations is required. For this purpose, tests with different systems and accident constellations were conducted and evaluated. It was found that the type of sensor used for the assistance systems has a great influence on the system’s performance. The lateral distance between the right side of the commercial vehicle and the VRU, as well as obstacles between them, along with the speed difference can have great influence on the reliability of the assistance system. Depending on the concrete time of the system’s warning signal, the accident can be avoided or not by the driver when reacting to this signal. UR - https://doi.org/10.3390/s24051517 KW - accident analysis KW - accident reconstruction KW - road safety KW - vehicle active safety Y1 - 2024 UR - https://doi.org/10.3390/s24051517 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-47143 SN - 1424-8220 VL - 24 IS - 5 PB - MDPI CY - Basel ER - TY - JOUR A1 - Bauder, Maximilian A1 - Paula, Daniel A1 - Kubjatko, Tibor A1 - Schweiger, Hans-Georg T1 - Evaluation of the vehicle behaviour when not responding to the take-over request of Tesla Autopilot and Volkswagen Travel Assist JF - Transportation Research Procedia N2 - In this work, driving tests were carried out with a Tesla Model 3 and VW ID.4. During the tests, the vehicles were controlled by an SAE Level 2 system (Tesla Autopilot and VW Travel Assist). The study aimed to investigate the behaviour of the vehicles when the driver does not react to the take-over request of the vehicle while it is in a non-critical driving situation. The aim was to clarify whether this can lead to accidents from a purely technical point of view and whether there is still room for improvement. As a result, it could be determined that a non-reaction of the driver to the take-over request leads to system-initiated braking decelerations, which can lead to a rear-end collision by the following traffic. Furthermore, secondary accidents are possible if the driver fails to act as a fallback. This could be reduced by improving the applicable UNECE standard R79 by specifying deceleration values for this case. In addition, the risk of an accident could be reduced by decelerating earlier and warning the environment. For this purpose, a driver monitoring system would also be recommended to allow situational decisions by the system. The implementation of the measures proposed could result in a significant increase in road safety while using these systems. UR - https://doi.org/10.1016/j.trpro.2023.11.167 Y1 - 2024 UR - https://doi.org/10.1016/j.trpro.2023.11.167 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-63210 SN - 2352-1465 VL - 2023 IS - 74 SP - 450 EP - 457 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Langer, Robin A1 - Bauder, Maximilian A1 - Paula, Daniel A1 - Kubjatko, Tibor A1 - Schweiger, Hans-Georg T1 - Development of a model environment for autonomous driving JF - Transportation Research Procedia N2 - Developing automated driving functions can be elaborate and cost-intensive. Simulation helps to decrease both, the effort and the costs. With physical model environments of a smaller scale, automotive research can be improved even further. This work presents a method with five steps for building a scaled model environment to answer research questions regarding autonomous driving functions in the automotive domain. For this purpose, the five steps of the method are first introduced and explained. Each step comes with indications that can be further extended. Then, the method is performed by creating a model environment. The model environment build in this work is a recreation of an urban intersection in Ingolstadt, Germany, in the scale of 1:10. In addition to two model vehicles, the model environment consists of pedestrians and traffic control elements such as signs, signals, various lanes and road markings. The advantages of the model environment are low costs and high reproducibility. On the other hand it comes with limitations. For example, the materials used for construction (polylactic acid) are different from the materials in reality. The aim of this work was achieved by providing a method for building a model environment for automotive domain. The limitations of the built model environment and actual testing of automated driving functions will be performed in the future. UR - https://doi.org/10.1016/j.trpro.2023.11.122 Y1 - 2024 UR - https://doi.org/10.1016/j.trpro.2023.11.122 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-63201 SN - 2352-1465 VL - 2023 IS - 74 SP - 133 EP - 140 PB - Elsevier CY - Amsterdam ER - TY - CHAP A1 - Sequeira, Gerald Joy A1 - Inderst, Maximilian A1 - Xhiku, Redjon A1 - Lugner, Robert A1 - Brandmeier, Thomas T1 - Sigmoid-Based Method for Longitudinal Crash Pulse Prediction in Intelligent Vehicles T2 - 2024 IEEE International Conference on Vehicular Electronics and Safety (ICVES) UR - https://doi.org/10.1109/ICVES61986.2024.10927899 Y1 - 2025 UR - https://doi.org/10.1109/ICVES61986.2024.10927899 SN - 979-8-3503-8727-8 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Inderst, Maximilian A1 - Lugner, Robert A1 - Brandmeier, Thomas A1 - Mehrzed, Shaen A1 - Sequeira, Gerald Joy A1 - Griebeler, Marcelo T1 - Definition of Requirements for the Temporal Accuracy of Inevitability Evaluation in Integral Pre-crash Systems T2 - FAST-Zero'23: 7th International Symposium on Future Active Safety Technology toward Zero Accidents - Proceedings Y1 - 2023 UR - https://tech.jsae.or.jp/paperinfo/en/content/conf2023-03.004/ PB - JSAE CY - Gobancho ER - TY - INPR A1 - König, Thomas A1 - Paula, Daniel A1 - Quaschner, Stefan A1 - Schweiger, Hans-Georg T1 - Influence of Blind Spot Assistance Systems in Heavy Commercial Vehicles on Accident Reconstruction N2 - Accidents between right-turning commercial vehicles and crossing vulnerable road users (VRU) in urban environments often lead to serious or fatal injuries and therefore play a significant role in forensic accident analysis. To reduce the risk of accidents, blind spot assistance systems have been installed in commercial vehicles for several years, among other things, to detect VRUs and warn the driver in time. However, since such systems cannot reliably prevent all turning accidents, an investigation by experts must clarify how the accident occurred and to what extent the blind spot assistance system influenced the course of the accident. The occurrence of the acoustic warning message can be defined as an objective reaction prompt for the driver, so that the blind spot assistance system can significantly influence the avoidability assessment. In order to be able to integrate the system into forensic accident analysis, a precise knowledge of how the system works and its limitations is required. For this purpose, tests with different systems and accident constellations were conducted and evaluated. It was found that the type of sensor used for the assistance systems has a great influence on the system’s performance. The lateral distance between the right side of the commercial vehicle and the VRU as well as obstacles between them and the speed difference can take great influence on the reliability of the assistance system. Depending on the concrete time of the system’s warning signal the accident can be avoided or not by the driver when reacting on this signal. UR - https://doi.org/10.20944/preprints202311.1308.v1 Y1 - 2023 UR - https://doi.org/10.20944/preprints202311.1308.v1 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58430 PB - Preprints CY - Basel ER - TY - CHAP A1 - Paula, Daniel A1 - König, Thomas A1 - Bauder, Maximilian A1 - Petermeier, Franziska A1 - Kubjatko, Tibor A1 - Schweiger, Hans-Georg T1 - Performance Tests of the Tesla Autopilot and VW Travel Assist on a Rural Road T2 - Transport Means 2022: Proceedings of the 26th International Scientific Conference - Part II UR - https://doi.org/10.5755/e01.2351-7034.2022.P2 KW - Accidents Analysis KW - SAE Level 2 Systems KW - VW Travel Assist KW - Tesla Autopilot KW - Performance test Y1 - 2022 UR - https://doi.org/10.5755/e01.2351-7034.2022.P2 SN - 2351-7034 SN - 1822-296X SP - 498 EP - 508 PB - Kaunas University of Technology CY - Kaunas ER - TY - JOUR A1 - Paula, Daniel A1 - Bauder, Maximilian A1 - König, Thomas A1 - Böhm, Klaus A1 - Kubjatko, Tibor A1 - Schweiger, Hans-Georg T1 - Fahrerassistenzsysteme – Herausforderungen & Chancen für die forensische Unfallanalyse JF - Zeitschrift für Verkehrssicherheit Y1 - 2022 UR - https://www.kirschbaum.de/fachzeitschriften/zeitschrift-fuer-verkehrssicherheit/zvs/aktuelles-heft-6.html#c11330 SN - 0044-3654 VL - 2022 IS - 4 PB - Kirschbaum Verlag GmbH CY - Bonn ER - TY - INPR A1 - Kettelgerdes, Marcel A1 - Hillmann, Tjorven A1 - Hirmer, Thomas A1 - Erdogan, Hüseyin A1 - Wunderle, Bernhard A1 - Elger, Gordon T1 - Accelerated Real-Life (ARL) Testing and Characterization of Automotive LiDAR Sensors to facilitate the Development and Validation of Enhanced Sensor Models N2 - In the realm of automated driving simulation and sensor modeling, the need for highly accurate sensor models is paramount for ensuring the reliability and safety of advanced driving assistance systems (ADAS). Hence, numerous works focus on the development of high-fidelity models of ADAS sensors, such as camera, Radar as well as modern LiDAR systems to simulate the sensor behavior in different driving scenarios, even under varying environmental conditions, considering for example adverse weather effects. However, aging effects of sensors, leading to suboptimal system performance, are mostly overlooked by current simulation techniques. This paper introduces a cutting-edge Hardware-in-the-Loop (HiL) test bench designed for the automated, accelerated aging and characterization of Automotive LiDAR sensors. The primary objective of this research is to address the aging effects of LiDAR sensors over the product life cycle, specifically focusing on aspects such as laser beam profile deterioration, output power reduction and intrinsic parameter drift, which are mostly neglected in current sensor models. By that, this proceeding research is intended to path the way, not only towards identifying and modeling respective degradation effects, but also to suggest quantitative model validation metrics. UR - https://doi.org/10.48550/arXiv.2312.04229 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2312.04229 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-59856 PB - arXiv CY - Ithaca ER - TY - JOUR A1 - Beutenmüller, Frank A1 - Brostek, Lukas A1 - Doberstein, Christian A1 - Han, Longfei A1 - Kefferpütz, Klaus A1 - Obstbaum, Martin A1 - Pawlowski, Antonia A1 - Rössert, Christian A1 - Sas-Brunschier, Lucas A1 - Schön, Thilo A1 - Sichermann, Jörg T1 - DISRUPT - Decentralized Intelligent System for Road User Prediction and Tracking JF - SAE Technical Paper UR - https://doi.org/10.4271/2025-01-0294 Y1 - 2025 UR - https://doi.org/10.4271/2025-01-0294 SN - 0148-7191 SN - 2688-3627 PB - SAE CY - Warrendale ER - TY - BOOK ED - Vaculin, Ondrej T1 - Applied Research Conference 2023 Conference Proceedings BT - 3rd July 2023 Technische Hochschule Ingolstadt Y1 - 2023 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-52446 PB - Technische Hochschule Ingolstadt CY - Ingolstadt ER - TY - JOUR A1 - Jamadar, Mohammad I. A1 - Sekhar, Ravi A1 - Yada, Vijay Ramarao A1 - Rairikar, Sandeep D. A1 - Thipse, Sukrut T1 - Emission Testing of Flex Fuel Vehicles up to M100/E100: Upgradation of Existing Test Facility for Vehicles below 3.5-ton GVW for Testing Methanol or Ethanol Operated Vehicles JF - Journal Européen des Systèmes Automatisés​ N2 - This paper is focused on enhancing the existing dilute emission measurement system to accommodate the emission testing of vehicles operating with gasoline blends with methanol and ethanol, dedicated M100/E100 etc. India is moving towards achieving the E20 blend on the pan-country level by April 2025 with the initiations of NITI Aayog and exploring alternate fuels like 100% methanol and ethanol. Government of India is now focused on introducing the flex fuel vehicle (FFV) technology that supports the usage of higher ethanol blends. As per CMVR guidelines for M and N category vehicles with a gross vehicle weight less than 3,500 kg; a dilute emission measurement system is used to evaluate tailpipe pollutants and fuel economy. Most of the present emission systems are compatible with testing the vehicle till M15 and E20 blends. Beyond this percentage, usage of a test facility for M100, E100, and other flex-fuel vehicles, require certain modifications in existing test facility to maintain the precision and reliability of the results considering higher water content in exhaust and effect of condensation on emission measurement due to dilution. The modifications needed, implementation and their impact are experimentally briefed in the present paper. UR - https://doi.org/10.18280/jesa.580816 Y1 - 2025 UR - https://doi.org/10.18280/jesa.580816 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-64502 SN - 2116-7087 VL - 58 IS - 8 SP - 1721 EP - 1732 PB - IIETA CY - Edmonton ER - TY - CHAP A1 - Kofler, Franziska A1 - Wendler, Mark A1 - Baumgartner, Christoph A1 - Kopják, József T1 - Sensorless Detection of Unbalanced Loads in Embedded Motor Control via ML-Trained Pattern Matching on Speed Signals T2 - SISY 2025: IEEE 23rd International Symposium on Intelligent Systems and Informatics, September 25-27, 2025, Subotica, Serbia, Proceedings UR - https://doi.org/10.1109/SISY67000.2025.11205383 Y1 - 2025 UR - https://doi.org/10.1109/SISY67000.2025.11205383 SN - 979-8-3315-9657-6 SP - 000339 EP - 000344 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Han, Longfei A1 - Kefferpütz, Klaus A1 - Beyerer, Jürgen ED - Rupniewski, Marek ED - Blunt, Shannon ED - Misiurewicz, Jacek ED - Greco, Maria Sabrina ED - Himed, Braham T1 - Improving B-Spline-Based 3D Extended Object Tracking Using Doppler Measurements T2 - Proceedings of the 2025 IEEE Radar Conference (RadarConf25), October 4–9, 2025, Kraków, Poland UR - https://doi.org/10.1109/RadarConf2559087.2025.11205008 Y1 - 2025 UR - https://doi.org/10.1109/RadarConf2559087.2025.11205008 SN - 979-8-3315-4433-1 SP - 599 EP - 604 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Niessen, Natascha A1 - Pirkl, Carolin A1 - Solana, Ana Beatriz A1 - Eichhorn, Hannah A1 - Spieker, Veronika A1 - Huang, Wenqi A1 - Sprenger, Tim A1 - Menzel, Marion Irene A1 - Schnabel, Julia A. ED - Felsner, Lina ED - Küstner, Thomas ED - Maier, Andreas ED - Qin, Chen ED - Ahmadi, Seyed-Ahmad ED - Kazi, Anees ED - Hu, Xiaoling T1 - INR Meets Multi-contrast MRI Reconstruction T2 - Reconstruction and Imaging Motion Estimation, and Graphs in Biomedical Image Analysis: First International Workshop, RIME 2025, and 7th International Workshop, GRAIL 2025, Daejeon, South Korea, September 27, 2025, Proceedings UR - https://doi.org/10.1007/978-3-032-06103-4_3 Y1 - 2025 UR - https://doi.org/10.1007/978-3-032-06103-4_3 SN - 978-3-032-06103-4 SP - 23 EP - 33 PB - Springer CY - Cham ER - TY - CHAP A1 - Shuvo, Shihab Hossain A1 - Riaz, Abdul Al Mahmud A1 - Paban, Masud Rana A1 - Howlader, Sajib A1 - Bhattacharjee, Ratul A1 - Talha, Md Abu T1 - Cyberbullying Detection in Bengali Social Media Using TF-IDF and Supervised Machine Learning Techniques T2 - 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN) UR - https://doi.org/10.1109/QPAIN66474.2025.11171789 Y1 - 2025 UR - https://doi.org/10.1109/QPAIN66474.2025.11171789 SN - 979-8-3315-9694-1 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Mayo, Perla A1 - Cencini, Matteo A1 - Fatania, Ketan A1 - Pirkl, Carolin A1 - Menzel, Marion Irene A1 - Menze, Bjoern H. A1 - Tosetti, Michela A1 - Golbabaee, Mohammad T1 - Deep Image Priors for Magnetic Resonance Fingerprinting with Pretrained Bloch-Consistent Denoising Autoencoders T2 - IEEE International Symposium on Biomedical Imaging (ISBI 2024): Conference Proceedings UR - https://doi.org/10.1109/ISBI56570.2024.10635677 Y1 - 2024 UR - https://doi.org/10.1109/ISBI56570.2024.10635677 SN - 979-8-3503-1333-8 PB - IEEE CY - Piscataway ER - TY - JOUR A1 - Denk, Florian A1 - Fröhling, Felix A1 - Brunner, Pascal A1 - Huber, Werner A1 - Margreiter, Martin A1 - Bogenberger, Klaus A1 - Kates, Ronald T1 - Influence of gaze strategies and cognitive load on safeguarding performance of motorists in right-turning scenarios involving potential conflicts with vulnerable road users JF - Transportation Research Part F: Traffic Psychology and Behaviour N2 - In urban traffic, while the fraction of collisions involving Vulnerable Road Users (VRU) is low, their importance is high due to the higher injury risk for VRU. Their infrequent occurrence on average (compared with far more common individual perceptual and behavioral errors by both drivers and VRUs) reflects an underlying fault tolerance in traffic processes. However, the degree of fault tolerance varies among traffic situations. The underlying perceptual and cognitive processes involved are complex and can require a high level of attention and concentration, particularly in situations with intersecting trajectories. These processes can occasionally fail, leading to collision risk. The situation of right-turning motorists (in right-hand-drive countries) encountering cyclists moving straight on a bike lane (with right of way) has a particularly low error tolerance, since motorists must actively scan for cyclists approaching from behind. In order to develop, test and assess solutions that mitigate collision risk in this situation, the behavior-related causation mechanisms need investigation. This is the focus of this article. We conducted a trial on our closed test track with n = 35 subjects. The experiment was designed as a within-subject design with three independent factors: maneuver, target velocity, and cognitive load in an n-back task. The trial included observations of participants' gaze control. A primary research focus was the quality and efficiency of the safeguarding gaze behavior of participants in order to draw conclusions on the causation mechanisms of collisions in this situation. For this purpose we define metrics in order to quantify the quality and efficiency of a specific gaze behavior. Furthermore, we studied the effect of factors cognitive load and target velocity on safety and secondary (n-back) task performance. Remarkably, only four out of 35 participants reached a collision risk of 0% relating to the defined quality metric. Furthermore, we identified four distinct gaze strategy groups through hierarchical clustering, where one group performed particularly few glances overall. This group showed significant differences with respect to the defined quality metric whereas the other groups showed only slight differences to each other. The results have implications on subsequent crash causation model development. UR - https://doi.org/10.1016/j.trf.2024.11.012 Y1 - 2024 UR - https://doi.org/10.1016/j.trf.2024.11.012 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-63967 SN - 1873-5517 VL - 2025 IS - 109 SP - 32 EP - 49 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Panchal, Dhruv A1 - Patel, Bhavesh A1 - Gohil, Hardik T1 - Experimental Investigation on Performance Characteristics of Dry Centrifugal Clutch with Grooved Friction Liners JF - International Journal of Automotive and Mechanical Engineering N2 - The deteriorated condition of friction liners after prolonged use is one of the primary causes of judder in centrifugal clutches. The friction characteristics can be retained by generating specific textures or grooves on the friction liner. An attempt has been made to study the characteristics of centrifugal clutch using grooved friction liners. A test cycle for centrifugal clutch has been developed using a number of engagements as the basis. A vehicle test bench was used for the experiment where the developed test cycle was automated. The performance characteristics of the centrifugal clutch have been recorded and analyzed with normal friction liners and grooved friction liners for 100 test cycles. For this study, the groove area ratio was retained at 0.15, and the grooves were cut at 90°. After completing 100 test cycles, the clutch with a grooved friction liner exhibited better characteristics. After completing 100 test cycles, the surface roughness reduction at the leading section of the grooved friction liner and normal friction liner has been found to be 6.44% and 8.11%, respectively. The thickness reduction at the leading section of the grooved friction liner and normal friction liner has been reported to be 3.73% and 4.98%, respectively. Throughout the run of 100 test cycles, the higher clutch housing temperature has been witnessed in the case of a clutch with a grooved friction liner. At the 100th test cycle, the clutch torque with a grooved friction liner was 15.22% more than the clutch torque with a normal friction liner. Even after prolonged use, the clutch with grooved friction liner exhibited better judder characteristics and also provided higher fuel economy for vehicles. UR - https://doi.org/10.15282/ijame.20.1.2023.01.0786 Y1 - 2023 UR - https://doi.org/10.15282/ijame.20.1.2023.01.0786 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-63929 SN - 2180-1606 VL - 20 IS - 1 SP - 10152 EP - 10164 PB - Universiti Malaysia Pahang Al-Sultan Abdullah Publishing CY - Pekan ER - TY - JOUR A1 - Novicki Neto, Leonardo A1 - Reway, Fabio A1 - Poledna, Yuri A1 - Funk Drechsler, Maikol A1 - Icking, Christian A1 - Huber, Werner A1 - Parente Ribeiro, Eduardo T1 - TWICE dataset: digital twin of test scenarios in a controlled environment JF - International Journal of Vehicle Systems Modelling and Testing (IJVSMT) UR - https://doi.org/10.1504/IJVSMT.2025.147353 Y1 - 2025 UR - https://doi.org/10.1504/IJVSMT.2025.147353 SN - 1745-6436 SN - 1745-6444 VL - 19 IS - 2 SP - 152 EP - 170 PB - Inderscience CY - Genf ER -