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 - 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 - JOUR A1 - Kiran, Iqra A1 - Azzam, Mohamed A1 - Endisch, Christian A1 - Butt, Nauman Zafar A1 - Lewerenz, Meinert T1 - Evaluation of Calendar Aging in Cells with Graphite: Silicon Anode Using Float Current Analysis Under the Influence of Voltage Hysteresis JF - Journal of The Electrochemical Society N2 - This study investigates the calendar aging of lithium-ion batteries with graphite-silicon anodes using float current analysis. While float current analysis is already a proven method for assessing aging in cells with graphite-based anodes, the presence of silicon introduces additional complexities due to its voltage hysteresis. We address this by comparing the results for the scaling factor separately for charge and discharge. The scaling factor is initially derived from charge and discharge GITT measurements on fresh cells, including an aging-induced shift among both electrode curves. This approach enables quantification of SEI growth ISEI growth, and cathode lithiation current ICL bridging measured results for float currents with capacity loss rate. As a result, the scaling factor during charge delivered the most meaningful results regarding fitted aging currents. By extending the estimation method based on the Arrhenius equation across temperatures from 5 °C to 50 °C, our model is validated against measured float currents, improving the predictive accuracy of long-term aging trends in silicon-containing anodes. Electrochemical impedance spectroscopy provided further insights into degradation mechanisms, revealing a strong correlation between cathode lithiation by salt decomposition and resistance increase at high voltages (⩾4.15 V), confirmed by pulse tests at 100% SOC showing a sharp resistance increase at elevated voltages. UR - https://doi.org/10.1149/1945-7111/ae0fe8 Y1 - 2025 UR - https://doi.org/10.1149/1945-7111/ae0fe8 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-63053 SN - 1945-7111 VL - 172 IS - 10 PB - IOP Publishing CY - Bristol ER - TY - JOUR A1 - Morales Torricos, Pablo A1 - Gallenberger, Andreas A1 - Droese, Dominik A1 - Kowal, Julia A1 - Endisch, Christian A1 - Lewerenz, Meinert T1 - Analyzing the Impact of Electrolyte Motion Induced Salt Inhomogeneity Effect on Apparent Aging: Role of Current Rates and Temperature Effects in Accelerated Cyclic Aging Tests in Li-Ion Batteries JF - Batteries & Supercaps N2 - Accurate and rapid assessment of lithium-ion battery lifetime is essential for predicting remaining lifespan, enabling the selection of appropriate cells for specific applications and determining suitability for second-life use. However, accelerated cyclic aging tests may underestimate a cell's total lifespan due to exaggerated capacity fade that does not occur under real-world conditions. This increased capacity fade is primarily driven by electrolyte motion induced salt inhomogeneity (EMSI) and loss of homogeneity of lithium distribution (HLD). This study investigates the impact of varying charge and discharge currents on capacity loss during accelerated testing in compressed NMC-Gr pouch cells. Most of the capacity loss observed during cycling is fully recoverable after a resting period, with some cells regaining up to 81% of their lost capacity. Contrary to expectations, cells subjected to the highest cycling currents do not exhibit the greatest recoverable capacity loss. This phenomenon can be attributed to the interplay between current and temperature: While higher cycling currents exacerbate EMSI and HLD loss, they simultaneously elevate cell temperature, which mitigates EMSI by weakening polarization, enhancing electrolyte salt diffusion and homogenizing lithium distribution in the anode. Consequently, higher temperatures counteract HLD and EMSI-effect and therefore reduce apparent capacity loss. UR - https://doi.org/10.1002/batt.202500559 Y1 - 2025 UR - https://doi.org/10.1002/batt.202500559 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-62944 SN - 2566-6223 VL - 9 IS - 4 PB - Wiley CY - Weinheim ER - TY - INPR A1 - Pandey, Amit A1 - Mohd, Zubair Akhtar A1 - Veettil, Nandana Kappuva A1 - Wunderle, Bernhard A1 - Elger, Gordon T1 - Quantitative Kernel Estimation from Traffic Signs using Slanted Edge Spatial Frequency Response as a Sharpness Metric T2 - Research Square N2 - 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. UR - https://doi.org/10.21203/rs.3.rs-6725582/v1 Y1 - 2025 UR - https://doi.org/10.21203/rs.3.rs-6725582/v1 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-62419 SN - 2693-5015 PB - Research Square CY - Durham ER - TY - CHAP A1 - Nieto, Marcos A1 - Otaegui, Oihana A1 - Panou, Maria A1 - Birkner, Christian A1 - Vaculin, Ondrej A1 - Rodríguez, Ariadna ED - McNally, Ciaran ED - Carroll, Páraic ED - Martinez-Pastor, Beatriz ED - Ghosh, Bidisha ED - Efthymiou, Marina ED - Valantasis-Kanellos, Nikolaos T1 - AWARE2ALL: Human Centric Interaction and Safety Systems for Increasing the Share of Automated Vehicles T2 - Transport Transitions: Advancing Sustainable and Inclusive Mobility, Proceedings of the 10th TRA Conference, 2024, Dublin, Ireland-Volume 1: Safe and Equitable Transport N2 - 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. UR - https://doi.org/10.1007/978-3-031-88974-5_112 Y1 - 2025 UR - https://doi.org/10.1007/978-3-031-88974-5_112 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-62356 SN - 978-3-031-88974-5 SP - 779 EP - 785 PB - Springer CY - Cham ER - TY - INPR A1 - Kern, Tobias A1 - Tolksdorf, Leon A1 - Birkner, Christian T1 - Comparison of Localization Algorithms between Reduced-Scale and Real-Sized Vehicles Using Visual and Inertial Sensors UR - https://doi.org/10.48550/arXiv.2507.11241 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2507.11241 PB - arXiv CY - Ithaca 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 - Roth, Carla A1 - Ulreich, Fabian A1 - Ebert, Martin T1 - Domain Awareness via Spectral-normalized Neural Gaussian Processes for E2E Autonomous Vehicle Control T2 - 2025 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV64158.2025.11097444 Y1 - 2025 UR - https://doi.org/10.1109/IV64158.2025.11097444 SN - 979-8-3315-3803-3 SP - 1668 EP - 1673 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Jagtap, Abhishek Dinkar A1 - Song, Rui A1 - Sadashivaiah, Sanath Tiptur A1 - Festag, Andreas T1 - V2X-Gaussians: Gaussian Splatting for Multi-Agent Cooperative Dynamic Scene Reconstruction T2 - 2025 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV64158.2025.11097436 Y1 - 2025 UR - https://doi.org/10.1109/IV64158.2025.11097436 SN - 979-8-3315-3803-3 SP - 1033 EP - 1039 PB - IEEE CY - Piscataway ER - TY - INPR A1 - Bhanderi, Savankumar A1 - Agrawal, Shiva A1 - Elger, Gordon T1 - Deep Segmentation of 3+1D Radar Point Cloud for Real-Time Roadside Traffic User Detection T2 - Research Square N2 - 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). UR - https://doi.org/10.21203/rs.3.rs-7222130/v1 Y1 - 2025 UR - https://doi.org/10.21203/rs.3.rs-7222130/v1 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-61996 SN - 2693-5015 PB - Research Square CY - Durham ER - TY - JOUR A1 - Weihmayr, Daniel A1 - Birkner, Christian A1 - Marzbani, Hormoz A1 - Jazar, Reza T1 - Data-Driven Vehicle Dynamics: Lever-Aging SINDy for Optimization-Based Vehicular Motion Planning JF - IEEE Access N2 - 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. UR - https://doi.org/10.1109/ACCESS.2025.3594892 Y1 - 2025 UR - https://doi.org/10.1109/ACCESS.2025.3594892 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-61981 SN - 2169-3536 VL - 13 SP - 136584 EP - 136597 PB - IEEE CY - New York ER - TY - CHAP A1 - Rozek, Lukas A1 - Harrison, Andrew A1 - Birkner, Christian T1 - Influence of Autonomous Vehicle Interior Design on Occupant Injuries T2 - 2025 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV64158.2025.11097519 Y1 - 2025 UR - https://doi.org/10.1109/IV64158.2025.11097519 SN - 979-8-3315-3803-3 SP - 1517 EP - 1522 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - de Borba, Thiago A1 - Vaculin, Ondrej A1 - Marzbani, Hormoz A1 - Jazar, Reza T1 - Cooperative Maneuver Coordination: Smart Infrastructure for VRUs Collision Avoidance with Trajectory Planning T2 - Proceedings: 2025 IEEE 3rd International Conference on Mobility, Operations, Services and Technologies, MOST 2025 UR - https://doi.org/10.1109/MOST65065.2025.00015 Y1 - 2025 UR - https://doi.org/10.1109/MOST65065.2025.00015 SN - 979-8-3315-1160-9 SP - 51 EP - 58 PB - IEEE CY - Piscataway ER - TY - INPR A1 - Tolksdorf, Leon A1 - Tejada, Arturo A1 - Birkner, Christian A1 - van de Wouw, Nathan T1 - Collision Probability Estimation for Optimization-based Vehicular Motion Planning UR - https://doi.org/10.48550/arXiv.2505.21161 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2505.21161 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Roßberg, Niklas A1 - Neumeier, Marion A1 - Hasirlioglu, Sinan A1 - Bouzouraa, Mohamed Essayed A1 - Botsch, Michael T1 - Assessing the Completeness of Traffic Scenario Categories for Automated Highway Driving Functions via Cluster-Based Analysis T2 - 2025 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV64158.2025.11097767 Y1 - 2025 UR - https://doi.org/10.1109/IV64158.2025.11097767 SN - 979-8-3315-3803-3 SP - 1787 EP - 1794 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Elter, Tim A1 - Dirndorfer, Tobias A1 - Botsch, Michael A1 - Utschick, Wolfgang T1 - Validation of a POMDP Framework for Interaction-aware Trajectory Prediction in Vehicle Safety T2 - 2025 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV64158.2025.11097498 Y1 - 2025 UR - https://doi.org/10.1109/IV64158.2025.11097498 SN - 979-8-3315-3803-3 SP - 663 EP - 670 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 - JOUR A1 - Azzam, Mohamed A1 - Aydin, Atakhan A1 - Endisch, Christian A1 - Sauer, Dirk Uwe A1 - Lewerenz, Meinert T1 - Float Current Analysis for Lithium-Ion Battery Aging: Insights into SEI Growth and Cathode Lithiation with EIS and ICP OES JF - Journal of The Electrochemical Society N2 - This study investigates calendar-aging mechanisms in lithium-ion batteries, focusing on cathode lithiation due to decomposition of conductive salt and SEI growth, by correlating quantified float currents, capacity loss rates, and pulse resistances with changes in electrochemical impedance spectroscopy (EIS) spectra. Seven SamSung 25 R cells are aged at different float voltages with periodic EIS measurements at 30 °C. Using a pre-characterization cell, the internal processes via EIS are allocated across various states of charge and temperatures and GITT measurements are performed to derive scaling factors. GITT, float currents and capacity loss rate measurements at 30 °C enables the separation of SEI growth ISEI growth and cathode lithiation current ICL based on float current behavior across a temperature range of 5 °C to 50 °C. The distribution of relaxation times (DRT) method is employed to deconvolute overlapping electrochemical processes. EIS and DRT analyses showed significant changes in cathode charge transfer resistance and diffusion, confirming that cathode lithiation correlates substantially to elevated internal resistance at high cell voltages. The theory of ISEI growth and ICL is further supported using inductively coupled plasma atomic emission spectroscopy by quantifying elemental inventory changes and linking phosphorus release and lithium consumption to degradation mechanisms. UR - https://doi.org/10.1149/1945-7111/adef85 Y1 - 2025 UR - https://doi.org/10.1149/1945-7111/adef85 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-60922 SN - 1945-7111 VL - 172 IS - 7 PB - IOP Publishing CY - Bristol ER - TY - JOUR A1 - Afraj, Shahabaz A1 - Vaculin, Ondrej A1 - Böhmländer, Dennis A1 - Hynčík, Luděk T1 - Vehicle crash simulation models for reinforcement learning driven crash-detection algorithm calibration JF - Advanced Modeling and Simulation in Engineering Sciences N2 - The development of finite element vehicle models for crash simulations is a highly complex task. The main aim of these models is to simulate a variety of crash scenarios and assess all the safety systems for their respective performances. These vehicle models possess a substantial amount of data pertaining to the vehicle’s geometry, structure, materials, etc., and are used to estimate a large set of system and component level characteristics using crash simulations. It is understood that even the most well-developed simulation models are prone to deviations in estimation when compared to real-world physical test results. This is generally due to our inability to model the chaos and uncertainties introduced in the real world. Such unavoidable deviations render the use of virtual simulations ineffective for the calibration process of the algorithms that activate the restraint systems in the event of a crash (crash-detection algorithm). In the scope of this research, authors hypothesize the possibility of accounting for such variations introduced in the real world by creating a feedback loop between real-world crash tests and crash simulations. To accomplish this, a Reinforcement Learning (RL) compatible virtual surrogate model is used, which is adapted from crash simulation models. Hence, a conceptual methodology is illustrated in this paper for developing an RL-compatible model that can be trained using the results of crash simulations and crash tests. As the calibration of the crash-detection algorithm is fundamentally dependent upon the crash pulses, the scope of the expected output is limited to advancing the ability to estimate crash pulses. Furthermore, the real-time implementation of the methodology is illustrated using an actual vehicle model. UR - https://doi.org/10.1186/s40323-025-00288-4 Y1 - 2025 UR - https://doi.org/10.1186/s40323-025-00288-4 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-60861 SN - 2213-7467 VL - 12 IS - 1 PB - SpringerOpen CY - Berlin 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 - JOUR A1 - Yu, Qing A1 - Kiran, Iqra A1 - Ehrensberger, Moritz A1 - Streck, Luiza A1 - Roth, Thomas A1 - Jossen, Andreas A1 - Endisch, Christian A1 - Lewerenz, Meinert T1 - Assigning Calendar Aging during Open Circuit and Float Current Analysis to Anode and Cathode Aging Using Three-Electrode Cells JF - Journal of the Electrochemical Society N2 - Analyzing calendar aging by float current analysis, instead of solely repeating capacity tests, gains more insights into aging. However, the underlying mechanisms of the recharge current required to keep the voltage constant are not yet fully understood. Therefore, this study performs float current and additional open circuit voltage (OCV) tests on 3-electrode cells for four different voltages at 30 °C. By monitoring the potentials of the anode and the cathode over time individually, the aging rate on both electrodes and the present capacity can be calculated based on adjusting the electrode-specific OCV curves according to the voltage slippery theory. The electrode-specific aging and the capacity prediction show high agreement among both methods and the capacity tests at the end of the experiment. As a result, the capacity loss appears linear-like and is associated with the loss of active lithium mainly due to SEI formation on the anode. Additionally, a significant cathode voltage decay is observed especially for higher cell voltage. According to the literature, this is associated with cathode lithiation where the conductive salt is decomposed by inserting active lithium into the cathode masking SEI losses. Finally, OCV and float current analysis return comparable results and support present 2-electrode evaluation approaches. UR - https://doi.org/10.1149/1945-7111/ade295 Y1 - 2025 UR - https://doi.org/10.1149/1945-7111/ade295 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-60504 SN - 1945-7111 VL - 172 IS - 6 PB - IOP Publishing CY - Bristol ER - TY - INPR A1 - Kruber, Friedrich A1 - Wurst, Jonas A1 - Botsch, Michael T1 - An Unsupervised Random Forest Clustering Technique for Automatic Traffic Scenario Categorization UR - https://doi.org/10.48550/arXiv.2004.02121 Y1 - 2020 UR - https://doi.org/10.48550/arXiv.2004.02121 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Gankin, Dennis A1 - Mayer, Sebastian A1 - Zinn, Jonas A1 - Vogel-Heuser, Birgit A1 - Endisch, Christian T1 - Modular Production Control with Multi-Agent Deep Q-Learning T2 - Proceedings: 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) UR - https://doi.org/10.1109/ETFA45728.2021.9613177 Y1 - 2021 UR - https://doi.org/10.1109/ETFA45728.2021.9613177 SN - 978-1-7281-2989-1 PB - IEEE CY - Piscataway ER - TY - JOUR A1 - Morales Torricos, Pablo A1 - Berg, Sascha A1 - Figgemeier, Egbert A1 - Endisch, Christian A1 - Lewerenz, Meinert T1 - The important role of lithiation-induced pressure change on apparent aging of lithium-ion batteries during accelerated cyclic aging tests JF - Journal of Energy Storage N2 - In assessing the lifespan of lithium-ion batteries in laboratory conditions, the measured capacity declines during accelerated cyclic aging tests but increases when the cells are left idle. This recoverable capacity loss, known in literature as apparent aging, results from an inhomogeneous lithium distribution in the anode appearing in dV/dQ and capacity difference analysis. This study explores the origin of the apparent aging by correlating lithium distribution in the anode and recoverable capacity loss, with the lithiation induced pressure change and generated electrolyte motion during cycling. To this end, we compressed five commercial pouch lithium-ion cells (NMC/Gr) with holder stiffnesses ranging from 0.9 to 15.4 MPa/mm and offset pressure from 289 to 681 kPa and subjected them to continuous cyclic aging tests. While offset pressure had no significant impact, we observed, that holder stiffnesses over 3.3 MPa/mm induces an apparent capacity loss, which is recoverable by 35 % during a resting phase. The root cause is the so-called electrolyte motion induced salt inhomogeneity (EMSI), driven by continuous high current cycling and electrolyte motion, which is intensified by higher holder stiffness but not by offset pressure. These insights are crucial for improving the accuracy of accelerated aging tests and enhancing battery lifespan predictions. UR - https://doi.org/10.1016/j.est.2025.117323 Y1 - 2025 UR - https://doi.org/10.1016/j.est.2025.117323 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-60173 SN - 2352-1538 VL - 2025 IS - 131, Part A PB - Elsevier CY - Amsterdam ER - TY - INPR A1 - Song, Rui A1 - Zhou, Liguo A1 - Lyu, Lingjuan A1 - Festag, Andreas A1 - Knoll, Alois T1 - ResFed: Communication Efficient Federated Learning by Transmitting Deep Compressed Residuals UR - https://doi.org/10.48550/arXiv.2212.05602 Y1 - 2022 UR - https://doi.org/10.48550/arXiv.2212.05602 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Devillers, Hugo A1 - Kurtenacker, Matthias A1 - Membarth, Richard A1 - Lemme, Stefan A1 - Kenzel, Michael A1 - Yazici, Ömercan A1 - Slusallek, Philipp ED - Knoll, Aaron ED - Peters, Christoph T1 - No More Shading Languages: Compiling C++ to Vulkan Shaders T2 - High-Performance Graphics - Symposium Papers N2 - Graphics APIs have traditionally relied on shading languages, however, these languages have a number of fundamental defects and limitations. By contrast, GPU compute platforms offer powerful, feature-rich languages suitable for heterogeneous compute. We propose reframing shading languages as embedded domain-specific languages, layered on top of a more general language like C++, doing away with traditional limitations on pointers, functions, and recursion, to the benefit of programmability. This represents a significant compilation challenge because the limitations of shaders are reflected in their lower-level representations. We present the Vcc compiler, which allows conventional C and C++ code to run as Vulkan shaders. Our compiler is complemented by a simple shading library and exposes GPU particulars as intrinsics and annotations. We evaluate the performance of our compiler using a selection of benchmarks, including a real-time path tracer, achieving competitive performance compared to their native CUDA counterparts. UR - https://doi.org/10.2312/hpg.20251167 Y1 - 2025 UR - https://doi.org/10.2312/hpg.20251167 UR - https://diglib.eg.org/handle/10.2312/hpg20251167 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-60151 SN - 978-3-03868-291-2 PB - The Eurographics Association CY - Goslar ER - TY - CHAP A1 - Wildgrube, Fabian A1 - Ehrett, Pete A1 - Trojahn, Paul A1 - Membarth, Richard A1 - Beckmann, Bradford A1 - Baumeister, Dominik A1 - Chajdas, Matthäus T1 - GPUs All Grown-Up: Fully Device-Driven SpMV Using GPU Work Graphs T2 - ISCA ´25: Proceedings of the 52nd Annual International Symposium on Computer Architecture N2 - Sparse matrix-vector multiplication (SpMV) is a key operation across high-performance computing, graph analytics, and many more applications. In these applications, the matrix characteristics, notably non-zero elements per row, can vary widely and impact which algorithm performs best. Thus, Graphics Processing Unit (GPU) SpMV algorithms often rely on costly preprocessing to determine what per-row algorithm to select to achieve high performance. In this work we combine SpMV preprocessing and the subsequent per-row processing on the GPU by leveraging the novel “Work Graphs” GPU programming model—initially designed for graphics applications—for dynamic on-device self-scheduling. Work Graphs allow for fine-grain dataflow execution of individual workgroups using emerging hardware and firmware support. As soon as preprocessing has generated sufficient work, workgroups of individual processing kernels are self-scheduled and executed, interleaved with those of other kernels. This improves cache locality and eliminates host interaction altogether. Across a suite of 59 sparse matrices, the best of various novel Work Graphs SpMV implementations outperforms state-of-the-art rocSPARSE “LRB” for a single SpMV by up to 7.19 × (mean: 3.35 ×, SD: 1.89). Furthermore, it achieves much more stable performance across various sparsity patterns than the rocSPARSE CSR-General algorithm, and even beats the advanced rocSPARSE CSR-Adaptive algorithm for up to 92 consecutive SpMV calculations. In addition, compared to rocSPARSE LRB, it reduces code complexity by 75%. Its memory footprint for supporting data structures is a fixed ∼ 25 MiB independent of matrix size, compared to rocSPARSE LRB’s data structures that scale with matrix size to hundreds of megabytes. Overall, this work showcases the performance potential of emerging dynamic on-device scheduling techniques for GPU compute applications. UR - https://doi.org/10.1145/3695053.3731060 Y1 - 2025 UR - https://doi.org/10.1145/3695053.3731060 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58868 SN - 979-8-4007-1261-6 SP - 1777 EP - 1791 PB - ACM CY - New York ER - TY - INPR A1 - Song, Rui A1 - Liu, Dai A1 - Chen, Dave Zhenyu A1 - Festag, Andreas A1 - Trinitis, Carsten A1 - Schulz, Martin A1 - Knoll, Alois T1 - Federated Learning via Decentralized Dataset Distillation in Resource Constrained Edge Environments N2 - In federated learning, all networked clients contribute to the model training cooperatively. However, with model sizes increasing, even sharing the trained partial models often leads to severe communication bottlenecks in underlying networks, especially when communicated iteratively. In this paper, we introduce a federated learning framework FedD3 requiring only one-shot communication by integrating dataset distillation instances. Instead of sharing model updates in other federated learning approaches, FedD3 allows the connected clients to distill the local datasets independently, and then aggregates those decentralized distilled datasets (e.g. a few unrecognizable images) from networks for model training. Our experimental results show that FedD3 significantly outperforms other federated learning frameworks in terms of needed communication volumes, while it provides the additional benefit to be able to balance the trade-off between accuracy and communication cost, depending on usage scenario or target dataset. For instance, for training an AlexNet model on CIFAR-10 with 10 clients under non-independent and identically distributed (Non-IID) setting, FedD3 can either increase the accuracy by over 71% with a similar communication volume, or save 98% of communication volume, while reaching the same accuracy, compared to other one-shot federated learning approaches. UR - https://doi.org/10.48550/arXiv.2208.11311 Y1 - 2022 UR - https://doi.org/10.48550/arXiv.2208.11311 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-60054 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Novicki Neto, Leonardo A1 - Reway, Fabio A1 - Poledna, Yuri A1 - Funk Drechsler, Maikol A1 - Parente Ribeiro, Eduardo A1 - Huber, Werner A1 - Icking, Christian T1 - TWICE Dataset: Digital Twin of Test Scenarios in a Controlled Environment N2 - Ensuring the safe and reliable operation of autonomous vehicles under adverse weather remains a significant challenge. To address this, we have developed a comprehensive dataset composed of sensor data acquired in a real test track and reproduced in the laboratory for the same test scenarios. The provided dataset includes camera, radar, LiDAR, inertial measurement unit (IMU), and GPS data recorded under adverse weather conditions (rainy, night-time, and snowy conditions). We recorded test scenarios using objects of interest such as car, cyclist, truck and pedestrian -- some of which are inspired by EURONCAP (European New Car Assessment Programme). The sensor data generated in the laboratory is acquired by the execution of simulation-based tests in hardware-in-the-loop environment with the digital twin of each real test scenario. The dataset contains more than 2 hours of recording, which totals more than 280GB of data. Therefore, it is a valuable resource for researchers in the field of autonomous vehicles to test and improve their algorithms in adverse weather conditions, as well as explore the simulation-to-reality gap. UR - https://doi.org/10.48550/arXiv.2310.03895 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2310.03895 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-59887 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Fidelis, Eduardo A1 - Reway, Fabio A1 - Ribeiro, Herick Y. S. A1 - Campos, Pietro A1 - Huber, Werner A1 - Icking, Christian A1 - Faria, Lester A1 - Schön, Torsten T1 - Generation of Realistic Synthetic Raw Radar Data for Automated Driving Applications using Generative Adversarial Networks N2 - The main approaches for simulating FMCW radar are based on ray tracing, which is usually computationally intensive and do not account for background noise. This work proposes a faster method for FMCW radar simulation capable of generating synthetic raw radar data using generative adversarial networks (GAN). The code and pre-trained weights are open-source and available on GitHub. This method generates 16 simultaneous chirps, which allows the generated data to be used for the further development of algorithms for processing radar data (filtering and clustering). This can increase the potential for data augmentation, e.g., by generating data in non-existent or safety-critical scenarios that are not reproducible in real life. In this work, the GAN was trained with radar measurements of a motorcycle and used to generate synthetic raw radar data of a motorcycle traveling in a straight line. For generating this data, the distance of the motorcycle and Gaussian noise are used as input to the neural network. The synthetic generated radar chirps were evaluated using the Frechet Inception Distance (FID). Then, the Range-Azimuth (RA) map is calculated twice: first, based on synthetic data using this GAN and, second, based on real data. Based on these RA maps, an algorithm with adaptive threshold and edge detection is used for object detection. The results have shown that the data is realistic in terms of coherent radar reflections of the motorcycle and background noise based on the comparison of chirps, the RA maps and the object detection results. Thus, the proposed method in this work has shown to minimize the simulation-to-reality gap for the generation of radar data. UR - https://doi.org/10.48550/arXiv.2308.02632 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2308.02632 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-59872 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Rauscher, Andreas A1 - Stenzel, Peer A1 - Endisch, Christian T1 - Investigation of Factors Influencing the End-of-Line Partial Discharge Testing of Electrical Machines T2 - 2025 IEEE Workshop on Electrical Machines Design, Control and Diagnosis (WEMDCD) UR - https://doi.org/10.1109/WEMDCD61816.2025.11014117 Y1 - 2025 UR - https://doi.org/10.1109/WEMDCD61816.2025.11014117 PB - IEEE CY - Piscataway ER - TY - INPR A1 - Neumeier, Marion A1 - Tollkühn, Andreas A1 - Dorn, Sebastian A1 - Botsch, Michael A1 - Utschick, Wolfgang T1 - Gradient Derivation for Learnable Parameters in Graph Attention Networks UR - https://doi.org/10.48550/arXiv.2304.10939 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2304.10939 PB - arXiv CY - Ithaca 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 - Lobo, Silas A1 - Festag, Andreas A1 - Facchi, Christian T1 - Adaptive Message Prioritization: How to Prioritize VRU Awareness Messages in a Congested V2X Network T2 - 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC) UR - https://doi.org/10.1109/ITSC58415.2024.10919704 Y1 - 2025 UR - https://doi.org/10.1109/ITSC58415.2024.10919704 SN - 979-8-3315-0592-9 SP - 423 EP - 430 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Wachtel Granado, Diogo A1 - Tasabat, Sinan A1 - Rothmeier, Thomas A1 - Cristófoli Duarte Silva, Letícia A1 - Huber, Werner T1 - Exploring Synthetic Radar Data and Deep Learning for Road User Classification in Autonomous Vehicles T2 - 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC) UR - https://doi.org/10.1109/ITSC58415.2024.10919565 Y1 - 2025 UR - https://doi.org/10.1109/ITSC58415.2024.10919565 SN - 979-8-3315-0592-9 SP - 2021 EP - 2026 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Wachtel Granado, Diogo A1 - Trevisol, Heitor Derder A1 - Rothmeier, Thomas A1 - Nassu, Bogdan Tomoyuki A1 - Huber, Werner T1 - Navigating on Adverse Weather: Enhancing LiDAR-Based Detection with the DBSPRY Dataset T2 - 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC) UR - https://doi.org/10.1109/ITSC58415.2024.10920224 Y1 - 2025 UR - https://doi.org/10.1109/ITSC58415.2024.10920224 SN - 979-8-3315-0592-9 SP - 4034 EP - 4039 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Brühl, Tim A1 - Shanmuganathan, Aravind Kumar A1 - Ewecker, Lukas A1 - Schwager, Robin A1 - Sohn, Tin Stribor A1 - Vaculin, Ondrej A1 - Hohmann, Sören T1 - Consideration of Safety Aspects in a Camera-Aided, Radar-Based Free Space Detection T2 - 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC) UR - https://doi.org/10.1109/ITSC58415.2024.10920194 Y1 - 2025 UR - https://doi.org/10.1109/ITSC58415.2024.10920194 SN - 979-8-3315-0592-9 SP - 3997 EP - 4004 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Rothmeier, Thomas A1 - Dal Vesco Hoger, Mayara A1 - Nassu, Bogdan Tomoyuki A1 - Huber, Werner A1 - Knoll, Alois T1 - Out of the Box: Weather Augmentation for Enhanced Detection in Bad Visibility Conditions T2 - 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC) UR - https://doi.org/10.1109/ITSC58415.2024.10919529 Y1 - 2025 UR - https://doi.org/10.1109/ITSC58415.2024.10919529 SN - 979-8-3315-0592-9 SP - 1410 EP - 1417 PB - IEEE CY - Piscataway ER - TY - JOUR A1 - Schreiber, Markus A1 - Lin, Yilei A1 - Sommer, Alessandro A1 - Wassiliadis, Nikolaos A1 - Morales Torricos, Pablo A1 - Rogge, Marcel A1 - Lewerenz, Meinert A1 - Grosu, Cristina A1 - Endisch, Christian A1 - Jossen, Andreas A1 - Lienkamp, Markus T1 - Apparent vs. true battery aging: Impact of various load characteristics on accelerated aging tests JF - Journal of Energy Storage N2 - Vehicle applications involve highly dynamic and variable operating conditions. These result from changing driving profiles and diverse driving behaviors. To accelerate battery aging tests, experiments are often based on constant load cycles. While efficient, this approach distorts the natural degradation behavior of the cells. This study compares cell aging under real-world and laboratory load conditions. For this purpose, we compare realistic driving profiles measured in a test vehicle in the field with synthetic constant power cycles. Average discharge power and charging sequences are kept identical for comparability. Results show that constant power cycles cause stronger cell aging than dynamic loads. Differential voltage analysis indicates more lithium inventory loss and active material loss at the negative electrode under static loads. Static loading also leads to strong inhomogeneity in the negative electrode and altered charge transfer and diffusion kinetics, as shown by impedance data. After 15 months of rest, the cells recovered up to 52 of lost capacity and 66 of the resistance increase. Impedance assessment and differential voltage analysis confirm the recovery and rehomogenization of the negative electrode. These findings show that conventional accelerated tests are strongly influenced by relaxation and load dynamics. As a result, their applicability to specific use cases, such as automotive applications, is strongly limited . Therefore, andraditional test strategies require reconsideration and redesign. UR - https://doi.org/10.1016/j.est.2025.116924 Y1 - 2025 UR - https://doi.org/10.1016/j.est.2025.116924 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-59653 SN - 2352-1538 VL - 2025 IS - 127 PB - Elsevier CY - Amsterdam ER - TY - INPR A1 - Han, Longfei A1 - Kefferpütz, Klaus A1 - Beyerer, Jürgen T1 - Decentralized Fusion of 3D Extended Object Tracking based on a B-Spline Shape Model N2 - Extended Object Tracking (EOT) exploits the high resolution of modern sensors for detailed environmental perception. Combined with decentralized fusion, it contributes to a more scalable and robust perception system. This paper investigates the decentralized fusion of 3D EOT using a B-spline curve based model. The spline curve is used to represent the side-view profile, which is then extruded with a width to form a 3D shape. We use covariance intersection (CI) for the decentralized fusion and discuss the challenge of applying it to EOT. We further evaluate the tracking result of the decentralized fusion with simulated and real datasets of traffic scenarios. We show that the CI-based fusion can significantly improve the tracking performance for sensors with unfavorable perspective. UR - https://doi.org/10.48550/arXiv.2504.18708 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2504.18708 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-59648 PB - arXiv CY - Ithaca ER - TY - INPR 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 UR - https://doi.org/10.48550/arXiv.2504.04631 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2504.04631 PB - arXiv CY - Ithaca ER - TY - THES A1 - von dem Bussche-Hünnefeld, Tetmar T1 - Klassifizierung unterschiedlicher E-Scooter Fahrerprofile mit Hilfe eines selbstentwickelten Messfahrzeuges N2 - Die Zahl der E-Scooter Fahrer nimmt weltweit zu. Sowohl Sharing-Angebote als auch E-Scooter zum Kauf für den privaten Gebrauch gewinnen an Beliebtheit. Diese neue Art der Fortbewegung muss bei der Entwicklung moderner Fahrerassistenzsysteme gesondert berücksichtigt werden, da noch nicht belegt ist, ob sie die selbe Dynamik wie bestehende Verkehrsteilnehmer aufweist. Moderne Fahrzeugsysteme werden bereits früh in der Entwicklung durch Simulationsumgebungen unterstützt, abgesichert und auf Wirksamkeit geprüft. Solche Simulationen sollten dann Modelle beinhalten, die E-Scooter Fahrer inklusive ihres physikalischen Limits der Manövrierbarkeit abbilden und durch Realdaten parametrisiert sowie kalibriert werden. Dazu wird ein E-Scooter mit Sensorik und einem Datenlogger ausgestattet. Eine Probandenstudie im Realfahrversuch dient der Datengenerierung. Anhand dieser Studie wird das Fahrerverhalten erforscht und Empfehlungen zur Parametrierung einer Simulationsumgebung aufgestellt. Anhand der, durch die 36 Probanden gewonnen, Daten werden die Parameter Ausrollverzögerung, Reaktionszeit, mittlere Bremsverzögerung, maximale Bremsverzögerung, maximaler Rollwinkel, maximaler Lenkwinkel und maximale Querbeschleunigung kategorisiert und ausgewertet. Die Auswertung befasst sich unter anderem mit Unterschieden zwischen den Geschwindigkeitsstufen, Erfahrungsstufen mit anderen Verkehrsmitteln, sowie dem Geschlecht, Alter, Gewicht und Größe des Fahrers. Dadurch können signifikante Zusammenhänge aufgedeckt werden und in manchen Fällen Abhängigkeiten zur genaueren Kalibrierung der Simulation genutzt werden. Die Reaktionszeit weist eine direkte Proportionalität zur Fahrgeschwindigkeit auf. Dieser Zusammenhang kann zur Parametrisierung genutzt werden. Für die maximale Bremsverzögerung stellen Regressionsgleichungen mit der Prädikatorvariable Fahrergewicht die beste Lösung zur Kalibrierung dar. Die mittlere Bremsverzögerung hingegen wird in Abhängigkeit des Geschlechts und der Geschwindigkeit parametrisiert. Eine geschwindigkeitsabhängige Parametrisierung kann ebenso beim maximalen Rollwinkel angewendet werden. Die beiden Variablen maximaler Lenkwinkel und maximale Querbeschleunigung weisen in der Auswertung keine, für die Parametrisierung relevanten, signifikanten Zusammenhänge auf. Daher wird hier eine Kalibrierung anhand der berechneten Mittelwerte empfohlen. Im Nachgang der Arbeit sollte das Versuchsfahrzeug um weitere Sensorik erweitert und die Robustheit erhöht werden. Auch sollten die Ergebnisse dieser Arbeit in weiteren Studien validiert und verfeinert werden. Dazu sind größere Stichprobenumfänge und homogenere Verteilungen in der Stichprobe nötig. Y1 - 2021 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-59584 CY - Ingolstadt ER - TY - INPR A1 - Kalyanasundaram, Abinav A1 - Chandra Sekaran, Karthikeyan A1 - Stäuber, Philipp A1 - Lange, Michael A1 - Utschick, Wolfgang A1 - Botsch, Michael T1 - Uncertainty-Aware Hybrid Machine Learning in Virtual Sensors for Vehicle Sideslip Angle Estimation N2 - Precise vehicle state estimation is crucial for safe and reliable autonomous driving. The number of measurable states and their precision offered by the onboard vehicle sensor system are often constrained by cost. For instance, measuring critical quantities such as the Vehicle Sideslip Angle (VSA) poses significant commercial challenges using current optical sensors. This paper addresses these limitations by focusing on the development of high-performance virtual sensors to enhance vehicle state estimation for active safety. The proposed Uncertainty-Aware Hybrid Learning (UAHL) architecture integrates a machine learning model with vehicle motion models to estimate VSA directly from onboard sensor data. A key aspect of the UAHL architecture is its focus on uncertainty quantification for individual model estimates and hybrid fusion. These mechanisms enable the dynamic weighting of uncertainty-aware predictions from machine learning and vehicle motion models to produce accurate and reliable hybrid VSA estimates. This work also presents a novel dataset named Real-world Vehicle State Estimation Dataset (ReV-StED), comprising synchronized measurements from advanced vehicle dynamic sensors. The experimental results demonstrate the superior performance of the proposed method for VSA estimation, highlighting UAHL as a promising architecture for advancing virtual sensors and enhancing active safety in autonomous vehicles. UR - https://doi.org/10.48550/arXiv.2504.06105 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2504.06105 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-59578 PB - arXiv CY - Ithaca ER - TY - JOUR A1 - Agrawal, Shiva A1 - Bhanderi, Savankumar A1 - Elger, Gordon T1 - Infra-3DRC-FusionNet: Deep Fusion of Roadside Mounted RGB Mono Camera and Three-Dimensional Automotive Radar for Traffic User Detection JF - Sensors N2 - Mono RGB cameras and automotive radar sensors provide a complementary information set that makes them excellent candidates for sensor data fusion to obtain robust traffic user detection. This has been widely used in the vehicle domain and recently introduced in roadside-mounted smart infrastructure-based road user detection. However, the performance of the most commonly used late fusion methods often degrades when the camera fails to detect road users in adverse environmental conditions. The solution is to fuse the data using deep neural networks at the early stage of the fusion pipeline to use the complete data provided by both sensors. Research has been carried out in this area, but is limited to vehicle-based sensor setups. Hence, this work proposes a novel deep neural network to jointly fuse RGB mono-camera images and 3D automotive radar point cloud data to obtain enhanced traffic user detection for the roadside-mounted smart infrastructure setup. Projected radar points are first used to generate anchors in image regions with a high likelihood of road users, including areas not visible to the camera. These anchors guide the prediction of 2D bounding boxes, object categories, and confidence scores. Valid detections are then used to segment radar points by instance, and the results are post-processed to produce final road user detections in the ground plane. The trained model is evaluated for different light and weather conditions using ground truth data from a lidar sensor. It provides a precision of 92%, recall of 78%, and F1-score of 85%. The proposed deep fusion methodology has 33%, 6%, and 21% absolute improvement in precision, recall, and F1-score, respectively, compared to object-level spatial fusion output. UR - https://doi.org/10.3390/s25113422 Y1 - 2025 UR - https://doi.org/10.3390/s25113422 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-59421 SN - 1424-8220 VL - 25 IS - 11 PB - MDPI CY - Basel 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 - 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 - Pfaller, Tobias A1 - Membarth, Richard T1 - Exploiting Data Redundancy in Im2Col Convolutions JF - PARS-Mitteilungen 2025 Y1 - 2025 UR - https://dl.gi.de/items/156c727e-ec90-4809-9ce6-ee27cc89eeb0 SN - 0177-0454 VL - 37 SP - 63 EP - 70 PB - Gesellschaft für Informatik CY - Bonn ER - TY - CHAP A1 - Riegl, Peter A1 - Chandra Sekaran, Karthikeyan A1 - Botsch, Michael T1 - Generation of realistic traffic scenarios for virtual and real test drives based on a hybrid machine learning framework T2 - 2024 IEEE International Conference on Vehicular Electronics and Safety (ICVES) UR - https://doi.org/10.1109/ICVES61986.2024.10927934 Y1 - 2025 UR - https://doi.org/10.1109/ICVES61986.2024.10927934 SN - 979-8-3503-8727-8 PB - IEEE CY - Piscataway 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 - INPR A1 - Rufino Júnior, Carlos Antônio A1 - Riva Sanseverino, Eleonora A1 - Gallo, Pierluigi A1 - Amaral, Murilo Machado A1 - Koch, Daniel A1 - Kotak, Yash A1 - Diel, Sergej A1 - Walter, Gero A1 - Schweiger, Hans-Georg A1 - Zanin, Hudson T1 - A Comprehensive Review of EV Lithium-Ion Battery Degradation N2 - Lithium-ion batteries with improved energy densities have made understanding the Solid Electrolyte Interphase (SEI) generation mechanisms that cause mechanical, thermal, and chemical failures more complicated. SEI processes reduce battery capacity and power. Thus, a review of this area's understanding is important. It is essential to know how batteries degrade in EVs to estimate battery lifespan as it goes, predict, and minimize losses, and determine the ideal time for a replacement. Lithium-ion batteries used in EVs mainly suffer two types of degradation: calendar degradation and cycling degradation. Despite the existence of several existing works in the literature, several aspects of battery degradation remain unclear or have not been analyzed in detail. This work presents a systematic review of existing works in the literature. The results of the present investigation provide insight into the complex relationships among various factors affecting battery degradation mechanisms. Specifically, this systematic review examined the effects of time, side reactions, temperature fluctuations, high charge/discharge rates, depth of discharge, mechanical stress, thermal stress, and the voltage relationship on battery performance and longevity. The results revealed that these factors interact in complex ways to influence the degradation mechanisms of batteries. For example, high charge currents and deep discharges were found to accelerate degradation, while low temperatures and moderate discharge depths were shown to be beneficial for battery longevity. Additionally, the results showed that the relationship between cell voltage and State-of-Charge (SOC) plays a critical role in determining the rate of degradation. Overall, these findings have important implications for the design and operation of battery systems, as they highlight the need to carefully manage a range of factors to maximize battery performance and longevity. The result is an analysis of the main articles published in this field in recent years. This work aims to present new knowledge about fault detection, diagnosis, and management of lithium-ion batteries based on battery degradation concepts. The new knowledge is presented and discussed in a structured and comprehensive way. UR - https://doi.org/10.20944/preprints202306.0228.v2 Y1 - 2023 UR - https://doi.org/10.20944/preprints202306.0228.v2 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58428 PB - Preprints CY - Basel ER - TY - CHAP A1 - Wachtel Granado, Diogo A1 - Rothmeier, Thomas A1 - Cristófoli Duarte Silva, Letícia A1 - Vossiek, Martin A1 - Huber, Werner T1 - Simulation and Validation of Automotive Radar Performance with Water Spray Over Radome T2 - 2024 IEEE Sensors 2024: Conference Proceedings UR - https://doi.org/10.1109/SENSORS60989.2024.10784774 Y1 - 2024 UR - https://doi.org/10.1109/SENSORS60989.2024.10784774 SN - 979-8-3503-6351-7 PB - IEEE CY - Piscataway ER - TY - INPR A1 - Han, Longfei A1 - Xu, Qiuyu A1 - Kefferpütz, Klaus A1 - Elger, Gordon A1 - Beyerer, Jürgen T1 - Applying Extended Object Tracking for Self-Localization of Roadside Radar Sensors N2 - Intelligent Transportation Systems (ITS) can benefit from roadside 4D mmWave radar sensors for large-scale traffic monitoring due to their weatherproof functionality, long sensing range and low manufacturing cost. However, the localization method using external measurement devices has limitations in urban environments. Furthermore, if the sensor mount exhibits changes due to environmental influences, they cannot be corrected when the measurement is performed only during the installation. In this paper, we propose self-localization of roadside radar data using Extended Object Tracking (EOT). The method analyses both the tracked trajectories of the vehicles observed by the sensor and the aerial laser scan of city streets, assigns labels of driving behaviors such as "straight ahead", "left turn", "right turn" to trajectory sections and road segments, and performs Semantic Iterative Closest Points (SICP) algorithm to register the point cloud. The method exploits the result from a down stream task -- object tracking -- for localization. We demonstrate high accuracy in the sub-meter range along with very low orientation error. The method also shows good data efficiency. The evaluation is done in both simulation and real-world tests. UR - https://doi.org/10.48550/arXiv.2407.03084 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2407.03084 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58361 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Han, Longfei A1 - Kefferpütz, Klaus A1 - Beyerer, Jürgen T1 - 3D Extended Object Tracking based on Extruded B-Spline Side View Profiles N2 - Object tracking is an essential task for autonomous systems. With the advancement of 3D sensors, these systems can better perceive their surroundings using effective 3D Extended Object Tracking (EOT) methods. Based on the observation that common road users are symmetrical on the right and left sides in the traveling direction, we focus on the side view profile of the object. In order to leverage of the development in 2D EOT and balance the number of parameters of a shape model in the tracking algorithms, we propose a method for 3D extended object tracking (EOT) by describing the side view profile of the object with B-spline curves and forming an extrusion to obtain a 3D extent. The use of B-spline curves exploits their flexible representation power by allowing the control points to move freely. The algorithm is developed into an Extended Kalman Filter (EKF). For a through evaluation of this method, we use simulated traffic scenario of different vehicle models and realworld open dataset containing both radar and lidar data. UR - https://doi.org/10.48550/arXiv.2503.10730 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2503.10730 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58331 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Song, Rui A1 - Liang, Chenwei A1 - Xia, Yan A1 - Zimmer, Walter A1 - Cao, Hu A1 - Caesar, Holger A1 - Festag, Andreas A1 - Knoll, Alois T1 - CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving N2 - Dynamic scene rendering opens new avenues in autonomous driving by enabling closed-loop simulations with photorealistic data, which is crucial for validating end-to-end algorithms. However, the complex and highly dynamic nature of traffic environments presents significant challenges in accurately rendering these scenes. In this paper, we introduce a novel 4D Gaussian Splatting (4DGS) approach, which incorporates context and temporal deformation awareness to improve dynamic scene rendering. Specifically, we employ a 2D semantic segmentation foundation model to self-supervise the 4D semantic features of Gaussians, ensuring meaningful contextual embedding. Simultaneously, we track the temporal deformation of each Gaussian across adjacent frames. By aggregating and encoding both semantic and temporal deformation features, each Gaussian is equipped with cues for potential deformation compensation within 3D space, facilitating a more precise representation of dynamic scenes. Experimental results show that our method improves 4DGS's ability to capture fine details in dynamic scene rendering for autonomous driving and outperforms other self-supervised methods in 4D reconstruction and novel view synthesis. Furthermore, CoDa-4DGS deforms semantic features with each Gaussian, enabling broader applications. UR - https://doi.org/10.48550/arXiv.2503.06744 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2503.06744 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58313 PB - arXiv CY - Ithaca 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 - JOUR A1 - Stöttner, Julia A1 - Hanzl, Christian A1 - Terbrack, Christoph A1 - Endisch, Christian T1 - Holistic evaluation and optimization of multilevel inverter designs for electric vehicle applications JF - Energy Reports N2 - To advance the development of multilevel inverters (MLIs) for electric vehicle applications, this study introduces novel asymmetric MLI (AMLI) configurations featuring buffer modules to enhance efficiency. A comprehensive comparative analysis of 125 distinct inverter systems is conducted, integrating five different microtopologies and 25 representative symmetrical MLI (SMLI) and AMLI systems. Unlike previous studies, this work employs a successive design process with a graph-based approach to systematically minimize conduction losses. Furthermore, experimental loss measurements ensure practical relevance. By applying Pareto optimization with cost, energy losses, and total harmonic distortion as objective functions, the study identifies the most promising MLI systems among all considered ones. While the cascaded H-bridge MLI emerges as the most cost-effective solution, specific SMLI configurations with 12 or 18 battery cells per module and AMLI designs featuring buffer modules exhibit lower inverter losses. In both cases, the incorporation of microtopologies that enable parallel operation leads to a remarkable reduction in inverter losses by more than 30 % compared to the least efficient MLI systems. Finally, a comparative assessment against a conventional B6-bridge SiC inverter highlights the significant advantages of these optimized MLI configurations in terms of efficiency and system performance. UR - https://doi.org/10.1016/j.egyr.2025.03.001 Y1 - 2025 UR - https://doi.org/10.1016/j.egyr.2025.03.001 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58297 SN - 2352-4847 VL - 2025 IS - 13 SP - 3561 EP - 3573 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Mohan, Nihesh A1 - Ahuir-Torres, Juan Ignacio A1 - Kotadia, Hiren R. A1 - Elger, Gordon T1 - Laser sintering of Cu particle-free inks for high-performance printed electronics JF - npj Flexible Electronics N2 - This study investigates laser sintering of Cu particle-free ink (Cu formate tetrahydrate—amino-2-propanol complex) as an alternative to conventional sintering in an oven (under inert/reducing atmosphere). Utilizing benefits of high-speed localized heating using laser, substrate damage can be prevented for low-melting substrates such as Polyethylene Terephthalate (PET). Firstly, a suitable sintering process window is achieved based on energy density for two different flexible polymeric susbtrates: Polyimide and PET using different laser parameters (laser power, scan rate and spot diameter). Subsequently, characterization of laser sintered traces are also made using different laser optic profiles (Gaussian and top hat). Different methodologies for fabrication of metallized Cu layer were also demonstrated. A very low bulk resistivity of 3.24 µΩcm (1.87 times of bulk Cu) was achieved on trace thickness of 0.85 ± 0.15 µm exhibiting good adherence to polymeric substrates. A promising fabrication process of low-cost and reliable flexible printed electronic devices is demonstrated. UR - https://doi.org/10.1038/s41528-025-00389-5 Y1 - 2025 UR - https://doi.org/10.1038/s41528-025-00389-5 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58266 SN - 2397-4621 VL - 9 IS - 1 PB - Springer CY - London ER - TY - JOUR A1 - Bazzi, Alessandro A1 - Sepulcre, Miguel A1 - Delooz, Quentin A1 - Festag, Andreas A1 - Vogt, Jonas A1 - Wieker, Horst A1 - Berens, Friedbert A1 - Spaanderman, Paul T1 - Multi-Channel Operation for the Release 2 of ETSI Cooperative Intelligent Transport Systems JF - IEEE Communications Standards Magazine N2 - Vehicles and road infrastructure are starting to be equipped with vehicle-to-everything (V2X) communication solutions to increase road safety and provide new services to drivers and passengers. In Europe, the deployment is based on a set of Release 1 standards developed by ETSI to support basic use cases for cooperative intelligent transport systems (C-ITS). For them, the capacity of a single 10 MHz channel in the ITS band at 5.9 GHz is considered sufficient. At the same time, the ITS stakeholders are working toward several advanced use cases, which imply a significant increment of data traffic and the need for multiple channels. To address this issue, ETSI has recently standardized a new multi-channel operation (MCO) concept for flexible, efficient, and future-proof use of multiple channels. This new concept is defined in a set of new specifications that represent the foundation for the future releases of C-ITS standards. The present article provides a comprehensive review of the new set of specifications, describing the main entities that extend the C-ITS architecture at the different layers of the protocol stack. In addition, the article provides representative examples that describe how these MCO standards will be used in the future and discusses some of the main open issues arising. The review and analysis of this article facilitate the understanding and motivation of the new set of Release 2 ETSI specifications for MCO and the identification of new research opportunities. UR - https://doi.org/10.1109/MCOMSTD.0001.2200080 Y1 - 2024 UR - https://doi.org/10.1109/MCOMSTD.0001.2200080 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58154 SN - 2471-2833 VL - 8 IS - 1 SP - 28 EP - 35 PB - IEEE CY - New York ER - TY - CHAP A1 - Wachtel Granado, Diogo A1 - Rothmeier, Thomas A1 - von dem Bussche-Hünnefeld, Tetmar A1 - Huber, Werner A1 - Vossiek, Martin T1 - Radar in the Rain: Understanding and Simulating Environmental Effects on ADAS Radar Sensors T2 - 2024 IEEE Radar Conference (RadarConf24) Proceedings UR - https://doi.org/10.1109/RadarConf2458775.2024.10548570 Y1 - 2024 UR - https://doi.org/10.1109/RadarConf2458775.2024.10548570 SN - 979-8-3503-2920-9 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Wachtel Granado, Diogo A1 - Schüßler, Christian A1 - von dem Bussche-Hünnefeld, Tetmar A1 - Rothmeier, Thomas A1 - Vossiek, Martin A1 - Huber, Werner T1 - Evaluation of Automotive Radar Simulation Tools for Adverse Weather Conditions: A Comparative Analysis of Real Measurement, HFSS and Monte-Carlo GO Methods T2 - 2024 IEEE Radar Conference (RadarConf24) Proceedings UR - https://doi.org/10.1109/RadarConf2458775.2024.10549398 Y1 - 2024 UR - https://doi.org/10.1109/RadarConf2458775.2024.10549398 SN - 979-8-3503-2920-9 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Fadl, Islam A1 - Schön, Torsten A1 - Behret, Valentino A1 - Brandmeier, Thomas A1 - Palme, Frank A1 - Helmer, Thomas ED - Bashford-Rogers, Thomas ED - Meneveaux, Daniel ED - Ammi, Mehdi ED - Ziat, Mounia ED - Jänicke, Stefan ED - Purchase, Helen ED - Radeva, Petia ED - Furnari, Antonino ED - Bouatouch, Kadi ED - Sousa, A. Augusto T1 - Environment Setup and Model Benchmark of the MuFoRa Dataset T2 - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - (Volume 3) N2 - Adverse meteorological conditions, particularly fog and rain, present significant challenges to computer vision algorithms and autonomous systems. This work presents MuFoRa a novel, controllable, and measured multimodal dataset recorded at CARISSMA’s indoor test facility, specifically designed to assess perceptual difficulties in foggy and rainy environments. The dataset bridges research gap in the public benchmarking datasets, where quantifiable weather parameters are lacking. The proposed dataset comprises synchronized data from two sensor modalities: RGB stereo cameras and LiDAR sensors, captured under varying intensities of fog and rain. The dataset incorporates synchronized meteorological annotations, such as visibility through fog and precipitation levels of rain, and the study contributes a detailed explanation of the diverse weather effects observed during data collection in the methods section. The dataset’s utility is demonstrated through a baseline evaluation example, asse ssing the performance degradation of state-of-the-art YOLO11 and DETR 2D object detection algorithms under controlled and quantifiable adverse weather conditions. The public release of the dataset (https://doi.org/10.5281/zenodo.14175611) facilitates various benchmarking and quantitative assessments of advanced multimodal computer vision and deep learning models under the challenging conditions of fog and rain. UR - https://doi.org/10.5220/0013307900003912 Y1 - 2025 UR - https://doi.org/10.5220/0013307900003912 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58070 SN - 978-989-758-728-3 SP - 729 EP - 737 PB - SciTePress CY - Setúbal ER - TY - JOUR A1 - Mohan, Nihesh A1 - Steinberger, Fabian A1 - Wächter, Sonja A1 - Erdogan, Hüseyin A1 - Elger, Gordon T1 - Additive Manufacturing for Automotive Radar Sensors Using Copper Inks and Pastes JF - Applied Sciences N2 - Radar sensors are critical for obstacle detection and navigation, especially for automated driving. Using the use-case “printing of heating coils on the inside of the front housing (primary radome)” needed for de-icing in winter, it is demonstrated that additive manufacturing (AM) can provide economic and functional benefits for manufacturing of the sensors. AM will allow significant cost reduction by eliminating parts and simplifying the manufacturing process. Different AM technologies for the coils were investigated, first, by applying the conductive traces by fused deposition modeling (FDM), and, second, by printing copper particle-free inks and pastes. The metal layers were electrically and mechanically characterized using a profilometer to measure the trace dimension and a four-point probe to measure the resistance. It was revealed that low-cost conductive filaments with low resistivity and current carrying capacity are commercially still not available. The best option sourced was a copper–polyester-based filament with 6000 µΩcm after printing. Therefore, low-cost particle-free copper inks and commercial copper flake paste were selected to print the heating coil. The Cu particle-free inks were amine-based Cu (II) formate complexes, where the Cu exists in an ionic form. Using contactless printing processes such as ink-jet printing or pneumatic dispensing, the traces could be deposited onto the low-melting temperature (225 °C) polymeric radome structure. After printing, the material needed to be sintered to form the conductive copper traces. To avoid damaging the polymer radome during sintering, two different processes were investigated: low-temperature (<150 °C) sintering in an oven for 30 min or fast laser sintering. The sintered Cu layers achieved the following specific electric resistivities when slowly sintered in the oven: paste 4 µΩcm and ink 8.8 µΩcm. Using laser sintering, the ink achieved 3.2 µΩcm because the locally high temperature provides better sintering. Also, the adhesion was significantly increased to (5 B). Therefore, laser sintering is the preferred technology. In addition, it allows fast processing directly after printing. Commercial equipment is available where printing and laser sintering is integrated. The potential of low-cost copper material and the integration in additive manufacturing of electronic systems using radar sensors as an example are demonstrated in this paper. UR - https://doi.org/10.3390/app15052676 Y1 - 2025 UR - https://doi.org/10.3390/app15052676 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58065 SN - 2076-3417 VL - 15 IS - 5 PB - MDPI CY - Basel ER - TY - CHAP A1 - Karpenahalli Ramakrishna, Chidvilas A1 - Mohan, Adithya A1 - Zeinaly, Zahra A1 - Belzner, Lenz ED - Rocha, Ana Paula ED - Steels, Luc ED - van den Herik, Jaap T1 - The Evolution of Criticality in Deep Reinforcement Learning T2 - Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025) - Volume 3 N2 - In Reinforcement Learning (RL), certain states demand special attention due to their significant influence on outcomes; these are identified as critical states. The concept of criticality is essential for the development of effective and robust policies and to improve overall trust in RL agents in real-world applications like autonomous driving. The current paper takes a deep dive into criticality and studies the evolution of criticality throughout training. The experiments are conducted on a new, simple yet intuitive continuous cliff maze environment and the Highway-env autonomous driving environment. Here, a novel finding is reported that criticality is not only learnt by the agent but can also be unlearned. We hypothesize that diversity in experiences is necessary for effective criticality quantification which is majorly driven by the chosen exploration strategy. This close relationship between exploration and criticality is studied utilizing two different strategies namely the ex ponential ε-decay and the adaptive ε-decay. The study supports the idea that effective exploration plays a crucial role in accurately identifying and understanding critical states. UR - https://doi.org/10.5220/0013114200003890 Y1 - 2025 UR - https://doi.org/10.5220/0013114200003890 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-57992 SN - 978-989-758-737-5 SP - 217 EP - 224 PB - SciTePress CY - Setúbal ER - TY - CHAP A1 - Tolksdorf, Leon A1 - Birkner, Christian A1 - Tejada, Arturo A1 - Van De Wouw, Nathan T1 - Fast Collision Probability Estimation for Automated Driving using Multi-circular Shape Approximations T2 - 2024 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV55156.2024.10588731 Y1 - 2024 UR - https://doi.org/10.1109/IV55156.2024.10588731 SN - 979-8-3503-4881-1 SP - 2529 EP - 2536 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Gerner, Jeremias A1 - Bogenberger, Klaus A1 - Schmidtner, Stefanie T1 - Temporal Enhanced Floating Car Observers T2 - 2024 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV55156.2024.10588538 Y1 - 2024 UR - https://doi.org/10.1109/IV55156.2024.10588538 SN - 979-8-3503-4881-1 SP - 1035 EP - 1040 PB - IEEE CY - Piscataway ER - TY - INPR A1 - Fertig, Alexander A1 - Balasubramanian, Lakshman A1 - Botsch, Michael T1 - Hybrid Machine Learning Model with a Constrained Action Space for Trajectory Prediction UR - https://doi.org/10.48550/arXiv.2501.03666 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2501.03666 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Ulreich, Fabian A1 - Kaup, André A1 - Ebert, Martin T1 - Novel Test Bench for End-to-End Validation of Monocular Depth Estimation Under the Influence of Glaring Situations T2 - 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC) UR - https://doi.org/10.1109/ITSC58415.2024.10920009 Y1 - 2025 UR - https://doi.org/10.1109/ITSC58415.2024.10920009 SN - 979-8-3315-0592-9 SP - 2426 EP - 2432 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Zhang, Yunfei A1 - Gerner, Jeremias A1 - Ilic, Mario A1 - Schmidtner, Stefanie A1 - Bogenberger, Klaus T1 - Autonomous Vehicles as Sensors: Traffic State Estimation T2 - 104th Annual Meeting of the Transportation Research Board (TRB) Y1 - 2025 PB - National Academy of Sciences CY - Washington ER - TY - CHAP A1 - Maksimovski, Daniel A1 - Facchi, Christian A1 - Festag, Andreas T1 - Packet Rate Control for Maneuver Coordination in Congested V2X Communication Environments T2 - 2024 IEEE 100th Vehicular Technology Conference (VTC2024-Fall), Proceedings UR - https://doi.org/10.1109/VTC2024-Fall63153.2024.10758036 Y1 - 2024 UR - https://doi.org/10.1109/VTC2024-Fall63153.2024.10758036 SN - 979-8-3315-1778-6 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Funk Drechsler, Maikol A1 - Poledna, Yuri A1 - Hjort, Mattias A1 - Kharrazi, Sogol A1 - Huber, Werner T1 - Vehicle Dynamics Parameter Estimation Methodology for Virtual Automated Driving Testing T2 - 2024 IEEE International Automated Vehicle Validation Conference (IAVVC), Proceedings UR - 10.1109/IAVVC63304.2024.10786416 Y1 - 2024 UR - 10.1109/IAVVC63304.2024.10786416 SN - 979-8-3503-5407-2 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Stenzel, Gerhard A1 - Schmid, Kyrill A1 - Kölle, Michael A1 - Altmann, Philipp A1 - Lingsch-Rosenfeld, Marian A1 - Zorn, Maximilian A1 - Bücher, Tim A1 - Gabor, Thomas A1 - Wirsing, Martin A1 - Belzner, Lenz ED - Steffen, Bernhard T1 - SEGym: Optimizing Large Language Model Assisted Software Engineering Agents with Reinforcement Learning T2 - Bridging the Gap Between AI and Reality, Second International Conference, AISoLA 2024, Crete, Greece, October 30 – November 3, 2024, Proceedings UR - https://doi.org/10.1007/978-3-031-75434-0_8 Y1 - 2024 UR - https://doi.org/10.1007/978-3-031-75434-0_8 SN - 978-3-031-75434-0 SP - 107 EP - 124 PB - Springer CY - Cham ER - TY - CHAP A1 - da Silva Junior, Amauri A1 - Birkner, Christian A1 - Jazar, Reza A1 - Marzbani, Hormoz T1 - From Design to Application: Emergency Maneuver Control in a 1:3.33 Scaled Vehicle T2 - 2024 18th International Conference on Control, Automation, Robotics and Vision (ICARCV) UR - https://doi.org/10.1109/ICARCV63323.2024.10821589 Y1 - 2024 UR - https://doi.org/10.1109/ICARCV63323.2024.10821589 SN - 979-8-3315-1849-3 SP - 170 EP - 177 PB - IEEE CY - Piscataway ER - TY - JOUR A1 - de Borba, Thiago A1 - Vaculin, Ondrej A1 - Marzbani, Hormoz A1 - Jazar, Reza T1 - Increasing Safety of Vulnerable Road Users in Scenarios With Occlusion: A Collaborative Approach for Smart Infrastructures and Automated Vehicles JF - IEEE Access N2 - The impact of Automated Vehicles (AVs) on road traffic safety has become the focus of discussions among governmental organizations, academia, stakeholders, and OEMs. Questions about how safe the automated driving features should be and how the road infrastructure should be improved for the arrival of this new technology must be clarified to enable full acceptance by the customers and society and prepare the mobility of future cities. The fundamental architecture of automated vehicles comprises perception, planning, decision, and actuation. The operation of the perception system, which is responsible for understanding the environment in which the vehicle is inserted, relies mainly on the onboard sensors. However, the available ranging and vision sensors, e.g., LiDAR, radar, and camera, have several limitations. Scenarios with occlusion present a real challenge for state-of-the-art perception systems. The occlusion, caused by obstructing the sensors’ detection field, limits the vehicle’s perception ability and inhibits the detection of other road users in the surroundings, especially Vulnerable Road Users (VRUs). Infrastructure composed of Roadside Units (RSUs) equipped with infrastructure-based sensors can overcome the perception limitations of a system based solely on onboard sensors by monitoring the road environment with a larger field of view and reduced sensitivity to occlusion. This paper presents a collaborative approach for smart infrastructures and automated vehicles for vulnerable road users’ collision avoidance. The proposed extended perception system comprises four main modules: traffic monitoring, long-term motion prediction, collision risk assessment, and trajectory planning. In the event of a safety-critical scenario, the infrastructure generates a safe and comfortable evasive maneuver to avoid a possible collision. Hence, the proposed approach provides a complete solution to overcome scenarios with occluded VRUs. It allows AVs to react to a critical situation with a longer time-to-collision than other systems relying only on onboard sensors, increasing the chance of successful avoidance even when implementing smoother maneuvers. This contributes considerably to the safe and comfortable operation of automated vehicles. UR - https://doi.org/10.1109/ACCESS.2025.3527865 Y1 - 2025 UR - https://doi.org/10.1109/ACCESS.2025.3527865 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-56466 SN - 2169-3536 VL - 13 SP - 8851 EP - 8885 PB - IEEE CY - New York ER - TY - CHAP A1 - Kanso, Ali A1 - Schneider, Marco A1 - Bashir, Attique A1 - Müller, Rainer T1 - Manipulability analysis to improve the performance of a 7-DoF serial manipulator T2 - 10th-2024 International Conference on Control, Decision and Information Technologies, CoDIT 2024 UR - https://doi.org/10.1109/CoDIT62066.2024.10708416 Y1 - 2024 UR - https://doi.org/10.1109/CoDIT62066.2024.10708416 SN - 979-8-3503-7397-4 SP - 1183 EP - 1188 PB - IEEE CY - Piscataway ER - TY - JOUR A1 - Langer, Robin A1 - Bauder, Maximilian A1 - Moghariya, Ghanshyam Tukarambhai A1 - Eckert, Michael Clemens Georg A1 - Kubjatko, Tibor A1 - Schweiger, Hans-Georg T1 - Testing and Validation of the Vehicle Front Camera Verification Method Using External Stimulation JF - Sensors N2 - The perception of the vehicle’s environment is crucial for automated vehicles. Therefore, environmental sensors’ reliability and correct functioning are becoming increasingly important. Current vehicle inspections and self-diagnostics must be adapted to ensure the correct functioning of environmental sensors throughout the vehicle’s lifetime. There are several promising approaches for developing new test methods for vehicle environmental sensors, one of which has already been developed in our previous work. A method for testing vehicle front cameras was developed. In this work, the method is improved and applied again. Various test vehicles, including the Tesla Model 3, Volkswagen ID.3, and Volkswagen T-Cross, are stimulated by simulating driving scenarios. The stimulation is carried out via a tablet positioned before the camera. The high beam assist is used to evaluate the vehicle’s reaction. It was observed whether the vehicle switched from high to low beam as expected in response to the stimulation. Although no general statement can be made, the principle of stimulation works. A vehicle reaction can be successfully induced using this method. In further test series, the influence of display brightness is examined for the first time in this work. The results show that the display brightness significantly influences the test procedure. In addition, the method is validated by stimulation with colored images. It is shown that no complex traffic simulation is necessary to trigger a vehicle reaction. In the following validation approach, the CAN data of the Tesla Model 3 is analyzed during the tests. Here, too, the assumption that the vehicle reaction is based solely on the detected brightness instead of identifying road users is confirmed. The final validation approach examines the method’s applicability to other vehicles and high beam assist technologies. Although the method could not be used on the Volkswagen T-Cross due to a fault detected by the vehicle’s self-diagnosis, it worked well on the Volkswagen ID.3. This vehicle has a dynamic light assist in which individual segments of the high beam are dimmed during stimulation. Although the method developed to stimulate vehicle front cameras is promising, the specific factors that trigger the vehicle responses remain to be seen. This uncertainty suggests that further research is needed better to understand the interaction of stimulation and sensor detection. UR - https://doi.org/10.3390/s24248166 Y1 - 2024 UR - https://doi.org/10.3390/s24248166 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-56097 SN - 1424-8220 VL - 24 IS - 24 PB - MDPI CY - Basel ER - TY - JOUR A1 - Walter, Gero A1 - Diel, Sergej A1 - Rufino Júnior, Carlos Antônio A1 - Schweiger, Hans-Georg A1 - Valente de Bessa, Iury A1 - Mallmann, Maíra A1 - Kirsten Vidal de Oliveira, Aline A1 - Odilio Dos Santos, Daniel A1 - Rüther, Ricardo T1 - Operating Behavior of a Photovoltaic-driven Electrolysis System JF - Revista Brasileira de Energia Solar UR - https://doi.org/10.59627/rbens.2024v15i1.456 Y1 - 2024 UR - https://doi.org/10.59627/rbens.2024v15i1.456 SN - 2526-2831 VL - 15 IS - 1 SP - 82 EP - 92 PB - ABENS CY - São Paulo ER - TY - CHAP A1 - Zdetski, Dennis A1 - Engert, Rainer A1 - Brandmeier, Thomas T1 - Wheelbase Determination using Micro-Doppler Signatures for Automotive Pre-Crash Algorithms T2 - European Microwave Week 2024 “Waves Connecting Europe”: Conference Proceedings UR - https://doi.org/10.23919/EuRAD61604.2024.10734969 Y1 - 2024 UR - https://doi.org/10.23919/EuRAD61604.2024.10734969 SN - 978-2-87487-079-8 SP - 264 EP - 267 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Rauscher, Andreas A1 - Stenzel, Peer A1 - Endisch, Christian T1 - Optimization of Sensor Setup and Filter Frequency for End-of-Line Partial Discharge Testing of Electrical Machines T2 - 2024 IEEE International Conference on Electrical Systems for Aircraft, Railway, Ship Propulsion and Road Vehicles & International Transportation Electrification Conference (ESARS-ITEC) UR - https://doi.org/10.1109/ESARS-ITEC60450.2024.10819886 Y1 - 2024 UR - https://doi.org/10.1109/ESARS-ITEC60450.2024.10819886 SN - 979-8-3503-7390-5 PB - IEEE CY - Piscataway ER - TY - JOUR A1 - Kohler, Markus A1 - Mitsios, Dionysios A1 - Endisch, Christian T1 - Reconstruction-based visual anomaly detection in wound rotor synchronous machine production using convolutional autoencoders and structural similarity JF - Journal of Manufacturing Systems N2 - Manufacturing wound rotor synchronous machines (WRSMs) for electric vehicle traction systems necessitates rigorous quality inspection to ensure optimal product performance and efficiency. This paper presents a novel visual anomaly detection method for monitoring the needle winding process of WRSMs, utilizing unsupervised learning with convolutional autoencoders (CAEs) and the structural similarity index measure (SSIM). The method identifies deviations from the desired orthocyclic winding pattern during each stage of the winding process, enabling early detection of winding errors and preventing resource wastage and potential damage to the product or winding machinery. Trajectory-synchronized frame extraction aligns the visual inspection system with the winding trajectory, ensuring precise monitoring traceable to a specific point in the winding process. We present the comprehensive Winding Anomaly Dataset (WAD), which comprises images of WRSM rotor prototypes with and without winding faults recorded in different lighting conditions. The proposed reconstruction-based anomaly detection technique is trained on fault-free data only and utilizes the introduced masked mean structural dissimilarity index measure (MMSDIM) to focus on the relevant sections of the winding during inference. Comprehensive comparative analysis reveals that the CAE with unregularized latent space and the maximum mean discrepancy Wasserstein autoencoder (MMD-WAE) outperform the beta variational autoencoder (beta-VAE) in terms of anomaly detection performance, with the CAE and WAE delivering comparable results. Extensive testing confirms the approach’s effectiveness, achieving 95.6 % recall at 100 % precision, an AUROC of 99.9 %, and an average precision of 99.1 % on the challenging WAD, considerably outperforming state-of-the-art visual anomaly detection models. This work thus offers a robust solution for WRSM production quality monitoring and promotes the incorporation of visual inspection in electric drive manufacturing systems. UR - https://doi.org/10.1016/j.jmsy.2024.12.005 Y1 - 2024 UR - https://doi.org/10.1016/j.jmsy.2024.12.005 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-55371 SN - 1878-6642 VL - 2025 IS - 78 SP - 410 EP - 432 PB - Elsevier CY - Amsterdam 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 - 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 - Bauder, Maximilian A1 - Langer, Robin A1 - Kubjatko, Tibor A1 - Schweiger, Hans-Georg T1 - Post-Processing Kalman Filter Application for Improving Cooperative Awareness Messages’ Position Data Accuracy JF - Sensors N2 - Cooperative intelligent transportation systems continuously send self-referenced data about their current status in the Cooperative Awareness Message (CAM). Each CAM contains the current position of the vehicle based on GPS accuracy, which can have inaccuracies in the meter range. However, a high accuracy of the position data is crucial for many applications, such as electronic toll collection or the reconstruction of traffic accidents. Kalman filters are already frequently used today to increase the accuracy of position data. The problem with applying the Kalman filter to the position data within the Cooperative Awareness Message is the low temporal resolution (max. 10 Hz) and the non-equidistant time steps between the messages. In addition, the filter can only be applied to the data retrospectively. To solve these problems, an Extended Kalman Filter and an Unscented Kalman Filter were designed and investigated in this work. The Kalman filters were implemented with two kinematic models. Subsequently, driving tests were conducted with two V2X vehicles to investigate and compare the influence on the accuracy of the position data. To address the problem of non-equidistant time steps, an iterative adjustment of the Process Noise Covariance Matrix Qand the introduction of additional interpolation points to equidistance the received messages were investigated. The results show that without one of these approaches, it is impossible to design a generally valid filter to improve the position accuracy of the CAM position data retrospectively. The introduction of interpolation points did not lead to a significant improvement in the results. With the Qmatrix adaptation, an Unscented Kalman Filter could be created that improves the longitudinal position accuracy of the two vehicles under investigation by up to 80% (0.54 m) and the lateral position accuracy by up to 72% (0.18 m). The work thus contributes to improving the positioning accuracy of CAM data for applications that receive only these data retrospectively. UR - https://doi.org/10.3390/s24247892 Y1 - 2024 UR - https://doi.org/10.3390/s24247892 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-55492 SN - 1424-8220 VL - 24 IS - 24 PB - MDPI CY - Basel ER - TY - CHAP A1 - Kettelgerdes, Marcel A1 - Pandey, Amit A1 - Unruh, Denis A1 - Erdogan, Hüseyin A1 - Wunderle, Bernhard A1 - Elger, Gordon T1 - Automotive LiDAR Based Precipitation State Estimation Using Physics Informed Spatio-Temporal 3D Convolutional Neural Networks (PIST-CNN) T2 - 2023 29th International Conference on Mechatronics and Machine Vision in Practice (M2VIP) UR - https://doi.org/10.1109/M2VIP58386.2023.10413394 Y1 - 2024 UR - https://doi.org/10.1109/M2VIP58386.2023.10413394 SN - 979-8-3503-2562-1 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Paret, Paul A1 - Bhogaraju, Sri Krishna A1 - Busse, Dirk A1 - Dahlbüdding, Alexander A1 - Elger, Gordon A1 - Narumanchi, Sreekant T1 - Thermomechanical Degradation of Sintered Copper under High-Temperature Thermal Shock T2 - Proceedings: IEEE 74th Electronic Components and Technology Conference, ECTC 2024 UR - https://doi.org/10.1109/ECTC51529.2024.00196 Y1 - 2024 UR - https://doi.org/10.1109/ECTC51529.2024.00196 SN - 979-8-3503-7598-5 SP - 1219 EP - 1224 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Olcay, Ertug A1 - Meeß, Henri A1 - Elger, Gordon T1 - Dynamic Obstacle Avoidance for UAVs using MPC and GP-Based Motion Forecast T2 - 2024 European Control Conference (ECC) UR - https://doi.org/10.23919/ECC64448.2024.10591083 Y1 - 2024 UR - https://doi.org/10.23919/ECC64448.2024.10591083 SN - 978-3-9071-4410-7 SP - 1024 EP - 1031 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Han, Longfei A1 - Xu, Qiuyu A1 - Kefferpütz, Klaus A1 - Lu, Ying A1 - Elger, Gordon A1 - Beyerer, Jürgen T1 - Scalable Radar-based Roadside Perception: Self-localization and Occupancy Heat Map for Traffic Analysis T2 - 2024 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/iv55156.2024.10588397 Y1 - 2024 UR - https://doi.org/10.1109/iv55156.2024.10588397 SN - 979-8-3503-4881-1 SP - 1651 EP - 1657 PB - IEEE CY - Piscataway 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 - CHAP A1 - Koch, Daniel A1 - Stein, Murillo A1 - de Abreu, Samuel Luna A1 - Diel, Sergej A1 - Schweiger, Hans-Georg T1 - Characterization and modeling of the swelling behavior of a LiFePO4 pouch cell in multiple operating conditions T2 - 2024 IEEE Vehicle Power and Propulsion Conference (VPPC), Proceedings UR - https://doi.org/10.1109/VPPC63154.2024.10755252 Y1 - 2024 UR - https://doi.org/10.1109/VPPC63154.2024.10755252 SN - 979-8-3315-4160-6 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Steinberger, Fabian A1 - Mohan, Nihesh A1 - Rämer, Olaf A1 - Elger, Gordon T1 - Low temperature die-attach bonding using copper particle free inks T2 - 2024 IEEE 10th Electronics System-Integration Technology Conference (ESTC), Proceedings UR - https://doi.org/10.1109/ESTC60143.2024.10712150 Y1 - 2024 UR - https://doi.org/10.1109/ESTC60143.2024.10712150 SN - 979-8-3503-9036-0 PB - IEEE CY - Piscataway ER - TY - THES A1 - Dietl, Laura T1 - Inverse soft actor-critic imitation learning for pedestrian trajectory prediction N2 - Pedestrian trajectory prediction has the potential to enhance safety in everyday traffic situations. By utilizing Vehicle-to-Everything (V2X) communication pedestrians will be able to communicate their intended future trajectory with other road users. Thus, enabling other road users to adapt their path accordingly, e.g., to avoid collisions. Due to the inherent multimodality of future paths, the impact of the social and environmental context, and the influence of personal factors on a person’s behavior, pedestrian trajectory prediction is a difficult endeavor. In light of these challenges, this thesis’ objective was to develop a pedestrian trajectory prediction model capable of generating realistic multimodal trajectories for environments that closely resemble everyday traffic scenarios. This was achieved by training a model using the Inverse Soft-Q Learning (IQLearn) algorithm, which adapts the Soft Actor-Critic (SAC) approach for use in addressing Inverse Reinforcement Learning (IRL) problems. As far as the author is aware, this was the first time of IQLearn being applied for path prediction. For model training the Stanford Drone Dataset (SDD), a prominent real world dataset, was employed. The dataset analysis reveals characteristics that must be considered during the development and evaluation of a model. Furthermore, a novel difficulty classification scheme helps to gain insight into the pedestrian paths’ complexity distribution within the dataset. It is based on the trajectories’ velocity, heading, number of starts and stops, and the newly developed social context measure, which gauges the level of attention a person must pay to their local neighbors. It shows that the SDD mostly contains simpler trajectories with only a small portion being complex and containing outlier behavior. Evaluating the model on the SDD shows that it: can compete with popular benchmark models based on common metrics; is able to predominantly predict three general types of paths, i.e., small bends, linear and stationary behavior, indicating that it learned a generalized representation of the trajectories within the training dataset; and is not able to generate multimodal paths, as it predicts future samples with only minor deviations from one another instead of a diverse range of realistic trajectories. The dataset, which contains primarily simpler paths, lacks the required complexity for the model to anticipate outlier behaviors. Instead, it often completes the trajectories in a logical manner, adhering to the constraints of the environment. Y1 - 2024 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53401 CY - Ingolstadt ER - TY - CHAP A1 - Ulreich, Fabian A1 - Kaup, André A1 - Ebert, Martin T1 - Uncertainty Quantification for Adaptive Measurement Noise in Kalman Filter Based Object Tracking T2 - 2024 Sensor Data Fusion: Trends, Solutions, Applications (SDF) UR - https://doi.org/10.1109/SDF63218.2024.10773809 Y1 - 2024 UR - https://doi.org/10.1109/SDF63218.2024.10773809 SN - 979-8-3315-2744-0 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Poledna, Yuri A1 - Reway, Fabio A1 - Funk Drechsler, Maikol A1 - Huber, Werner A1 - Icking, Christian A1 - Parente Ribeiro, Eduardo ED - Juárez-Ramírez, Reyes ED - Fernández y Fernández, Carlos ED - Perez Gonzalez, Hector G. ED - Ramírez-Noriega, Alan ED - Jiménez, Samantha ED - Guerra-García, César ED - Licea Sandoval, Guillermo T1 - An Open-Source High-Level Fusion Algorithm in ROS for Automated Driving Applications T2 - Proceedings: 2022 10th International Conference in Software Engineering Research and Innovation (CONISOFT 2022) UR - https://doi.org/10.1109/CONISOFT55708.2022.00031 Y1 - 2023 UR - https://doi.org/10.1109/CONISOFT55708.2022.00031 SN - 978-1-6654-6126-9 SP - 174 EP - 181 PB - IEEE CY - Los Alamitos ER - TY - CHAP A1 - Poledna, Yuri A1 - Funk Drechsler, Maikol A1 - Donzella, Valentina A1 - Chan, Pak Hung A1 - Duthon, Pierre A1 - Huber, Werner T1 - REHEARSE: adveRse wEatHEr datAset for sensoRy noiSe modEls T2 - 2024 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IV55156.2024.10588491 Y1 - 2024 UR - https://doi.org/10.1109/IV55156.2024.10588491 SN - 979-8-3503-4881-1 SP - 2451 EP - 2457 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Cristófoli Duarte Silva, Letícia A1 - Funk Drechsler, Maikol A1 - Poledna, Yuri A1 - Huber, Werner A1 - Antonio Fiorentin, Thiago ED - Ariwa, Ezendu ED - Fong, Simon T1 - Synthetic Extreme Weather for AI Training: Concept and Validation T2 - Proceedings: 2023 Third International Conference on Digital Data Processing, DDP 2023 UR - https://doi.org/10.1109/DDP60485.2023.00044 Y1 - 2023 UR - https://doi.org/10.1109/DDP60485.2023.00044 SN - 979-8-3503-2901-8 SP - 188 EP - 194 PB - IEEE CY - Piscataway 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 - Schwan, Hannes A1 - Schmid, Maximilian A1 - Elger, Gordon T1 - Layer Resolved Thermal Impedance Measurement with Laser Stimulated Transient Thermal Analysis of Semiconductor Modules T2 - THERMINIC 2024: Proceedings of 2024, 30th International Workshop on Thermal Investigations of ICs and Systems UR - https://doi.org/10.1109/THERMINIC62015.2024.10732233 Y1 - 2024 UR - https://doi.org/10.1109/THERMINIC62015.2024.10732233 SN - 979-8-3503-8782-7 PB - IEEE CY - Piscataway 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 -