@article{BauderBoehmKubjatkoetal.2022, author = {Bauder, Maximilian and B{\"o}hm, Klaus and Kubjatko, Tibor and Wech, Lothar and Schweiger, Hans-Georg}, title = {C-ITS relevant critical vehicle-to-vehicle accident scenarios for accident analysis}, volume = {22}, pages = {3562}, journal = {Sensors}, number = {9}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {https://doi.org/10.3390/s22093562}, year = {2022}, abstract = {The relevance of scientific investigations, whether simulative or empirical, is strongly related to the environment used and the scenarios associated with it. Within the field of cooperative intelligent transport systems, use-cases are defined to describe the benefits of applications. This has already been conducted in the available safety-relevant Day 1 applications longitudinal and intersection collision risk warning through the respective technical specifications. However, the relevance of traffic scenarios is always a function of accident severity and frequency of a retrospective consideration of accident databases. In this study, vehicle-to-vehicle scenarios with high frequency and/or severe personal injuries are therefore determined with the help of the CISS database and linked to the use-cases of the safety-relevant Day 1 applications. The relevance of the scenarios thus results on the one hand from the classical parameters of retrospective accident analysis and on the other hand from the coverage by the named vehicle-to-x applications. As a result, accident scenarios with oncoming vehicles are the most relevant scenarios for investigations with cooperative intelligent transport systems. In addition, high coverage of the most critical scenarios within the use-cases of longitudinal and intersection collision risk warning is already apparent.}, language = {en} } @article{BauderLechelerWechetal.2022, author = {Bauder, Maximilian and Lecheler, Katrin and Wech, Lothar and B{\"o}hm, Klaus and Paula, Daniel and Schweiger, Hans-Georg}, title = {Determination of accident scenarios via freely available accident databases}, volume = {12}, journal = {Open Engineering}, number = {1}, publisher = {De Gruyter}, address = {Berlin}, issn = {2391-5439}, doi = {https://doi.org/10.1515/eng-2022-0047}, pages = {453 -- 467}, year = {2022}, abstract = {The derivation of real accident scenarios from accident databases represents an important task within vehicle safety research. Simulations are increasingly used for this purpose. Depending on the research interest, a wide range of accident databases exists worldwide, which differ mainly in the number of recorded data per accident and availability. This work aims to identify critical vehicle-to-vehicle accidents based on freely available accident databases to derive concrete scenarios for a subsequent simulation. For this purpose, the method of the pre-crash matrix is applied using the example of the freely available Crash Investigation Sampling System database of the National Highway Traffic Safety Administration. An analysis of existing databases worldwide shows that this is the most detailed, freely available database. The derivation of scenarios succeeds here by a new method, whereby a center of gravity calculation is carried out based on the damages of the vehicles according to Collision Deformation Classification nomenclature. In addition, the determination of other necessary parameters, as well as the limits of the database, is shown in order to derive a scenario that can be simulated. As a result, the constellations of the five most frequent vehicle-to-vehicle accident scenarios according to the Crash Investigation Sampling System database are presented. In particular, other institutions should follow National Highway Traffic Safety Administration's example and make data freely available for accident research.}, language = {en} } @inproceedings{SchneiderLugnerInderstetal.2021, author = {Schneider, Kilian and Lugner, Robert and Inderst, Maximilian and Weigl, Tobias and Brandmeier, Thomas}, title = {Verification of Crash Severity Estimation Algorithm for Autonomous Driving Using Real Crash Data}, booktitle = {ICVISP 2020: Proceedings of the 2020 4th International Conference on Vision, Image and Signal Processing}, publisher = {ACM}, address = {New York}, isbn = {978-1-4503-8953-2}, doi = {https://doi.org/10.1145/3448823.3448850}, year = {2021}, language = {en} } @inproceedings{daSilvaJuniorBirknerShirur2020, author = {da Silva Junior, Amauri and Birkner, Christian and Shirur, Naveen}, title = {Development of Lateral Control for Different Electric Vehicle Drive and Steering Systems}, booktitle = {FISITA Web Congress 2020}, publisher = {FISITA}, address = {Bishops Stortford}, url = {https://www.fisita.com/library/f2020-vdc-075}, year = {2020}, language = {en} } @inproceedings{SequeiraSurveAfrajetal.2020, author = {Sequeira, Gerald Joy and Surve, Manasi and Afraj, Shahabaz and Brandmeier, Thomas}, title = {A novel concept for validation of pre-crash perception sensor information using contact sensor}, booktitle = {2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-7281-4149-7}, doi = {https://doi.org/10.1109/ITSC45102.2020.9294242}, year = {2020}, language = {en} } @inproceedings{SequeiraAfrajSurveetal.2020, author = {Sequeira, Gerald Joy and Afraj, Shahabaz and Surve, Manasi and Brandmeier, Thomas}, title = {LiDAR point cloud analysis for vehicle contour estimation using polynomial approximation and curvature breakdown}, booktitle = {2020 IEEE 92nd Vehicular Technology Conference (VTC2020-Fall) Proceedings}, publisher = {IEEE}, address = {Piscataway (NJ)}, isbn = {978-1-7281-9484-4}, issn = {2577-2465}, doi = {https://doi.org/10.1109/VTC2020-Fall49728.2020.9348457}, year = {2020}, language = {en} } @article{MothershedLugnerAfrajetal.2020, author = {Mothershed, David Michael and Lugner, Robert and Afraj, Shahabaz and Sequeira, Gerald Joy and Schneider, Kilian and Brandmeier, Thomas and Soloiu, Valentin}, title = {Comparison and Evaluation of Algorithms for LiDAR-Based Contour Estimation in Integrated Vehicle Safety}, volume = {23}, journal = {IEEE Transactions on Intelligent Transportation Systems}, number = {5}, publisher = {IEEE}, address = {New York}, issn = {1558-0016}, doi = {https://doi.org/10.1109/TITS.2020.3044753}, pages = {3925 -- 3942}, year = {2020}, language = {en} } @article{HeldSteinhauserKochetal.2021, author = {Held, Patrick and Steinhauser, Dagmar and Koch, Andreas and Brandmeier, Thomas and Schwarz, Ulrich}, title = {A Novel Approach for Model-Based Pedestrian Tracking Using Automotive Radar}, volume = {23}, journal = {IEEE Transactions on Intelligent Transportation Systems}, number = {7}, publisher = {IEEE}, address = {New York}, issn = {1558-0016}, doi = {https://doi.org/10.1109/TITS.2021.3066680}, pages = {7082 -- 7095}, year = {2021}, language = {en} } @inproceedings{LugnerKrauseInderstetal.2021, author = {Lugner, Robert and Krause, Robert and Inderst, Maximilian and Schneider, Kilian and Sequeira, Gerald Joy and Brandmeier, Thomas}, title = {Interface and Optimizations for Crash Severity Estimation and Inevitability Modelling in Pre-Crash Safety Systems}, booktitle = {FISITA World Congress 2021}, publisher = {FISITA}, address = {Bishops Stortford}, url = {https://www.fisita.com/library/f2021-pif-070}, year = {2021}, language = {en} } @inproceedings{SchlampSchneiderLugneretal.2022, author = {Schlamp, Anna-Lena and Schneider, Kilian and Lugner, Robert and Sequeira, Gerald Joy and Brandmeier, Thomas}, title = {Approximation of the overlap for integral safety systems}, booktitle = {Fahrzeugsicherheit: Auf dem Weg zur Fahrzeugsicherheit 2030}, publisher = {VDI Verlag}, address = {D{\"u}sseldorf}, isbn = {978-3-18-102387-7}, doi = {https://doi.org/10.51202/9783181023877-407}, pages = {407 -- 418}, year = {2022}, language = {en} } @article{SequeiraKondaLugneretal.2022, author = {Sequeira, Gerald Joy and Konda, Anudeep Reddy and Lugner, Robert and Jumar, Ulrich and Brandmeier, Thomas}, title = {Crash Pulse Prediction Using Regression Algorithm with Gradient Descent Optimization Method for Integrated Safety Systems}, volume = {10 (2022)}, pages = {09-10-02-0009}, journal = {SAE International journal of transportation safety}, number = {2}, publisher = {SAE International}, address = {Warrendale}, issn = {2327-5634}, doi = {https://doi.org/10.4271/09-10-02-0009}, year = {2022}, language = {en} } @inproceedings{ShirurBirknerFosteretal.2022, author = {Shirur, Naveen and Birkner, Christian and Foster, Andreas and Bleeck, Matthias}, title = {Active control of airbag filling: sensor, valve, test bench, best-practice of industry-university-cooperation}, booktitle = {Fahrzeugsicherheit 2022: Auf dem Weg zur Fahrzeugsicherheit 2030}, publisher = {VDI-Verlag GmbH}, address = {D{\"u}sseldorf}, isbn = {978-3-18-092387-1}, issn = {0083-5560}, doi = {https://doi.org/10.51202/9783181023877-35}, pages = {35 -- 46}, year = {2022}, language = {en} } @inproceedings{Plaschkies2021, author = {Plaschkies, Franz}, title = {Convergence of Artificial Intelligence and Passive Vehicle Safety}, booktitle = {SafetyWeek: Die Zukunft der Fahrzeugsicherheit}, year = {2021}, language = {en} } @article{KamannSteinhauserGrusonetal.2020, author = {Kamann, Alexander and Steinhauser, Dagmar and Gruson, Frank and Brandmeier, Thomas and Schwarz, Ulrich}, title = {Extended Object Tracking Using Spatially Resolved Micro-Doppler Signatures}, volume = {6}, journal = {IEEE Transactions on Intelligent Vehicles}, number = {3}, publisher = {IEEE}, address = {Piscataway}, issn = {2379-8904}, doi = {https://doi.org/10.1109/TIV.2020.3035433}, pages = {440 -- 449}, year = {2020}, language = {en} } @inproceedings{SteinhauserHeldThoereszetal.2021, author = {Steinhauser, Dagmar and Held, Patrick and Th{\"o}resz, Bernhard and Brandmeier, Thomas}, title = {Towards Safe Autonomous Driving}, booktitle = {Proceedings of the 17th European Radar Conference}, subtitle = {Challenges of Pedestrian Detection in Rain with Automotive Radar}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-2-87487-061-3}, doi = {https://doi.org/10.1109/EuRAD48048.2021.00110}, pages = {409 -- 412}, year = {2021}, language = {en} } @article{ShirurBirknerBleecketal.2023, author = {Shirur, Naveen and Birkner, Christian and Bleeck, Matthias and Forster, Andreas and Deserno, Thomas Martin and Henze, Roman}, title = {3D simulations and laboratory experiments to evaluate a dynamic airbag valve}, volume = {29}, journal = {International Journal of Crashworthiness}, number = {2}, publisher = {Taylor \& Francis}, address = {London}, issn = {1754-2111}, doi = {https://doi.org/10.1080/13588265.2023.2252214}, pages = {378 -- 388}, year = {2023}, abstract = {Airbag pressure determines the restraint effect during a vehicle crash. The pressure required to restrain the occupant depends on pre-crash detection, collision parameters and the occupant's mass and position. This work modulated airbag pressure for optimum safety using a novel airbag control valve for cold-gas inflators. This paper evaluates the valve's stationary and dynamic performances for Helium by 3D flow simulations using a pressure-based solver in ANSYS Fluent® and SAE J2238 laboratory tank tests. The predicted and measured tank pressures for the fully open (stationary) valve were agreed by an average 93.73\% with an excellent correlation (correlation coefficient, R = 0.9995). For the first dynamic operation with 10 ms switching time, the results agreed by 92.78\% with R = 0.9975. In the second test with 30 ms switching, 83.67\% agreement was observed with R = 0.9893. The research concluded that the valve modulates the bag pressure and is implementable in vehicles.}, language = {en} } @inproceedings{ShirurBirknerForsteretal.2022, author = {Shirur, Naveen and Birkner, Christian and Forster, Andreas and Deserno, Thomas Martin and Henze, Roman}, title = {Smart airbag: an innovative adaptive airbag considering out-of-position (OOP) for restraint effect optimization and injury mitigation}, volume = {2022}, booktitle = {15th International Symposium and Exhibition on Sophisticated Car Safety Systems}, publisher = {Fraunhofer ICT}, address = {Pfinztal}, issn = {0722-4087}, url = {https://publica.fraunhofer.de/entities/publication/c890596b-4b7e-4406-a5f6-d2b5e588f2e7/details}, year = {2022}, language = {en} } @inproceedings{BenArabGuMohammadietal.2023, author = {Ben Arab, Amine and Gu, Jing and Mohammadi, Hassan and Book, Mia and Brandmeier, Thomas and Ferdowsizadeh Naeeni, Alireza}, title = {From Vehicle Setup to Dataset Generation: A Holistic Approach to Long-Range Automated Valet Parking Development}, booktitle = {Uni-DAS: 15. Workshop Fahrerassistenz und automatisiertes Fahren (FAS 2023)}, publisher = {Uni-DAS e. V.}, address = {Darmstadt}, isbn = {978-3-941543-74-4}, url = {https://www.uni-das.de/fas-workshop/2023.html}, pages = {1 -- 16}, year = {2023}, language = {en} } @techreport{LoefflerVoglLabenskietal.2022, author = {L{\"o}ffler, Christian and Vogl, Carina and Labenski, Volker and Weihmayr, Daniel and Gloger, Timm and Schwaderer, Till and Firmbach, Markus and Stoll, Johann and Blum, Kristin and Koebe, Markus}, title = {D3.5 Demo 2 Vehicle demonstrator for object detection in adverse weather conditions update}, url = {https://www.safe-up.eu/deliverables}, pages = {59}, year = {2022}, language = {en} } @techreport{KovacevaFlannaganKolketal.2023, author = {Kovaceva, Jordanka and Flannagan, Carol and Kolk, Harald and Wimmer, Peter and Schories, Lars and Ramasamy, Ellankavi and Becker, Julian and L{\"o}ffler, Christian and Lorente Mallada, Jorge and Weihmayr, Daniel and Castells, Jacint and Davidsson, Johan}, title = {D5.8 Safety Impact Assessment-Updated Report}, url = {https://www.safe-up.eu/deliverables}, pages = {84}, year = {2023}, language = {en} } @inproceedings{Doenmez2023, author = {D{\"o}nmez, {\"O}mer}, title = {Development of a high-level System Architecture for a cost-effective Automated Valet Parking System}, booktitle = {FISITA World Congress 2023}, publisher = {FISITA}, address = {Bishops Stortford}, url = {https://www.fisita.com/library/fwc2023-sca-040}, year = {2023}, language = {en} } @book{Doenmez2023, author = {D{\"o}nmez, {\"O}mer}, title = {Entwicklung eines Automated Valet Parking Systems im Rahmen des Forschungsprojekts ANTON}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-43117-4}, doi = {https://doi.org/10.1007/978-3-658-43117-4}, pages = {XVII, 79}, year = {2023}, language = {de} } @inproceedings{BookLugnerBrandmeier2023, author = {Book, Mia and Lugner, Robert and Brandmeier, Thomas}, title = {Relevanz von Bewegungsmodellen f{\"u}r Entwicklungen im Bereich des vorausschauenden Passiven Fußg{\"a}ngerschutzes}, booktitle = {14. VDI-Tagung Fahrzeugsicherheit, Fahrzeugsicherheit im Kontext neuer, nachhaltiger Mobilit{\"a}tskonzepte}, subtitle = {Schutz von verletzlichen Verkehrsteilnehmern}, editor = {VDI Wissensforum GmbH,}, publisher = {VDI Verlag}, address = {D{\"u}sseldorf}, isbn = {978-3-18-102426-3}, doi = {https://doi.org/10.51202/9783181024263-325}, pages = {325 -- 338}, year = {2023}, language = {de} } @unpublished{AfrajVaculinBoehmlaenderetal.2023, author = {Afraj, Shahabaz and Vaculin, Ondrej and B{\"o}hml{\"a}nder, Dennis and Hynč{\´i}k, Luděk}, title = {Vehicle Crash Simulation Models for Reinforcement Learning driven crash-detection algorithm calibration}, titleParent = {Research Square}, publisher = {Research Square}, address = {Durham}, doi = {https://doi.org/10.21203/rs.3.rs-3004299/v1}, year = {2023}, abstract = {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.}, language = {en} } @article{WeihmayrBirknerMarzbanietal.2025, author = {Weihmayr, Daniel and Birkner, Christian and Marzbani, Hormoz and Jazar, Reza}, title = {Data-Driven Vehicle Dynamics: Lever-Aging SINDy for Optimization-Based Vehicular Motion Planning}, volume = {13}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2025.3594892}, pages = {136584 -- 136597}, year = {2025}, abstract = {Motion planning remains a crucial challenge for the widespread adoption of autonomous vehicles. This paper presents a novel approach that integrates an empirical plant model within an optimization-based motion planning architecture. The model prioritizes performance and efficiency while maintaining interpretability. We introduce a methodology that utilizes a data-driven approach to derive an interpretable description of the evolution of vehicle states over time using sparse regression. This method allows effective learning from limited datasets, eliminating the need for extensive and expensive data collection. Our approach addresses the trade-off between performance and accuracy, enabling adaptation to diverse driving scenarios. We affirm the efficacy of our methodology via an extensive analysis, evaluating the independent prediction performance across diverse metrics. Additionally, we examine the overall tracking performance when incorporated into an optimization-based framework. Finally, we present a comparative analysis and discuss the subsequent impact on overall motion planning and decision-making in relation to a state-of-the-art single-track model.}, language = {en} } @inproceedings{PlaschkiesVaculin2020, author = {Plaschkies, Franz and Vaculin, Ondrej}, title = {Estimation of the Impact of Human Body Variation on Its Crash Behavior Using Machine Learning Methods}, booktitle = {FISITA Web Congress 2020}, publisher = {Fisita}, address = {Bishops Stortford}, url = {https://www.fisita.com/library/f2020-pif-051}, year = {2020}, language = {en} } @inproceedings{SlavikVaculin2021, author = {Slav{\´i}k, Martin and Vaculin, Ondrej}, title = {Concept of Mission Control System for IN2Lab testing field for Automated Driving}, booktitle = {FISITA World Congress 2021}, publisher = {FISITA}, address = {Bishops Stortford}, url = {https://www.fisita.com/library/f2021-acm-119}, year = {2021}, language = {en} } @inbook{Vaculin2022, author = {Vaculin, Ondrej}, title = {Automatizovan{\´e} ř{\´i}zen{\´i}}, booktitle = {Automatizovan{\´e} ř{\´i}zen{\´i} vozidel a autonomn{\´i} doprava: Technick{\´e} a humanitn{\´i} perspektivy}, editor = {Čern{\´y}, David and Vaculin, Ondrej and Z{\´a}mečn{\´i}k, Petr}, publisher = {Academia}, address = {Prag}, isbn = {978-80-200-3358-1}, pages = {131 -- 152}, year = {2022}, language = {mul} } @book{OPUS4-2868, title = {Automatizovan{\´e} ř{\´i}zen{\´i} vozidel a autonomn{\´i} doprava}, subtitle = {Technick{\´e} a humanitn{\´i} perspektivy}, editor = {Čern{\´y}, David and Vaculin, Ondrej and Z{\´a}mečn{\´i}k, Petr}, publisher = {Academia}, address = {Prag}, isbn = {978-80-200-3358-1}, pages = {389}, year = {2022}, language = {mul} } @inproceedings{VanderschurenVaculinNewlands2025, author = {Vanderschuren, Maria and Vaculin, Ondrej and Newlands, Alexandra}, title = {Vehicle rescue sheets: opportunities and barriers in the South African context}, booktitle = {43rd Annual Southern African Transport Conference 2025}, publisher = {SATC}, address = {Johannesburg}, isbn = {978-0-0370-8021-0}, url = {http://hdl.handle.net/2263/104908}, year = {2025}, language = {en} } @inproceedings{VaculinHaryantodeBorba2025, author = {Vaculin, Ondrej and Haryanto, Aditya and de Borba, Thiago}, title = {Potential of infrastructure-based sensors to road safety}, booktitle = {43rd Annual Southern African Transport Conference 2025}, publisher = {SATC}, address = {Johannesburg}, isbn = {978-0-0370-8021-0}, url = {http://hdl.handle.net/2263/104958}, year = {2025}, language = {en} } @inproceedings{HanumegowdaDewanganBhupalaetal.2022, author = {Hanumegowda, Anusha and Dewangan, Soumya and Bhupala, Srihari and Gruson, Frank and Steinhauser, Dagmar}, title = {Extended Object Tracking with IMM Filter for Automotive Pre-Crash Safety Applications}, booktitle = {2021 18th European Radar Conference Proceedings}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-2-87487-065-1}, doi = {https://doi.org/10.23919/EuRAD50154.2022.9784586}, pages = {177 -- 180}, year = {2022}, language = {en} } @inproceedings{SezginVriesmanHeldetal.2022, author = {Sezgin, Fatih and Vriesman, Daniel and Held, Patrick and Zimmer, Alessandro and Brandmeier, Thomas}, title = {A Deep Learning Approach for Pedestrian Behavior Interpretation Based on Radar Point Clouds}, booktitle = {2021 18th European Radar Conference Proceedings}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-2-87487-065-1}, doi = {https://doi.org/10.23919/EuRAD50154.2022.9784515}, pages = {66 -- 69}, year = {2022}, language = {en} } @inproceedings{SequeiraHarlapurObandoOrtegonetal.2021, author = {Sequeira, Gerald Joy and Harlapur, Bhuvan and Obando Ortegon, David and Lugner, Robert and Brandmeier, Thomas and Soloiu, Valentin}, title = {Investigation of Influence from Variation in Color on LiDAR Sensor for Perception of Environment in Autonomous Vehicles}, booktitle = {Proceedings ELMAR-2021: 63rd International Symposium ELMAR-2021}, editor = {Muštra, Mario and Vukovic, Josip and Zovko-Cihlar, Branka}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-6654-4437-8}, doi = {https://doi.org/10.1109/ELMAR52657.2021.9550943}, pages = {71 -- 76}, year = {2021}, language = {en} } @unpublished{HaryantoVaculin2025, author = {Haryanto, Aditya and Vaculin, Ondrej}, title = {YoFlow Method for Scenario Based Automatic Accident Detection}, publisher = {TechRxiv}, address = {Piscataway}, doi = {https://doi.org/10.36227/techrxiv.175099959.99453472/v1}, year = {2025}, abstract = {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.}, language = {en} } @article{HaryantoVaculin2025, author = {Haryanto, Aditya and Vaculin, Ondrej}, title = {YoFlow Method for Scenario Based Automatic Accident Detection}, volume = {7}, journal = {IEEE Open Journal of Intelligent Transportation Systems}, publisher = {IEEE}, address = {New York}, issn = {2687-7813}, doi = {https://doi.org/10.1109/OJITS.2025.3639557}, pages = {61 -- 73}, year = {2025}, abstract = {Recent advances in sensor and computing technologies have enabled road side units (RSUs) to not only monitor traffic flow but also process data in real time to improve road safety. However, leveraging RSUs for proactive accident detection remains a challenging and underexplored task, partly due to the lack of diverse accident data. To address this, this study proposes two key contributions: (i) a scenario-based synthetic data generation framework, and (ii) YoFlow, a novel system for vehicle-tovehicle accident detection from a simulated RSU camera perspective. The proposed framework leverages the PEGASUS method for scenario generation strategy and BeamNG.tech for generating synthetic traffic videos. This approach led to the development of the SB-SIF dataset, which includes five representative intersection crash scenarios derived from German accident data. The SB-SIF dataset contains 914 crash videos, 123 near-miss events, and 924 normal traffic instances and is publicly available at: https://doi.org/10.5281/zenodo.15267252. The proposed YoFlow system identifies accidents by analyzing temporal variations in vehicle speed vectors, using YOLO for vehicle classification and CUDA-accelerated dense optical flow to capture abrupt motion changes. The extracted features are processed and classified using an XGBoost model, achieving 94\% recall and 90\% precision in accident detection.}, language = {en} } @article{Sequeira2023, author = {Sequeira, Gerald Joy}, title = {Prediction based activation of vehicle safety systems - a contribution to improve to occupant safety by validation of pre-crash information and crash severity plus restraint strategy prediction}, volume = {71}, journal = {at - Automatisierungstechnik}, number = {3}, publisher = {De Gruyter}, address = {Berlin}, issn = {0178-2312}, doi = {https://doi.org/10.1515/auto-2022-0167}, pages = {243 -- 245}, year = {2023}, language = {en} } @inproceedings{PaulaBauderKoenigetal.2022, author = {Paula, Daniel and Bauder, Maximilian and K{\"o}nig, Thomas and Dengler, Yannick and B{\"o}hm, Klaus and Kubjatko, Tibor and Schweiger, Hans-Georg}, title = {Impact of vehicle electrification on fundamental accident reconstruction parameters}, booktitle = {Proceedings of the 30th Annual Congress of the EVU}, publisher = {EVU}, address = {Berlin}, pages = {34 -- 41}, year = {2022}, language = {en} } @inproceedings{BauderPaulaBoehmetal.2022, author = {Bauder, Maximilian and Paula, Daniel and B{\"o}hm, Klaus and Kubjatko, Tibor and Wech, Lothar and Schweiger, Hans-Georg}, title = {Opportunities and challenges of cooperative intelligent transportation systems on accident analysis}, booktitle = {Proceedings of the 30th Annual Congress of the EVU}, publisher = {EVU}, address = {Berlin}, year = {2022}, language = {en} } @article{GrafSteinhauserVaculinetal.2025, author = {Graf, Michael and Steinhauser, Dagmar and Vaculin, Ondrej and Brandmeier, Thomas}, title = {Impact of Adverse Weather on Road Safety: A Survey of Test Methods for Enhancing Safety of Automated Vehicles and Sensor Robustness in Challenging Environmental Conditions}, volume = {13}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2025.3622501}, pages = {179817 -- 179838}, year = {2025}, abstract = {Adverse weather conditions can significantly affect environmental sensors and reduce the ability of automated vehicles to interpret the environment. This can lead to the failure of driving and safety functions. To validate and increase the robustness of these, several adverse weather test methods have been introduced in recent years. The survey first gives an overview of the current traffic and accident analysis with a focus on adverse weather influences to assess the most relevant weather phenomena. Overall, rain and glare are the statistically most important adverse weather phenomena in terms of accidents. Heavy fog is rare but can cause very serious accidents. In a second step, meteorological knowledge is incorporated and the key environmental indicators for the respective weather conditions are determined, particularly taking the environmental sensor characteristics into account. Both sets of information are then utilized to provide a qualified overview of simulative and physical test methods used to reproduce critical adverse weather situations. These methods are employed to investigate the disturbance effects of inclement weather on sensors and to test the robustness of automated vehicles. The paper reveals that various approaches are used to reproduce weather effects and that test methods, each with different advantages and disadvantages, have been developed to varying degrees depending on the type of the weather phenomena. Overall, this review integrates perspectives from road safety research, meteorology, and testing methodologies to provide new insights into the validation of automated driving systems in challenging weather conditions.}, language = {en} } @inproceedings{SequeiraInderstXhikuetal.2025, author = {Sequeira, Gerald Joy and Inderst, Maximilian and Xhiku, Redjon and Lugner, Robert and Brandmeier, Thomas}, title = {Sigmoid-Based Method for Longitudinal Crash Pulse Prediction in Intelligent Vehicles}, booktitle = {2024 IEEE International Conference on Vehicular Electronics and Safety (ICVES)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3503-8727-8}, doi = {https://doi.org/10.1109/ICVES61986.2024.10927899}, year = {2025}, language = {en} } @inproceedings{InderstLugnerBrandmeieretal.2023, author = {Inderst, Maximilian and Lugner, Robert and Brandmeier, Thomas and Mehrzed, Shaen and Sequeira, Gerald Joy and Griebeler, Marcelo}, title = {Definition of Requirements for the Temporal Accuracy of Inevitability Evaluation in Integral Pre-crash Systems}, booktitle = {FAST-Zero'23: 7th International Symposium on Future Active Safety Technology toward Zero Accidents - Proceedings}, publisher = {JSAE}, address = {Gobancho}, url = {https://tech.jsae.or.jp/paperinfo/en/content/conf2023-03.004/}, year = {2023}, language = {en} } @article{deBorbaVaculinMarzbanietal.2023, author = {de Borba, Thiago and Vaculin, Ondrej and Marzbani, Hormoz and Jazar, Reza}, title = {Increasing Safety of Automated Driving by Infrastructure-Based Sensors}, volume = {11}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2023.3311136}, pages = {94974 -- 94991}, year = {2023}, abstract = {This paper describes the development of an intelligent infrastructure, a test field, for the safety assurance of automated vehicles within the research project Ingolstadt Innovation Laboratory (IN2Lab). It includes a description of the test field architecture, the RoadSide Units (RSU) concept based on infrastructure-based sensors, the environment perception system, and the mission control system. The study also proposes a global object fusion method to fuse objects detected by different RSUs and investigate the overall measurement accuracy obtained from the usage of different infrastructure-based sensors. Furthermore, it presents four use cases: traffic monitoring, assisted perception, collaborative perception, and extended perception. The traffic monitoring, based on the perception information provided by each roadside unit, generates a global fused object list and monitors the state of the traffic participants. The assisted perception, using vehicle-to-infrastructure communication, broadcasts the state information of the traffic participants to the connected vehicles. The collaborative perception creates a global fused object list with the local detections of connected vehicles and the detections provided by the roadside units, making it available for all connected vehicles. Lastly, the extended environment perception monitors specific locations, recognizes critical scenarios involving vulnerable road users and automated vehicles, and generates a suitable avoidance maneuver to avoid or mitigate the occurrence of collisions.}, language = {en} } @article{AfrajVaculinBoehmlaenderetal.2025, author = {Afraj, Shahabaz and Vaculin, Ondrej and B{\"o}hml{\"a}nder, Dennis and Hynč{\´i}k, Luděk}, title = {Vehicle crash simulation models for reinforcement learning driven crash-detection algorithm calibration}, volume = {12}, pages = {17}, journal = {Advanced Modeling and Simulation in Engineering Sciences}, number = {1}, publisher = {SpringerOpen}, address = {Berlin}, issn = {2213-7467}, doi = {https://doi.org/10.1186/s40323-025-00288-4}, year = {2025}, abstract = {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.}, language = {en} } @inproceedings{deBorbaVaculinMarzbanietal.2025, author = {de Borba, Thiago and Vaculin, Ondrej and Marzbani, Hormoz and Jazar, Reza}, title = {Cooperative Maneuver Coordination: Smart Infrastructure for VRUs Collision Avoidance with Trajectory Planning}, booktitle = {Proceedings: 2025 IEEE 3rd International Conference on Mobility, Operations, Services and Technologies, MOST 2025}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3315-1160-9}, doi = {https://doi.org/10.1109/MOST65065.2025.00015}, pages = {51 -- 58}, year = {2025}, language = {en} } @article{deBorbaVaculinMarzbanietal.2025, author = {de Borba, Thiago and Vaculin, Ondrej and Marzbani, Hormoz and Jazar, Reza}, title = {Increasing Safety of Vulnerable Road Users in Scenarios With Occlusion: A Collaborative Approach for Smart Infrastructures and Automated Vehicles}, volume = {13}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2025.3527865}, pages = {8851 -- 8885}, year = {2025}, abstract = {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.}, language = {en} } @article{DoenmezVaculindeBorba2024, author = {D{\"o}nmez, {\"O}mer and Vaculin, Ondrej and de Borba, Thiago}, title = {A Cost Effective Solution to an Automated Valet Parking System}, volume = {25}, journal = {International Journal of Automotive Technology}, number = {2}, publisher = {Springer}, address = {Heidelberg}, issn = {1976-3832}, doi = {https://doi.org/10.1007/s12239-024-00031-9}, pages = {369 -- 380}, year = {2024}, abstract = {Automated Valet Parking Systems (AVPS) relieve the driver of the entire parking process. Many of the systems known today rely on a combination of automotive sensors with sensors of the infrastructure. For this purpose, parking facilities are equipped with comprehensive sensor technology to support the vehicles in environment sensing and route planning. This approach is comparatively expensive which is why many parking operators don't provide that technology to their customers. This paper proposes a lean AVPS system architecture that requires minimal effort to adapt the infrastructure. At the same time, state-of-the-art vehicle technology is used to make AVPS more profitable overall. At the beginning, an overview will be given describing the state of the art of AVPS. Subsequently, requirements for the AVPS will be elaborated, whereby the system can be designed and implemented in the following. Finally, the presentation of simulation results shows that one doesn't have to extend the infrastructure with sensors to develop a safe and reliable AVPS.}, language = {en} } @inproceedings{RozekHarrisonBirkner2025, author = {Rozek, Lukas and Harrison, Andrew and Birkner, Christian}, title = {Influence of Autonomous Vehicle Interior Design on Occupant Injuries}, booktitle = {2025 IEEE Intelligent Vehicles Symposium (IV)}, publisher = {IEEE}, address = {Piscataway}, isbn = {979-8-3315-3803-3}, doi = {https://doi.org/10.1109/IV64158.2025.11097519}, pages = {1517 -- 1522}, year = {2025}, language = {en} } @inproceedings{PlaschkiesPossoliVaculinetal.2023, author = {Plaschkies, Franz and Possoli, Ketlen and Vaculin, Ondrej and Schumacher, Axel and de Andrade Junior, Pedro}, title = {Evaluation Approach for Machine Learning Concepts in Occupant Protection Based on Multi-Attribute Decision Making}, pages = {23-0055}, booktitle = {Proceedings of the 27th International Technical Conference on the Enhanced Safety of Vehicles}, publisher = {NHTSA}, address = {Washington}, url = {https://www-nrd.nhtsa.dot.gov/departments/esv/27th/TOC.htm}, year = {2023}, language = {en} } @inproceedings{deBorbaVaculinPatel2021, author = {de Borba, Thiago and Vaculin, Ondrej and Patel, Parth}, title = {Concept of a Vehicle Platform for Development and Testing of Low-Speed Automated Driving Functions}, booktitle = {FISITA World Congress 2021}, publisher = {FISITA}, address = {Bishops Stortford}, url = {https://www.fisita.com/library/f2021-acm-118}, year = {2021}, language = {en} }