Fakultät Elektro- und Informationstechnik
Refine
Document Type
- Conference Paper (205)
- Article (118)
- Master's Thesis (68)
- Bachelor Thesis (40)
- Preprint (12)
- Part of a Compilation / Book Chapter (4)
- Book (2)
Institute
- Fakultät Elektro- und Informationstechnik (449)
- Institut für Innovative Mobilität (IIMo) (121)
- CARISSMA Institute of Electric, Connected and Secure Mobility (C-ECOS) (63)
- CARISSMA Institute of Safety in Future Mobility (C-ISAFE) (59)
- CARISSMA Institute of Automated Driving (C-IAD) (51)
- Fraunhofer-Anwendungszentrum "Vernetzte Mobilität und Infrastruktur" (47)
- AImotion Bavaria (40)
- Fakultät Informatik (19)
- CARISSMA (17)
- Human-Computer Interaction Group (HCIG) (11)
Review
- peer-review (266)
- nein (35)
- ja (21)
- editorial review (11)
Version
- published (157)
Cooperative Intelligent Transportation Systems have achieved a mature technology stage and are in an early phase of mass deployment in Europe. Relying on Vehicle-to-X communication, these systems were primarily developed to improve traffic safety, efficiency, and driving comfort. However, they also offer great opportunities for other use cases. One of them is forensic accident analysis, where the received data provide details about the status of other traffic participants, give insights into the accident scenario, and therefore help in understanding accident causes. A high accuracy of the sent information is essential: For safety use cases, such as traffic jam warning, a poor accuracy of the data may result in wrong driver information, undermine the usability of the system and even create new safety risks. For accident analysis, a low accuracy may prevent the correct reconstruction of an accident. This paper presents an experimental study of the first generation of Cooperative Intelligent Transportation Systems in Europe. The results indicate a high accuracy for most of the data fields in the Vehicle-to-X messages, namely speed, acceleration, heading and yaw rate information, which meet the accuracy requirements for safety use cases and accident analysis. In contrast, the position data, which are also carried in the messages, have larger errors. Specifically, we observed that the lateral position still has an acceptable accuracy. The error of the longitudinal position is larger and may compromise safety use cases with high accuracy requirements. Even with limited accuracy, the data provide a high value for the accident analysis. Since we also found that the accuracy of the data increases for newer vehicle models, we presume that Vehicle-to-X data have the potential for exact accident reconstruction.
It is well known that lithium-ion batteries pose a certain safety risk. The thermal runaway of a cell and the subsequent thermal propagation through the battery are considered particularly dangerous. Effective solutions for their mitigation are therefore of great interest. Previous studies have shown the significant influence
of a cell’s state of charge (SOC) on its behavior during thermal runaway. This relation may be exploitable in a battery pack to improve its safety. This study aims to assess the leverage of active SOC reduction in the imminent threat of thermal runaway. Implementing such a technique could become feasible with the emergence of reconfigurable battery systems. Four experiments were conducted, each with a module of three fresh 63 Ah high energy pouch cells in a spring-loaded bracing. The experiments studied different stationary SOC configurations, uniform (100% and 60%) and non-uniform (100%–60%–100% and 100%–20%–100%). The results indicate that thermal propagation is substantially delay (87 s) by discharging a cell in its path. The SOC reduction primarily decreases the maximum temperature of the respective cell. Further effects are a calmer thermal runaway and prolonged propagation time within the cell as well as to the next cell. In comparison, the SOC reduction has little impact on the cell’s own triggering time, as the triggering time is mainly determined by the thermal energy transferred from the preceding cell and hence by its SOC. Furthermore, the analysis of the experimental data (temperature, voltage, pressure, video) gives insights into the propagation of thermal runaway through the individual layers of a cell. With reference to the position of a cell relative to the origin of the thermal propagation, a decrease of its mass loss and an increase of its internal propagation time is observed. This effect is attributed to the decreasing module pressure due to progressive loss of material. The assessment shows that active SOC reduction techniques have great leverage for mitigating or even stopping thermal propagation in a battery pack.
Automatizované řízení
(2022)
This thesis aims to provide an improved MRI sequence for substantia nigra imaging at the Klinikum Ingolstadt. The substantia nigra is a biomarker for the neurodegenerative disease Parkinson's disease (PD). To get a comprehensive understanding of the topic, the following areas are described in this work: the human brain structure and functional regions of the brain stem, the origin of magnetism and the different properties of brain tissue when exposed to a magnetic field, the fundamental mode of operation of MRI and different sequences, and finally the applied techniques for image quality evaluation.
Using this gained understanding, the SWI is systematically altered to test different parameter settings. The data of a total of six PD patients and 20 volunteer subjects is collected and analysed regarding their image quality.
Based on the results found from these, the predictable changes caused by parameter changes are stated and an improved sequence is proposed.
Die Messung von Körperschall an Fahrzeugen zählt aufgrund der komplexen
Fahrzeuggeometrie und der physikalischen Eigenschaften von Körperschall zu den
herausfordernden Messungen an einem PKW. Dieses Arbeitspapier soll ein
umfangreiches Konzept zum Aufbau eines mikrocontrollerbasierten Teststands zur
Messung von Körperschall, mittels piezoelektrischer Tonabnehmer bereitstellen. Um
ein zufriedenstellendes Messergebnis zu erhalten, ist es notwendig, die Signale der
piezoelektrischen Tonabnehmer durch die Verwendung eines Ladungsverstärkers und
darauffolgendem Spannungsverstärker aufzubereiten und danach zu digitalisieren.
Zur Erhöhung der Aussagekraft der Messergebnisse, werden diese in dBFS- und
Beschleunigungspegel ausgegeben. Der entwickelte Teststand stellt einen
vollfunktionierenden Messaufbau zur Körperschallmessung am System
Gesamtfahrzeug im Außenbereich dar und beinhaltet eine Vorbereitung zur
Einzelkomponentenmessung. Die Ergebnisse dieser Arbeit können dazu dienen, die
Messung von Körperschall an Fahrzeugen zu verbessern, oder die Etablierung von
Körperschallmessungen in anderen Bereichen voranzutreiben.
Influence of Blind Spot Assistance Systems in Heavy Commercial Vehicles on Accident Reconstruction
(2024)
Accidents between right-turning commercial vehicles and crossing vulnerable road users (VRUs) in urban environments often lead to serious or fatal injuries and therefore play a significant role in forensic accident analysis. To reduce the risk of accidents, blind spot assistance systems have been installed in commercial vehicles for several years, among other things, to detect VRUs and warn the driver in time. However, since such systems cannot reliably prevent all turning accidents, an investigation by experts must clarify how the accident occurred and to what extent the blind spot assistance system influenced the course of the accident. The occurrence of the acoustic warning message can be defined as an objective reaction prompt for the driver, so that the blind spot assistance system can significantly influence the avoidability assessment. In order to be able to integrate the system into forensic accident analysis, a precise knowledge of how the system works and its limitations is required. For this purpose, tests with different systems and accident constellations were conducted and evaluated. It was found that the type of sensor used for the assistance systems has a great influence on the system’s performance. The lateral distance between the right side of the commercial vehicle and the VRU, as well as obstacles between them, along with the speed difference can have great influence on the reliability of the assistance system. Depending on the concrete time of the system’s warning signal, the accident can be avoided or not by the driver when reacting to this signal.
Sowohl der Anteil und Umfang von Software, als auch die Komplexität und die Entwicklungsgeschwindigkeit bei neuen Produkten nimmt stetig zu. Um diesen Anforderungen gerecht zu werden, ist es notwendig, die Softwareentwicklung fortlaufend zu optimieren und zu verbessern. Durch die Vergrößerung des Softwareanteils eines Produktes nehmen auch die Wechselwirkungen zwischen den digitalen, als auch den übergeordneten, technischen Systemen, in welche die digitalen integriert sind, stetig zu. Hieraus ist der Begriff der Embedded Software entstanden: Ein digitales System, Welches in ein technisches System eingebettet ist und als universeller Systemintegrator zwischen Steuerung, Überwachung und/oder Regelung dient.
Zur Entwicklung von Embedded Software wird eine Toolkette verwendet. Diese besteht aus einer Vielzahl einzelner Programme, welche miteinander verzahnt sind. Eine solche Toolkette ist auf einzelne Entwicklungsprogramme und Softwarehersteller spezifiziert, weswegen entsprechende Entwicklungswerkzeuge Unikaten gleichen. Die Firma ESPRiT Engineering entwickelt derzeit selbst eine eigene Toolkette, um als Dienstleister herstellerübergreifend und -unabhängig Embedded Software für Kunden zu entwickeln. Um sicherheitskritische Software mit einer Toolkette zu entwickeln, muss diese entsprechend zertifiziert werden, wofür eine Klassifizierung und Qualifizierung notwendig ist.
Das Besondere an der folgenden Arbeit ist, dass sich die Toolkette derzeit noch im frühen Entwicklungsstadium befindet und bereits hier entwicklungsbegleitend gemäß ISO 26262 auf potentielle Toolfehler und deren Auswirkungen auf das endgültige Softwareprodukt untersucht wird. Deshalb wird in dieser Arbeit auch nach geeigneten Möglichkeiten gesucht, potenzielle Fehler sicher aufzudecken. Daran anknüpfend werden geeignete, prozessuale oder toolbasierte Testmaßnahmen erstellt, wodurch die Klassifizierung der Toolkette ermöglicht wird. Für Fehler, welche durch entsprechende Maßnahmen nicht sicher aufgedeckt werden können, werden die Möglichkeiten zur Qualifizierung untersucht und vorgestellt. Begleitend ist eine zugehörige Prozesslandschaft definiert worden.
Durch diese Neuerung im Bereich der Toolkettenentwicklung erhofft sich die Firma ESPRiT Engineering, die Toolkette schneller und effizienter fertigzustellen, sowie parallel ein geeigneteres Endprodukt zu erhalten.
Steigende Kundenanforderungen und im Verlauf der Jahre immer komplexer werdende Fahrzeugsysteme, haben in der Automobilindustrie zu höheren Fehlerauftretenswahrscheinlichkeiten geführt. Im Test- und Absicherungsprozess liegt die Herausforderung eine aus Kundensicht hervorragende Qualität bei gleichzeitiger Reduktion des Aufwandes und der Kosten zu liefern. Um diesen Umständen gerecht zu werden, halten zunehmend simulationsgestützte Testmethoden Einzug im Test- und Absicherungsprozess.
Die vorliegende Masterarbeit befasst sich mit der Entwicklung einer Simulationsmethodik, die für den automatisierten Schnittstellentest im Bereich Audio- und Videoübertragung im Fahrzeug eingesetzt werden kann. Die Erarbeitung und Entwicklung der Methodik erfolgt an einer Funktion, die an der Schnittstelle zwischen dem Park- und Infotainmentsteuergerät angesiedelt ist und als Kommunikationsmedium Automotive Ethernet verwendet. Dabei reicht sie von der Generierung des Videostreams der nahen Fahrzeugumgebung durch Umfeldkameras bis zur Wiedergabe an der Anzeigeeinheit im Fahrzeuginnenraum. Definiertes Ziel bei der Entwicklung der Simulationsmethodik ist es, dass Entwickler die Befähigung erhalten Freigabeentscheidungen des auf dem Infotainmentsteuergerät verorteten Funktionsteils zu treffen. Herzstück der Arbeit ist die Modellbildung des in ein Audio Video Transport Protocol (AVTP) und im H.264 Kompressionsformat
eingebetteten Videostream vorzunehmen. Zweiter Bestandteil ist die Simulation der über SOME/IP-Paketen (Pakete, welche die Scalable service-Oriented MiddlewarE over Internet Protocol als Transport nutzen) übertragenen Steuersequenzen zur Anforderung des Videostreams bzw. Veränderung von Anzeigeoptionen im Erscheinungsbild. Nach der Integration beider Bausteine in ein Gesamtsimulationsmodell wird dieses in einem manuell durchgeführten Testfall an einer Hardware-in-the-Loop-Prüfumgebung verifiziert. Die umgesetzte Methodik bietet als Hauptbestandteil erstmals, innerhalb des gesamten Entwicklungsprozesses, die Möglichkeit Teile der Schnittstellenfunktion auf der Zielhardware des Infotainmentsteuergeräts zu verifizieren und abzusichern.
Towards to Battery Digital Passport: Reviewing Regulations and Standards for Second-Life Batteries
(2024)
Greenhouse gas emissions from transportation harm the environment. In response to these environmental concerns, numerous countries encourage the adoption of electric vehicles (EVs) as a more environmentally friendly option than traditional gasoline-powered vehicles. Advances in battery technology have made batteries an alternative solution for energy storage in stationary applications and for electric mobility. Reduced lithium-ion batteries (LIBs) production costs due to economies of scale, electrode material and cell design developments, and manufacturing process improvements have driven this success. This trend is expected to increase the number of LIBs on the market that may be discarded in the environment at the end of their useful life if more sustainable alternatives are not technologically mature. This coming environmental concern can be mitigated by collecting wasted EV batteries, reconfiguring them, and reusing them for applications with less stringent weight, performance, and size requirements. This method would extend battery life and reduce environmental effects. The present work investigates the main regulatory structures of the second-life battery industry that require rules, technical standards, and laws. To achieve this objective, a systematic review was carried out following a strict protocol that includes identifying relevant studies, extracting data and information, evaluating, and summarizing information. This paper explains the primary rules and technical standards governing the second-life battery business. The findings highlight the need for universities, research institutions, and government agencies to evaluate the second-life battery industry objectively. This would enable the creation of new technological regulations and laws for this burgeoning industry.
Multidimensional Magnetic Resonance Imaging (MRI) is a versatile tool for microstructure mapping. We use a diffusion weighted inversion-recovery spin echo (DW-IR-SE) sequence with spiral readouts at ultra-strong gradients to acquire a rich diffusion-relaxation data set with sensitivity to myelin water. We reconstruct 1D and 2D spectra with a two-step convex optimization approach and investigate a variety of multidimensional MRI methods, including 1D multi-component relaxometry, 1D multi-component diffusometry, 2D relaxation correlation imaging, and 2D diffusion-relaxation correlation spectroscopic imaging (DR-CSI), in terms of their potential to quantify tissue microstructure, including the myelin water fraction (MWF). We observe a distinct spectral peak that we attribute to myelin water in multi-component T1 relaxometry, T1-T2 correlation, T1-D correlation, and T2-D correlation imaging. Due to lower achievable echo times compared to diffusometry, MWF maps from relaxometry have higher quality. While 1D multi-component T1 data allows much faster myelin mapping, 2D approaches could offer unique insights into tissue microstructure and especially myelin diffusion.
Removing the bias and variance of multicentre data has always been a challenge in large scale digital healthcare studies, which requires the ability to integrate clinical features extracted from data acquired by different scanners and protocols to improve stability and robustness. Previous studies have described various computational approaches to fuse single modality multicentre datasets. However, these surveys rarely focused on evaluation metrics and lacked a checklist for computational data harmonisation studies. In this systematic review, we summarise the computational data harmonisation approaches for multi-modality data in the digital healthcare field, including harmonisation strategies and evaluation metrics based on different theories. In addition, a comprehensive checklist that summarises common practices for data harmonisation studies is proposed to guide researchers to report their research findings more effectively. Last but not least, flowcharts presenting possible ways for methodology and metric selection are proposed and the limitations of different methods have been surveyed for future research.
Federated learning allows for cooperative training among distributed clients by sharing their locally learned model parameters, such as weights or gradients. However, as model size increases, the communication bandwidth required for deployment in wireless networks becomes a bottleneck. To address this, we propose a residual-based federated learning framework (ResFed) that transmits residuals instead of gradients or weights in networks. By predicting model updates at both clients and the server, residuals are calculated as the difference between updated and predicted models and contain more dense information than weights or gradients. We find that the residuals are less sensitive to an increasing compression ratio than other parameters, and hence use lossy compression techniques on residuals to improve communication efficiency for training in federated settings. With the same compression ratio, ResFed outperforms current methods (weight- or gradient-based federated learning) by over 1.4× on federated data sets, including MNIST, FashionMNIST, SVHN, CIFAR-10, CIFAR-100, and FEMNIST, in client-to-server communication, and can also be applied to reduce communication costs for server-to-client communication.
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.
Environment perception using camera, radar, and/or lidar sensors has significantly improved in the last few years because of deep learning-based methods. However, a large group of these methods fall into the category of supervised learning, which requires a considerable amount of annotated data. Due to uncertainties in multi-sensor data, automating the data labeling process is extremely challenging; hence,
it is performed manually to a large extent. Even though full automation of such a process is difficult, semiautomation can be a significant step to ease this process. However, the available work in this regard is still very limited; hence, in this paper, a novel semi-automatic annotation methodology is developed for labeling RGB camera images and 3D automotive radar point cloud data using a smart infrastructure-based sensor setup. This paper also describes a new method for 3D radar background subtraction to remove clutter and a new object category, GROUP, for radar-based object detection for closely located vulnerable road users. To validate the work, a dataset named INFRA-3DRC is created using this methodology, where 75% of the
labels are automatically generated. In addition, a radar cluster classifier and an image classifier are developed, trained, and tested on this dataset, achieving accuracy of 98.26% and 94.86%, respectively. The dataset and Python scripts are available at https://fraunhoferivi.github.io/INFRA-3DRC-Dataset/.
Crash-Prone Fault Combination Identification for Over-Actuated Vehicles During Evasive Maneuvers
(2024)
Throughout a vehicle’s lifecycle, systems may fail during operation, requiring effective fault management by the vehicle controller. Various system faults affect vehicle handling differently. Additionally, vehicle velocity and road friction directly impact handling and stability. Thus, it is essential to investigate relevant factors, such as actuator faults, vehicle velocity, road friction, and their combinations, before developing a fault-tolerant controller to mitigate potential critical situations. Our work thus focuses on identifying faults and fault combinations that might lead to crashes for over-actuated vehicles during evasive maneuvers and those impacting comfort parameters. We employ a state-of-the-art vehicle controller optimized for evasive lane changes for over-actuated vehicles. The driving scenario encompasses critical conditions defined in ISO 26262 with ASIL-D, including velocities up to 130 km/h and requiring steering away from obstacles. Failure Mode and Effects Analysis, Design of Experiments, and statistical tools are used to determine fault combinations most likely to lead to crashes during evasive maneuvers. Our results indicate that the vehicle controller successfully handled the maneuver in over 53% of investigated cases, reaching up to 75.1% on dry surfaces. Road friction emerges as the most critical parameter for collision avoidance and comfort. Brake faults exhibit a higher influence on vehicle handling than other actuator faults, while single motor faults do not significantly impact vehicle parameters. Regarding two-factor interactions, brake actuators dominate, followed by steering and motor. These findings provide valuable insights for developing fault-tolerant controllers for over-actuated vehicles, guiding decisions on addressing specific faults to enhance safety and comfort parameters.
Accurate and comprehensive semantic segmentation of Bird's Eye View (BEV) is essential for ensuring safe and proactive navigation in autonomous driving. Although cooperative perception has exceeded the detection capabilities of single-agent systems, prevalent camera-based algorithms in cooperative perception neglect valuable information derived from historical observations. This limitation becomes critical during sensor failures or communication issues as cooperative perception reverts to single-agent perception, leading to degraded performance and incomplete BEV segmentation maps. This paper introduces TempCoBEV, a temporal module designed to incorporate historical cues into current observations, thereby improving the quality and reliability of BEV map segmentations. We propose an importance-guided attention architecture to effectively integrate temporal information that prioritizes relevant properties for BEV map segmentation. TempCoBEV is an independent temporal module that seamlessly integrates into state-of-the-art camera-based cooperative perception models. We demonstrate through extensive experiments on the OPV2V dataset that TempCoBEV performs better than non-temporal models in predicting current and future BEV map segmentations, particularly in scenarios involving communication failures. We show the efficacy of TempCoBEV and its capability to integrate historical cues into the current BEV map, improving predictions under optimal communication conditions by up to 2% and under communication failures by up to 19%. The code will be published on GitHub.
A simulation study to analyse the impact of V2X communication on the emergency vehicle response time
(2024)
Focused on the crucial intersection of urban mobility and public safety, the thesis investigates the practical implications of integrating V2X technology for the streets of Ingolstadt. This study employs simulation techniques to mimic real-world situations, evaluating the tangible benefits of V2X-enabled vehicles in speeding up emergency arrival time.
By connecting theory with simulations, this work aims to guide policymaking and technology development dept. for improved emergency response systems, for the roads of Ingolstadt.
The increasing demand for electric vehicles EV in recent years has led to a growing need for advanced BMS that can accurately estimate the state of health SOH of batteries. The SOH is a critical parameter that determines the performance and lifespan of batteries, and accurate estimation of these parameters is essential for optimizing battery utilization and improving the overall efficiency and reliability of EV. Accurately estimating the SOH of batteries in real driving conditions is a challenging task due to the dynamic nature of driving cycles, which can cause significant variations in battery behavior. Moreover, the accuracy of existing estimation techniques is often affected by factors such as battery degradation, temperature variations, and non-linearities in battery behavior.
To address these challenges, researchers and engineers have developed a wide range of techniques and algorithms for estimating the SOH of batteries in real driving conditions. These techniques include model-based approaches, data-driven methods, and hybrid techniques that combine both model-based and data-driven approaches. The objective of this master thesis is to critically review the existing literature on estimation techniques for SOH in real driving cycles, identify the strengths and limitations of different approaches, and propose a novel estimation technique that can overcome the limitations of existing approaches. The proposed technique will be evaluated using real-world data obtained from a test vehicle.
It is vital to do a precise assessment of the condition of these batteries in order to guarantee that they can be used safely and to prevent explosions that may possibly be catastrophic. The challenges that were discussed before could be solved with the assistance of prediction models. The purpose of this research is to evaluate the accuracy of predictions made by a variety of machine learning algorithms on the state of the battery. In order to achieve this result, time series forecasting techniques are used to data metrics. It was shown that Long Short-Term Memory LSTM models perform very well when it comes to the creation of forecasts that can be relied upon. An accurate forecast made with the aid of machine learning models may assist in increasing sales of electric vehicles and ensuring that these batteries are used in a secure manner.
This paper delves into the integration of Artificial Intelligence (AI) within the infotainment industry and its impact on privacy concerns. The rise of personalized experiences in infotainment has transformed user engagement by offering tailored recommendations across various content categories such as news, music, videos, and social media updates. However, the continuous gathering of personalized data by AI raises privacy issues. Despite these concerns, AI algorithms analyze user preferences, behaviors, and demographics to provide personalized content, improving user satisfaction and interaction. While some regions have implemented regulations to protect user privacy, finding a balance between the benefits of AI, user expectations, and privacy protection presents a challenge. Enhancing transparency, user control, and consent procedures are essential to ensure the ethical use of AI systems and safeguard user information. Recognizing the potential risks associated with AI-driven infotainment allows stakeholders to collaborate on a comprehensive framework that maximizes the advantages of AI while preserving privacy.
Collaborative perception in automated vehicles leverages the exchange of information between agents, aiming to elevate perception results. Previous camera-based collaborative 3D perception methods typically employ 3D bounding boxes or bird's eye views as representations of the environment. However, these approaches fall short in offering a comprehensive 3D environmental prediction. To bridge this gap, we introduce the first method for collaborative 3D semantic occupancy prediction. Particularly, it improves local 3D semantic occupancy predictions by hybrid fusion of (i) semantic and occupancy task features, and (ii) compressed orthogonal attention features shared between vehicles. Additionally, due to the lack of a collaborative perception dataset designed for semantic occupancy prediction, we augment a current collaborative perception dataset to include 3D collaborative semantic occupancy labels for a more robust evaluation. The experimental findings highlight that: (i) our collaborative semantic occupancy predictions excel above the results from single vehicles by over 30%, and (ii) models anchored on semantic occupancy outpace state-of-the-art collaborative 3D detection techniques in subsequent perception applications, showcasing enhanced accuracy and enriched semantic-awareness in road environments.
Traffic accidents remain a major global health concern, with millions losing their lives and many more suffering life-altering injuries each year. Especially the delay in emergency services' arrival at the accident scene, caused by various factors, can significantly impact the outcome for the victims. Hence, prompt help from bystanders can save lives and decrease damage to health in the case of an accident. Incorporating innovative systems can help improve response time and provide rapid and reliable access to first aid at the crash scene, ultimately contributing to reducing fatalities and disabilities resulting from road traffic accidents.
This thesis presents the development of a first aider request system that is activated by the eCall, automatically identifying and calling first aiders to the accident scene. The system is designed for usage in vehicles and notifies nearby first aiders via smartphone application or in-vehicle infotainment system. The core of this thesis delves into the design, development, and rigorous evaluation of this system. It explores various technical considerations, system configurations, and task distribution strategies, ensuring optimal system functionality and efficiency. By incorporating an intuitive smartphone application and seamless in-vehicle integration, the system prioritizes accessibility and ease of use for potential first aiders.
The results hold promise for enhancing post-crash response. By harnessing the help of nearby first aiders, the system has the potential to reduce casualties, improve patient outcomes, and ultimately save lives. The findings presented in this thesis demonstrate the first aider request system's valuable contribution to advancing road safety and lifesaving efforts.
Emergent Cooperation from Mutual Acknowledgment Exchange in Multi-Agent Reinforcement Learning
(2022)
Peer incentivization (PI) is a recent approach, where all agents learn to reward or to penalize each other in a distributed fashion which often leads to emergent cooperation. Current PI mechanisms implicitly assume a flawless communication channel in order to exchange rewards. These rewards are directly integrated into the learning process without any chance to respond with feedback. Furthermore, most PI approaches rely on global information which limits scalability and applicability to real-world scenarios, where only local information is accessible. In this paper, we propose Mutual Acknowledgment Token Exchange (MATE), a PI approach defined by a two-phase communication protocol to mutually exchange acknowledgment tokens to shape individual rewards. Each agent evaluates the monotonic improvement of its individual situation in order to accept or reject acknowledgment requests from other agents. MATE is completely decentralized and only requires local communication and information. We evaluate MATE in three social dilemma domains. Our results show that MATE is able to achieve and maintain significantly higher levels of cooperation than previous PI approaches. In addition, we evaluate the robustness of MATE in more realistic scenarios, where agents can defect from the protocol and where communication failures can occur. We also evaluate the sensitivity of MATE w.r.t. the choice of token values.
Diese Arbeit widmet sich dem Thema einer kombinierten Messmethode für Sauerstoff und Kohlendioxid. Zunächst werden mit den optischen, elektrochemischen, resistiven und Lumineszenz-Quenching-basierten Methoden vier geeignete Verfahren aus dem Stand der Technik näher kritisch beleuchtet. Anschließend wird untersucht, ob es möglich ist, einen optischen Sensor für beide Gase aus kommerziell erhältlichen Bauteilen und einem STMF103C8-Microcontroller mit 12bit-A/D-Wandler entwerfen. Nach der Durchführung von Tests kommt die Arbeit zum Schluss, dass die Entwicklung eines Dual-Sensors auf Basis optischer Messprinzipien möglich sein kann, aber hierfür noch weitere Versuchsiterationen mit vorgeschlagenen Verbesserungsansätzen notwendig werden.
In scalable traffic analysis for smart city applications and the increasing trend of autonomous driving in the foreseeable future, the implementation of multiple sensor systems for environmental perception will become essential. With the possibility of raw data transmission using 5G communication technology, a centralized approach using sensor data fusion of multiple sensors has been implemented to provide better collaborative environmental perception in infrastructure. Multi-target tracking plays an important role in environmental perception and has attracted enormous interest and effort in the research community resulting in approaches with different benefits and shortcomings. The thesis focuses on the implementation and evaluation of different types of model-based approaches for data association problems, namely Global Nearest Neighbour (GNN), Joint Probabilistic Data Association (JPDA) and Multiple Hypothesis Tracking (MHT) in the context of centralized multi-target tracking. The thesis presents methods for data processing and measurement mapping from sensor coordinates to world coordinates. The thesis also presents the use of homography to determine the position and orientation of the sensors. The implementation of the trackers is conducted in MATLAB and the evaluation of the trackers is performed using GOSPA metrics. The results indicate that GNN achieves optimal performance when targets are spatially distant and is computationally the most cost effective. JPDA demonstrates superior efficacy when targets are in close proximity. Overall, the performance of MHT is compromised by its computational expense.
Fault testing in the production line of automotive traction machines is essential to ensure the desired lifetime. Since repetitive partial discharges (PDs) caused by anomalies in the insulation system lead to premature breakdowns of electrical machines, a reliable PD detection is of great importance. This paper proposes deep learning (DL) methods to improve the discrimination of PD from background noise in comparison with the state-of-the-art amplitude based PD detection in the production line. First, a systematic data extraction and labeling procedure is introduced to obtain correctly labeled datasets from arbitrary PD measurements. In addition, datasets are enhanced with low signal-to-noise ratio PD pulses by applying a special data augmentation approach. 13 different convolutional, recurrent and fully connected neural networks are compared for various time-frequency representations of the input signals. Hyperparameters for input transform, network topology and solver are optimized for all 13 combinations to ensure a fair case study. As a result, the two-dimensional convolutional neural network with continuous wavelet transform achieves the best accuracy of around 99.76% on a test dataset of PD signals originating from previously not utilized test objects. All DL models considered in this comparison outperform the state-of-the-art threshold-based PD classification. Even for PD events with an amplitude close to the noise level, the detection rate is still around 95% for the best network. Furthermore, without applying the proposed data augmentation procedure, the DL models investigated are not able to distinguish small PD pulses from noise.