Refine
Year of publication
Document Type
- conference proceeding (article) (23)
- Article (10)
- conference proceeding (presentation) (8)
- Other (3)
- Part of a Book (2)
- Book (1)
- Doctoral Thesis (1)
- Moving Images (1)
- Report (1)
Publication reviewed
- begutachtet (31)
- nicht begutachtet (18)
Keywords
In deep learning, in order to improve learning performance, preprocessing and ingenuity to combine a plurality of discriminators are performed. It can be inferred that it has elements exceeding the set of learning. Therefore, a configuration to combine multiple recognition elements with low loss will be studied. The advance category classification method is expected to narrow the scope of learning in the next stage. Combining elements specialized for FalsePositive/FalseNegative removal after the positive/negative determination is considered to be effective if the accuracy of the subsequent stage is high. We conducted a license plate recognition experiment by combining these and achieved the best performance for Caltech data.
Deep Learning-Based Multi-scale Multi-object Detection and Classification for Autonomous Driving
(2019)
Autonomous driving vehicles need to perceive their immediate environment in order to detect other traffic participants such as vehicles or pedestrians. Vision based functionality using camera images have been widely investigated because of the low sensor price and the detailed information they provide. Conventional computer vision techniques are based on hand-engineered features. Due to the very complex environmental conditions this limited feature representations fail to uniquely identify a specific object. Thanks to the rapid development of processing power (especially GPUs), advanced software frameworks and the availability of large image datasets, Convolutional Neural Networks (CNN) have distinguished themselves by scoring the best on populthis information, the boundingar object detection benchmarks in the research community. Using deep architectures of CNN with many layers, they are able to extract both low-level and high-level features from images by skipping the feature design procedures of conventional computer vision approaches. In this work, an end-to-end learning pipeline for multi-object detection based on one existing CNN architecture, namely Single Shot MultiBox Detector (SSD) [1], with real-time capability, is first reviewed. The SSD detector predicts the object’s position based on feature maps of different resolution together with a default set of bounding boxes. Using the SSD architecture as a starting point, this work focuses on training a single CNN to achieve high detection accuracy for vehicles and pedestrians computed in real time. Since vehicles and pedestrians have different sizes, shapes and poses, independent NNs are normally trained to perform the two detection tasks. It is thus very challenging to train one NN to learn the multi-scale detection ability. The contribution of this work can be summarized as follows:
A detailed investigation on different public datasets (e.g., KITTI [2], Caltech [3] and Udacity [4] datasets). The datasets provide annotated images from real world traffic scenarios containing objects of vehicles and pedestrians.
A data augmentation and weighting scheme is proposed to tackle the problem of class imbalance in the datasets to enable the training for both classes in a balanced manner.
Specific default bounding box design for small objects and further data augmentation techniques to balance the number of objects in different scales.
Extended SSD+ and SSD2 architectures are proposed in order to improve the detection performance and keeping the computational requirements low.
In the early phase of new vehicle system developments, it is crucial to fully define and optimize working system and functional architectures. Architecture definition and validation in turn requires a quick and accurate evaluation of a system‟s overall performance. Modeling and simulating a complete vehicle system, however, is complex and in many cases was either technically not achievable or simply has been omitted within the development process. It is the utmost challenge in system modeling and simulation to realistically reflect interaction of various electrical, mechanical, thermal, and software elements as attributed to individual system modules and their relations. State-of-the-art tools meanwhile bear this capability. In this paper we present an approach how they may effectively and efficiently be incorporated into a car system development process. To accomplish this target, we „virtualize‟ all system entities while defining and reflecting all relevant system aspects. Our proposed development flow allows simulating, evaluating, and validating complete vehicle systems and their behavior. The proposed flow will sustainably change car system development processes.
Trajectory Modelling for Autonomous Driving: Investigating the Artificial Potential Field Method
(2024)
Although the focus of autonomous driving is on maximizing safety and efficiency, comfort and familiarity will play a key role in the adoption of autonomous driving. Therefore, it is important to develop algorithms that can mimic human driving skills and adapt to individual driving styles. The potential field method (PFM) is an obstacle avoidance algorithm for autonomous driving that uses a repulsive potential field, as a environment model, to navigate the vehicle to the lowest risk potential. In this paper, the PFM is used in a overtake scenario at high speed, to test the impact of using prediction when calculating the ideal yaw rate. Analysis is done on how the potential field can be used for lane keeping while following a car and then for overtaking it. A driving simulator is used to record human driving data and compare it with automated driving using a PFM as is proposed by [3], with modifications to enable future prediction.
The following paper points out the key role of IT in the future of car development. At the moment a fundamental change in the structure of automotive IT organizations can be observed. The fact that software update cycle in automotive, about 1 year, in comparison with Apple, Google or Tesla is too much. The entertainment industry is constantly proceeding ahead much faster than the automotive industry. On top of this, new emerging platforms like Apple CarPlay and Android Auto are providing the look and the feel of a mobile phone regarding the control of the car. The vehicle itself is getting more and more as an “ultimate mobile application or app”. This shows the need of speeding up the Time-to-Market of new innovations in automotive industry.
The structure of IT departments has to support these process. No wonder that CIOs of car manufacturers are looking for new structures in their IT departments that enable faster cycle update for automotive applications taking in consideration safety and security requirements.
This only represents a particular interest, as for Apple and Google, we can see that Google has already a fleet of 23 self-driving cars in place which has already autonomously driven more than one million miles with only 12 accidents on public roads and Apple is said to work under the project name "Titan" on its own electric car.
Another important aspect is the software running in the car itself, e.g. the software that “fuses” data from sensors into a comprehensible form: objects have to be accurately located in the environment model of the socalled ego vehicle as a basis for decisions making either by the driver himself or even by the software that can determine within a fraction of a second what the car is going to do. High definition maps also play a very important role in enabling autonomous driving, being developed and maintained by companies such as Nokia HERE, with accuracy of only a few centimeters are thought to be of strategic importance for Advanced Driver Assistance Systems and Self Driving Cars.
“We’re the engine room of the system,” says Mr. Ristevski, vice president of reality capture and processing for former Nokia’s mapping unit named HERE. To be independent from Apple and Google maps and with that from possible competitors, it is said to be the main reason why the German premium car manufacturer Audi, BMW and Daimler bought the online map service for about € 2.5 bn. This is only the first step in the restructuring of the automotive industry.
The goal of the presented work is to develop an automotive radar sensor behavioral model to outline closed loop interaction of driver and vehicle in a synthetic environment. For this interaction open simulation interface (OSI) and functional mock-up interface (FMI) standards are used. This paper describes the architecture overview, working concept of FMI, OSI and different radar functions like radar channel and digital signal processing (DSP) in detail. The description of the scenario for the verification of radar behavioral model results and development of highly automated driving (HAD) functions for the closed loop simulation is elaborated in this paper.
Der allgemeine technologische Fortschritt, insbesondere in der Halbleitertechnik, beschert allen Industriezweigen bisher ungeahnte Entwicklungsschübe, die ganz allgemein auch auf die Software-Entwicklung ausstrahlen und sich somit auch auf die Software-Entwicklungsmethoden auswirken. Die Entwicklungsmethoden für Steuergeräte-Software, befinden sich daher in dem Übergang von manueller C-Code Programmierung hin zu einem graphischen Entwurf. Diese Entwurfsmöglichkeiten bringen viele Vorteile mit sich, wie z.B. Verringerung der Komplexität, Verkürzung der Software-Entwicklungszeit, Verbesserung der Software-Qualität und Automatisierung des Software-Produktionsprozesses.
Allerdings wirft dieser Abstraktionsschritt eine wesentliche Frage auf: Wie lässt sich überprüfen und sicherstellen, dass die eingesetzten Software-Entwicklungswerkezeuge für die Transformation vom graphischen Modell zum generierten C-Code und darüber hinaus zum Objektcode fehlerfrei arbeiten? Typische Methoden, um das notwendige Vertrauen in diese Transformationen zu erhalten sind: Betriebsbewährtheit, Audit des Entwicklungsprozesses des Werkzeuges sowie das Validieren der Entwicklungswerkzeuge. Insbesondere beim Validieren der Entwicklungswerkzeuge fehlte ein Leitfaden wie ein solcher Validierungsprozess aussehen könnte und in welchem Umfang - Stichwort Testtiefe - ein Entwicklungswerkzeug zu testen wäre.
In diesem Beitrag wird gezeigt, wie diese Lücke methodisch geschlossen werden konnte: Die Anforderungen an einem Validierungsprozess wurden ganz allgemein für Entwicklungswerkzeuge hergeleitet und entsprechende Validierungssuite zur Qualifizierung von C-Codegeneratoren und Target-Compilern umgesetzt und angewendet. Die Ergebnisse fließen in die entsprechenden Entwicklungsprozesse in Form von Modellierungsrichtlinien ein. Dieses Vorgehen setzt damit den Stand der Technik.
Die Herleitungsbasis für die Anforderungen an eine Validierungssuite bildeten die Anforderungen an Software-Entwicklungswerkzeuge (Das Entwicklungswerkzeug soll die "Eigenschaft X" haben). Dazu wurden einschlägige Normen und Standards, wie DIN EN 61508, RTCA DO-178B, IEC 60880, PTB-Softwareprüfstelle und MOD EDF Std 00-55, sorgfältig analysiert und entsprechend kategorisiert. Dieser Anforderungskatalog wurde dann in einen in sich stimmigen Anforderungskatalog für eine Validierungssuite (Die Validierungssuite soll validieren, dass das Entwicklungswerkzeug die "Eigenschaft X" hat) umformuliert und veröffentlicht und können beim TÜV Nord bezogen werden.
Der Validierungsprozess ist zweistufig vorgesehen. In einem ersten Schrott wird ein Gutachten für die prinzipielle Eignung der Modellierungssprache eingeholt. Diese Vorprüfung der Eingabeelemente eines Entwicklungswerkzeuges dient dazu, das Entwicklungswerkzeug hinsichtlich all jener Anforderungen zu prüfen, deren Erfüllung von einer weitgehend automatisierten Validierungssuite nicht geprüft werden können. Auf diese Weise kann auch frühzeitig sichergestellt werden, ob grundsätzliche Abweichungen zu den Anforderungen einer Qualifizierung eines Entwicklungswerkzeuges im Wege stehen und ermöglicht somit eine frühzeitige Behebung. Die sich daran anschließende Hauptprüfung des Entwicklungswerkzeuges durch eine Validierungssuite prüft das Entwicklungswerkzeug ausführungsbasiert um die notwendige Testtiefe zu erreichen.
Im Ausblick wird diskutiert, ob und wie die Anforderungen zur prinzipiellen Eignung einer Modellierungssprache beim Entwurf neuer Modellierungssprachen für sicherheitsrelevante Entwicklungsprojekte an dem Beispiel der Modellierungssprache Modelica wegweisend sein können.
A Novel Approach on Virtual Systems Prototyping Based on a Validated, Hierarchical, Modular Library
(2013)
Development of highly innovative systems requires adaptation of standard processes in order to reflect its specific characteristics. Unknown “best solutions” with respect to system requirements or their efficacy at development start is one of those most common characteristics in innovation projects. In
those cases adequate tailoring or revision of system development processes may increase quality of the technical solution while at the same time reducing the involved project risks and costs. This paper describes a novel methodology to establish Virtual Prototyping for multi-domain system development by Design Space Exploration (DSE) based on Virtual Systems Prototyping (VSP). VSP comprises four elementary steps to systematically build up the space of potential solutions. It offers a structural and dynamic insight view to validate performance indicators against a set of requirements. Our approach allows choosing the “best solution” within the design phase while simultaneously providing a high
confidence level of its efficacy prior to implementation. VSP, therefore, is a powerful instrument for increasing the quality confidence level of innovative systems while reducing risk and cost of their implementation. VSP complements the method of prototyping on system design level inherently by a tool chain based on a multi-domain validated, hierarchical and modular library. The set of tool supported process steps makes DSE based on VSP a valuable methodology for effectively and efficiently developing innovative systems. The authors demonstrate their new approach on the basis of an automotive example in the context of novel fully-electric powertrain car architectures.
Wie kann man Studierende in ihrer individuellen Persönlichkeitsentwicklung unterstützen und Kompetenzen vermitteln und fördern, damit sie für das spätere Berufsleben gut vorbereitet sind? Im Masterstudiengang für Fahrerassistenzsysteme und Advanced Driver Assistance Systems (ADAS) werden – unterstützt durch den Forschungsschwerpunkt „Innovative Lehr- und Lernformen“ – angehende Ingenieurinnen und Ingenieure konfrontiert mit neuen Lehr-/Lernformaten. Dazu zählen das agile Projektmanagement-Tool Scrum ebenso wie Design-Thinking-Workshops, die auch in Unternehmen eingesetzt werden, um neue Ideen zu entwickeln und in Teams strukturiert Lösungen für Herausforderungen der Zukunft zu finden.
Simulation of autonomous driving needs a realistic representation of the environment. There are several options. We propose a method,
which uses highly accurate global geoinformation (GIS) data from the City of Kempten for testing sensors, sensor fusion and driving functions (algorithms). The geo-information data is converted into an ASAM Open Simulation Interface (ASAM OSI) representation and benchmarked against ASAM OSI ground-truth data. This allows virtual validation and testing against highly accurate geo-referenced data
and a realistic environment representation.
To avoid rear end collisions by following drivers, a high-speed and reliable vehicle detection is needed. One of elements of detecting vehicles is a recognition method of number plates. To detect number plate region, horizontal and vertical differential filters have been used. To improve the precision, we propose a combination of luminance decision and an extended sobel filter.
Stefan Schneider, Method Engineer responsible for Dymola at BMW, speaking about the importance of FMI technology for BMW vehicle development.
The Design of a new car moves from real car prototype to software based virtual design methods, see e.g. [1]. These methods accelerate both the design and the development of new functions. Especially safety functions are of interest. The rear-end collision, which is typically caused by other drivers, is an accident that cannot be easily controlled by the ego driver. In the case, a rear-end collision takes place, a fast detection of the status and a fast evacuation are needed. This paper classifies the rear-end collisions and proposes methods of avoiding the accident and if this is not possible of minimizing the damage. Rigorous and accurate evaluation of the risk of the coming collision by fast and real-time processing and reliable detection of accidents should be realized. To improve the reliability, the integration of several detecting elements is needed. At the detection of the collision, it is necessary to minimize false positive and permit false negative identifications. Then, logical AND of results of detection elements is used to exclude the false positive error.
The types of the ego-car positions in rear-end collisions are running and stopping in a traffic jam. Types of driver’s behaviours in following vehicles are e.g. look away, inattentive, careless, dozing, etc. Types of situations are e.g. poor visibility in snow, in the fog, insufficient vehicle distance, etc. The collision should be detected at least two seconds or 50 meters before the accident at the difference speed of 100 km/h. The evacuation may be indicated to the following car by light and sound signals or electric impulses. To judge that the collision shall surely occur, the moving object must be identified as a real vehicle. Detection elements to identify real vehicle are the number plate, vehicle symmetry, the tires, the windscreen, the face or the eyes of the driver etc. In this paper, among the above elements, the number plate detection is deeply improved. The method presented is mainly developed to improve correct detection rate in comparison with conventional methods. The features of the number plate are many vertical and horizontal lines combined to numbers with horizontal to vertical aspect ratio in the order of the detected rectangle of the number plate. Additionally there is a relatively high luminance of background of number plate area. In this paper, in addition to these features, an advanced sobel filter is introduced to adapt to the size variation of the number plate depending on the distance between two cars. The basic coefficients of the original sobel filter is (1,0,-1). The proposed advanced sobel filter is (1,0,0,-1). By using the original and the advanced sobel filters, larger plates and smaller plates will be detected adaptively. The resulted rear-end collision avoidance software will be integrated and tested in the virtual system design approach.
With cross-domain simulation starting to reduce prototypes in automotive research and development, BMW aims to establish effective model exchange and tool coupling to leverage the
specialised modelling capabilities of the various simulation tools. In this paper an overview is given why BMW believes that this requires a standardised interface between simulation tools. The Functional Mock-up Interface (FMI) Standard is viewed as the best chance yet towards the goal of sustainable cross-domain simulation in the area of functional development, briefly demonstrated here with two pilot projects. This view has led to a wealth of ongoing projects involving FMI throughout the research and development process. The paper further lists first insights from these projects, distributed around seven key development areas necessary for a successful industrialisation of the standard. These include a stable, centrally manageable tool chain and an emphasis on user experience. They span tool independent parameterisation and the possibility to exchange complex data structures. Tools for model architects and concepts for the logistics of sharing models will need to be developed and refined. Finally, the authors’ hope is that successful industrialisation will be possible with a clear, future proof road map for subsequent versions of the standard.
For more than a decade, ADAC accident researchers have analysed road accidents with severe injuries, recording some 20,000 accidents. An important task in accident research is to determine the causative factors of road accidents. Apart from vehicle engineering and human factors, accident research also focuses on infrastructural and
environmental aspects.
To find out what accident scenarios are the most common in ADAC accident research and what driver assistance systems can prevent them, our first task was to conduct a detailed accident analysis.
Using CarMaker, we performed a realistic simulation of accident scenarios, including crashes, with varying parameters. To begin with, we made an initial selection of driver assistance systems in order to determine those with the greatest accident prevention potential.
One important finding of this study is that the safety potential of the individual driver assistance systems can actually be examined. It also turned out that active safety offers even much more potential for development and innovation than passive safety. At the same time, testing becomes more demanding, too, as new systems keep entering the market, many of them differing in functional details.
ADAC will continue to test all driver assistance systems as realistically as possible so as to be able to provide advice
to car buyers. Therefore, it will be essential to develop and improve test conditions and criteria.
Advanced driver assistance systems (ADAS), Highly Automated Driving Functions (HAD) and Autonomous Driving (AD) provide among comfort to the driver also a great potential for future mobility and tends to increase traffic and car safety. All ADAS, HAD and AD functions and especially those associated with high safety levels, require paradigm-changing approaches for the homologation: some ADAS and AD functions require up to about 200 million km of real drive testing for the qualification. This amount of real drive testing is not feasible for any OEM and therefore there is a strong need for a mixed test strategy where the performed real drive tests take credit from a virtual campaign evaluation. Such a combined real and virtual test strategy could reduce the necessary efforts for the qualification of a given function development and its validation.
To support virtual testing, the triangle of the driver, the vehicle and the environment has to be modeled for simulation. The interface between the vehicle and the environment, i.e. a sensor that is a device to transform physical information into electrical signals, is of crucial importance for the ADAS, HAD and AD function, because it replaces step by step the perception of the driver in the car.
This presentation gives a survey about the challenges of the modeling of sensors and their interaction with the fusion strategy and the automated driving functions and the crucial role of high fidelity environment models in order to get confidence in the simulations as a part for the homologation.
The presentations lists also first insights in results of the environment modeling of the city of Kempten/Allgäu.
The functional mock-up interface (FMI) for co-simulation (CS) aims to provide a generic representation of dynamic system models, which can be coupled for co-simulations. A system model con-forming to FMI is called a functional mock-up unit (FMU). Being a standardised interface FMI for CS defines not only the required structure of FMUs but also provides an application programming interface (API) for coupled integration of FMUs in a support-ing simulation environment. FMI for CS is an exten-sion of FMI for Model Exchange (ME), which is mainly intended to provide standardised model descriptions. Since this work is focused on co-simulation the indicating suffix shall be omitted such that FMI stands for FMI for CS. FMI facilitates enhanced simulation workflows through better exchange of models between de-partments and vendors. While a growing number of vendors seeks to adopt FMI, the compliance of integration environments and FMUs to the FMI standard gains in significance. Only fully compliant simulation environments and FMUs reliably yield simulation results that aid actual design decisions. The intention of this work is to develop a proper means to detect ambiguities and errors in imple-mentations of FMI 1.0. The task is twofold in that both FMUs and integration environments using these FMUs may violate constraints given by the FMI standard. This work will focus on the role of integration environments.
In the early phase of the product development, it is crucial to quickly and accurately evaluate a systems overall performance in order to fully define and optimize viable system and functional architectures. The presentation explains the development steps for an embedded controller. Typically, the behavior of a dynamic system (plant and controller) is in general to complex to treat by theory or formulas. Several simulation methods has established for analyzing such systems.
The presented virtual integration method allows to model and simulate the entire system, and thus the validation of the design decisions in an early phase of the development. This approach is conducted on a model in equation based languages to gain knowledge about the (intended) real system behabior. Such an abstraction typically allows to focus on the main properties and their effects of the studied multi-domain system.
The new approach of virtual integration is demonstrated for the development of a control algorithm for an embedded controller. The entire system - both the plant and the control components – is designed with the modeling language Modelica. All necessary activities are presented for the role of the function developer and explained for the example traffic light controller for a simple intersection.
The virtual integration method usualy combines components that require specific domain solvers for mechanical, electrical, etc. components, and, consequently, is based on the co-simulations.
Entscheidende Elemente und Verfahren, die zum heutigen autonomen Fahren führten, wurden von Prof. Dickmanns entwickelt. Die Tragweite seiner Arbeiten kann gar nicht überschätzt werden. Autonomes Fahren wird die Zahl der Unfälle reduzieren und die Mobilität der Menschen in unserer alternden Gesellschaft erhalten. Sie hat zudem das Potential, die Innenstädte von parkenden Autos zu befreien und diese Flächen den Menschen zurückzugeben. Für seine herausragende Rolle in der Entwicklung des autonomen Fahrens wird Prof. Dickmanns am 14. Oktober 2017 mit dem Eduard-Rhein-Technologiepreis im Ehrensaal des Deutschen Museums geehrt. Prof. Dr. Christoph Günther
Kempten hat sich zu einer Drehscheibe für angehende Automobilingenieure entwickelt. Der ADAS-Master der Universität ist der weltweit einzige seiner Art. Sechs Studenten erzählen uns, warum sie vom automatisierten Fahren fasziniert sind, was sie von zukünftigen Arbeitgebern erwarten und wie sich der „Fahrspaß“ mit autonomen Autos verändern wird.
The performance of an automated driving system is crucially affected by its environmental perception. The vehicle's perception of its environment provides the foundation for the automated responses computed by the system's logic algorithms. As perception relies on the vehicle's sensors, simulating sensor behavior in a virtual world constitutes virtual environmental perception. This is the task performed by sensor models. In this work, we introduce a real-time capable model of the measurement process for an automotive lidar sensor employing a ray tracing approach. The output of the model is point cloud data based on the geometry and material properties of the virtual scene. With this low level sensor data as input, a vehicle internal representation of the environment is constructed by means of an occupancy grid mapping algorithm. By using a virtual environment that has been constructed from high-fidelity measurements of a real world scenario, we are able to establish a direct link between real and virtual world sensor data. Directly comparing the resulting sensor output and environment representations from both cases, we are able to quantitatively explore the validity and fidelity of the proposed sensor measurement model.
Fueled by the continuous, rapid progress within microelectronics, ever more intelligent and intricate functions are realized in mechatronic systems. To control the complexity associated with such designs, modelbased control design methods are increasingly adapted in industry. Despite Modelica’s obvious suitability to
efficiently create appropriate high fidelity system models, the utilization of Modelica for developing discrete control functions is not yet wide spread. Adoption of Modelica for this task offers the potential for a seamless development methodology from the logical virtual model down to the technical system architecture, with corresponding traceability and maintainability benefits.
This contribution will specifically address this potential and propose a Modelica sub- and superset adequate for use within the development of safety-relevant control applications.
we present a tool for the automatic generation of test stimuli for small numerical support functions, e.g., code for trigonometric functions, quaternions, filters, or table lookup. Our tool is based on KLEE to produce a set of test stimuli for full path coverage. We use a method of iterative deepening over abstractions to deal with floating-point values. During actual testing the stimuli exercise the code against a reference implementation. We illustrate our approach with results of experiments with low-level trigonometric functions, interpolation routines, and mathematical support functions from an open source UAS autopilot.
Development and Simulation of a Test Environment for Vehicle Dynamics, Virtual Test Track Layout
(2017)
This paper presents an overview of a hybrid test strategy for ADAS functions testing and validation. The hybrid test strategy represents a combination of real and virtual validation procedure providing a substitute to elaborate real tests in the development process. ADAS sensor – front view camera – modeling approaches are presented where the causes of relevant optical aberrations and their effects on the acquired images are investigated. In this context, distortion, blur and vignetting models are created and demonstrated. Additionally, a toolchain, a method for camera simulation and testbed setups are defined and presented as enablers for hybrid test strategies.
Dieser Beitrag fasst die Ergebnisse der Diplomarbeit „Bewertung des Simulationsverhaltens von Co-Simulations-Werkzeugen für einen Fahrdynamikregelverbund“ von Herrn Andreas Maier an der Fachhochschule Augsburg bei der BMW AG zusammen. Das Ziel der Diplomarbeit war die Evaluierung von auf dem Markt erhältlichen Integrationswerkzeugen für die gekoppelte Simulation um anschließend mit geeigneten Kandidaten den Einfluss der Co-Simulation mittels eines BMW internen Fahrdynamikregelmodells zu untersuchen. Aus der Diplomarbeit wird der Schwerpunkt Analyse präsentiert. Wesentliches Ergebnis dieser Analyse ist der Nachweis für bitidentisches Verhalten einer Co-Simulation mittels Integrationsplattform und eines Co-Simulation reproduzierenden Modells. Als Referenzverhalten wird das Verhalten angesehen, bei dem das originale Gesamtmodell in unabhängige Teilsysteme zerlegt wurde, deren externe Verbindungssignale durchVerzögerungsblöcke ergänzt wurden. Durch diese Maßnahmen kann belegt werden, dass der Einfluss der Integrationsschicht keine unerwarteten Effekte in die Anwendungsschicht einschleppt.
This work gives an introduction into possible tool qualification approaches, and then proposes a generic approach to tool qualification using a Tool Validation Suite Approach. Here “tool” is usually used in the sense of “integrated code generator tool with target compiler“. Central to the Validation Suite Approach is the use of an Automated Test Environment with capability of automatic execution of large numbers of test cases. The presentation also provides the results of an effort to systematically gather and structure all relevant requirements on a Validation Suite from existing and upcoming standards in a generic Validation Suite Requirement Catalogue ([5], attached after this article). The presentation provides examples of the various requirements and different requirement classes and explains the role of the requirement catalogue in the Validation Suite approach. Further the contribution presents the steps according to this Validation Suite Approach to tool qualification which will lead to tool qualification and if desired certification. It outlines how assessment of a specific tool validation suite against the requirements may progress. The remainder of the presentation describes the role of validation suite operation and maintenance activities and re-qualification of tools which have been previously qualified, and gives experience and status of the currentwork. The presentation is outlined in the following sections. The topics covered in this paper include • Description of validation suite approach • Goals • Benefits of approach, • Issues to solve • Elements of validation suite • Role of test environment
Numerische Methoden
(2006)
Diese Einführung in die Numerische Mathematik behandelt die Themenbereiche Rechengenauigkeit, lineare Gleichungssysteme, Interpolation, Integration, Fouriertransformation, Nullstellenbestimmung sowie gewöhnliche und partielle Differentialgleichungen sehr anschaulich. Der Schwerpunkt liegt auf effizienten, rechnergestützten Lösungsansätzen, z. B. Wavelets, Splines und Mehrgitterverfahren. Viel Wert wird dabei auf aktuelle Anwendungsbeispiele aus dem Umfeld Computer Science gelegt, wie Bildverarbeitung, Computer-Graphik, Data Mining und Wettervorhersage. Historische Beispiele ergänzen die Darstellung. Dieses Lehrbuch eignet sich somit für Studierende der Informatik, Mathematik sowie Ingenieur- und Naturwissenschaften, die einen modernen Zugang zum Einsatz numerischer Methoden suchen.
Die Neuauflage wurde aktualisiert und Erfahrungen der täglichen Vorlesungspraxis eingearbeitet. Neue Anwendungsbereiche wurden mit aufgenommen, insbesondere aus der Softwareentwicklung für industrielle Anwendungen und aus dem Bereich des Internet. Zusätzlich wurde als Unterstützung eine Webseite eingerichtet, die es den Studierenden ermöglicht, interaktiv und mit Lösungshilfen die Übungsaufgaben des Buches selbstständig zu bearbeiten.
In this paper, we describe a new approach for synthetic image augmentation and its advantages in training Deep Neural Networks (DNNs) for object classification and localization. To address the need for a significant amount of data when training DNNs, for image-based ADAS functions, our method relies on virtually generated scenarios augmented via a physics-based camera model. The camera model implements various optical effects on ideal-synthetic images. For the scope of this paper, we illustrate the performance differences associated with the vignetting effect when training DNNs with and without image augmentation. We show that training on images altered by our camera vignetting model yield to a better performance than using ideal-synthetic images, additionally we illustrate the relationship between the network's performance results and the implemented effect (vignetting in this case). For a start, our results open the possibility for using camera models for training neural networks on synthetic data and pave the way toward further investigations on significant optical and image sensor effects to be modeled/implemented for performance enhancement during the training process. The approach is conducted and evaluated by training a DNN for car detection using the Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI) and Virtual KITTI (VKITTI) datasets.
Rob Harwood, Ansys global industry director, met with professor Stefan-Alexander Schneider from the University of Applied Sciences at Kempten in Bavaria, Germany. Professor Schneider runs one of the world’s only master’s courses on advanced driver assistance systems and autonomous vehicles. Their conversation revealed how the University of Applied Sciences is helping to develop the disruptive technologies of tomorrow and the engineers who will deliver them. They all discussed why simulation is critical for autonomous vehicles.