Prof. Dr.-Ing. habil.

Trapp, Mario

Filters

Reset filters

Settings
Now showing 1 - 10 of 72
  • Publication
    Towards Uncertainty Reduction Tactics for Behavior Adaptation
    ( 2023)
    Kreutz, Andreas
    ;
    Weiß, Gereon
    ;
    Trapp, Mario
    An autonomous system must continuously adapt its behavior to its context in order to fulfill its goals in dynamic environments. Obtaining information about the context, however, often leads to partial knowledge, only, with a high degree of uncertainty. Enabling the systems to actively reduce these uncertainties at run-time by performing additional actions, such as changing a mobile robot’s position to improve the perception with additional perspectives, can increase the systems’ performance. However, incorporating these techniques by adapting behavior plans is not trivial as the potential benefit of such so-called tactics highly depends on the specific context. In this paper, we present an analysis of the performance improvement that can theoretically be achieved with uncertainty reduction tactics. Furthermore, we describe a modeling methodology based on probabilistic data types that makes it possible to estimate the suitability of a tactic in a situation. This methodology is the first step towards enabling autonomous systems to use uncertainty reduction in practice and to plan behavior with more optimal performance.
  • Publication
    Adaptively Managing Reliability of Machine Learning Perception under Changing Operating Conditions
    ( 2023)
    Salvi, Aniket
    ;
    Weiß, Gereon
    ;
    Trapp, Mario
    Autonomous systems are deployed in various contexts, which makes the role of the surrounding environment and operational context increasingly vital, e.g., for autonomous driving. To account for these changing operating conditions, an autonomous system must adapt its behavior to maintain safe operation and a high level of autonomy. Machine Learning (ML) components are generally being introduced for perceiving an autonomous system’s environment, but their reliability strongly depends on the actual operating conditions, which are hard to predict. Therefore, we propose a novel approach to learn the influence of the prevalent operating conditions and use this knowledge to optimize reliability of the perception through self adaptation. Our proposed approach is evaluated in a perception case study for autonomous driving. We demonstrate that our approach is able to improve perception under varying operating conditions, in contrast to the state-of-the-art. Besides the advantage of interpretability, our results show the superior reliability of ML-based perception.
  • Publication
    Fuzzy Interpretation of Operational Design Domains in Autonomous Driving
    ( 2022-07)
    Salvi, Aniket
    ;
    Weiß, Gereon
    ;
    Trapp, Mario
    ;
    Oboril, Fabian
    ;
    Buerkle, Cornelius
    The evolution towards autonomous driving involves operating safely in open-world environments. For this, autonomous vehicles and their Autonomous Driving System (ADS) are designed and tested for specific, so-called Operational Design Domains (ODDs). When moving from prototypes to real-world mobility solutions, autonomous vehicles, however, will face changing scenarios and operational conditions that they must handle safely. Within this work, we propose a fuzzy based approach to consider changing operational conditions of autonomous driving based on smaller ODD fragments, called μODDs. By this, an ADS is enabled to smoothly adapt its driving behavior for meeting safety during shifting operational conditions. We evaluate our solution in simulated vehicle following scenarios passing through different μODDs, modeled by weather changes. The results show that our approach is capable of considering operational domain changes without endangering safety and allowing improved utility optimization.
  • Publication
    Preface
    ( 2022)
    Trapp, Mario
    ;
    Saglietti, Francesca
    ;
    Spisländer, Marc
    ;
    Bitsch, Friedemann
  • Publication
    Safety Implications of Runtime Adaptation to Changing Operating Conditions
    ( 2022)
    Salvi, Aniket
    ;
    Weiß, Gereon
    ;
    Trapp, Mario
    ;
    Oboril, Fabian
    ;
    Buerkle, Cornelius
    With further advancements of autonomous driving, also larger application scenarios will be addressed, so-called Operational Design Domains (ODDs). Autonomous vehicles will likely experience varying operating conditions in such broader ODDs. The implications of changing operating conditions on safety and required adaptation is, however, an open challenge. In our work, we exemplary investigate a vehicle following scenario passing through altering operating conditions and Responsibility Sensitive Safety (RSS) as formal model to define appropriate longitudinal following distances. We provide a deeper analysis of the influence of switching the safety model parameter values to adapt to new operating conditions. As our findings show that hard switches of operating conditions can lead to critical situations, we propose an approach for continuously adapting safety model parameters allowing for a safe and more comfortable transition. In our evaluation, we utilize driving simulations to compare the hard switching of parameters with our proposal of gradual adaptation. Our results highlight the implications of changing operating conditions on the driving safety. Moreover, we provide a solution to adapt the safety model parameters of an autonomous vehicle in such a way that safety model violations during transition can be avoided.
  • Publication
    Towards Collaborative Perception in Automated Driving: Combining Vehicle and Infrastructure Perspectives
    ( 2021)
    Zacchi, Joao-Vitor
    ;
    Trapp, Mario
    Environment perception constitutes a foundational block for autonomous systems such as automated driving systems. Enhancing such features is imperative to breach the barrier of complex environments such as urban scenarios. Occlusions, appearances, and disappearances are a few of the difficulties traditional tracking algorithms may face in an urban context that hinders their performance. Moreover, approaches that deal with the data association problem are still physically limited by the point-of-view of the ego vehicle. In order to address these issues, we propose in this position paper a framework to merge different perspectives enabling collaborative perception and thus to enhance the dependability of the environment perception of automated vehicles in complex scenarios. To this end, each participant, i.e., automated vehicles and infrastructure, sends their perception results to the framework. A perception result includes Bayesian Occupancy Filter providing probabilistic information about object positions. Moreover, the results might include an additional classification of the objects, enabling us to optimize predicting future trajectories of the objects, which is particularly important for non-automated participants such as human-driven cars or pedestrians. The framework facilitates a more complete and clarified view of the context to enhance decision-making of the individual vehicles.
  • Publication
    Dependable and Efficient Cloud-Based Safety-Critical Applications by Example of Automated Valet Parking
    ( 2021)
    Drabek, Christian
    ;
    Shekhada, Dhavalkumar
    ;
    Weiß, Gereon
    ;
    Trapp, Mario
    ;
    Ishigooka, Tasuku
    ;
    Otsuka, Satoshi
    ;
    Mizuochi, Mariko
    Future embedded systems and services will be seamlessly connected and will interact on all levels with the infrastructure and cloud. For safety-critical applications this means that it is not sufficient to ensure dependability in a single embedded system, but it is necessary to cover the complete service chain including all involved embedded systems as well as involved services running in the edge or the cloud. However, for the development of such Cyber-Physical Systems-of-Systems (CPSoS) engineers must consider all kinds of dependability requirements. For example, it is not an option to ensure safety by impeding reliability or availability requirements. In fact, it is the engineers' task to optimize the CPSoS' performance without violating any safety goals. In this paper, we identify the main challenges of developing CPSoS based on several industrial use cases and present our novel approach for designing cloud-based safety-critical applications with optimized performance by the example of an automated valet parking system. The evaluation shows that our monitoring and recovery solution ensures a superior performance in comparison to current methods, while meeting the system's safety demands in case of connectivity-related faults.
  • Publication
    Wertschöpfung durch Software in Deutschland
    (Fraunhofer-Gesellschaft, 2021)
    Aichroth, Patrick
    ;
    Bös, Joachim
    ;
    Sladeczek, Christoph
    ;
    Bodden, Eric
    ;
    Liggesmeyer, Peter
    ;
    Trapp, Mario
    ;
    Falk Howar
    ;
    Otto, Boris
    ;
    Rehof, Jakob
    ;
    Spiekermann, Markus
    ;
    Arzt, Steven
    ;
    Steffen, Barbara
    ;
    Nouak, Alexander
    ;
    Köhler, Henning
    Informationstechnologie und insbesondere Software ist ein wachsender Sektor in jeder entwickelten Gesellschaft. Softwarebasierte Produkte und Dienstleistungen sind die »digitale Infrastruktur« des 21. Jahrhunderts: Digitale Unternehmen, datenzentrierte Geschäftsmodelle und Dienstleistungen, maschinelles Lernen, Industrie 4.0, autonomes Fahren all diese Trends basieren auf leistungsfähigen Kommunikationsnetzwerken, modernen Rechenplattformen und Software- Stacks inklusive Basisdiensten, die derzeit von den sogenannten »Big Five« aus den USA dominiert werden: Google, Amazon, Microsoft, und in geringerem Maße, Apple und Facebook. Ein gesunder und wachsender IKT-Sektor ist die Basis für zukünftigen Wohlstand. Europa und auch Deutschland fallen hier in Bezug auf Innovation und Wachstum hinter die USA und Asien (China, Taiwan, Japan) zurück: Die 100 erfolgreichsten Softwareunternehmen stammen zu 90 Prozent aus den USA. Europa und der Rest der Welt importieren Leistungen dieser Unternehmen für den Betrieb der eigenen Infrastruktur. China dagegen baut mit Firmen wie Alibaba, Tencent und Baidu bereits ein eigenes unabhängiges Ökosystem auf, das digitale Infrastruktur (Online Handel, Cloud-Rechenplattformen, Soziales Internet, etc.) für die chinesische Gesellschaft und Wirtschaft bereitstellt. Insgesamt erzielen einige asiatische Länder Wachstumsraten ihrer IKT-Sektoren, die deutlich über dem Wachstum in Europa liegen. Bei der bereits erreichten und insbesondere bei der angestrebten Digitalisierung unserer Gesellschaft stellen diese beiden Sachverhalte strategische Risiken für unseren Wohlstand und unsere Unabhängigkeit dar. Bundeskanzlerin Angela Merkel kommentierte dies auf dem Digitalgipfel 2019 in Dortmund mit: »Europa muss das auch alles können! «Die skizzierte Lage ist in Zahlen und Analysen gut dokumentiert und allgemein akzeptiert. Die entscheidende Frage ist heute, wie und wo gehandelt werden kann und muss, um in Europa beziehungsweise in Deutschland die notwendige Stärkung und Unabhängigkeit des eigenen Software-Sektors zu erreichen. Dieser Bericht beleuchtet den Zustand des europäischen und deutschen Software-Ökosystems, analysiert potenzielle Risiken und Bedrohungen, insbesondere durch fehlende europäische Kompetenzen im Bereich Software- und Basisdienste. Zwar wird darauf Bezug genommen, wie die Ökosysteme in den USA und in China entstanden sind und wie sie gedeihen, eine erneute Gegenüberstellung von deutscher und US-amerikanischer oder chinesischer Softwareindustrie ist jedoch nicht Gegenstand des vorliegenden Papiers. Vielmehr ist es das Ziel, pragmatisch umsetzbare Handlungsempfehlungen für die Bundesregierung zur Erhöhung der softwarebasierten Wertschöpfung in Deutschland vorzustellen, die mit den bestehenden Stärken und mit der bestehenden Struktur der Wertschöpfung in Deutschland kongruent sind.
  • Publication
    SINADRA: Towards a Framework for Assurable Situation-Aware Dynamic Risk Assessment of Autonomous Vehicles
    ( 2020)
    Reich, Jan
    ;
    Trapp, Mario
    Assuring an adequate level of safety is the key challenge for the approval of autonomous vehicles (AV). The full performance potential of AV cannot be exploited at present because traditional assurance methods at design time are based on a risk assessment involving worst-case assumptions about the operating environment. Dynamic Risk Assessment (DRA) is a novel technique that shifts this activity to runtime and enables the system itself to assess the risk of the current situation. However, existing DRA approaches neither consider environmental knowledge for risk assessments, as humans do, nor are they based on systematic design-time assurance methods. To overcome these issues, in this paper we introduce the model-based SINADRA framework for situation-aware dynamic risk assessment. It aims at the systematic synthesis of probabilistic runtime risk monitors employing tactical situational knowledge to imitate human risk reasoning with uncertain knowledge. To that end, a Bayesian network synthesis and assurance process is outlined for DRA in different operational design domains and integrated into an adaptive safety management architecture. The SINADRA monitor intends to provide an information basis at runtime to optimally balance residual risk and driving performance, in particular in non-worst-case situations.
  • Publication
    Considering Reliability of Deep Learning Function to Boost Data Suitability and Anomaly Detection
    ( 2020)
    Gauerhof, Lydia
    ;
    Hagiwara, Yuki
    ;
    Schorn, Christoph
    ;
    Trapp, Mario
    The increased demand of Deep Neural Networks (DNNs) in safety-critical systems, such as autonomous vehicles, leads to increasing importance of training data suitability. Firstly, we focus on how to extract the relevant data content for ensuring DNN reliability. Then, we identify error categories and propose mitigation measures with emphasis on data suitability. Despite all efforts to boost data suitability, not all possible variations of a real application can be identified. Hence, we analyse the case of unknown out-of-distribution data. In this case, we suggest to complement data suitability with online anomaly detection using FACER that supervises the behaviour of the DNN.