Logo des Repositoriums

Auflistung nach Schlagwort "Autonomous Driving"

1 - 6 von 6
  • ConferencePaper
    18th Workshop on Automotive Software Engineering (ASE’21)
    (Software Engineering 2021, 2021) Ebel, Patrick; Helke, Steffen; Schaefer, Ina; Vogelsang, Andreas
    Software-based systems play an increasingly important role and enable most of the innovations in modern cars. This workshop deals with various topics related to the development of automotive software and discusses suitable methods, techniques, and tools necessary to master the most current challenges researchers and practitioners are facing.
  • Konferenzbeitrag
    19th Workshop on Automotive Software Engineering (ASE'22)
    (Software Engineering 2022, 2022) Dörr, Heiko; Helke, Steffen
    Software based systems play an increasingly important role and enable most of the innovations in modern cars. This workshop deals with various topics related to the development of automotive software and discusses suitable methods, techniques, and tools necessary to master the most current challenges researchers and practitioners are facing.
  • Workshopbeitrag
    Autonome Fahrzeuge: Von Akzeptanz zu Wohlbefinden
    (Mensch und Computer 2019 - Workshopband, 2019) Geisler, Stefan
    Die breite Einführung autonomer Fahrzeuge, ob für den Individualverkehr oder auch den öffentlichen Nahverkehr, ist nur noch eine Frage der Zeit. Dies bedeutet unweigerlich, dass in absehbarer Zeit alle Verkehrsteilnehmer*innen mit dieser Art von Fahrzeugen in Berührung kommen werden. In diesem Artikel soll diskutiert werden, wie Ansätze des Positive Computing helfen können, die Ausgestaltung der automatisierten Fahrzeuge so vorzunehmen, dass sie zum Wohlbefinden der Menschen in Verkehrssituationen beitragen.
  • Dissertation
    Exploration of smart infrastructure for drivers of autonomous vehicles: design space, out-of-view visualization and explanations
    (2020) Wiegand, Gesa
    The connection between vehicles and infrastructure is an integral part of providing autonomous vehicles information about the environment. Autonomous vehicles need to be safe and users need to trust their driving decision. When smart infrastructure information is integrated into the vehicle, the driver needs to be informed in an understandable manner what the smart infrastructure detected. Nevertheless, interactions that benefit from smart infrastructure have not been the focus of research, leading to knowledge gaps in the integration of smart infrastructure information in the vehicle. For example, it is unclear, how the information from two complex systems can be presented, and if decisions are made, how these can be explained. Enriching the data of vehicles with information from the infrastructure opens unexplored opportunities. Smart infrastructure provides vehicles with information to predict traffic flow and traffic events. Additionally, it has information about traffic events in several kilometers distance and thus enables a look ahead on a traffic situation, which is not in the immediate view of drivers. We argue that this smart infrastructure information can be used to enhance the driving experience. To achieve this, we explore designing novel interactions, providing warnings and visualizations about information that is out of the view of the driver, and offering explanations for the cause of changed driving behavior of the vehicle. This thesis focuses on exploring the possibilities of smart infrastructure information with a focus on the highway. The first part establishes a design space for 3D in-car augmented reality applications that profit from smart infrastructure information. Through the input of two focus groups and a literature review, use cases are investigated that can be introduced in the vehicle's interaction interface which, among others, rely on environment information. From those, a design space that can be used to design novel in-car applications is derived. The second part explores out-of-view visualizations before and during take over requests to increase situation awareness. With three studies, different visualizations for out-of-view information are implemented in 2D, stereoscopic 3D, and augmented reality. Our results show that visualizations improve the situation awareness about critical events in larger distances during take over request situations. In the third part, explanations are designed for situations in which the vehicle drives unexpectedly due to unknown reasons. Since smart infrastructure could provide connected vehicles with out-of-view or cloud information, the driving maneuver of the vehicle might remain unclear to the driver. Therefore, we explore the needs of drivers in those situations and derive design recommendations for an interface which displays the cause for the unexpected driving behavior. This thesis answers questions about the integration of environment information in vehicles'. Three important aspects are explored, which are essential to consider when implementing use cases with smart infrastructure in mind. It enables to design novel interactions, provides insights on how out-of-view visualizations can improve the drivers' situation awareness and explores unexpected driving situations and the design of explanations for them. Overall, we have shown how infrastructure and connected vehicle information can be introduced in vehicles' user interface and how new technology such as augmented reality glasses can be used to improve the driver's perception of the environment.
  • Workshopbeitrag
    Investigating Car Futures from Different Angles
    (Mensch und Computer 2019 - Workshopband, 2019) Stevens, Gunnar; Meurer, Johanna; Pakusch, Christina; Bossauer, Paul
    The design of self-driving cars is one of the most exciting and ambitious challenges of our days and every day, new research work is published. In order to give an orientation, this article will present an overview of various methods used to study the human side of autonomous driving. Simplifying roughly, you can distinguish between design science-oriented methods (such as Research through Design, Wizard of Oz or driving simulator ) and behavioral science methods (such as survey, interview, and observation). We show how these methods are adopted in the context of autonomous driving research and dis-cuss their strengths and weaknesses. Due to the complexity of the topic, we will show that mixed method approaches will be suitable to explore the impact of autonomous driving on different levels: the individual, the social interaction and society.
  • Zeitschriftenartikel
    “What’s the Robo-Driver up to?” Requirements for Screen-based Awareness and Intent Communication in Autonomous Buses
    (i-com: Vol. 18, No. 2, 2019) Fröhlich, Peter; Schatz, Raimund; Buchta, Markus; Schrammel, Johann; Suette, Stefan; Tscheligi, Manfred
    Autonomous buses are expected to become a cornerstone of future mobility systems. Especially during their introduction, passengers may require reassurance about the vehicle’s awareness of the situation on the road and of its intended next actions to further acceptance. In order to investigate the need and requirements for information about the vehicle’s awareness and intent from the perspective of first-time users, we conducted two user studies in a state-of-the-art autonomous bus at public demonstration spaces. In the first study, participants underwent a demonstration ride with the bus and were then asked about their needs for awareness and intent communication. The second study took participants on a ‘simulated ride’ within a stationary bus, in which typical scenarios of the road ahead were presented, together with different awareness and intent cues. Our results suggest that, first, future autonomous bus passengers may be in need of such awareness and intent communication screens. Second, we found that awareness and intent communication may be of greater importance for the indication of potential hazard recognition than for indicating route directions. Third, due to their complementary strengths, none of the three compared types of visual communication (text, icon and augmented reality) should be used in isolation.