Dr. rer. nat.

Weiß, Gereon

Filters
Reset filters

Settings
Now showing 1 - 10 of 27
  • Publication
    Managing Uncertainty of AI-based Perception for Autonomous Systems
    ( 2019)
    Henne, Maximilian
    ;
    Schwaiger, Adrian
    ;
    Weiß, Gereon
    With the advent of autonomous systems, machine perception is a decisive safety-critical part to make such systems become reality. However, presently used AI-based perception does not meet the required reliability for usage in real-world systems beyond prototypes, as for autonomous cars. In this work, we describe the challenge of reliable perception for autonomous systems. Furthermore, we identify methods and approaches to quantify the uncertainty of AI-based perception. Along with dynamic management of the safety, we show a path to how uncertainty information can be utilized for the perception, so that it will meet the high dependability demands of life-critical autonomous systems.
  • Publication
    Towards Dynamic Safety Management for Autonomous Systems
    ( 2019)
    Trapp, Mario
    ;
    Weiß, Gereon
    Safety assurance of autonomous systems is one of the current key challenges of safety engineering. Given the specific characteristics of autonomous systems, we need to deal with many uncertainties making it difficult or even impossible to predict the system's behaviour in all potential operational situations. Simply using established static safety approaches would result in very strict worst-case assumptions making the development of autonomous systems at reasonable costs impossible. This paper therefore introduces the idea of dynamic safety management. Using dynamic safety management enables a system to assess its safety and to self-optimize its performance at runtime. Considering the current risk related to the actual context at runtime instead of being bound to strict worst-case assumptions provides the essential basis for the development of safe and yet cost-efficient autonomous systems.
  • Publication
    Towards safety-awareness and dynamic safety management
    ( 2018)
    Trapp, Mario
    ;
    Weiß, Gereon
    ;
    Schneider, Daniel
    Future safety-critical systems will be highly automated or even autonomous and they will dynamically cooperate with other systems as part of a comprehensive ecosystem. This together with increasing utilization of artificial intelligence introduces uncertainties on different levels, which detriment the application of established safety engineering methods and standards. These uncertainties might be tackled by making systems safety-aware and enabling them to manage themselves accordingly. This paper introduces a corresponding conceptual dynamic safety management framework incorporating monitoring facilities and runtime safety-models to create safety-awareness. Based on this, planning and execution of safe system optimizations can be carried out by means of self-adaptation. We illustrate our approach by applying it for the dynamic safety assurance of a single car.
  • Publication
    Safety & security testing of cooperative automotive systems
    ( 2018)
    Seydel, Dominique
    ;
    Weiß, Gereon
    ;
    Pöhn, Daniela
    ;
    Wessel, Sascha
    ;
    Wenninger, Franz
    Cooperative behavior of automated traffic participants is one next step towards the goals of reducing the number of traffic fatalities and optimizing traffic flow. The notification of a traffic participant's intentions and coordination of driving strategies increase the reaction time for safety functions and allow a foresighted maneuver planning. When developing cooperative applications, a higher design complexity has to be handled, as components are distributed over heterogeneous systems that interact with a varying timing behavior and less data confidence. In this paper, we present a solution for the development, simulation and validation of cooperative automotive systems together with an exemplary development flow for safety and security testing.
  • Publication
    Rapid Innovation Toolkit for the development of dependable cooperative applications
    ( 2018)
    Seydel, Dominique
    ;
    Weiß, Gereon
    Cooperative applications have an enormous potential to improve future mobility systems. Though, special challenges regarding safety and security arise out of the connectivity and the distribution of the application among heterogeneous systems. These include expensive and time-consuming development and test phases. Especially, the debugging of an application, whose sub-functions are located on heterogeneous and partially mobile systems, requires a new kind of testing environment. The test and validation of the overall application is complex, as the wireless link implies varying timing behaviour and less data confidence. For this purpose, the proposed testbed integrates the DANA (""Description and Analysis of Networked Applications"") Framework to achieve a central overview of the overall application and the behaviour of all systems involved. This software tool kit is able to find deviations from the specified behaviour and also it can instantly locate and identify erroneous functions. In this paper, we present a solution for the complete development cycle of cooperative automotive systems together with an exemplary development flow for safety and security testing.
  • Publication
    Towards integrating undependable self-adaptive systems in safety-critical environments
    ( 2018)
    Weiß, Gereon
    ;
    Schleiß, Philipp
    ;
    Schneider, Daniel
    ;
    Trapp, Mario
    Modern cyber-physical systems (CPS) integrate more and more powerful computing power to master novel applications and adapt to changing situations. A striking example is the recent progression in the automotive market towards autonomous driving. Powerful artificial intelligent algorithms must be executed on high performant parallelized platforms. However, this cannot be employed in a safe way, as the platforms stemming from the consumer electronics (CE) world still lack required dependability and safety mechanisms. In this paper, we present a concept to integrate undependable self-adaptive subsystems into safety-critical environments. For this, we introduce self-adaptation envelopes which manage undependable system parts and integrate within a dependable system. We evaluate our approach by a comprehensive case study of autonomous driving. Thereby, we show that the potential failures of the AUTOSAR Adaptive platform as exemplary undependable system can be handled by our concept. In overall, we outline a way of integrating inherently undependable adaptive systems into safety-critical CPS.
  • Publication
    Evaluation of Traffic Control Systems as ITS Infrastructure for Automated Driving
    ( 2018)
    Franze, Juliane
    ;
    Seydel, Dominique
    ;
    Weiß, Gereon
    ;
    Haspel, Ulrich
    Vehicles with automated driving systems require more sensor information about their environment than non-automated vehicles. Detection with camera, lidar or other sensors is already state of the art in newer vehicles. As of today though, they only work in close proximity and lack the incorporation of existing traffic information from local authorities. In this paper, we present a novel way of providing traffic management information to vehicles, sent directly from Road Authorities. We use existing ITS (Intelligent Transport Systems) infrastructure and assess how information on traffic control and reroutes, displayed on variable message signs, can be used as sensory input for vehicles. We examine real world data from a South German Road Authority. The evaluation of latency, reliability and integrity of traffic information has been conducted end-to-end as well as between the six stations that are involved. We show the general feasibility of our proposal and discuss which obstacles need to be overcome for a wider use in other road systems.
  • Publication
    Method for automatic resumption of runtime verification monitors
    ( 2017)
    Drabek, Christian
    ;
    Weiß, Gereon
    ;
    Bauer, Bernhard
    In networked embedded systems created with parts from different suppliers, deviations from the expected communication behavior often cause integration problems. Therefore, runtime verification monitors are used to detect if observed communication behavior fulfills defined correctness properties. However, in order to resume verification if unspecified behavior is observed, the runtime monitor needs a definition of the resumption. Otherwise, further deviations may be overlooked. We present a method for extending state-based runtime monitors with resumption in an automated way. This enables continuous monitoring without interruption. The method may exploit diverse resumption algorithms. In an evaluation, we show how to find the best suited resumption extension for a specific application scenario and compare the algorithms.
  • Publication
    DANA - Description and Analysis of Networked Applications
    ( 2017)
    Drabek, Christian
    ;
    Weiß, Gereon
    We introduce the DANA platform for specifying and analyzing networked applications. DANA was originally created targeting the automotive domain for the verification and validation of software interface behavior in new infotainment and advanced driver assistant systems that are integrated on a single hardware platform. The messages in these interfaces can contain complex data, e.g., playlists with images. Therefore, valid behavior is described as a layered reference model. The platform can use the model to generate test cases, code for simulation, and to verify a live or recorded trace. Exchangeable resumption algorithms enable DANA to resume runtime verification after a deviation using the original state machine without manual changes. A generic input model allows quick integration of new sources for messages. Therefore, DANA can easily be applied to other domains where interactive behavior can be observed. In this paper, we present the tool, its layered reference model, and show its application for runtime verification.
  • Publication
    Generic management of availability in fail-operational automotive systems
    ( 2017)
    Schleiß, Philipp
    ;
    Drabek, Christian
    ;
    Weiß, Gereon
    ;
    Bauer, Bernhard
    The availability of functionality is a crucial aspect of mission- and safety-critical systems. This is for instance demonstrated by the pursuit to automate road transportation. Here, the driver is not obligated to be part of the control loop, thereby requiring the underlying system to remain operational even after a critical component failure. Advances in the field of mixed-criticality research have allowed to address this topic of fail-operational system behaviour more efficiently. For instance, general purpose computing platforms may relinquish the need for dedicated backup units, as their purpose can be redefined at runtime. Based on this, a deterministic and resource-efficient reconfiguration mechanism is developed, in order to address safety concerns with respect to availability in a generic manner. To find a configuration for this mechanism that can ensure all availability-related safety properties, a design-time method to automatically generate schedules for different modes of operations from declaratively defined requirements is established. To cope with the inherent computational complexity, heuristics are developed to effectively narrow the problem space. Subsequently, this method's applicability and scalability are respectively evaluated qualitatively within an automotive case study and quantitatively by means of a tool performance analysis.