Auflistung nach Autor:in "Holzapfel, Florian"
1 - 4 von 4
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragApplying Brain Machine Interfaces to Aircraft Control: Potentials and Challenges(56. Fachausschusssitzung Anthropotechnik der DGLR: Der Mensch zwischen Automatisierung, Kompetenz und Verantwortung, 2014) Fricke, Tim; Holzapfel, FlorianBrain machine interfaces (BMI) have already successfully been used in laboratory control tasks. A next important step is to apply them in an operational context. A European research project investigates brain controlled aircraft flight, where manual incep
- KonferenzbeitragOn the Design and Model-Based Validation of Flight Control System Automation for an Unmanned Coaxial Helicopter(Software Engineering 2023 Workshops, 2023) Hofsäß, Hannes; Hosseini, Barzin; Rhein, Julian; Holzapfel, FlorianAn existing coaxial helicopter with a maximum takeoff weight of 600 kg has been transformed into a unmanned aerial system. To enable unmanned experimental validation of novel flight control-laws in flight tests, the helicopter's flight control system has been extended by digital components. As the loss of the helicopter platform due to a failure in the experimental digital flight control system has been identified a risk for the project, contingency procedures have been considered in the system design. In this paper, we suggest a model-based and lean development approach for system automation development, which to the best of the authors knowledge, is new. Within the process we suggest to introduce Operational Sequence Diagrams that only represent procedural system behavior to describe the Design Reference Scenarios of the Concept of Operations. Thereby we enable the total exploitation of a System Architecture Behavioral model within the design process, considering the definition of procedures, the validation of architecture design and automated code generation. To validate the suggested approach, we present its application to the design of the system automation for the flight control system of the unmanned helicopter. The system has been successfully integrated and tested in caged flight tests in November 2022.
- KonferenzbeitragTool Qualification Aspects in ML-Based Airborne Systems Development(Software Engineering 2023 Workshops, 2023) Dmitriev, Konstantin; Kaakai, Fateh; Ibrahim, Mohamad; Durak, Umut; Potter, Bill; Holzapfel, FlorianMachine Learning (ML) technology can provide the best results in many highly complex tasks such as computer vision and natural language processing and quickly evolving further. These unique ML capabilities and apparent potential can enable the next epoch of automation in airborne systems including single pilot or even autonomous operation of large commercial aircraft. The main problems to be solved towards ML deployment in commercial aviation are safety and certification, because there are several major incompatibilities between ML development aspects and traditional design assurance practices, in particular traceability and coverage verification issues. In this paper, we study the qualification aspects of tools used for development and verification of ML-based systems (ML tools) and propose mitigation measures for some known ML verification gaps through ML tools qualification. In particular, we review the DO-330 and DO-200B tool classification approach with respect to ML-specific workflows and propose to extend the tool qualification criteria for ML data management and ML model training tools.
- KonferenzbeitragTowards COTS component synchronization for low SWaP-C flight control systems(SE 2024 - Companion, 2024) Sax, Franz; Holzapfel, FlorianThe rise of innovative and novel fly-by-wire air vehicles like e-VTOLs for Advanced Air Mobility demands flight control systems whose components are low size, weight, power and cost (SWaP-C), but nevertheless offer high performance. One approach towards this mismatch is to use COTS components from e.g. the automotive sector and use their extensive features to enhance performance in a given system architecture. This paper describes one method of minimizing the latency in the communication between two COTS components by using an easily realizable algorithm with minimal memory, code and computation requirements for relative synchronization of the execution cycles of the components. A description of the resulting control problem, as well as simulation results from a dedicated MATLAB simulation environment are given. Those are then compared with an implementation on a representative set of devices from the EPUCOR flight control system.