FOundations for Continuous Engineering of Trustworthy Autonomy
Convergence of data-driven and model-based engineering
The underlying targeted scientific breakthrough of FOCETA lies in the convergence of model-driven and data-driven approaches. This convergence is further complicated by the need to apply verification and validation incrementally and avoid complete re-verification and re-validation efforts.
FOCETA’s paradigm will be implemented through a framework built on three scientific pillars:
Integration of learning-enabled components and model-based components via a contract-based methodology which allows incremental modification of system under analysis including threat models for cyber-security or environment models
Adaptation of verification techniques applied in model-driven design to learning components, with the goal of enabling transparent and unbiased decision making
Development of a new design paradigm for autonomous systems with incremental synthesis techniques unifying both the enforcement of safety and security critical properties as well as performance optimization
Implemented in open source tools and with open data exchange standards.
The recording of the seminar "Exact Robustness Verification for Attention Networks", held on 3rd May 2022 is now available. A special thank to Brian Hsuan-Cheng Liao from DENSO for the presentation. The research was performed in collaboration with Chih-Hong Cheng from...
The recording of the seminar "Information-flow Interfaces", held on 19th April 2022 is now available. A special thank to Ana Oliveira da Costa from Technische Universität Wien and Dejan Nickovic from AIT Austrian Institute of Technology GmbH for the presentation....
The recording of the seminar "TEMPEST Synthesis Tool for Shields in Probabilistic Environments", held on 22nd March 2022 is now available. A special thank to Bettina Könighofer and Stefan Pranger from the Graz University of Technology for the presentation. Stay tuned...