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 paper version of this communication material will be distributed by the FOCETA partners during their participation in conferences, workshops and other events. The documents can be downloaded here: Leaflet: web version - print version Poster: web version - print...
Talk: H2020 Research Project FOCETA – Foundations for Continuous Engineering of Trustworthy Autonomy
Applications are increasingly being developed based on complex autonomous systems driven by artificial intelligence. As smart robots are starting to replace humans in complicated or dangerous tasks on the road, in industry, or hospitals, their safety, autonomy, and trustworthiness are the subjects of concern. This is due to the increasing complexity of deployments, especially those of learned-enabled systems, not easily traced by continuous engineering (DevOps). The EU-funded H2020 FOCETA project plans to develop the foundation for continuous engineering of trustworthy learning-enabled autonomous systems integrating data-driven and model-based engineering. In this talk, I will highlight some of the research challenges that the project team tries to tackle together with some early reflections, including specification, V&V techniques, training, and runtime monitoring.
“Ethical aspects and recommendations for trustworthy highly automated/autonomous systems” Erwin Schoitsch, AIT Austrian Institute of Technology Time: April 23, 2021 9 am (CET) Location: The talk will be held remotely (will be updated accordingly when invitation is...