Design.R – AI-assisted CPS Design

The project is part of the Symbiotic Design for CPS (SDCPS) program, with a goal to develop AI-based approaches to enable correct-by-construction design of military-relevant CPS. Beyond novel theoretical discoveries we focus our innovation and research efforts to deliver AI-based Co-Designers that are integratable with the dominantly model-based Cyber-Physical System (CPS) design flows and tool suites. Our vision is the reformulation of the conventional engineering process of CPS as a continuously learning, self-improving process of collaborative discovery. Breakthroughs will emerge from the symbiosis of new, AI-based data-driven approaches in design flows to complement human intuitions and classical analytics for synthesizing and validating candidate solutions.

The project is led by the Institute for Software Integrated Systems of Vanderbilt, and includes collaborators from University of Alberta, Canada and University of Szeged, Hungary. Vanderbilt’s Péter Völgyesi (PI) has over two decades of experience with model-based design, design automation and integration platforms. The Institute for Software Integrated Systems has pioneered generations of metaprogrammable tool suites for modeling and model transformation and their use in design automation. The University of Alberta team, led by Prof. Csaba Szepesvári, has developed several fundamentally novel AI/ML algorithms that led to breakthroughs, such as DeepMind's AlphaGo. As the lead of the foundation group at Google's DeepMind, Prof. Szepesvári has a broad perspective on recent advancements in AI that can change the status quo in model-based design automation. Prof. Miklós Maróti, the lead of the mathematics research team at University of Szeged, has foundational work in applying AI methods within mathematics: augmenting SAT solvers with AI-based approximations to solve algebraic problems and proving stability properties of dynamical systems by learning their Lyapunov functions.

Press Release:


Cyber-Physical Systems (CPS) are systems where the functionality emerges from the networked interaction of computational and physical processes. The tight interaction of physical and computational processes turns the design of these systems into a multi-domain co-design problem that integrates traditionally separated design domains into a coupled design space exploration process. As a prime contractor for the OpenMETA design automation tool suite, developed under DARPA’s AVM program, our team developed horizontal model, tool, and execution integration platforms and gained transitioning experience in the vehicle, electronics, and aerospace design domains. We also gained a deep understanding of the fundamental and practical limitations of model- and component-based design. 

This project is built on the lessons learned from this prior experience, seeking applicable and feasible AI-based methods to support the complex design process across multiple engineering domains. The developed tools are used and demonstrated in Unmanned Underwater and Aerial Vehicle (UUV/UAV) design problems.

Award Number
Lead PI
Peter Volgyesi
Christopher White, Janos Sztipanovits, Xenofon Koutsoukos, Akos Ledeczi
University of Alberta
University of Szeged