Please select the desired project time frame:

• July 2026
• January 2026
• July 2025
• January 2025
• July 2024
• January 2024
• July 2023
• January 2023
• July 2022
• January 2022
• July 2021
• January 2021
• July 2020
• January 2020
• July 2019
• January 2019
• July 2018
• January 2018
• July 2017
• January 2017
• July 2016
• January 2016
• July 2015
• January 2015
• July 2014
• January 2014
• July 2013
• January 2013
• July 2012
• January 2012
• July 2011
• January 2011
• July 2010
• January 2010
• July 2009
• January 2009
• July 2008
• January 2008
• July 2007
• January 2007
• July 2006
• January 2006
• July 2005
• January 2005
• July 2004
• January 2004
• July 2003
• January 2003
• July 2002
• January 2002
• July 2001
• January 2001

Start of funding 01.01.2021

Endowing Artificial Intelligence with Control-Theoretic Guarantees: Data-Based Optimization in Real Time for Dynamic Systems

---

Unlike most machine learning algorithms, which have yet to be equipped with guarantees of convergence and stability in real time for feedback applications to dynamical systems, one of the earliest example of data-based optimization algorithms, the so-called “extremum seeking” (ES) approach, whose original idea is traced back to a century-old patent in France in 1922, possesses provable properties of stability and even assignable convergence rates. This an example of Artificial Intelligence (AI) decades before the notion of AI was formalized. For finite-dimensional systems, the mathematical guarantees for ES were developed by Prof. M. Krstic around 2000. Over the last few years, he has extended the ES algorithm design and stability analysis from Ordinary Differential Equations (ODE) to Partial Differential Equations (PDE). The visit by Prof. M. Krstic to FAU will be an opportunity to explore the cooperation in this area with further PDE applications in view, including gas transport networks.

Final report:
Prof. M. Krstic visited FAU in Seotember 2022 thanks to the generous financial support of the visiting scholarship of BACATEC “Endowing Artificial Intelligence with Control-Theoretic Guarantees: Data-Based Optimization in Real Time for Dynamic Systems”. He had the opportunity to meet and discuss possible cooperation programs with various officials of FAU and its perimetric institutions. he also delivered the Inaugural FAU MoD Lecture “Learning-Based Optimization and PDE Control in User_Assignable Finite Time”. He also had the opportunity to meet and discuss with the young researchers of the Chair Dynamics, Control and Numerics, led by E. Zuazua, main organizer of this visit.

During this visit it was unanimously acknowledged that:

1. The interface between the traditional area of Control Engineering and the emerging new paradigms in Machine Learning is a very rich and promising subject of research and technology, of common interest for both teams and institutions.

2. There is a huge potential for cooperation, based on complementary expertise in learning, branching off from a common scientific expertise in PDE control, with the outcome of developing new joint training and exchange programs between FAU and UC-SD.

3. These objectives pertain to the priorities of FAU in alignment with the HighTech Agenda Bayern.

4. Such a collaborative scheme would particularly allow to develop internship programs for the PhD students of both institutions to visit the other one for one semester (approximately) to complement their training through intensive research cooperation.

5. Important opportunities for technological transfer also arise. For instance, former PhD students and postdocs of both PIs are now holding researcher positions in leading software and Arificial Intelligence companies such as NVIDIA and Sherpa AI.