On Learning- and Optimization-based Methods for Risk-Averse Control of Autonomous Systems
Speaker: Riccardo Bonalli (Laboratory of Signals and Systems, Université Paris-Saclay, France)
Title: On Learning- and Optimization-based Methods for Risk-Averse Control of Autonomous Systems
Time: Wednesday, 2023.02.22, 10:00 a.m. (CET)
Place: fully virtual (contact Dr. Jakub Lengiewicz to register)
Format: 30 min. presentation + 30 min. discussion
From energy networks to space systems: complex Autonomous Systems (AS) have become pervasive in our society. In this context, the design of increasingly sophisticated methods for the modeling and control of AS is of utmost relevance, given that they regularly operate in uncertain and dynamic circumstances.
On the one hand, to mitigate hazardous and possibly catastrophic uncertain perturbations during the decision-making (or planning) process, one is led to reliably infuse Learning-based Models (LM) in the control pipeline. LM offers numerous advantages, including accurate representations of sophisticated systems which accomplish complex tasks. Nevertheless, due to the high degree of uncertainty in which AS operates, one must devise LM capable of offering guarantees of reliability.
On the other hand, beneficially leveraging the aforementioned LM for safe-against-uncertainty deployment of AS may come only under specific optimal planning and control processes. In particular, the best trade-off is offered by risk-averse Stochastic Optimal Control Problems (SOCP), providing controls which optimize sophisticated stochastic worst-case-averse costs known as risk measures.
This talk aims at introducing two promising techniques which start bridging the aforementioned gaps. Specifically, the first part of the talk will show how general, i.e., non-linear stochastic differential equations may be estimated through appropriate sampling- and RKHS-based LM, offering high-order error bounds in law. The second part of the talk will address the design of conditions for optimality which can then be leveraged to solve general, i.e., non-smooth risk-averse SOCP through efficient numerical computations.
Dr. Riccardo Bonalli Riccardo Bonalli obtained his PhD in applied mathematics from Sorbonne Université in 2018, in collaboration with ONERA-The French Aerospace Lab. He was a postdoctoral researcher with the Department of Aeronautics and Astronautics, Stanford University. Currently, Riccardo is a tenured CNRS researcher with the Laboratory of Signals and Systems (L2S), at Université Paris-Saclay. His main research interests concern theoretical and numerical robust optimal control with techniques from differential geometry, statistical analysis, and machine learning and applications in aerospace systems and robotics.