A Caltech Library Service

Control of Unknown Dynamical Systems: Robustness and Online Learning of Feedback Control


Ho, Dimitar (2024) Control of Unknown Dynamical Systems: Robustness and Online Learning of Feedback Control. Dissertation (Ph.D.), California Institute of Technology. doi:10.7907/fb64-vk24.


Over the past few decades, our physical and digital worlds have become increasingly intertwined and reliant on each other. Advancements in areas such as machine learning, online optimization, and control theory, along with ubiquitous access to computational power, have played a crucial role in this technological evolution. As a result, we are now moving towards a future where complex and intelligent dynamical systems, with humans in the loop, govern our daily lives.

Building advanced control systems is a critical step in this journey, as they enable swift and data-informed decision-making. However, as we aim to create even more sophisticated closed-loop systems, we must proceed with a careful balance of ambition and caution. While the benefits of these interconnected systems are abundant and our dependence on them deepens, ensuring the actual reliability and safety of the systems becomes increasingly challenging due to the growing complexity of their dynamics. This challenge is particularly prominent in safety-critical applications involving physical systems, which often have strict and non-negotiable safety and performance requirements. To establish a harmonious relationship between our physical and digital worlds, it is crucial to develop intelligent closed-loop control systems that are not only fast and efficient, but also reliable and fault-tolerant.

The title of this thesis, "Control of Unknown Dynamical Systems: Robustness and Online Learning of Feedback Control," reflects the central focus of this work on addressing this pressing challenge. The thesis aims to develop theoretical frameworks and tools that provide insights and contribute new approaches to the design of control systems capable of handling the inherent uncertainty in real-world dynamical systems.

The first part of the thesis focuses on the design of closed-loop systems that are robust to dynamic uncertainty, particularly in settings involving nonlinear dynamics and complex control constraints. The second part introduces a general framework for learning-to-control algorithms that provide worst-case guarantees, even in scenarios where the dynamic uncertainty is arbitrarily large. By addressing these key aspects, this work aims to advance our understanding and capabilities in designing control systems that can effectively deal with uncertainty.

Item Type:Thesis (Dissertation (Ph.D.))
Subject Keywords:Large-Scale Systems, Complex Dynamical Systems, Distributed Control, Machine Learning, Control Theory, Learning Theory, Robust Adaptive Control, System Identification, Nonlinear Systems, Robust Control, Learning to Control, Robust Data-Driven Control,
Degree Grantor:California Institute of Technology
Division:Engineering and Applied Science
Major Option:Control and Dynamical Systems
Thesis Availability:Public (worldwide access)
Research Advisor(s):
  • Doyle, John Comstock
Thesis Committee:
  • Wierman, Adam C. (chair)
  • Yue, Yisong
  • Burdick, Joel Wakeman
  • Doyle, John Comstock
Defense Date:7 August 2023
Record Number:CaltechTHESIS:09062023-095903699
Persistent URL:
Related URLs:
URLURL TypeDescription Homepage and Blog adapted for Chapter 6 adapted for Chapter 6 adapted for Chapter 2 and 3 adapted for Chapter 4 adapted for Chapter 4 adapted for Chapter 3 adapted for Chapter 5
Ho, Dimitar0000-0002-7856-985X
Default Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:16177
Deposited By: Dimitar Ho
Deposited On:19 Sep 2023 16:15
Last Modified:29 Sep 2023 00:09

Thesis Files

[img] PDF - Final Version
See Usage Policy.


Repository Staff Only: item control page