This course on Data-Driven Control with Machine Learning aims to teach learners the application of machine learning techniques to solve hard, non-convex optimization problems in control theory. The course covers topics such as linear system identification, balanced model reduction, model predictive control, extremum seeking control, reinforcement learning, and deep reinforcement learning. The teaching method includes lectures and examples, with a focus on practical applications in Matlab and Simulink. This course is intended for individuals interested in control theory, machine learning, and data-driven approaches to optimization problems.
Overview
Syllabus
Data-Driven Control: Overview.
Data-Driven Control: Linear System Identification.
Data-Driven Control: The Goal of Balanced Model Reduction.
Data-Driven Control: Change of Variables in Control Systems.
Data-Driven Control: Change of Variables in Control Systems (Correction).
Data-Driven Control: Balancing Example.
Data-Driven Control: Balancing Transformation.
Data-Driven Control: Balanced Truncation.
Data-Driven Control: Balanced Truncation Example.
Data-Driven Control: Error Bounds for Balanced Truncation.
Data-Driven Control: Balanced Proper Orthogonal Decomposition.
Data-Driven Control: BPOD and Output Projection.
Data-Driven Control: Balanced Truncation and BPOD Example.
Data-Driven Control: Eigensystem Realization Algorithm.
Data-Driven Control: ERA and the Discrete-Time Impulse Response.
Data-Driven Control: Eigensystem Realization Algorithm Procedure.
Data-Driven Control: Balanced Models with ERA.
Data-Driven Control: Observer Kalman Filter Identification.
Data-Driven Control: ERA/OKID Example in Matlab.
System Identification: Full-State Models with Control.
System Identification: Regression Models.
System Identification: Dynamic Mode Decomposition with Control.
System Identification: DMD Control Example.
System Identification: Koopman with Control.
System Identification: Sparse Nonlinear Models with Control.
Model Predictive Control.
Sparse Identification of Nonlinear Dynamics for Model Predictive Control.
Machine Learning Control: Overview.
Machine Learning Control: Genetic Algorithms.
Machine Learning Control: Tuning a PID Controller with Genetic Algorithms.
Machine Learning Control: Tuning a PID Controller with Genetic Algorithms (Part 2).
Machine Learning Control: Genetic Programming.
Machine Learning Control: Genetic Programming Control.
Extremum Seeking Control.
Extremum Seeking Control in Matlab.
Extremum Seeking Control in Simulink.
Extremum Seeking Control: Challenging Example.
Extremum Seeking Control Applications.
Reinforcement Learning: Machine Learning Meets Control Theory.
Deep Reinforcement Learning: Neural Networks for Learning Control Laws.
Data-driven nonlinear aeroelastic models of morphing wings for control.
Overview of Deep Reinforcement Learning Methods.
Reinforcement Learning Series: Overview of Methods.
Model Based Reinforcement Learning: Policy Iteration, Value Iteration, and Dynamic Programming.
Q-Learning: Model Free Reinforcement Learning and Temporal Difference Learning.
Nonlinear Control: Hamilton Jacobi Bellman (HJB) and Dynamic Programming.
Taught by
Steve Brunton
