Video and Webinar Series

Data-Driven Control

Learn about model-free adaptive control methods, including extremum seeking and model reference adaptive control. You’ll see how these algorithms work, their overall benefits and drawbacks.

You’ll also explore constraint enforcement, which is important for learning-based systems that are deployed in safety-critical applications. Constraint enforcement ensures that any action requested by the controller does not result in the system exceeding a safety bound. 

If you would like to learn about other data-driven techniques, please see reinforcement learning and deep learning-based model predictive control

Reinforcement Learning

Deep Learning-Based Model Predictive Control

What is Extremum Seeking Control | Learning-Based Control Get an introduction to an adaptive control method called extremum seeking control. You’ll see how to build the algorithm one component at a time in Simulink to highlight the benefits and drawbacks of this method.

Constraint Enforcement for Improved Safety | Learning-Based Control Learn about enforcing systems constraints, which are essential for learning-based systems in safety-critical applications. These constraints ensure that any control actions you not result in the system exceeding a safety bound.

What Is Model Reference Adaptive Control? | Learning-Based Control See how an adaptive control method called model reference adaptive control (MRAC) can adapt in real time to variations and uncertainty in the system that is being controlled.