Leveraging Data-Driven and AI-Based Techniques for Control Algorithm Development

Traditional control methods often struggle with complex systems, such as those used in aerospace, automated driving, robotics, and motor control applications. One key challenge is their inability to adapt to unknown dynamics and disturbances. Also, these methods traditionally rely on first-principles modeling, which becomes impractical when dealing with the complexity, nonlinearity, or uncertainty of these systems. However, as data availability and computational resources have increased, data-driven control techniques have emerged as a viable alternative or supplement to traditional control methods to improve system performance. In this session, you will learn about:

The basics of data-driven control and using MATLAB^® and Simulink^® products for techniques such as reinforcement learning, data-driven model predictive control, and active disturbance rejection control.

Case studies demonstrating how various industries have successfully applied these techniques to tackle complex control challenges.