Applied Control Systems 2: autonomous cars (360 tracking)

Learn to implement autonomous vehicle trajectory tracking with Model Predictive Control (MPC)! This course, led by Aerospace & Robotics Engineer Mark, builds upon "Applied Control Systems 1" to teach you how to create self-driving cars that follow complex 2D paths.

Specifically, you'll discover:

• Nonlinear MPC for Autonomous Cars: Go beyond straight-road lane changes! We'll remove simplifying assumptions and apply linear MPC to nonlinear systems using Linear Parameter Varying (LPV) techniques. This allows your autonomous vehicle to track a general 2D trajectory.
• MPC Constraints: Master the use of quadratic solvers like qpsolvers and quadprog to enforce realistic limits on velocities, accelerations, and steering wheel angles of your autonomous car. Ensure your vehicle operates within safe and practical parameters.
• Mathematical Foundations: Gain a solid understanding of the mathematics behind autonomous vehicle control, including MPC and Model Predictive Control.
• Python Implementation: Get hands-on experience with Python code to implement these advanced control strategies.
• Real-World Applications: Develop skills applicable to a wide range of control systems engineering problems.

This course is a direct continuation of "Applied Control Systems 1" and is perfect for those looking to advance their knowledge of autonomous vehicle control.

Enroll now and start building sophisticated control systems! Check out my free preview videos to see what you'll learn.