Robot Learning

Catalog description

This course introduces students to the principles and methods of robot learning for manipulators, combining foundational robotics concepts with modern learning-based approaches. Topics include manipulator kinematics and control, trajectory representation, learning from demonstration, probabilistic movement models, dynamic movement primitives, reinforcement learning, and safety in learning-based control. The course emphasizes weekly simulation labs and assignments, where students implement algorithms in Python and apply them to simulated robotic arms. Through these labs and assignments, students progressively gain hands-on experience in modeling, learning, and evaluating manipulation skills. By the end of the course, students will be able to critically analyze different learning methods for manipulators and apply them to real-world inspired tasks.