Learning for Robotics

This elective tackles how a robot turns sensor input into purposeful action in the physical world, weaving together the classical pipeline (kinematics, motion planning, control) with the modern learning stack (deep perception, vision-language-action models, deep RL). Expect four homeworks that exercise each layer of that pipeline, weekly quizzes to keep you honest on the math, and a sizable term project where you build something end-to-end. It assumes you're comfortable with linear algebra, probability, and ML at the CS 464 level, and serves as the natural bridge from "I know neural networks" to reading current robotics research.