Robotics

This course isolates the 'where am I' half of SLAM and goes deep on the probabilistic tools robots use to pin down their position when a map already exists: predict-update filtering, particle filters, Kalman filters, and recovering from catastrophic tracking failure. It's part 1 of the Perception & Autonomy track and assumes you already have a conceptual grasp of SLAM from Autonomous Navigation & SLAM, since here we set mapping aside and focus purely on state estimation. Built for learners who want to understand not just that robots use probability to localize, but why, and how the math actually behaves when sensors lie.