Localization, mapping, and control for a simulated robot — from particle filters to PID-driven path following.
Coursework on the core algorithms behind mobile robot autonomy: answering where a robot is, what the world around it looks like, and how it should move — through a sequence of simulated robotics projects.
Implemented particle filters and Kalman filters for robot localization under sensor noise, built occupancy-grid mapping from simulated range data, and wrote PID controllers and search-based planners (A*, RRT) to drive a robot along a planned path while avoiding obstacles.
A working localization-to-control pipeline: the robot could estimate its pose from noisy sensor data, plan a route through a mapped environment, and follow it with a tuned PID controller.