Your robot can now see its surroundings. The next question is what to do with that information: where am I, where do I want to go, and how do I get there without hitting anything? This module covers the three ideas that answer it: mapping, planning, and localization.
You'll start with the occupancy grid, a simple map that divides the world into cells marked free or occupied. Then you'll learn how A* searches that grid for a short, collision-free path from the start to the goal, which is the core of motion planning.
A plan is only useful if the robot knows where it actually is. You'll see how a particle filter estimates the robot's position on a known map, and how SLAM builds the map and tracks the robot at the same time. These ideas are what ROS 2 navigation stacks are built on, and they lead into Machine Learning & Simulation.
A short explanation of occupancy grid maps, the simple cell-based representation robots use to describe free and occupied space.
A lecture on how the A* algorithm searches a grid map to find a short, collision-free path from a start to a goal.
How a particle filter estimates where a robot is on a known map, the idea behind Monte Carlo localization.
A quick introduction to simultaneous localization and mapping: building a map while keeping track of the robot inside it.