Part 1: Introduction & Feature Detection

Some people claim to have a poor sense of direction. They might compare themselves to a robot and feel much better.

Part 2: Pose Optimization

Once our features are detected and associated, we aim to estimate the movement between the two observations.

After Part 1, which focused on feature detection and association, we now delve into estimating our position and orientation over time.

Choosing the Pose Model to Optimize

A pose represents the position and orientation of our robot in space. We can express it in the way and in the coordinate system that suits us best (I’ve seen spherical, but here, we prefer Cartesian).

Localize a mobile robot in a virtual environment with constraint programming.