Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers error sources in odometry, including deterministic sources like limited encoder resolution and wheel misalignment, and non-deterministic sources like variations in wheel contact points. It also discusses feature-based localization, the Kalman Filter algorithm for fusing noisy processes and sensing, and the propagation of actuator noise to pose noise. The lecture emphasizes the importance of modeling odometry error and sensor error, and provides insights into the Kalman Filter for sensor fusion. Various examples and models are presented to illustrate the concepts.