⚠️ This site is an experimental alpha - features may change and data may be reset

Localization and Mapping

Course: Self-Driving Cars: From Fundamentals to Advanced Autonomy

Introduction to Global Localization

Global localization is a fundamental process in self-driving cars that determines the vehicle's position and orientation (pose) in a global coordinate frame, essential for navigation and path planning. Unlike local odometry, which tracks relative motion, global methods provide absolute positioning, often using external references.

Key components include:

In self-driving cars, these sensors address the limitations of each other: GPS for long-term accuracy and IMU for high-frequency updates during GPS outages.

For example, consider a vehicle navigating a city; GPS provides the rough global position, while IMU bridges gaps when entering a tunnel.

Basic pose can be represented as a transformation matrix: $$ T = \begin{bmatrix} R & t \ 0 & 1 \end{bmatrix} $$ where $R$ is the rotation matrix and $t$ is the translation vector.

← Back to Self-Driving Cars: From Fundamentals to Advanced Autonomy