ShisatoYano/AutonomousVehicleControlBeginnersGuide

What it solves

This project provides a structured learning resource for beginners to understand the algorithms and software architectures used in autonomous vehicle control. It bridges the gap between theoretical concepts and practical implementation by providing runnable Python sample codes and design documents.

How it works

The repository is organized as a collection of Python simulations and components. Users can run specific scripts to visualize how different autonomous driving algorithms function. The project covers several core domains of autonomous navigation, including:

• Localization: Determining the vehicle's position (e.g., using Extended Kalman Filters).
• Mapping: Creating environmental maps (e.g., NDT map construction).
• Path Planning: Determining the optimal route to a destination.
• Path Tracking: Ensuring the vehicle follows the planned path.
• Perception: Interpreting sensor data to understand the surroundings.

Who it’s for

It is designed for beginners, students, and researchers who want to study autonomous vehicle algorithms through hands-on coding and simulation.

Highlights

• Comprehensive Scope: Covers the full pipeline of autonomous navigation from perception to path tracking.
• Animated Demos: Includes runnable simulations with animated visualizations for each algorithm.
• Educational Focus: Serves as a technical guide book with accompanying design documents.
• Developer Friendly: Provides Docker and Dev Container support for easy environment setup.