Python sample codes and documents about Autonomous vehicle control algorithm. This project can be used as a technical guide book to study the algorithms and the software architectures for beginners.

• What is this?
• Goal of this project
• Requirements
• How to use
• Examples of Simulation
  • Localization
    • Extended Kalman Filter Localization
    • Unscented Kalman Filter Localization
    • Particle Filter Localization
  • Mapping
    • Binary Occupancy Grid Map
    • Cost Map
    • Potential Field Map
    • NDT Map
  • Path Planning
    • A*
    • Bidirectional A*
    • Hybrid A*
    • D*
    • Dijkstra
    • ACO
    • Q-Learning
    • PSO
    • PRM
    • RRT
    • Bidirectional RRT*
    • RRT*
    • Informed RRT*
  • Path Tracking
    • Pure pursuit Path Tracking
    • Adaptive Pure pursuit Path Tracking
    • Rear wheel feedback Path Tracking
    • LQR(Linear Quadratic Regulator) Path Tracking
    • Stanley steering control Path tracking
    • MPPI Path Tracking
  • Perception
    • Rectangle fitting Detection
    • Sensor's Extrinsic Parameters Estimation
• Documents
• License
• Use Case
• Contribution
• Author

This is a sample codes collections about Autonomous vehicle control algorithm. Each source codes are implemented with Python to help your understanding. You can fork this repository and use for studying, education or work freely.

I want to release my own technical book about Autonomous Vehicle algorithms in the future. The book will include all of codes and documents in this repository as contents.

Please satisfy with the following requirements on native or VM Linux in advance.
For running each sample codes:

• Python 3.13.x
• Matplotlib
• NumPy
• SciPy

For development:

• pytest (for unit tests)
• pytest-cov (for coverage measurement)

For setting up the environment with Docker:

• VS Code
• Docker

1. Clone this repository

   $ git clone https://github.com/ShisatoYano/AutonomousVehicleControlBeginnersGuide

2. Set up the environment for running each codes

   • Set up with Docker on WSL:
     • Before cloning thi repo, install Docker in advance
     • Clone this repo following the above Step 1
     • Open this repo's folder by VSCode
     • Create Dev Container
     • And then, all required libraries are installed automatically

3. Execute unit tests to confirm the environment were installed successfully

   $ . run_test_suites.sh

4. Execute a python script at src/simulations directory

   • For example, when you want to execute localization simulation of Extended Kalman Filter:

     $ python src/simulations/localization/extended_kalman_filter_localization/extended_kalman_filter_localization.py

5. Add star to this repository if you like it!!

Each simulation script adds its own module search paths at runtime with sys.path.append(...), since this project doesn't use a standard Python package layout. Static analysis tools (Pylance/pyright) can't see those runtime sys.path.append(...) calls, so without extra configuration your editor will show false "import could not be resolved" errors and code completion won't work for these modules.

To fix this, pyrightconfig.json (for pyright/Pylance, e.g. Neovim or VS Code without Dev Containers) and .devcontainer/devcontainer.json's python.analysis.extraPaths (for VS Code + Dev Containers) list every directory under src/components and src/simulations that directly contains a .py file.

Whenever you add a new module (a new directory under src/components or src/simulations), regenerate both files by running:

$ python generate_pyrightconfig.py

This scans the project and rewrites both files automatically, so you don't need to edit them by hand.

Run this script on your host machine, not inside the container. It only uses the Python standard library (json, pathlib), and since the project directory is bind-mounted into the container as-is, the files it writes are the same on both sides either way. Running it on the host is simplest since it doesn't depend on the container's Python environment at all.

Planning

Planning

Planning

Planning with dynamic obstacle replanning

Planning(Reduce frames by sampling every nth node to prevent memory exhaustion)

Ant Colony Optimization
Author: Banaan Kiamanesh

Reinforcement learning with a Q-table policy

Particle Swarm Optimization

Planning

A* seed path smoothed with Elastic Bands optimisation

Planning

Planning

Planning

Planning

Estimation by Unscented Kalman Filter

Design documents of each Python programs are prepared here. The documents are still not completed. They have been being updated. If you found any problems in them, please tell me by creating an issue.
Documents link

MIT

I started this project to study an algorithm and software development for Autonomous Vehicle system by myself. You can also use this repo for your own studying, education, researching and development.

If this project helps your task, please let me know by creating a issue.
Any paper, animation, video as your output, always welcome!! It will encourage me to continue this project.

Your comment and output is added to this list of user comments.

Any contribution by creating an issue or sending a pull request is welcome!! Please check this document about how to contribute.

Shisato Yano