This is the companion repository for my articles discussing the ROS 2 implementation of various algorithms based on the Probabilistic Robotics book.
This work aims to help me fully understand the algorithms by applying them to real-world problems with a ROS 2-powered robot. As a learning project, the algorithms are implemented as described in the book using Python. As a result, they are not optimized and are not intended for production environments. Again, the goal is to learn the algorithms by applying them with real-world robots.
Note: This repository will undergo many changes. Newly added code will be a bit messy at first as I focus on rapid implementation, but it will be refactored for better quality over time.
If you encounter any problems with the code, please open an Issue, and I will try to fix it ASAP. For questions specific to a given implementation, please feel free to leave a comment on the related article. For general questions or to simply connect, please use any of the contact information below.
Implemented within the package rse_gaussian_filters, this series of articles covers mainly chapters 1 through 3 of the book and introduces the Kalman family of filters as well as the Information Filter.
This series will explore algorithms like Histogram and Particle Filters that model uncertainty without assuming a specific parametric form.
This series of articles will cover Mobile Robot Localization with the Extended Kalman Filter and other approaches.
This article will cover the problem of creating a map of the environment using Occupancy Grids.
Feel free to reach out to me via email or connect with me on social media:
- 📧 Email: carlos.argueta@soulhackerslabs.com
