A web companion to a great SLAM tutorial.
Hello SLAM is a hands-on tour through the algorithms a robot uses to figure out where it is and what the world looks like — Bayes filters, Kalman and particle filters, and modern graph-based SLAM.
What this site is
This site is a web rendering of the hello-slam Jupyter-notebook course by Nikolaos Stathoulopoulos. It is built as a Next.js MDX site so the notebooks can be read in the browser, on any device, with consistent typography, math rendering, and cross-linking between chapters.
What you will learn
Across 4 chapters and 12 lessons, the course covers the probabilistic foundations of SLAM and then walks through three major families of algorithms:
- 0. Introduction — A short overview of Simultaneous Localization and Mapping — what it is, why we need it, and the shape of the problem.
- 1. Kalman Filters — Recursive Bayesian state estimation, motion and sensor models, the Kalman & Extended Kalman filters, and EKF-SLAM.
- 2. Particle Filters — Occupancy grid mapping, Monte Carlo localization, FastSLAM and Rao-Blackwellized particle filters.
- 3. Least Squares & Graph-based SLAM — Nonlinear least-squares estimation, the least-squares formulation of SLAM, and landmark graph-based SLAM.
Credits
All course content — explanations, derivations, figures, and the underlying notebooks — is the work of Nikolaos Stathoulopoulos. This site is an unofficial web port intended to make the material easier to read. See the credits page for full attribution and licensing notes.