FixTheRobot Explore Robotics / Probability for Robotics / Resources

Probability for Robotics · 34 resources

Resources

Lecture videos, textbooks, course syllabi and open-source code for probability in robotics. Each entry says whether it is free, what its licence allows, and how it was checked.

Last checked on 2026-11-10. Back to the course.

How to read the labels

  • Free anyone may read or watch it at no cost. It says nothing about copying.
  • Reuse allowed, also commercial the licence lets you copy and adapt the material, with attribution, including in a commercial product.
  • Reuse non-commercial only or same licence required you may copy and adapt it under conditions: not commercially, or only if your result carries the same licence.
  • No reuse the source says it may not be redistributed or adapted. Read it and cite it.
  • Reuse not established no licence statement was found. Assume ordinary copyright: link to it, do not copy it.

What “checked” means. Pages were opened and playlists confirmed automatically, and licences were read where the entry says so. No video was watched in full and no repository's code was reviewed: the description of each source comes from its own page or table of contents. This course cites these sources; its text, figures and code were written for this site and copy none of them.

Start here: one video and one reading per module

ModuleWatchRead
M1 Introduction to Probability in RoboticsStachniss: Probability PrimerMIT RES.6-012, unit 1
M2 Random Variables and Probability DistributionsMIT RES.6-012 playlistBlitzstein and Hwang, Introduction to Probability
M3 Conditional Probability and Bayes' Rule3Blue1Brown: Bayes theoremPiech, Probability for Computer Scientists
M4 Expectation, Variance and CovarianceBrunton: Probability BootcampBarfoot, chapter “Primer on Probability Theory”
M5 Probabilistic Motion and Observation ModelsStachniss: Motion ModelsUCSD ECE276A schedule and slides
M6 Bayesian Filtering and Belief EstimationStachniss: Bayes FilterSärkkä and Svensson, chapter 6
M7 Kalman FilterStachniss: Kalman Filter & EKFBarfoot, chapter “Linear-Gaussian Estimation”
M8 Extended and Unscented Kalman FiltersChalmers: Sensor fusion and nonlinear filteringSärkkä and Svensson, chapters 7 and 8
M9 Particle Filters and Monte Carlo LocalizationStachniss: Particle Filter and Monte Carlo LocalizationSärkkä and Svensson, chapter 11
M10 Occupancy Grid Mapping and Probabilistic MappingStachniss: Occupancy Grid MapsThrun, Burgard and Fox, Probabilistic Robotics, chapter 9 (paid book)
M11 Maximum Likelihood, MAP and Factor GraphsStachniss: Graph-based SLAM using Pose GraphsDellaert and Kaess, Factor Graphs for Robot Perception
M12 Uncertainty on Manifolds, Error-State Filtering, Smoothing and POMDPsUMich ROB 530 playlistSolà, A micro Lie theory

Core references (9)

The sources the course is built around. If you use only a few, use these.

  • Probabilistic Robotics

    S. Thrun, W. Burgard, D. Fox. MIT Press, 2005 · Book

    The standard textbook. Recursive state estimation, Gaussian and nonparametric filters, motion and perception models, localization, occupancy grid mapping, SLAM and decision making under uncertainty.

    PaidNo reuseModules: M1, M5, M6, M7, M8, M9, M10, M12

    Licence: Copyrighted book. Checked: could not be reached; listed from prior knowledge.

  • Online Training: Mobile Robotics

    C. Stachniss, University of Bonn · Video lectures

    An ordered list of lectures. Those closest to this course are linked below.

    FreeReuse not established: link onlyModules: M1, M5, M6, M7, M8, M9, M10, M11

    Licence: No licence statement found. Checked: page opened; playlist or video confirmed.

  • SLAM Course (2013)

    C. Stachniss, University of Freiburg · Video lectures

    A full course on the Kalman filter family, particle filters, FastSLAM and graph-based SLAM. Its course page with slides is served over plain http and is therefore not linked here.

    FreeReuse not established: link onlyModules: M7, M8, M9, M10, M11

    Licence: No licence statement found. Checked: playlist or video confirmed.

  • MIT RES.6-012 Introduction to Probability

    J. Tsitsiklis, P. Jaillet. MIT OpenCourseWare · Course: short videos, notes

    The best structured free probability course. Short clips that match lesson-sized units.

    FreeReuse non-commercial onlyModules: M1, M2, M3, M4

    Licence: CC BY-NC-SA 4.0. Checked: page opened; playlist or video confirmed; licence read.

  • UCSD ECE276A Sensing & Estimation in Robotics

    N. Atanasov, UC San Diego · Course: schedule, slides

    A clean syllabus: motion and observation models, Bayes filter, particle filter, Kalman filter, EKF and UKF, matrix Lie groups, each with a reading.

    FreeReuse not established: link onlyModules: M5, M6, M7, M8, M9, M12

    Licence: No licence statement found. Checked: page opened.

  • State Estimation for Robotics, 2nd edition

    T. D. Barfoot. Cambridge University Press, 2024 · Book (author’s PDF)

    Chapters: Primer on Probability Theory; Linear-Gaussian Estimation; Nonlinear Non-Gaussian Estimation; Handling Nonidealities in Estimation; Variational Inference; Primer on Three-Dimensional Geometry; Matrix Lie Groups; Pose Estimation Problems.

    FreeNo reuseModules: M4, M7, M8, M11, M12

    Licence: Copyrighted; the publisher holds the rights. Checked: document downloaded and read.

  • Bayesian Filtering and Smoothing, 2nd edition

    S. Särkkä, L. Svensson. Cambridge University Press, 2023 · Book (authors’ PDF)

    The rigorous reference for Bayesian filtering equations, extended and general Gaussian filtering, particle filtering and smoothing.

    FreeNo reuseModules: M6, M7, M8, M9, M12

    Licence: Personal use only; no redistribution or derivative works. Checked: document downloaded and read.

  • Factor Graphs for Robot Perception

    F. Dellaert, M. Kaess. Foundations and Trends in Robotics 6(1-2), 2017 · Monograph (author-hosted PDF)

    Chapters: Smoothing and Mapping; Exploiting Sparsity; Elimination Ordering; Incremental Smoothing and Mapping; Optimization on Manifolds; Applications.

    FreeNo reuseModules: M11, M12

    Licence: Copyright 2017 F. Dellaert and M. Kaess. Checked: document downloaded and read.

  • GTSAM

    Georgia Tech Borg Lab · Software library and tutorial

    A C++ library, with Python bindings, for sensor fusion with factor graphs. The production tool for the ideas of module 11.

    FreeReuse allowed, also commercialModules: M11

    Licence: BSD (library code); bundled third-party libraries carry their own licences. Checked: page opened; licence read.

Probability foundations (6)

For modules 1 to 4: probability without robotics. Pick one course and stay with it.

Robotics courses with lectures (11)

Full courses that cover the same ground as modules 5 to 12, each from its own angle.

  • SLAM Lectures

    C. Brenner, Leibniz University Hannover · Video lectures

    Builds each filter step by step in Python.

    FreeReuse not established: link onlyModules: M5, M6, M7, M8, M9

    Licence: No licence statement found. Checked: playlist or video confirmed.

  • UMich ROB 530 Mobile Robotics

    M. Ghaffari, University of Michigan · Video lectures and code

    A graduate course with a modern treatment, including filtering on Lie groups.

    FreeReuse allowed, same licence requiredModules: M6, M7, M8, M9, M11, M12

    Licence: Course repository: GPL-3.0. Checked: playlist or video confirmed; licence read.

  • Berkeley CS287 Advanced Robotics (Fall 2019)

    P. Abbeel, UC Berkeley · Course: slides, videos

    Filtering, smoothing and planning under uncertainty.

    FreeReuse not established: link onlyModules: M6, M7, M8, M9, M12

    Licence: No licence statement found for the lectures. Checked: page opened; playlist or video confirmed.

  • Sensor fusion and nonlinear filtering

    Chalmers University of Technology (channel of L. Hammarstrand) · Video lectures

    A rigorous video course on Bayesian filtering.

    FreeReuse not established: link onlyModules: M6, M7, M8, M9

    Licence: No licence statement found. Checked: playlist or video confirmed.

  • USC CSCI 545 Robotics

    D. Seita, University of Southern California · Course: slides, videos

    A recent course built on Probabilistic Robotics.

    FreeReuse not established: link onlyModules: M5, M6, M7, M9

    Licence: No licence statement found. Checked: page opened.

  • UW CSE 571 Probabilistic Robotics

    D. Fox, University of Washington · Course pages

    The course of one of the textbook’s authors, with every offering archived.

    FreeReuse not established: link onlyModules: M5, M6, M7, M9

    Licence: No licence statement found. Checked: page opened.

  • CMU 16-831 Statistical Techniques in Robotics

    K. Kitani, Carnegie Mellon University · Syllabus

    A more statistical and learning-oriented view.

    FreeReuse not established: link onlyModules: M6, M9, M12

    Licence: No licence statement found. Checked: page opened.

  • Artificial Intelligence for Robotics (CS373)

    S. Thrun, Udacity · Online course

    Beginner-friendly: histogram localization, Kalman filters, particle filters.

    FreeReuse not established: link onlyModules: M6, M7, M9

    Licence: No licence statement found. Checked: page opened.

  • State Estimation and Localization for Self-Driving Cars

    University of Toronto, Coursera · Online course

    Least squares, Kalman filters, GPS and IMU fusion.

    Free to auditReuse not established: link onlyModules: M7, M8, M11

    Licence: No licence statement found. Checked: page opened.

  • Stanford AA228 Decision Making under Uncertainty

    M. Kochenderfer, Stanford University · Course pages

    Belief states and POMDPs.

    FreeReuse not established: link onlyModules: M12

    Licence: No licence statement found. Checked: page opened.

  • MIT 16.412 Cognitive Robotics

    B. Williams. MIT OpenCourseWare · Course: lectures

    Planning and decision making under uncertainty.

    FreeReuse non-commercial onlyModules: M12

    Licence: CC BY-NC-SA 4.0. Checked: page opened; licence read.

Kalman and Bayes filter explainers (4)

Shorter material for modules 6 to 8.

Advanced and reference (4)

For modules 11 and 12, and for readers who want the original formulations.

  • A micro Lie theory for state estimation in robotics

    J. Solà, J. Deray, D. Atchuthan, 2018 · Paper

    The shortest route to uncertainty on rotations and poses.

    FreeReuse non-commercial onlyModules: M12

    Licence: CC BY-NC-SA 4.0. Checked: page opened; licence read.

  • Quaternion kinematics for the error-state Kalman filter

    J. Solà, 2017 · Paper

    The reference for the error-state Kalman filter in inertial navigation.

    FreeReuse non-commercial onlyModules: M12

    Licence: CC BY-NC-SA 4.0. Checked: page opened; licence read.

  • Probabilistic Machine Learning: An Introduction

    K. Murphy. MIT Press, 2022 · Book (draft PDF)

    A broad reference for probability, Gaussians and inference.

    FreeNo reuseModules: M2, M3, M4, M11

    Licence: CC BY-NC-ND (no adaptation, non-commercial). Checked: page opened; licence read.

  • PythonRobotics

    A. Sakai and contributors · Code collection

    Sample implementations of localization, mapping and SLAM algorithms in Python.

    FreeReuse allowed, also commercialModules: M7, M8, M9, M10, M11

    Licence: MIT. Checked: licence read.