The definitive textbook on probabilistic techniques for autonomous robots, rebuilt chapter by chapter as interactive lessons. From Bayes filters to SLAM, with live simulations at every step.
Uncertainty in robotics, why probabilistic reasoning, road map.
Probability basics, Bayes rule, belief distributions, the Bayes filter.
Kalman filter, extended Kalman filter, information filter.
Histogram filter, particle filter, importance sampling.
Velocity motion model, odometry model, sampling algorithms.
Beam models, likelihood fields, feature-based sensor models.
Markov localization, EKF localization, multi-hypothesis tracking.
Grid localization, MCL algorithm, recovery from failures.
Multi-sensor fusion, inverse measurement models, MAP mapping.
EKF-SLAM, unknown correspondences, feature management.
Information form SLAM, sparsity, Taylor expansion derivation.
SEIF SLAM, sparsification, amortized recovery, multi-vehicle SLAM.
EM algorithm for mapping, grid-based EM, layered EM mapping.
Gradient descent mapping, cycle detection, multi-robot, 3D mapping.