Lectures
-
01
Introduction
Module I
Autonomy spectrum · Perception–Decision–Action loop · The system tuple · Historical arc
-
02
Dynamical Systems
Module II
State–space models · Mechanics · Partial Observability
-
03
Dynamical Systems (II)
Module II
Observability · Belief state · Flow & well-posedness · Stability · Linearisation · Discretisation
-
04
Probability and Optimisation
Module II
Probability · Bayesian inference · Entropy · Convex optimisation · MAP estimation
-
05
State Estimation (I)
Module III
Hidden-state problem · Belief · Bayes filter · Corridor example · Gaussian machinery (opening)
-
06
State Estimation (II)
Module III
Gaussian machinery · Closure theorems · Conjugacy · Kalman filter: predict, update, gain, algorithm
-
07
State Estimation (III)
Module III
Kalman optimality · Joseph form · Riccati & observability · Steady-state filter · Sensor fusion
-
08
State Estimation (IV)
Module III
EKF / UKF · Monte Carlo · Importance sampling · Particle filter · Belief as sufficient statistic
-
09
Observation Models (I): Signals and Proprioceptive Sensors
Module III
Data processing inequality · Sufficient statistics · Encoders & aliasing · IMU & Allan variance
-
10
Observation Models (II): Complementary Filter and Time of Flight
Module III
Complementary filter · CF → KF cascade · Time of flight · SNR & detection · Matched filter · Resolution & pulse compression
More lectures to come
Ongoing until December 2026 — you can still register ↗
-
Maksym Shamrai
PhD in Applied Mathematics
Profile