Syllabus

Introduction and overview of Systems Identification, Adaptive Control and applications. (2 hours)

Parameter Estimation Techniques (Least Squares, Weighted and Recursive Least Squares), Estimator properties including error bounds and convergence, MES, ML and MAP estimators, Nonlinear Least Squares, Model Structures and Predictors. (6 hours)

Recursive Identification of Linear dynamic systems: RLS, ELS, IV, RML, Stochastic Approximation, Extended Kalman Filter, generalized prediction error framework and state models, convergence analysis, Akaike's Information Criteria (AIC), Bayesian Information Criteria (BIC), Time varying parameters, Nonlinear System Identification. (8 hours)

Time-series modeling and analysis such as Auto-regressive (AR), Moving average(MA), Auto-regressive moving average (ARMA), Auto-regressive model with exogenous input (ARX), ARMAX, ARIMA, ARIMAX, SARIMA, SARIMAX, Box-Jenkins approach. (10)

Adaptive schemes, Adaptive control theory and Applications, Situations when constant Gain feedback is insufficient, the adaptive control problem of MRAS based on stability theory, direct MRAS for general linear systems, Prior knowledge in MRAS, MRAS for partially known systems, use of robust estimation methods in MRAS, indirect self-tuning regulators, direct self-tuning regulators, linear quadratic STR, adaptive predictive control, prior knowledge in STR. Linear-in-the-parameters model, Gain Scheduling Control, Dual Control, Implementation issues. (8 hours)

Reinforcement Learning, Basics of RL: agent, environment, rewards, Q-learning and policy learning, Applications in adaptive control and optimization, Comparison with traditional feedback control (PID). (6 hours)

Provide a rigorous understanding of mathematical modeling, parameter estimation, and system identification techniques for linear and nonlinear dynamic systems

Develop competency in classical and modern adaptive control methods, including direct, indirect, and model-reference adaptive systems (MRAS).

Introduce reinforcement learning (RL) foundations for control and optimal decision-making in model-free and model-based frameworks.

Enable students to integrate system identification with adaptive and RL-based controllers for intelligent autonomous systems.

Equip learners with practical skills to apply advanced control algorithms using MATLAB/Python and evaluate performance on real-world systems.

Develop mathematical models of dynamic systems using parametric and non-parametric identification methods.

Estimate system parameters using least squares, maximum likelihood, and recursive identification techniques.

Design and analyze adaptive control algorithms such as MRAS, self-tuning regulators, and Lyapunov-based adaptive laws.

Apply reinforcement learning algorithms—including value-based, policy-based, and actor-critic methods—to control problems.

Integrate system identification, adaptive control, and RL-based control to create intelligent, data-driven control systems.

Implement identification and control algorithms using simulation tools and evaluate their real-time performance.

K.J. Astrom and B. Wittenmark, Adaptive Control, Pearson

L. Ljung, System Identification Theory for the user, Prentice-Hall, 2007

Richard S. Sutton, Andrew G. Barto, Reinforcement Learning: An introduction., MIT press, 1998.

K.S. Narendra and A.M. Annaswamy, Stable Adaptive Systems,, Prentice-Hall, 1989.

Arun K. Tangirala, Principles of system identification: theory and practice., CRC press, 2018.

Andrew Ng,, Machine Learning Yearning: Technical Strategy for AI Engineers in the era of Deep Learning,, https://www. mlyearning. org (2019).