(1 credit). Weekly technical presentations from local and visiting scholars on current topics related to the theory, design and development, and application of autonomous vehicle systems.
(3 credits). Automation, robot technology, kinematics, dynamics, trajectory planning, and control of two-dimensional and spatial robots; robot programming; design and simulation of robotic devices.
(3 credits). Overview of Micro/Nano-robotic systems. Physics of reduced length scales (scaling effects in the physical parameters, surface forces, contact mechanics, and micro/nano-scale dynamical phenomena), Basics of micro/nano-manufacturing, microfabrication and soft lithography, Biomimetic design strategies for mobile micro-robots, Principle of transduction, material properties and characteristics of Micro/nano-actuators (piezoelectric, shape-memory alloy, and a variety of MEMS and polymer actuators), Control requirements and challenges of micro/nano-actuators, Micro/nano sensors for mobile microrobotic applications, Micro/nano-manipulation (scanning probe microscopy, operation principles, designing experiments for nanoscale mechanical characterization of desired samples).
(3 credits). Principles of autonomous robotics control for unstructured environments. Probability theory, numerical techniques for recursive Bayesian estimation and multi-sensor data fusion, simultaneous localization and mapping, quantification of belief, Bayesian control.
(3 credits). This course treats a specific advanced topic of current research interest in the area of intelligent systems. Papers from the current literature or research monographs are likely to be used instead of a textbook. Student participation in a seminar style format may be expected.
(3 credits). Understand the fundamental problems in path planning, multi-robot coordination, sensor-based planning, and active perception; discuss and critique the state-of-the-art algorithms and techniques for solving the aforementioned problems; identify open research problems and initiate progress towards solving them; implement algorithms using existing robotics tools (such as ROS) and on actual ground/aerial robots.
(3 credits). Techniques for automated analysis of images and videos. Image formation, feature detection, segmentation, multiple view geometry, recognition, and video processing.
(3 credits). Advanced introduction to the theory of time-varying and time-invariant linear systems represented by state equations; solutions of linear systems, uniform stability and other stability criteria, uniform observability and controllability, state feedback and observers.
(3 credits). Advanced introduction to the theory of optimal control of time-varying and time-invariant linear systems; Solutions to the linear-quadratic regulator, optimal filtering, and linear-quadratic-Gaussian problems; Robustness analysis and techniques to enhance robustness of controllers.
(3 credits). Develop an applied understanding of state-space representations for linear time invariant multi-input multi-output dynamic systems in both time domain and frequency domain. Introduction to modern state-space control methods; state feedback and output feedback. Realistic design problems with numerical simulations of practical implementations.
(3 credits). Analysis and design of sampled-data systems, extraction of discrete-time dynamic models from experimental data, and implementation of dynamic compensators on digital processors. In-depth design experience with LQR optimal control and an introduction to Kalman filtering. Realistic design problems with numerical simulations of pratical implementations.
(3 credits). Introduction to the theory of systems of coupled, nonlinear, time-varying ordinary differential equations: existence and uniqueness of solutions; continuous dependence on parameters; stability of equilibria and stability analysis techniques; input-to-state stability; input-output stability; nonlinear design techniques including input-state and input-output feedback linearization, backstepping, and sliding mode control.
(3 credits). Introduction to the theory and methodology used to design adaptive controllers for uncertain systems, addressing issues such as input constraints, disturbance rejection, partial measurements, and robustness.
(3 credits). Recognizing and solving convex optimization problems. Convex sets, functions, and optimization problems. Least-squares, linear, and quadratic optimization. Geometric and semidefinite programming. Vector optimization. Duality theory. Convex relaxations. Approximation, fitting, and statistical estimation. Geometic problems. Control and trajectory planning.
(3 credits). Electromechanical design and control applications. Design and building of electronic interfaces and controllers for mechanical devices, sensors, signal acquistion, filtering, and conditioning. Microcontroller-based closed-loop control and device communications. Sensor and actuator selection, installation, and application strategies.
(3 credits). Advanced topics in Mechatronic design. Circuit board design and fabrication, sensors, microcontroller programming, and additional topics in device communications, sensors, and applications. A design project is an integral part of the course.
(3 credits). Current and state-of-the-art trends in computer vision, particularly in object recognition and scene understanding. Application of approaches in computer vision to various automatic perception problems. Strengths and weaknesses of computer vision techniques. Open questions and future research directions.
(3 credits). Relevant rigid body kinematics and dynamics fundamentals for vehicles such as aircraft, spacecraft, and ships. Provides foundation for advanced courses and research on dynamics and control of vehicles. Review of particle motion and application to aircraft performance and satellite orbital mechanics. Rigorous modeling of rotational and translational motion of rigid bodies. Linearization of equations of motion for stability analysis, modal analysis, control system synthesis, with introduction to classical control system concepts. Sensors and actuators commonly used on vehicles. Specific examples from aircraft, missiles, spacecraft, rockets, ships, and submersibles.
(3 credits). Derivation of the equations of motion of a ship; waves and wave forces on structures; description of wave statistics and spectral representation in a given sea state; ship response in regular waves; ship response in random waves.
(3 credits). Study of the dynamics of high-speed craft, including surface effects ships, hydrofoil vessels, semi-displacement monohulls and catamarans, and planning vessels.
(3 credits). Topics in the dynamics and control of systems including airplanes, helicopters, spacecraft, and structures. Physics and data-based modeling from the control system designer's perspective. Structure of the control-oriented equations of motion in relation to robust control design. Bio-inspiried design.
(3 credits). Algorithms and principles involved in machine learning; focus on perception problems arising in computer vision, natural language processing and robotics; fundamentals of representing uncertainty, learning from data, supervised learning, ensemble methods, unsupervised learning, structured models, learning theory and reinforcement learning; design and analysis of machine perception systems; design and implementation of a technical project applied to real-world datasets (images, text, robotics).
(3 credits). Advanced concepts in machine learning. Probabilistic graphical models and structured output prediction. Directed models (Bayes Nets), undirected models (Markov/Conditional Random Fields), exact inference (junction tree), approximate inference (belief propagation, dual decomposition), parameter learning (MLE, MAP, EM, max-margin), structure learning.
(3 credits). Advanced concepts in Machine Learning and Deep Learning. Topics include models (multi-layer perceptrons, convolutional neural networks, recurrent neural networks, long short-term memory networks, memory networks), learning algorithms (backpropagation, stochastic sub-gradient descent, dropout), connections to structured predictions (Boltzmann machines, “unrolled” belief propagation), and applications to perception and AI problems (image classification, detection, and segmentation; image captioning; automatic game playing).
(3 credits) Computational algorithms for mobile robot planning. Topics include graph-based planning, sampling-based planning, planning under state and action uncertainty, Markov Decision Process, reinforcement-learning, vision-based navigation, obstacle avoidance, and multi-robot planning. The course will balance theory with applications; the assignments will require students to implement many of the algorithms studied in class. Programming experience in either C++ or Python required.