Online Robotics Master's Program

Application of mathematical optimization techniques, including linear and nonlinear methods, to design and manufacture of devices and systems of interest to mechanical engineers; optimization techniques include: constrained and unconstrained optimization in several variables, problems for structured multi-stage decision, and linear programming; formulation of design and manufacturing problems using computer- based methods; optimum design of parts and assemblies to minimize the cost of manufacture.

Elements of a robotic/flexible automation system; overview of applications; manipulator anatomy; drive systems; end effectors; sensors; computer control: functions, levels of intelligence, motion control, programming and interfacing to sensors and actuators; applications: identification, hardware selection, work cell design, economics, case studies; design of parts and assemblies; advanced topics.

Introduction to state space concepts; state space description of physical systems such as electrical, mechanical, electromechanical, thermal, hydraulic, pneumatic, aerospace, etc. systems. Eigenvalues, eigenvectors and other topics in linear algebra, modal decomposition and other coordination transformations. Relationship between classical transfer function methods and modern state methods. Analysis of linear continuous and discrete time linear systems, solution by state transition matrix, control ability, observability and stability properties; synthesis of linear feedback control systems via pole assignment and stabilizability and performance index minimization. Brief introduction to optimal control, estimation and identification.

This course emphasizes the development of modeling and simulation concepts and analysis skills necessary to design, program, implement and use computers to solve complex systems/products analysis problems. The key emphasis is on problem formulation, model building, data analysis, solution techniques and evaluation of alternative designs/processes in complex systems/products. Overview of modeling techniques and methods used in decision analysis, including multi- attribute utility models, decision trees, and optimization methods are discussed.

Review of introductory robotics and modern control topics. Biomechanics of human locomotion: kinematics and kinetics. Design, analysis, sensing, actuation, and low-level control of robotic exoskeletons and powered orthoses. Finite state machines for powered orthoses. Principles of human cooperative control for rehabilitation and assistance. Model-based and model-free assistive controllers. Machine learning control in wearable robotics. Overview of wearable inertial sensors and applications to motion analysis and wearable robotics. Supervised learning methods for motor task classification and motion analysis.

Mobile robot geometry, kinematics, and dynamics. Control and estimation for autonomous vehicles. Motion planning, including discrete and continuous methods, and sampling-based planning. Simultaneous localization and mapping, including active SLAM and autonomous exploration with occupancy grids. Markov decision processes and partially observable Markov decision processes with application to mobile robots; planning under uncertainty. Introduction to supervised learning and reinforcement learning, including deep learning. Applications of machine learning to autonomous navigation.

This course presents tool, techniques, algorithms, and programming techniques using the Python programming language for data intensive applications and decision making. The course formally introduces techniques to: (i) gather,(ii) store, and (iii) process large volumes of data to make informed decisions. Such techniques find applicability in many engineering application areas, including communications systems, embedded systems, smart grids, robotics, Internet, and enterprise networks, or any network where information flows and alters decision making.

In this course we will talk about the foundational principles that drive machine learning applications and practice implementing machine learning algorithms. Specific topics include supervised learning, unsupervised learning, neural networks, and graphical models. The main goal of the course is to equip you with the tools to tackle new ML problems you might encounter in life.

This course will offer the students an overview of the technology of autonomous mobile robotic systems the mechanisms that allow a mobile robot to move through a real-world environment to perform its tasks. Since the design of any successful mobile robot involves the integration of many different disciplines -- among them kinematics, signal analysis, information theory, artificial intelligence, and probability theory -- the course will discuss all facets of mobile robotic system, including hardware design, wheel design, kinematics analysis, sensors and perception, localization, mapping, motion planning, navigation, and robot control architectures. Multi-robot systems will also be introduced due to their broader applications, such as search and rescue tasks, and exploring tasks.

An introduction course for machine learning theory, algorithms and applications. This course aims to provide students with the knowledge in understanding key elements of how to design algorithms/systems that automatically learn, improve and accumulate knowledge with experience. Topics covered in this course include decision tree learning, neural networks, Bayesian learning, reinforcement learning, ensembling multiple learning algorithms, and various application problems. The students will have chances to simulate their algorithms in a programming language and apply them to solve real-world problems.