Courses

Involves teaching computer programs to improve their performance through guided training and unguided experience. Takes both symbolic and numerical approaches. Topics studied concept learning, decision trees, neural nets, latent variable models, probabilistic inference, time series models, Bayesian learning, sampling methods, computational learning theory, support vector machines, and reinforcement learning.

Projects: Linear Models for Supervised Learning, Non-Linear Models for Unsupervised Learning, Machine Learning Fairness on COMPASS system

• Projects

Introduces those areas of artificial intelligence that relate to fundamental issues and techniques of computer vision and image processing. Emphasizes physical, mathematical, and image-processing aspects of vision. Topics include image formation, edge detection, segmentation, convolution, image-enhancement techniques, extraction of features (such as color, texture, and shape), object detection, 3-D vision, and computer system architectures and applications.

Projects: Edge Detection, Panorama Stitching, Face Detection using Viola Jones Algorithm

• Projects

In these course i acquired the knowledge of key Algorithms relevant to programming intelligent robots. This course is breifly describe on key core concepts of robot estimation, linear optimal control, randomized motion planning, trajectory optimization, Kalman filtering, particle filtering, and selected topics in optimization.

Outcomes: BUG Algorithms, BFS/DFS Algorithms, Djikstra, RANSAC, Rapidly exploring-Random Trees, Bayes Filter, Kalman Filter, Particle Filter, Introduction to SLAM and Introduction to Photogrammetry etc.

Projects: Motion Planning using Bug Algorithm, Path Planning using A* and Vector Field Histogram(VFH) algorithm, Grid Localization using Bayes Filter

Major Project: Object Binning and obstacle avoidance with SLAM

The objective of this course is to provide working knowledge required to formulate and analyze problems related to the application of collaborative robots. This course also provided methodologies for solutions to such formulated problems.

Outcomes: D-H Parameters, Introduction to Robot Dynamics and Controls.

Major Project: Kinematics and Dynamics of FANUC Co-Bot CR-4iA

• Projects

The objective of this course is to provide working knowledge required to formulate and analyze problems in robotic systems design. This course also provide methodologies for solutions to such formulated problems. Comprehensive skill level will be reached through basic topics such as: a) Kinematics, b) Inverse Kinematics, c) Computation of the Manipulator's Jacobian, d) Newton-Euler Formulation of Equations of Motion,e) Lagrange's Formulation of Equations of Motion. There is steep learning in MATLAB.

Outcomes: Robot Kinematics, D-H Parameters and Introduction to Robot Dynamics.

Major Project: Create 2-DOF Spherical Robot using Simscape Multibody

Control of dynamic systems by digital computer. Characterization of discrete-time systems, discrete state space, Z transforms, time domain analysis of discrete-time control systems. Effects of sampling time. Discrete root locus. Frequency domain methods for compensator design. Laboratory experiences in the computer control of electromechanical systems with C/C++ programming.

Outcomes: Discrete systems and control model, Design of digital control system, Time domain analysis, PID controller, Root Locus, Introduction to estimators(Kalman Filter) and State Space techniques.

Projects: Design a controller for 6V DC Motor, Design a controler and regulator for a self-balancing robot.

Examines system modeling and identification of plants to be controlled; use of feedback control systems; design of feedback control laws including P, I, D; block diagrams, transfer functions, and frequency response functions; control system design and analysis in the time domain and frequency domain; computer simulation of control systems; stability analysis using Routh-Hurwitz criterion; design for stability, speed of response, and accuracy; root locus, and Bode Plots; compensation strategies.

Outcomes: Design of control system, Time domain analysis, frequency domain analysis, PID controller, Root Locus and Bode Plot.