Twin Cities campus
 
Twin Cities Campus

Robotics Minor

College of Science and Engineering - Adm
College of Science and Engineering
Link to a list of faculty for this program.
Contact Information
Minnesota Robotics Institute, Shepherd Laboratories, 100 Union St SE, Minneapolis, MN 55455
Email: mnri@umn.edu
Website: https://cse.umn.edu/mnri
  • Program Type: Graduate minor related to major
  • Requirements for this program are current for Spring 2022
  • Length of program in credits (master's): 9
  • This program does not require summer semesters for timely completion.
The Robotics minor is designed to familiarize master's students with the areas relevant to robotics, such as robot modeling and control; perception using cameras and other sensors; and cognition to reason, plan, and make decisions. Students will learn state-of-the-art methods for developing and using robots, and be exposed to cutting edge technologies and theories forming the basis for the next generation of robots and their applications in areas such as agriculture, underwater exploration, autonomous driving, and manufacturing applications.
Program Delivery
  • via classroom (the majority of instruction is face-to-face)
Prerequisites for Admission
The preferred undergraduate GPA for admittance to the program is 3.00.
Special Application Requirements:
Students interested in the minor are strongly encouraged to confer with their major field advisor and director of graduate studies, and the Robotics director of graduate studies regarding feasibility and requirements.
For an online application or for more information about graduate education admissions, see the General Information section of this website.
Program Requirements
Use of 4xxx courses towards program requirements is not permitted.
Courses offered on both the A-F and S/N grading basis must be taken A-F. The minimum cumulative GPA for minor field coursework is 3.00.
Required courses (9 credits)
Cognition (3 credits)
Select 3 credits from the following in consultation with the Robotics director of graduate studies:
CSCI 5511 - Artificial Intelligence I (3.0 cr)
CSCI 5512 - Artificial Intelligence II (3.0 cr)
CSCI 5521 - Machine Learning Fundamentals (3.0 cr)
CSCI 5525 - Machine Learning: Analysis and Methods (3.0 cr)
Perception (3 credits)
Select 3 credits from the following in consultation with the Robotics director of graduate studies:
CSCI 5561 - Computer Vision (3.0 cr)
EE 5561 - Image Processing and Applications: From linear filters to artificial intelligence (3.0 cr)
Robot Modeling and Control (3 credits)
Select 3 credits from the following in consultation with the Robotics director of graduate studies:
AEM 5321 - Modern Feedback Control (3.0 cr)
CSCI 5551 - Introduction to Intelligent Robotic Systems (3.0 cr)
CSCI 5552 - Sensing and Estimation in Robotics (3.0 cr)
EE 5231 - Linear Systems and Control (3.0 cr)
ME 5286 - Robotics (4.0 cr)
Program Sub-plans
Students are required to complete one of the following sub-plans.
Students may not complete the program with more than one sub-plan.
Masters
  
More program views..
View college catalog(s):
· College of Science and Engineering

View future requirement(s):
· Fall 2022

View PDF Version:
Search.
Search Programs

Search University Catalogs
Related links.

College of Science and Engineering

Graduate Admissions

Graduate School Fellowships

Graduate Assistantships

Colleges and Schools

One Stop
for tuition, course registration, financial aid, academic calendars, and more
 
CSCI 5511 - Artificial Intelligence I
Credits: 3.0 [max 3.0]
Course Equivalencies: CSci 4511W/CSci 5511
Prerequisites: [2041 or #], grad student
Typically offered: Every Fall
Introduction to AI. Problem solving, search, inference techniques. Logic/theorem proving. Knowledge representation, rules, frames, semantic networks. Planning/scheduling. Lisp programming language. prereq: [2041 or instr consent], grad student
CSCI 5512 - Artificial Intelligence II
Credits: 3.0 [max 3.0]
Course Equivalencies: CSci 5512W/CSci 5512
Typically offered: Every Spring
Uncertainty in artificial intelligence. Probability as a model of uncertainty, methods for reasoning/learning under uncertainty, utility theory, decision-theoretic methods. prereq: [STAT 3021, 4041] or instr consent
CSCI 5521 - Machine Learning Fundamentals
Credits: 3.0 [max 3.0]
Typically offered: Periodic Fall
Problems of pattern recognition, feature selection, measurement techniques. Statistical decision theory, nonstatistical techniques. Automatic feature selection/data clustering. Syntactic pattern recognition. Mathematical pattern recognition/artificial intelligence. Prereq: [2031 or 2033], STAT 3021, and knowledge of partial derivatives
CSCI 5525 - Machine Learning: Analysis and Methods
Credits: 3.0 [max 3.0]
Typically offered: Fall Even Year
Models of learning. Supervised algorithms such as perceptrons, logistic regression, and large margin methods (SVMs, boosting). Hypothesis evaluation. Learning theory. Online algorithms such as winnow and weighted majority. Unsupervised algorithms, dimensionality reduction, spectral methods. Graphical models. prereq: Grad student or instr consent
CSCI 5561 - Computer Vision
Credits: 3.0 [max 3.0]
Typically offered: Every Spring
Issues in perspective transformations, edge detection, image filtering, image segmentation, and feature tracking. Complex problems in shape recovery, stereo, active vision, autonomous navigation, shadows, and physics-based vision. Applications. prereq: CSci 5511, 5521, or instructor consent.
EE 5561 - Image Processing and Applications: From linear filters to artificial intelligence
Credits: 3.0 [max 3.0]
Course Equivalencies: EE 5561/EE 8541
Typically offered: Every Spring
Image enhancement, denoising, segmentation, registration, and computational imaging. Sampling, quantization, morphological processing, 2D image transforms, linear filtering, sparsity and compression, statistical modeling, optimization methods, multiresolution techniques, artificial intelligence concepts, neural networks and their applications in classification and regression tasks in image processing. Emphasis is on the principles of image processing. Implementation of algorithms in Matlab/Python and using deep learning frameworks. prereq: [4541, 5581, CSE grad student] or instr consent
AEM 5321 - Modern Feedback Control
Credits: 3.0 [max 3.0]
Course Equivalencies: AEM 5321/EE 5231
Typically offered: Every Fall
State space theory for multiple-input-multiple-output aerospace systems. Singular value decomposition technique, applications to performance/robustness. Linear quadratic gaussian and eigenstructure assignment design methods. Topics in H[infinity symbol]. Applications. prereq: 4321 or EE 4231 or ME 5281 or equiv
CSCI 5551 - Introduction to Intelligent Robotic Systems
Credits: 3.0 [max 3.0]
Typically offered: Periodic Fall
Transformations, kinematics/inverse kinematics, dynamics, control. Sensing (robot vision, force control, tactile sensing), applications of sensor-based robot control, robot programming, mobile robotics, microrobotics. prereq: 2031 or 2033 or instr consent
CSCI 5552 - Sensing and Estimation in Robotics
Credits: 3.0 [max 3.0]
Typically offered: Periodic Spring
Bayesian estimation, maximum likelihood estimation, Kalman filtering, particle filtering. Sensor modeling and fusion. Mobile robot motion estimation (odometry, inertial,laser scan matching, vision-based) and path planning. Map representations, landmark-based localization, Markov localization, simultaneous localization/mapping (SLAM), multi-robot localization/mapping. prereq: [5551, Stat 3021] or instr consent
EE 5231 - Linear Systems and Control
Credits: 3.0 [max 3.0]
Typically offered: Every Fall
The course studies finite-dimensional linear systems in continuous and discrete time. Such systems are described by ordinary differential and difference equations. Input-output and state-space descriptions are provided and analyzed. Introductory methods for controlling such systems are developed. prereq: [3015, CSE grad student] or instr consent
ME 5286 - Robotics
Credits: 4.0 [max 4.0]
Grading Basis: A-F or Aud
Typically offered: Every Spring
The course deals with two major components: robot manipulators (more commonly known as the robot arm) and image processing. Lecture topics covered under robot manipulators include their forward and inverse kinematics, the mathematics of homogeneous transformations and coordinate frames, the Jacobian and velocity control, task programming, computational issues related to robot control, determining path trajectories, reaction forces, manipulator dynamics and control. Topics under computer vision include: image sensors, digitization, preprocessing, thresholding, edge detection, segmentation, feature extraction, and classification techniques. A weekly 2 hr. laboratory lasting for 8-9 weeks, will provide students with practical experience using and programming robots; students will work in pairs and perform a series of experiments using a collaborative robot. prereq: [3281 or equiv], [upper div ME or AEM or CSci or grad student]