Undergraduate Course: Introduction to Vision and Robotics (INFR09019)
|School||School of Informatics
||College||College of Science and Engineering
|Credit level (Normal year taken)||SCQF Level 9 (Year 3 Undergraduate)
||Availability||Available to all students
|Summary||A mobile robot is a machine controlled by software that use sensors and other technology to identify its surroundings and move around its environment. This course provides a general understanding of mobile robotics and related concepts, covering topics such as sensing, computer vision (i.e., visual perception), state estimation (e.g., localisation and mapping) and motion planning. The emphasis is on algorithms, probabilistic reasoning, optimization, inference mechanisms, and behavior strategies, as opposed to electromechanical systems design. Practically useful tools and simulators for developing real robotic systems will also be covered in this course. More course information can be found on its corresponding LEARN page here: https://www.learn.ed.ac.uk/ultra/courses/_99697_1/cl/outline
In the end of the course, students will develop sufficient skills in the analysis of predominant mobile robots, being able to understand the visual perception and navigation system for a self-driving car.
The issues addressed will include the following:
* Applications of robotics and vision; the nature of the problems to be solved; historical overview and current state of the art.
* Robot actuators and sensors. Parallels to biological systems.
* Robot control: Open-loop, feed-forward and feedback; PID (proportional integral differential) control.
* Image formation, transduction and simple processing; thresholding, filtering and classification methods for extracting object information from an image.
* Active vision and attention.
* Sensors for self monitoring.
* General approaches and architectures. Classical vs. behaviour-based robotics. Wider issues and implications of robot research.
The course also involves hands-on practicals in which vision and robot systems will be programmed.
Relevant QAA Computing Curriculum Sections: Artificial Intelligence; Computer Vision and Image Processing
Entry Requirements (not applicable to Visiting Students)
|Prohibited Combinations|| Students MUST NOT also be taking
Advanced Robotics (INFR11213)
Students MUST NOT also be taking
Introduction to Mobile Robotics (INFR10085)
|Other requirements|| This course is open to all Informatics students including those on joint degrees. For external students where this course is not listed in your DPT, please seek special permission from the course organiser (lecturer).
This course assumes experience of AI knowledge and representation issues (equivalent to first and second year courses in Informatics); enough school algebra and geometry to understand the optics of image formation with lenses; enough school physics to understand Newton's Laws of Motion; the general mechanical intuitions required in such tasks as bicycle maintenance; enough electrical knowledge to understand how electric batteries make electric motors work. You are expected to be familiar with these mathematical methods: Bayes rule, Multivariate Gaussian Distribution, Covariance matrices, Convolution, the Jacobean (relating derivatives of a vector valued function to its vector valued inputs).
Information for Visiting Students
|High Demand Course?
Course Delivery Information
|Not being delivered|
On completion of this course, the student will be able to:
- Students will be able to recall and explain the essential facts, concepts and principles in robotics and computer vision, demonstrated through written answers in examination conditions.
- Students will be able to describe and evaluate the strengths and weaknesses of some specific sensor and motor hardware; and some specific software methods for sensory processing and motor control, demonstrated through written answers in examination conditions.
- Students will be able to employ hardware (e.g. cameras, robots) and software (e.g. Matlab,robot simulator) tools to solve a practical problem of sensory-motor control, and will show a working system in a practical class.
- Students will, in writing a joint report, identify problem criteria and context, discuss design and development, test, analyse and evaluate the behaviour of the sensory-motor control system they have developed.
|Russell & Norvig Chapters 24 & 25 in Artificial Intelligence: A modern approach, Prentice Hall, 1995, ISBN: 0130803022 - Highly Recommended|
Robin R. Murphy, Introduction to AI Robotics, MIT Press, 2000, ISBN: 0262133830, Recommended, suppementary for Robotics
Solomon and Breckon, Fundamentals of Digital Image Processing, Wiley-Blackwell, 2010, ISBN 978-0470844731, Highly Recommended
Ulrich Nehmzoe, Mobile Robotics: A Practical Introduction, 2nd Edition, Recommended
W. Burger, M Burge: principles of Digital Image Processing, Springer 2009, ISBN: 978-848001909, Covers some of IVR, AV matreials but maybe less than 50%, also on-line free inside the University
RC Gonzalez, RE Woods, SL Eddins: Digital Image Processing Using MATLAB, 2nd Edition, Prentice Hall 2009, ISBN: 9780982085400, Excellent but expensive, covers alot of IVR some of AV
E. Alpaydin, Introduction to Machine Learning, The MIT PRess, October 2004, ISBN: 0262012111, Recommended. Chapters are a deeper exploration of the Bayesin Classification topic
|Graduate Attributes and Skills
||The activities of the course are designed to further develop intellectual skills in the areas of: laboratory, writing (lab reports and short essays), teamwork, critical analysis, programming and laboratory skills.
|Keywords||Robotics,Computer Vision,Image Processing,Artificial Intelligence
|Course organiser||Dr Chris Lu
|Course secretary||Mrs Michelle Bain
Tel: (0131 6)51 7607