Postgraduate Course: Intelligent Autonomous Robotics (Level 11) (INFR11070)
||School of Informatics
||College of Science and Engineering
||Not available to visiting students
|Credit level (Normal year taken)
||SCQF Level 11 (Postgraduate)
|Home subject area
||Other subject area
||Taught in Gaelic?
||The aims of this course are to introduce the fundamental problems of producing real world intelligent behaviour in robots, some of the different kinds of information processing techniques and control architectures that have been developed, and how biological systems can be modelled on robots and contribute to their design.
The course is structured around a practical-based programme involving the construction of a series of small mobile LEGO vehicles of increasing sensorimotor sophistication. We will cover related sensing and control ideas, approaches, and organisational architectures. We consider some alternative types of mechanism suggested for the production of desired intelligent behaviour by both engineers (simple control theory) and biologists (e.g. muscle control, biomimetic robotics, learning).
|| It is RECOMMENDED that students have passed
Introduction to Vision and Robotics (INFR09019)
|| It is RECOMMENDED that students also take
Advanced Vision (Level 10) (INFR10001) OR
|| Students MUST NOT also be taking
Intelligent Autonomous Robotics (Level 10) (INFR10005)
|| For Informatics PG and final year MInf students only, or by special permission of the School. A good grounding in mathematics and some knowledge of first-order differential equations are essential. In addition, hands-on experience of working with small mechanical parts, computer assembly and skills such as using LEGO kits and Mindstorm kits would be useful.
This course may be taken as a co-requisite for MSc students on the Intelligent Robotics theme, they will be taking at least one of Advanced Vision (Level 10) and/or Machine Learning & Sensorimotor Control.
Course Delivery Information
|Delivery period: 2011/12 Semester 1, Not available to visiting students (SS1)
||WebCT enabled: No
|No Classes have been defined for this Course|
||First class information not currently available|
|Main Exam Diet S2 (April/May)||2:00|
Summary of Intended Learning Outcomes
|1 - Knowledge of robot control architectures and sensors, understanding of the issues involved in programming real robots as opposed to simulators.
2 - Familiarity with current approaches to robotics, including reactive, subsumption, cybernetic, classical planning and evolutionary and multirobot approaches.
3 - Familiarity with current literature on state-of-the-art in mobile robot planning and navigation (with the expectation of being tested in exam conditions)
4 - Understanding the main issues and methods in mobile robot navigation.
5 - Understand how to model and evaluate models of biological systems on robots.
6 - Build and program a robot to do specified tasks, dealing with sensing and acting in the real world, achieve a set of milestones defined on a weekly timetable, evaluate the results and present the work in a written report.
7 - Presentation of your work to a group, working in a small group.
|Written Examination 50
Assessed Assignments 50
Oral Presentations 0
One assignment, carried out in groups of 2 or 3, account for 22% of the course marks. This requires you to build and program a robot using the kits, electronics, sensors and programming environments provided and to present the results in a written report. The other 8% of the marks will be assigned to completion of a set of weekly timetabled sub-goals, which will have a mini-report component and a rigorous evaluation criterion for each milestone. In addition, a literature reading list will be setup which will contain examinable material for the final exam.
||* The problem of designing intelligent autonomous systems.
* Building and programming LEGO Vehicles.
* Reactive control of behavior.
* The subsumption architecture.
* Fundamentals of control: first order and second order.
* Sensor Integration.
* Evolutionary and collective robotics.
* Robots as biological models.
* Simple navigation: gradient following, potential fields, landmarks.
* Navigation with maps: localization and learning maps.
Relevant QAA Computing Curriculum Sections: Artificial Intelligence, Intelligent Information Systems Technologies
||* Valentino Braitenberg: Vehicles. MIT Press 1984
* Ronald C Arkin: Behavior-based Robotics, MIT press, 1998
* Robin R. Murphy, Introduction to AI Robotics, MIT Press 2000
* Roland Siegwart and Illah R. Nourbakhsh, Introduction to Autonomous Mobile Robots, MIT Press 2004
Timetabled Laboratories 10
Non-timetabled assessed assignments 40
Private Study/Other 30
||Dr Michael Rovatsos
Tel: (0131 6)51 3263
||Miss Kate Weston
Tel: (0131 6)50 2701
copyright 2011 The University of Edinburgh -
3 April 2011 11:21 am