2024/25 Taught Postgraduate Module Catalogue

OCOM5205M Robotics

15 creditsClass Size: 100

Module manager: Dr Abdulrahman Altahhan
Email: a.altahhan@leeds.ac.uk

Taught: 1 Mar to 30 Apr View Timetable

Year running 2024/25

Pre-requisites

OCOM5100M

Programming for Data Science

This module is not approved as an Elective

Module summary

This module is designed to teach fundamental concepts of Reinforcement Learning and intelligent agents, focusing on robotic planning, and control.

Objectives

This module introduces the students to the principles of reinforcement learning and its application on intelligent robotics. It aims to give students an understanding of the concepts and techniques of reinforcement learning as a major paradigm of machine learning that is used successfully to allow a robot (physical and virtual) to learn or teach itself to perform a task. Applications go beyond traditional robotics tasks to the wider realms of intelligent agents and of deep reinforcement learning, including gaming (Atari, Alpha Go etc.) as well as covering traditional applications of robotic walking (robot learns to walk), navigation (e.g. a robot navigating from one position to another) and manipulation of objects (e.g. a robot moving its arm to reach an object). The module also aims to introduce students to the software tools used in modern reinforcement learning and robotics to develop resilient intelligent agents.

Learning outcomes
On completion of this module students should be able to:

1. Understand and use the fundamental concepts in modern robotics, including robot navigation and manipulation.
2. Understand and use the fundamental concepts of reinforcement learning techniques.
3. Understand and evaluate the challenges of training an intelligent agent.
4. Use and develop software to control intelligent agents.

Syllabus

Topics for this module may involve:

- Robotic planning and control through simulations
- RL framework for prediction and control
- Value function methods
- Applications on Games and other control of Intelligent Agents domains

Teaching methods

Delivery type	Number	Length hours	Student hours
On-line Learning	6	1.00	6.00
Group learning	6	2.00	12.00
Independent online learning hours			28.00
Private study hours			104.00
Total Contact hours			18.00
Total hours (100hr per 10 credits)			150.00

Private study

Private study will include directed reading and exercises and self-directed research in support of learning activities, as well as in preparation for assessments.

Independent online learning involves non-facilitated directed learning. Students will work through bespoke interactive learning resources and activities in the VLE.

Opportunities for Formative Feedback

Online learning materials will provide regular opportunity for students to check their understanding (for example through formative MCQs with automated feedback). Regular group activity embedded into learning will allow self and peer assessment providing opportunities for formative feedback from peers and tutors.

Methods of assessment

Coursework

Assessment type	Notes	% of formal assessment
Assignment	Online test (Programming and/or MCQ)	50.00
In-course Assessment	Project	50.00
Total percentage (Assessment Coursework)		100.00

This module will be reassessed by a project assessment that is similar to Assessment 2.

Reading list

The reading list is available from the Library website

Last updated: 26/04/2024

Disclaimer

Browse Other Catalogues

• Undergraduate module catalogue
• Taught Postgraduate module catalogue
• Undergraduate programme catalogue
• Taught Postgraduate programme catalogue

Errors, omissions, failed links etc should be notified to the Catalogue Team.PROD