Robotics

Core modules:

Data Modelling and Machine Intelligence

All of our lives are affected by machine intelligence and data models - Google is a very visible example. But if you are a victim of identity theft, if you want a loan to buy a house or if you want to pass through immigration at an airport, a model derived from data using some form of machine learning technique will be involved.
Engineers increasingly look to machine intelligence techniques such as neural networks and other machine learning methods to solve problems that are not amenable to conventional analysis e.g. by application of Newton's and Kirchhoff's laws, and other physical principles. Instead they use measurements of system variables to compute a model of the process that can then be used in design, analysis and forecasting. System identification is a specific example of data modelling.
We will look at the underlying principles of machine learning, the advantages and limitations of the various approaches and effective ways of applying them with the aim of making you a competent practitioner.

15 credits

Foundations of Robotics

This is an introductory module on the foundations of robotics. The aim of this module is to consolidate fundamental robotics engineering aspects, including ethical ones, as well as introduce relevant topics to those new to the discipline. The module is separated into five distinct themes:
(a) Introduction to robotics and robot ethics
(b) Introductory maths
(c) Systems modelling and simulation
(d) Control systems analysis and design
(e) Introduction to programming

15 credits

Mechatronics for Robotics

This course focuses on the methods for developing and analysing mechanical, electrical, computational, and control systems, emphasising their integration into advanced mechatronic systems. It aims to equip students with the competencies necessary to design, analyse, fabricate, integrate, and evaluate complex mechatronic systems. The curriculum includes lectures that cover the essential principles of mechatronic systems, touching on areas such as Components, Integration, and Control: system fabrication, a variety of sensors and instrumentation, actuation methods, digital data acquisition, signal preprocessing, hardware interfacing, as well as programming for microcontrollers and their peripherals. Additionally, the module features practical sessions that focus on the real use of mechatronic components. A significant component of the course is a comprehensive project, where students engage in the development and refinement of a fully functional mechatronic system.

15 credits

Manipulator Robotics

The module aims to explore robotic manipulators, from theoretical concepts and modelling to practical implementations. You will be introduced to the different types and applications of robotic manipulators. An emphasis is placed on modelling and simulation. Sensing and actuation is also covered, with a focus on control of robot manipulators. You will be exposed to a wide range of practical applications of robotic manipulators, and encouraged to discuss and reflect on the implications of using robots (e.g. ethical considerations, safety, social and economic impacts), especially within manufacturing.

15 credits

Machine Vision

The module gives knowledge of machine vision methods for a broad range of applications. It introduces you to image and video processing models and methods and provides you with skills on how to embed them in autonomous systems. You will be able to apply the acquired knowledge to both industrial and research areas.

15 credits

Mobile Robotics and Autonomous Systems

Robotics and autonomous systems are having an increasing impact on society and the way we live. From advanced manufacturing and surgical robots to unmanned aerial systems and driverless cars, this exciting area is presenting increasing technological challenges. This module provides you with the advanced knowledge and understanding to apply control and systems engineering concepts to the closely related disciplines of robotics and autonomous systems. The module covers theoretical and technical analysis, and design aspects of mobile and manipulator robots with reference to their applications. The module further covers advanced techniques in autonomous decision making for robots and autonomous vehicles.

15 credits

Multisensor and Decision Systems

The ability to use data and information from multiple sources and make informed decisions based on that data is key to many applications, e.g. manufacturing, aerospace, robotics, finance and healthcare. Through effective use of multisensory data and decision making we can reduce uncertainty, improve robustness and reliability, enhance efficiency and ultimately improve the performance of systems. In this module you will develop an in depth knowledge and understanding of multisensor and decision systems and the underlying mathematics and algorithms. You will develop your confidence in solving complex problems requiring the application of multisensory and decision techniques to a wide variety of applications.

15 credits

Robotics Project and Dissertation

The aim of the project is to give you the opportunity to develop further your advanced knowledge and skills and apply these to a specific problem or set of problems. It builds on the taught modules and develops a greater level of independence. You will be allocated a project supervisor with whom you will develop the project specification and who will provide overall guidance on the project. However, you are expected to demonstrate a high level of initiative and independence. You will also develop skills in creative and critical thinking, analysis, reflection, effective project management and communication. The project is very different from many of your taught modules where the lecturer takes the lead in your learning. In the project, you are expected to take the lead and the supervisor is expected to provide overall guidance and help.

60 credits

Optional modules - examples include:

Deep Learning

An important field within artificial intelligence is machine learning, which enables systems to learn from data rather than being explicitly programmed to solve a task. Conventional machine learning algorithms tend to rely on a human to carefully engineer and extract features to present to a machine learning algorithm, which can be time-consuming and difficult. A deep learning system, by contrast, takes raw data as input and learns to extract features automatically. This approach has led to significant improvements in processing images, video, speech and audio. Deep learning has also had an impact on the design of intelligent agents, giving rise to the area of deep reinforcement learning, which is where an agent learns in a reward-based framework. An example of deep reinforcement learning is where the Google DeepMind team designed an agent that learned to play Atari computer games to better-than-human-expert level.

15 credits

Industrial Training Programme (ITP) in Computational Intelligence

This module will provide an insight into advanced computational intelligence systems via industry-relevant project work. This will be in collaboration with an industrial partner. The industrial partner will set a real technical challenge and your group will undertake practical and theoretical work and present a report that will also require an in-depth literature review. To supplement the main technical challenge there will be focused technical seminars on relevant topics. These topics will be provided by both academics and industry engineers. In addition, the industrial partner will provide seminars relevant to both professional and technical skills to help you complete the project.

15 credits