SWAGºÏ¼¯

Robotics technologies are being increasingly adopted across various industries, these include automotive, oil and gas, aerospace and energy as well as potential significant future growth in the service robot domain. The aim of this module is to introduce students to different types of robots and their practical uses. Students will experience offline programming of industrial robot as well as hands on programming during a study tour on the last day of the module.

• Introduction to Robotics and history of robots
• Classification of robotic systems
• Industrial Robots
• Basic control of robots
• Robot sensing
• Robotic applications
• Offline programming of industrial robot
• Practical robot programming

On successful completion of this module you should be able to:

1. Distinguish different types of robots across different domains, appraise their characteristics and examine their common applications.
2. Examine critical components of different robot systems and critique the functionalities and performance of different configurations.
3. Distinguish industrial robot programming methods and techniques, and construct robot procedures for automated operations.
4. Demonstrate a systematic approach in constructing an offline programme using professional robot simulation software package.
5. Develop an industrial robot programme and integrate onto a real robot to perform simple tasks.

This module aims to provide students with the fundamental knowledge for solving robot control problems that will be applicable in the design of robot control systems. The syllabus covers control theories that are essential for the control of robot manipulators as well as mobile robots.

On successful completion of this module you should be able to:

1. Examine a given control problem and appraise the suitability of a control system as a solution
2. Construct Forward Kinematic and Inverse Kinematic solutions for a Multi Degree of Freedom Robots
3. Design a feedback control system for solving a real world situation
4. Construct the path and motion planning of a robot manipulator for solving a practical task

The aim of this module is to provide students with the necessary knowledge and understanding for the application of machine learning & artificial intelligence techniques to real world industrial problems within the domain of robotics and beyond.

• Introduction to Machine Learning Theory Applications.
• Decision tree modelling, logical reasoning.
• Probability theory and Bayesian methods.
• Classification methods and clustering techniques.
• Bio-inspired artificial intelligence algorithms.
• Reinforcement learning.
• Case study for robotics applications.

On successful completion of this module a student should be able to:

1. Construct a wide range of machine learning techniques to solve industry problems particularly within the domain of robotics.
2. Appraise the application of machine learning approaches to a wider set of data mining and classification type problems.
3. Using a provided implementation, plan machine learning analysis on suitable forms of computer and robotics data.
4. Examine the concepts and operation of a range of machine learning algorithms in order to facilitate re-implementation in a software programming environment with which they are already familiar
5. Develop programme in solving machine learning problems through interactive learning workshops.
   
   
   

This module aims to answer the question ‘what is object oriented programming (OOP)’ and to provide the students with the understanding and skills necessary to write well designed and robust OO programs in C++. Students will learn how to write C++ code, starting from fundamental programming aspects and progressing through to advanced OOP. Hands-on programming sessions form an essential part of the module.

• Programming concepts and their implementation
• The OOP methodology, classes, abstraction and encapsulation.
• Destructors and memory management.
• Stream input and output.
• Function and operator overloading.
• Inheritance and aggregation.
• Polymorphism and virtual functions.
• Templates, Exception handling.
• The C++ Standard Library and STL.

As robots and robotic devices are increasingly becoming part of our day-to-day lives it is vital that we know how to effectively integrate them with people new advanced systems. This module explores the changing landscape of robotics in society and how we comply with evolving demands and perspectives of ethics and safety standards. With a focus on fundamental human factors and psychological principles we examine how to optimise the integration of people with different types of robotic systems and environments. Students will be given the opportunity to apply practical human analysis tools and techniques that complement traditional engineering approaches to enhance usability and performance in the design of safe human-robot interaction.

Fundamental psychology: exploring basic principles of human cognition, how we process the many types of information we encounter and make sense of it all, to understand how people interpret and respond to situations with robot systems.

Human performance and error: applying knowledge of the key factors that shape human performance, decision-making and situation awareness, the typical sources of error, and practical methods of analysis and classification, to the design of human-robot systems.

Social cognition and behaviour: understanding how aspects of a person’s surrounding culture and social environment can impact on their attitudes and behaviours towards robots, and on distributed cognition across ‘hybrid’ multi-agent systems.

HCI and user-centred design: evaluating fundamental principles and methods for the design of human-system interfaces, displays and controls, to optimise both the functional and emotional impacts of human-robot interactions. 

Safety standards and ethics: appraising current formal standards and legal requirements for human-robot design in relation to the evolving landscape of robotics in society, with particular focus on ethical implications and emerging issues

The aim of this module is to introduce you to human-robot interaction design and technology, and their applications. You will learn about natural user interface and its applications in interaction. There will be opportunities to experience and practice hands-on programming of industrial collaborative robots to carry out basis tasks.

• Introduction to Human-Robot Interaction
• Human-Robot Interactive Systems
• Interaction Design/ Collaboration and teamwork
• Natural User Interface
• Natural Language User Interface
• Safe Human-Robot Interaction
• Robot programming for collaborative tasks

On successful completion of this module a student should be able to:

1. Examine different types of HRI system and appraise fundamental HRI theory and principles in HRI systems design.
2. Differentiate different types of human-robot interface, distinguish their functionalities and investigate novel applications.
3. Implement HRI and safety principles to develop a safe HRI system that complies to current robot standards.
4. Appraise and implement intuitive user interfaces in enhancing the efficiency and seamlessness of the interaction between humans and robots.
5. Design and construct a robot programme for carrying out human-robot collaborative tasks

The most powerful method of sensing available to humans is vision. In computing and robotics visual information is represented as a digital image. In order to process visual information in computer systems we need to know about processing digital images. By processing visual information we can develop automated visual interpretation and understanding – artificial vision, itself a large part of wider field of the Artificial Intelligence. In order to achieve this we must be able to extract high-level visual information such as edges and regions from images and additionally allow for the efficient storage of large amounts of visual data which can then be used in robotics applications.

• Image Applications
• Image Representation
• Image Capture Hardware
• Image Sampling & Noise
• Image Geometry & Locality, Processing Operations Upon Images
• Camera Projection / Convolution Model
• Image Transformation
• Image Enhancement
• Stereo Vision and Object Tracking
• Case SWAGºÏ¼¯: Vision Based Metrology in Robotics

On successful completion of this module you should be able to:

1. Appraise the applications of common digital image representations techniques in solving Machine Vision problems.
2. Demonstrate a systematic application of Local and Global Image Transformations, and Basic Image Feature extraction for image processing.
3. Construct computer programme for implementing Image processing in Frequency domain.
4. Construct computer programme for implementing counter noise in digital images.
5. Analyse and appraise the robotics applications of three dimensional Stereo vision based systems and Object Tracking.

The aim of this module is to introduce the students to the algorithms suitable for real life problems concerning autonomy in robotics: path planning, task allocation, robotic perception, mapping and navigation, cooperative robotics, including accuracy assessment and uncertainty reduction for these applications.

• Introduction to autonomy aspects (1 hour)
• Sensing technologies, perception and estimation (6 hours)
• Practical session on estimation and filtering (3 hours)
• SLAM (4 hours)
• Practical session on SLAM (3 hours)
• Autonomy in Robotics: path planning and following (4 hours)
• Practical session on path planning and following (3 hours)
• Multi-agent task allocation (3 hours)
• Case study: Space Robotics applications (2 hours)

On successful completion of this module you should be able to:

1) Examine fundamental meaning and appraise the applicability of AI methods for robotics with multiple degrees of autonomy.
2) Examine commonly used AI algorithms and develop solutions to practical examples in context of the autonomous robotics.
3) Appraise suitable methods for autonomy in common robotics applications and analyse their performance in real-life scenarios.
4) Develop and enhance the level of autonomy in robotic systems through implementation of AI algorithms, and critique the performance of the algorithm in a simulated environment.