Aims and Fit of Module

In the field of robotics, computer vision models powered by deep neural networks are of utmost importance. These models enable robots to perceive and understand the world around them with greater precision and reliability.

The module aims to provide students with a solid understanding of deep neural networks in computer vision systems specifically tailored for robotics applications. By exploring advanced techniques such as convolutional neural networks, vision transformers, recurrent neural networks, and other cutting-edge approaches, students will gain the necessary knowledge and skills to design and develop advanced robotic systems capable of accurately perceiving the surrounding environment. The module also aims to meet the increasing demand for professionals with expertise in deep neural networks and computer vision systems within the robotics industry.

More specifically, this module shall enable students to:
• Demonstrate expertise in foundational computer vision principles and leading-edge techniques applied in robotics systems and automation.
• Examine deep learning architectures and algorithms for computer vision in robotic applications, gaining hands-on experience implementing and evaluating them.
• Investigate state-of-the-art computer vision methods and models, analysing their capabilities, limitations and potential to advance robotic perception and intelligence.

Learning outcomes

A Show familiarity with both the theoretical and practical aspects of computer vision.
B Demonstrate understanding of applying theoretical knowledge of deep learning computer vision systems to solve real-world problems.
C Critically evaluate deep learning models and algorithms for computer vision tasks by analyzing their underlying principles, strengths, limitations, and potential enhancements
D Develop proficiency in designing and implementing end-to-end deep learning solutions for computer vision through hands-on experience with data preprocessing, model architecture, training methodology, performance evaluation, and result validation.
E Understand recent advanced computer vision topics such as vision transformers, generative models, RNN in vision tasks and latent space amongst others
F Apply knowledge to real-world computer vision applications in robotics industries by gaining familiarity with common tasks and use cases and crafting solutions tailored to their needs.

Method of teaching and learning

The teaching philosophy of the module follows very much the philosophy of Syntegrative Education. This has meant that the teaching delivery pattern, which follows more intensive block teaching, allows more meaningful contribution from industry partners. This philosophy is carried through also in terms of assessment, with reduction on the use of exams and increase in coursework, especially problem-based assessments that are project focused. The delivery pattern provides space in the semester for students to concentrate on completing the assessments.

This module is delivered with a combination of delivery in lectures, laboratory exercise, tutorials and a seminar at the end of the delivery.

The concepts introduced during the lecture are illustrated using step-by-step analysis of practical training, complete case studies and live programming tutorials.

In the laboratory practice, students will have opportunities to solve a set of exercises during the laboratories under the supervision of the lecturer and the teaching assistant.

At the end of each week, there will be a tutorial to emphasize keynotes that have been discussed in lectures and laboratory practice during that week.

At the end of the delivery, there will be a seminar to review the whole module delivery.