MSc Robotics / Course details

This unit will give students a foundation in Cognitive Robotics and Computer Vision and introduce the essential concepts, algorithmic tools, and key applications in both areas.

Programming skills and knowledge of basic linear algebra and statistics.

The unit aims to introduce the essential concepts, algorithmic tools and key applications of cognitive robotics and computer vision. This involves exploring the challenges of building practical applications in these areas and discussing novel approaches to designing vision systems and robots that learn. The unit also aims to encourage the development of the necessary technical and critical skills for evaluating state-of-the-art algorithms in research publications in these areas.

1. Understand common cognitive robotics and machine vision algorithms.

2. Explain the design of vision algorithms.

3. Describe properties of image data and be able to solve problems about extraction of features and other quantitative information.
 

4. Evaluate algorithms for the purposes of understanding research publications in robotics and computer vision.

5. Design basic systems for image analysis and cognitive robotics, and evaluate and justify their design.

6. Write a program for the analysis of image and robotics data.

7. Prepare a technical report on the evaluation of this program on suitable test data.

8. Critically assess technologies and analyse their suitability for specific application scenarios.

Topics covered in the unit include: an introduction to cognitive robotics; developmental, evolutionary and swarm robotics; human-robot interaction and social robots; language and speech interfaces; deep learning; image processing and local features; visual object recognition and tracking; vision-based robot localisation and navigation; segmentation, face detection and model-based vision; motion generation using learnt computational models of human motion.

1. Weekly interactive lectures and tutorials (synchronous) providing opportunities for discussion and questions.

2. Supervised weekly labs (computer vision and machine learning software labs and robot demos). These will also provide opportunities for discussion and questions, and support for coursework and formative exercises.

3. Asynchronous teaching material in the form of video lectures, formative exercises, lecture slides and code examples delivered via the virtual learning environment.

1. Individual feedback will be provided via the virtual learning environment (VLE) when marks are returned.

2. Guidance and feedback will be provided during supervised weekly labs (synchronous).

3. VLE discussion board to provide guidance and feedback (asynchronous).

1. David A. Forsyth and Jean Ponce, Computer Vision: A Modern Approach, Pearson, 2012.

2. Richard Szelinski, Computer Vision: Algorithms and Applications, Springer, 2023.

3. R. Hartley, and A. Zisserman: Multiple View Geometry in Computer Vision, CUP, 2004.

4. A. Cangelosi and M. Asada, Cognitive Robotics, MIT Press, 2022

Additional info on Assessment:

Written assignment (50%) refers to written assignment and practical skills assessment (coding)

 

Additional info on Independent study hours:

Coursework and written assessment (minimum 25 hours)

Videos / Formative Exercises (20 hours)

 

Additional info on enrolling onto the unit:

Please contact the unit lead to get permission to do the unit if you are not a Comp Sci student/ unable to enrol onto the unit.