PhD in Computing Science - Extending self-calibrating interfaces to direct control tasks

   College of Science and Engineering

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Dr Jonathan Grizou, Dr J Williamson  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

This project will build on and combine previous work from the two supervisors under one applied demonstrator. In the process, you will learn, develop, and study new algorithmic technics worthy of publication in top international machine learning conferences such as NeurIPS or ICML.

Your challenge will be to develop a calibration-free EMG controller (using muscle signals recorded on the forearm of a user) to control a series of simple games. To do so, you will build on work from "Rewarding the Original" [1] to establish a set of motions and their respective embeddings representation suitable for use with sensor systems. This will be used to infer possible controllers to apply self-calibrating principles [2, 3, 4] to continuous scenarios by implementing novel principles of visual superposition.

This project will involve:

1.      Developing and implementing models to extract control manifolds in a sensor embedding space.

2.      Designing and implementing mechanisms for visual superposition of candidate controllers in a series of continuous scenarios.

3.      Evaluating the performance and efficacy of the resulting systems through empirical trials.

The PhD will thus involve a mix of development of novel machine learning technics, their implementation to a functional demonstrator, and experimental work with human subjects.

The successful candidate will have a strong background in machine learning with an interest for interactive learning as well as a desire to learn principles from human-computer interaction and user modelling. Strong software development skills are essential for this studentship. 

The PhD will be supervised by Dr. Jonathan Grizou and Dr. John H. Williamson at the University of Glasgow. We encourage candidates to contact Dr. Jonathan Grizou in advance of submitting for informal discussion.

Please refer to the following website for details on how to apply.

Please email the PhD supervisor Dr. Jonathan Grizou to confirm that you have submitted your application.

[1] Williamson, John, and Roderick Murray-Smith. "Rewarding the original: explorations in joint user-sensor motion spaces." Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 2012.

[2] Grizou, J., Iturrate, I., Montesano, L., Oudeyer, P. Y., & Lopes, M. (2014, June). Calibration-free BCI based control. In Proceedings of the AAAI Conference on Artificial Intelligence. 

[3] ] Iturrate, I., Grizou, J., Omedes, J., Oudeyer, P. Y., Lopes, M., & Montesano, L. (2015). Exploiting task constraints for self-calibrated brain-machine interface control using error-related potentials. PloS one, 10(7), e0131491.

[4] Grizou, J. (2022). Interactive introduction to self-calibrating interfaces. arXiv preprint arXiv:2212.05766.

Computer Science (8) Mathematics (25)

Funding Notes

The School of Computing Science is offering studentships to support tuition fees at the home level and living expenses at the recommended UKRI rate with an annual stipend (£18,622 per annum in session 2023/24).