Competition Funded PhD Project (Students Worldwide)
About the Project
A fully funded PhD opportunity to participate in the world-leading research undertaken by the EPSRC Doctoral Landscape Award at the University of Sheffield.
Supervised by Dr Zhixiang Chen.
The University of Sheffield is one of the leading Russell Group universities in the UK. We carry out cutting-edge research with strong links to industry. When you enrol to do a PhD with us, you will be working with world-leading academics and have access to top of the range facilities. As a PhD student you will have the opportunity to gain skills not only to conduct research, but also to take your career to the next level, whether you want to stay in academia, go into industry or the public sector, or set up your own company. You will have access to a range of training and support services to help you excel in your studies and beyond.
Project Description
Understanding how humans move is one of the most fascinating and important challenges in modern science and technology. From everyday activities like walking or lifting objects, to complex motions such as sports or rehabilitation exercises, our movements carry a wealth of information about health, intention, and interaction with the world around us. Being able to capture and interpret this information reliably can unlock breakthroughs in areas such as healthcare, physiotherapy, robotics, and human-computer interaction.
This PhD project will explore new ways of understanding human motion by combining two exciting areas of research: 3D human modelling and large-scale artificial intelligence systems known as “foundation models.”
The first step will be to create accurate 3D models of the human body in motion. These models capture not only the outward appearance of movement, but also its structure and dynamics — how different parts of the body are connected and interact. Unlike simple video recognition systems, 3D models can represent motion in a way that is more realistic and transferable across different people, tasks, and environments.
Building on this foundation, the second part of the project will develop methods that use these 3D models to guide advanced artificial intelligence systems in making sense of movement. Foundation models, such as those behind recent breakthroughs in image, text, and language understanding, have shown an extraordinary ability to generalise knowledge across tasks. Applying these models to human motion opens up the possibility of recognising subtle patterns, predicting future movements, and interpreting actions with far greater accuracy and flexibility than current approaches allow.
The third and most ambitious part of the project aims to move beyond simple recognition or classification of movement (for example, “this person is walking” or “this person is running”). Instead, the goal is to link human motion directly with natural language, enabling systems to generate descriptive explanations of what is happening in a given scenario. For instance, in a healthcare context, the system might describe a patient’s walking pattern and highlight signs of recovery or risk. In rehabilitation or sports, it could provide feedback on technique. More broadly, such systems could support safer human-robot collaboration in workplaces, or enhance accessibility technologies by translating motion into text or speech.
This project is highly novel because it brings together two rapidly advancing areas — 3D modelling of human motion and large foundation models — in a way that has not yet been fully explored. It is also timely: the demand for intelligent systems that can understand people’s actions and communicate them meaningfully is growing across sectors, especially healthcare, assisted living, and digital interaction. At the same time, the tools and data needed to make this vision a reality are now becoming available, creating a unique opportunity for innovation.
Students undertaking this project will gain expertise in computer vision, machine learning, and human-centred applications of artificial intelligence, while also developing skills in interdisciplinary research. The project is designed to be adaptable, offering the student opportunities to explore applications that match their interests, whether in healthcare, robotics, sports science, or beyond.
In summary, this PhD will push the boundaries of what is possible in human motion understanding. By creating systems that not only recognise movement but can also describe and explain it in meaningful ways, the project has the potential to deliver scientific advances and real-world impact, helping technology to better understand, support, and collaborate with people.
How to apply
Interested candidates are strongly encouraged to contact the project supervisors to discuss your interest in and suitability for the project prior to submitting your application.
Please refer to the EPSRC DLA webpage for detailed information about the EPSRC DLA and how to apply.
Applicants must ensure that they use the correct application form linked to the EPSRC DLA webpage and must submit an application for October 2027 entry. The form is unique to the EPSRC DLA. It contains the list of advertised projects from which to select, and three questions specific to the DLA.
The application deadline is 17:00 GMT 13 January 2027.
The majority of our DLA studentships will be allocated to candidates who qualify for Home fee status, in accordance with EPSRC funding regulations which place strict limits on international recruitment.
Funding Notes
The award will fund the full tuition fee and a maintenance stipend at the UKRI rate (currently £21,805 per annum) for 3.5 years, as well as a research grant to support costs associated with the project.
