Dr Massimiliano Di Luca

Supervisor Details

Contact Details

School of Psychology, University of Birmingham

Scientific Background

Research Interests

Dr Di Luca investigates the mechanisms of human perception using psychophysical methods and computational modelling. The goal of his research is to understand how the brain progressively builds the perception of the environment by picking up information through actions and by integrating sensations over time.

Scientific Inspiration

Leonardo Da Vinci because he combined art and scientific inquiry with an interdisciplinary approach.

Research Groups

Virtual Reality Lab

Augmented Reality Music Ensemble (ARME) Project

Supervision Style

In three words or phrases: Motivation, guided autonomy, inspiration.

Provision of Training

Your training will be supervised by both me, Mark Elliot, my experienced postdocs and RAs.

Progression Monitoring and Management

Because your project will be connected with a larger project, you will take part in a weekly meeting where you will be able to discuss the updates of your project with the other project members.

I prefer to have weekly 1:1 to provide each project member with advice and guidance and I’m happy to schedule ad-hoc meetings.

Communication

I am known to email at odd hours but I never expect a quick reply. The team has a WhatsApp group chat to ask urgent questions and to organise social events.

PhD Students can expect scheduled meetings with me:

In a group meeting

At least once a week

In year 1 of PhD study

At least once a week

In year 2 of PhD study

At least once a week

In year 3 of PhD study

At least once a week

These meetings will be a mixture of face to face or via video chat or telephone. I am usually contactable for an instant response 3 or 4 days per week.

Working Patterns

The timing of work in my lab is flexible, and other than attending pre-arranged meetings, I expect students to manage their own time.

Notice Period for Feedback

I need at least 1 week's notice to provide feedback on written work of up to 5000 words.

MIBTP Project Details

Primary supervisor for:

Predicting Motor Intent and Cognitive states in Virtual Reality using multimodal sensing and machine learning

See the PhD Opportunities section to see if this project is currently open for applications via MIBTP.

Please Note: The main page lists projects via BBSRC Research Theme(s) quoted and then relevant Topic(s).

Predicting Motor Intent and Cognitive states in Virtual Reality using multimodal sensing and machine learning

Secondary Supervisor(s): Dr Ulysses Bernadet

University of Registration: University of Birmingham

BBSRC Research Themes: Understanding the Rules of Life (Neuroscience and Behaviour)

Project Outline

Human computer interaction relies on understanding user intent and cognitive state to deliver personalised, adaptive experiences. With increasing access to multimodal data from head-mounted displays, mobile VR/AR devices, and physiological sensors, we can

predict user intent and cognitive states in real time.

This enables frameworks that adapt to individual thresholds, improving usability and engagement. Recent studies have modelled user intent using motion, EEG, EMG, and eye gaze data [1,2]. These studies provide insight into the efficacy of the modalities in

predicting upcoming actions and cognitive states. Furthermore, recent advances in machine learning (ML), including large language models (LLMs), open opportunities to interpret multimodal signals more effectively and enable personalised adaptations of VR environments in real time. The novelty of this project lies in determining which signals have the greatest impact, how early intent can be reliably predicted, and how these predictions can be used to dynamically adapt VR environments to optimise task performance and improve user engagement.

This project will develop ML models that integrate multimodal sensing data to predict both upcoming actions and mental states (e.g. attention, engagement, workload) during complex VR tasks such as virtual object manipulation, spatial navigation, and fine-motor control. You will also design or adapt immersive VR environments to collect the necessary multimodal data and evaluate prediction performance across different task contexts. As part of creating these environments, the project will quantify the contribution of each sensing modality and identify the optimal sensor set for task-specific prediction. Where existing sensors are insufficient, the work may also explore developing lightweight, task-specific sensing approaches to improve prediction accuracy or enhance user comfort.

[1] https://pubmed.ncbi.nlm.nih.gov/37624723

[2] https://www.mdpi.com/2079-9292/14/10/2052

APPLY HERE