Research

ATLAS focuses on turning important psychological constructs into instruments and interventions that work in the real world. We develop and validate tools that do more than describe outcomes: they measure the mechanisms and processes that drive behaviour, learning, and adaptation. Using behavioural experiments, digital assessments, computational modelling, and AI-enabled methods, we study adult learning, decision-making, motivation, apathy, developmental screening, and reinforcement learning in ways that are scalable, interpretable, and useful in educational, clinical, and policy contexts.

Programmes

1. Metacognition & Adult Learning
   We develop technology-enhanced interventions to strengthen metacognition and self-regulated learning in adults, and evaluate them using converging measures including self-report, behavioural tasks, cognitive testing, and neuroimaging. Our goal is to understand not only whether adults learn, but how they plan, monitor, regulate, and improve their own learning over time.
2. Digital & AI-Enabled Learning Support
   We design and evaluate digital systems that provide more adaptive support for learners. This includes app-based micro-learning, reflective prompts, and AI-enabled pipelines that help interpret learner responses and generate more personalised scaffolds and feedback. Our aim is to use AI responsibly to improve learning support while maintaining interpretability, validity, and strong grounding in behavioural theory.
3. Digital Adult Learning Quality & Transfer
   We study how to define and measure “good” digital adult learning beyond crude indicators such as completion, attendance, or satisfaction. This includes work on quality benchmarking, learning transfer, user experience, inclusivity, and cost-effectiveness across different modes of adult learning delivery. Our goal is to generate more robust, comparable, and decision-relevant evidence for institutions, educators, and policymakers.
4. Developmental Digital Screening (ASD)
   We are developing caregiver-friendly, home-based digital tools for earlier identification of autism risk in children. These tools are designed to be accessible, scalable, and sensitive to meaningful developmental differences, and we validate them across autistic and typically developing cohorts.
5. Decision-Making, Motivation & Reinforcement Learning
   We use behavioural tasks and computational approaches to study the mechanisms underlying decision-making, apathy, motivation, and reinforcement learning. By developing and applying process-sensitive measures, we aim to identify how people evaluate effort, reward, uncertainty, and feedback, and how these mechanisms vary across individuals and clinical groups.