At the Centre for Artificial Intelligence and Machine Learning (CAIML), research focuses on advancing human–AI collaboration, particularly in complex environments that feature uncertainty. A key priority is developing intelligent systems that are transparent, trustworthy, and aligned with human thinking, drawing on insights from cognitive science and neuroscience.
CAIML explores areas such as machine reasoning, artificial empathy, and theory of mind in AI, helping systems better interpret and respond to human behaviour. This work underpins two core research themes:
Intelligent Sensing and Understanding
This theme focuses on how AI can interpret and make sense of complex, real-world data from multiple sources. Researchers develop advanced machine learning techniques to extract meaningful insights that support situational awareness and decision-making.
Intelligent Planning and Response
This theme explores how AI can support decision-making under uncertainty and enable coordinated action between humans and intelligent systems.
Key areas include:
Developing AI tools to model complex scenarios and optimise strategies across multi-domain operations. This includes simulating adversarial conditions, multi-agent interactions, and adaptive planning in contested environments.
Designing natural and effective ways for humans to interact with intelligent systems. Research includes language-based navigation, gesture-driven communication, and advanced robotic control in uncertain or constrained environments.
Using computer vision and deep learning to interpret visual data across applications such as medical imaging, remote sensing (including aerial, satellite, and underwater environments), and multimodal data integration (combining image, audio, and video).
Identifying unusual patterns or behaviours in dynamic environments. Applications include cyber security (network intrusion detection), maritime monitoring (vessel behaviour analysis), and human safety (driver impairment detection).
Together, these areas aim to create seamless, intuitive collaboration between humans and machines, enabling informed, timely responses in rapidly evolving situations.
Centre Members
Publications
Gebre, A. K., Mundt, M., Dent, E., Webster, J., Saleem, A., Gilani, S. Z., ... & Sim, M. (2026). Machine learning derived abdominal aortic calcification is associated with physical frailty in community-dwelling adults: the UK Biobank Imaging Study. GeroScience, 1-12.
Centre Members
Publications
OUTBACK: A multimodal synthetic dataset for rural Australian off-road robot navigation
Wijayathunga, L., Dabare, D., Rassau, A., Chai, D., & Islam, S. M. S. (2025). A High-fidelity Multimodal Synthetic Dataset Generation Framework for Off-road Unstructured Terrain Navigation Training of Autonomous Robots. Journal of Intelligent & Robotic Systems, 112(1), 10.
Centre Members
Publications
Asim, M. M., Smallwood, C. B., Tariq, A., Lo, J., & Gilani, S. Z. (2026). RampWatch: An in-the-wild dataset and text-guided detection framework for recreational vessels. In Proceedings of the 2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (pp. 7576-7585). IEEE. https://doi.org/10.1109/WACV61042.2026.00731
Centre Members
Publications
Semantic context improvisational retrieval-augmented generation for empathic conversational AI
Tahir, S., Abu-Khalaf, J., Johnson, J., Shah, A. (2026). Semantic Context Improvisational Retrieval-Augmented Generation for Empathic Conversational AI. Neural Computing and Applications, 1(Accepted/In press), 15.
CAIML researchers are developing new technology that could change how drunk and dangerous drivers are identified. Using a single 3D deep learning model, researchers are able to detect three major causes of road accidents simultaneously; blood alcohol concentration, fatigue and expression, such as anger. Read more.
Centre Members
Publications
Jack of Many Faces: A Step Towards Facial Expression and Physiological State Analysis with a Single Network
Centre Members
Publications
ConSel: Concept-Aware Self-Supervised Learning for Regression Beyond Ordinal Tasks
Tariq, A., Saleem, B., Azad, R., Masek, M., & Gilani, Z. (2026, June). ConSel: Concept-Aware Self-supervised Learning for Regression Beyond Ordinal Tasks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings.
