Members of IPAB.
|Robot Learning for Decision Making under Uncertainty, Dexterous Manipulation and Control, Human-Robot Interaction, Physics-informed Machine Learning, Safe and Trustworthy Artificial Intelligence
|Stefano V. Albrecht
|Robust sequential decision making by autonomous agents in complex dynamic environments. Deep reinforcement learning, multi-agent reinforcement learning, models of other agents (beliefs, goals, plans) in interactive decision making.
|Computer vision, machine learning, deep learning, weakly supervised learning, multiple task learning, object recognition, action classification
|Model-based vision, 3D/range data interpretation and applications, video sequence analysis
|Neurorobotics, self-organisation of behaviour, prosthetic control, computational neuroscience, neuroinformatics
|Computer vision. Deep learning. Lifelong machine learning. Transfer and multi-task learning. Learning to Learn. Domain adaptation. Language and vision. Reinforcement Learning for control. Active Learning. Weakly supervised learning
|Statistical simulation and testing. Temporal logics for Cyber-Physical Systems. Neuro-Symbolic Learning for Robotics. Risk-Driven Design for Black-Box Models.
Medical Robotics, Image-guided Surgery, Continuum Robots, Dynamic Modeling and Simulation, Applications of Control Theory in Robotics
|Computer graphics, robotics and biomechanics: human motion analysis and synthesis, physically-based animation and real-time computer graphics.
|Computer Graphics, 3D Vision and Medical Image Processing: 3D Shape Creation and Analysis with applications in Sketch-based Modeling, Shape Reconstruction and Analysis from Point Clouds, and Medical Image Processing and Modeling.
|Zhibin (Alex) Li
Control of complex behaviors for robots, eg humanoids, to achieve human-comparable ability to move and manipulate through control theories, optimization and machine learning.
|Chris Xiaoxuan Lu
|Mobile Robotics. Mixed Reality. Spatial AI under Low-visibility. Fog Robotics and Edge IoT. Human-robot Collaboration. Secure and Privacy-aware Autonomous Systems
Dexterous motion, dynamics modelling, and control of physical interaction, for humans and robotic systems.
Computer Vision, Motion Estimation, Temporal Modeling, Object Segmentation, Object Tracking, Deep Learning, Unsupervised Learning
|Knowledge representation and reasoning, cognitive systems, and interactive learning in the context of human-robot and human-agent collaboration.
|Graphics, Stochastic sampling, signal processing and image manipulation
Humanoid/legged robotics; computer graphics; Motion planning; Optimal control
|Geometry processing, computer graphics, directional field processing, meshing, reconstruction in medical imaging, discrete differential geometry
|Statistical Machine Learning for Robotics; Planning, Optimisation and Adaptive Control for Anthropomorphic (Humanoid) Platforms; Computational Motor Control; Rehabilitation Robotics
|Perceptual systems for the control of behaviour, robot models of animals, simulation of neural circuits
|Robot learning and control, specifically in the development of probabilistic machine learning and computer vision tools for robotics applications
Associate Academic Staff
|Mobile robot programming languages
|Computational semantics, particularly discourse, conversation and gestures; learning strategies in complex games; learning to adapt to unforeseen possibilities
|Oisin Mac Aodha
Machine Learning, Computer Vision, and Computer-Assisted Teaching
|Neural Systems and Rehabilitation Engineering, Machine Learning for Health
|Planning and activity management, Human-robot collaboration, Emergency response, search and rescue
|Machine learning and computer vision
|Construction of networks of neurons and the computations performed by them
Safe and Compliant Human-Robot Interaction/Cooperation/Collaboration, Robot Manipulation, Tele-cooperation (Tele-(operation/manipulation) + Human-Robot Cooperation)
|Perception for robotic manipulation, robot learning, state estimation.
|Pak Yin Chan
|Human-computer Interaction, Egocentric Vision, Pattern Recognition, Statistical Learning
Bio-inspired artificial intelligence,Computational neuroethology, Computational modelling, Learning and memory, Insect-inspired navigation
|Florent Le Moel
|Mohammad Mohades Kasaei
|Efficient machine learning for robotics including deep reinforcement learning and computer vision.
|Joao Pousa de Moura
|Prediction and planning, simulation and testing, safety verification and validation, autonomous vehicles
PhD Research Students
|Institute Administrative Assistant
|Business Development Executive
|3D vision, statistical modelling of visual data, dynamic models
|Agent architectures and action selection for real and virtual robots
|Head of School of Informatics
|Biorobotics, especially sensory biorobotic systems; user modelling in computer games; computational neuroscience and machine learning
Computer Vision for Robotics