This scholarship is to support the Horizon Europe project PRIMI: Performance in Human Robot Interaction via Mental Imagery, led by Professor Alessandro Di Nuovo (scientific coordinator). The project
aims to create the next-gen humanoid robots with efficient computation, high cognition, and autonomy, by synergistically combining interdisciplinary research development in neurophysiology, psychology, machine intelligence, cognitive mechatronics, neuromorphic
engineering, and humanoid robotics. The PRIMI project seeks to create more capable interactive robots with advanced abilities, able to provide innovative and personalised services. Prototypes will be used in stroke rehabilitation studies.
You will join the Smart Interactive Technologies (SIT) research laboratory; a vibrant interdisciplinary group, led by Prof. Alessandro Di Nuovo, that conducts world-leading research on Artificial
Intelligence and Robotics. The group is currently running several research projects worth over £2.5 million funding from the European Commission and UKRI.
This PhD project will focus on machine intelligence techniques and neuromorphic computing technologies to create active inference models for interactive learning in robots with human-like performance.
Background
Humans can learn faster with less data by reducing surprise or uncertainty by making predictions based on internal models. Indeed, neurophysiology and developmental psychology increasingly highlight
the embodied nature of intelligence, which is shaped the experiences acquired through the body, such as manipulatives, gestures, and movements.
To overcome the current limitations, the research methodology will adopt the developmental neuromorphic approach with cognitive agents that are embodied in humanoid robotic platforms. Developmental
robotics fundamentally differs from traditional machine learning as it targets task-independent self-determined learning via interaction with the environment rather than task-specific inference over selected, human-edited sensory data. It also differs from
traditional cognitive robotics because it focuses on the processes that allow the formation of cognitive capabilities rather than these capabilities themselves. Neuromorphic computing investigates large-scale processing systems that support natural neuronal
computations through spike-driven communication to imitate the efficient neuro-synaptic framework of the physical brain. Compared to traditional approaches, key advantages of neuromorphic computing are energy efficiency, execution speed and robustness against
local failures.
Eligibility
Candidates should have (or expect to obtain before the start of the PhD) a minimum of an upper second-class honours degree (2.1) or equivalent in Computer Science, Neuroscience, or a closely related
subject.
To be eligible for a waiver of the international fees, candidates should have a strong Master’s degree and/or scientific publications on the subject of the research project.
For further details on entry requirements, please click here
How to apply
All applications must be submitted using the online
application form. To apply, click here.
We strongly recommend you contact the lead academic, Prof. Alessandro Di Nuovo, a.dinuovo@shu.ac.uk, to discuss your application.
Start date for studentship: February 2024
Interviews are scheduled for: TBC