The research aim is to create novel artificial intelligence technologies that allow robots to coexist harmoniously with the environment and socially interact with human beings, empowering these individuals, not replacing them.
The research is carried out by the Smart Interactive Technology (SIT) group led by Dr Alessandro Di Nuovo. The group focuses on two main research and innovation streams:
- Neuro-Developmental Robotics - an area of research on how machines can learn by simulating child-like brains that can be embodied into humanoid robots and then educated and develop their cognitive skills like children.
- Socially Assistive Robotics - an area of societal impact of artificial intelligence and robotics that aims at supporting healthcare and social workers in the care of the children, the elderly and the disabled.
Our foundational research in Neuro-Developmental Robotics aims at providing the methodological basis and cognitively plausible engineering principles for the next generation of intelligent robots, mimicking advanced capabilities of the human intelligence for real understanding and interaction with the external world.
The ambition is to create an open-ended artificial mind for robots that can grow up like a child - autonomously learning and developing new skills via multimodal interaction with humans and the environment. This will enable a globally desired paradigm shift in AI and robotics: from performing narrowly pre-defined tasks to autonomous mental development.
To this end, our EPSRC ALDENS project is pioneering an innovative cross-disciplinary approach to generate models of interactive robots with real-time developmental human-like learning made possible by efficient brain-like (neuromorphic) computing, which will go above and beyond what is currently possible with the mainstream deep-learning approach. The ALDENS project will establish the new developmental neuromorphic paradigm, a synergic combination that will go beyond the limitations of the individual paradigms: developmental robotics will deliver the missing learning mechanisms for neuromorphic spiking neural networks; meanwhile, neuromorphic computing will provide efficient brain-like resources with an accurate representation of the real world.
The EPSRC NUMBERS (2017-2020) project delivered the first step toward the vision of robots that lean like children by creating a developmental neurorobotics model of number understanding. The research evidenced similarities between children and robotic embodiment in the early development of numerical cognition (Di Nuovo & McClelland, Nature Machine Intelligence, 2019).
The modelling of numerical abilities in artificial cognitive systems can help to confirm existing child development hypotheses and define new ones through computational simulations. New research will help to discover innovative principles for the design of artificial agents with advanced reasoning capabilities and clarify the underlying algorithms (e.g., deep learning) that can be highly effective but difficult to understand for humans.
This area of research counts prestigious national (Prof. Cangelosi, University of Manchester) and international partners from the USA (Prof. McClelland, Stanford University).
Socially Assistive Robotics
We actively collaborate with the Advanced Wellbeing Research Centre on development and application of new and emerging technologies to help people move, improving health and wellbeing across the population.
Examples of our research projects on this topic are:
The EPSRC project I'M ACTIVE - Intelligent Multimodal Assessment and Coaching Through Identification of Vulnerabilities in Older People. Research in machine intelligence and healthcare sensor technologies will be guided by stakeholders and users to create a user-friendly platform specifically designed to offer assistance to older adults at risk of frailty. The platform will be tailored to older adults needs to overcome the cognitive and physical barriers to increase acceptability and use of these new technologies among this population.
The EPSRC NetworkPlus EMERGENCE: Healthcare Robots from Labs into Service. The network will facilitate innovative digital solutions for the care of older people via the creation of a sustainable healthcare robotics eco-system. The network connects and create synergies among researchers, industry, and healthcare providers, in order to build the infrastructure and systems to drive world-class advances in healthcare robotics research and development to support people living with frailty within communities in the UK.
The H2020 MSCA-IF CARER-AID that created an intelligent robotic assistant to support caregivers in early diagnosis and treatment of individuals with autism spectrum disorder associated with intellectual disability. The project successfully demonstrated the integration of the robotic assistant in the daily therapy of children. The research is now being applied to support children with autism in Sheffield in collaboration with the Sheffield Children's Hospital.
We created a prototype of a robot-led psychometric Cognitive Assessment Through Human-robot Interaction (CATHI) system that has won the IBM support via SUR Awards and a best application paper award.
Currently, we are a beneficiary of the H2020 MSCA-ITN European Training Network on PErsonalized Robotics as SErvice Oriented applications (PERSEO, 2021-2024), a multidisciplinary project that received a 4 million grant from the European Union to train a cohort of 15 outstanding doctoral candidates to be the new generation of interdisciplinary researchers and professionals for the forthcoming market of personal robots.