Machine Learning for the next generation of paediatric wheelchairs

The project is supported by the University of Liverpool Doctoral Network in Future Digital Health, which is directed at creating and maintaining a community of AI health care professionals that can realise the benefits that AI can bring to Health Care. The vision is that of a world-class centre providing high-quality doctoral training within the domain of AI for Future Digital Health. Each available PhD project has been carefully co-created in collaboration with a health provider and/or a healthcare commercial interest so that the outcomes of the PhD research will be of immediate benefit. The network will be providing doctoral training, culminating in a PhD, in a collaborative environment that features, amongst other things, peer-to-peer and cohort-to-cohort based learning. On completion students will be well-placed to take up rewarding careers within the domain of AI and Digital Health.
Independent mobility is one primary signifier impacting multiple health outcomes in children [1,2]. Beyond core mobility-related health outcomes, the acquisition of gross motor milestones and independent mobility is important in ongoing emotional, psychosocial and cognitive development. Providing powered mobility (to those who lack it) improves cognitive and perceptual skills, reduce learned helplessness, increase confidence, and increase participation in everyday activities [3]. However, research on assistive paediatric mobility is still largely unexplored, and development of paediatric assistive mobility is hindered by three main factors: i) Scarcity of research in paediatric assistive area (mobility sector in specific); ii) Lack of holistic, convergent and innovative thinking within paediatric mobility services; iii) Slow pace of assistive market in adopting new and emerging technologies and design principles [4,5].

Paediatric powered wheelchairs have maximum potential for improving multiple health outcomes in children and for offering unlimited independent mobility. However, they are still often designed simply as smaller versions of adult wheelchairs, and do not take full advantage of modern design, manufacturing, control and software technologies. As a result, the use base for such wheelchairs (in terms of age, disability, etc.) is not as broad as it could be, and training is often based on personal experience of the users, carers and clinicians.

This PhD will tackle these problems using advanced sensing and machine learning, with the final goal of contributing to the next generation of paediatric assistive mobility. Two intertwined research questions motivate the project: i) what sensor and data are needed to enable active assistance in paediatric powered wheelchairs? ii) what sensors and data will enable a deeper understanding of the children’s learning process, to provide better guidance to future users?

Answering the first question will involve mechatronic design and machine learning to implement sensor-driven functionalities such as obstacle avoidance, assisted driving and active safety (e.g. emergency stop in presence of dangers). The aim is to lower the barrier of adoption of powered wheelchairs, making them accessible to children at a younger age and/or having a broader spectrum of disabilities. Some research in the area is available [6], but only for adults. The answer to the second question will involve again mechatronic/sensing design and machine learning to map inputs such as obstacles around a child to outputs represented by the choice of action of the child driving the wheelchair. Techniques such as CNN, RNN and Bayesian inference [7,8] will be used to create such mapping. Understanding this mapping, and its evolution as a child gets better at driving the wheelchair, will contribute to a better understanding of the users learning process that, in turn, will enable the creation of better training guidelines for the future users of these devices.

Initial prototypes and algorithms will be developed in collaboration between the @LERT robotic lab in Engineering (Paoletti, Nickpour) and the smartLab in Computer Science (Luo). Realistic training data for machine learning algorithms will be obtained by instrumenting existing wheelchairs and engaging with the Alder Hey’s wheelchair users’ group. Final validation will be performed in the Home Simulator at Alder Hey. The UoL team has strong links with designers and manufacturers of paediatric powered wheelchairs, including MERU, Designability and DragonMobilty. This PhD project will feed into and benefit from this unique network, and therefore it has the potential for a major, and much wider, impact in the provision of powered wheelchairs in the UK.

To apply, please visit https://www.liverpool.ac.uk/study/postgraduate-research/how-to-apply/