Human Activity Analysis In Smart Environments

Lead Research Organisation: Aston University
Department Name: College of Engineering and Physical Sci

Abstract

"(AI)-Driven Virtual Training Buddy
Remote virtual fitness training has recently seen a massive boom. This trend is very
welcome not only because more people are engaging in physical activity, but also because
of the sustainability of remote training.
However, the interaction with coaches and training buddies still heavily relies on direct
human intervention limiting the affordability and customisability of the fitness training. With
recent developments in computer vision and natural language processing new tools such as
reliable markerless pose tracking and realistic language generation, the performance of the
trainee can be reliably tracked and realistic feedback can be given.
The proposed project is about the creation of an artificially intelligent, autonomous
virtual training buddy that has the ability to communicate verbally and non-verbally with the
user effectively as well as to demonstrate exercises to the user. The aim of the personalised
human-like agent is to increase training motivation and ultimately training adherence.The
virtual training buddy will establish initial rapport with the user, set goals and motivation in
pre-training, guide the user during the training session, and provide post-training feedback.
The investigation will be centred around what communication method and style
(verbally and non-verbally) is the most effective to maximise the users' intrinsic and extrinsic
training motivation. The applicability of artificial intelligence techniques including machine
learning and computational intelligence methods for the optimal intervention timing and
method will be studied. By establishing performance metrics for the set exercises, the agent
will try to estimate fatigue, and by adjusting rest times and exercise set length to keep the
trainee enged. Additionally, to achieve personalisation, we envisage building in mechanisms
for self-improvement of the autonomous virtual training buddy based on interactions with the
user. This project is in collaboration with the global, world-leading industrial partner"

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/T518128/1 01/10/2020 30/09/2025
2747358 Studentship EP/T518128/1 01/10/2022 31/03/2026 Gatis Jurkans