Skip to main content

Research Repository

Advanced Search

Collaborative HRI and machine learning for constructing personalised physical exercise databases

Delgado Bellamy, Daniel M.; Caleb-Solly, Praminda

Authors

Praminda Caleb-Solly



Contributors

K Althoefer
Editor

J Konstantinova
Editor

K Zhang
Editor

Abstract

Recent demographics indicate that we have a growing population of older adults with increasingly complex care-related needs, and a shrinking care workforce with limited resources to support them. As a result, there are a large number of research initiatives investigating the potential of intelligent robots in a domestic environment to augment the support care-givers can provide and improve older adults’ well-being, particularly by motivating them in staying fit and healthy through exercise. In this paper, we propose a robot-based coaching system which encourages collaboration with the user to collect person-specific exercise-related movement data. The aim is to personalise the experience of exercise sessions and provide directed feedback to the user to help improve their performance. The way each individual user is likely to perform specific movements will be based on their personal ability and range of motion, and it is important for a coaching system to recognise the movements and map the feedback to the user accordingly. We show how a machine learning technique, a Nearest Neighbour classifier enhanced with a confidence metric, is used to build a personalised database of 3D skeletal tracking data. This approach, combined with collaborative Human-Robot Interaction to collect the data, could be used for robust and adaptable exercise performance tracking by a collaborative robot coach, using the information to provide personalised feedback.

Citation

Delgado Bellamy, D. M., & Caleb-Solly, P. (2019). Collaborative HRI and machine learning for constructing personalised physical exercise databases. In K. Althoefer, J. Konstantinova, & K. Zhang (Eds.), Towards Autonomous Robotic Systems (209-220). https://doi.org/10.1007/978-3-030-23807-0_18

Online Publication Date Jun 28, 2019
Publication Date 2019
Deposit Date Sep 28, 2021
Publisher Springer Verlag
Pages 209-220
Series Title Lecture Notes in Computer Science
Series ISSN 0302-9743
Book Title Towards Autonomous Robotic Systems
ISBN 9783030238063
DOI https://doi.org/10.1007/978-3-030-23807-0_18
Public URL https://uwe-repository.worktribe.com/output/7855512
Additional Information First Online: 28 June 2019; Conference Acronym: TAROS; Conference Name: Annual Conference Towards Autonomous Robotic Systems; Conference City: London; Conference Country: United Kingdom; Conference Year: 2019; Conference Start Date: 3 July 2019; Conference End Date: 5 July 2019; Conference Number: 20; Conference ID: taros2019; Conference URL: https://www.qmul.ac.uk/robotics/events/taros2019/