Understanding and predicting human movement is an important scientific endeavour with applications to rehabilitation, security/surveillance, smart environments, robotics, etc. Specifically, in Smart Environments (SE) and Human-Robot Interaction (HRI) models of human movement allow to anticipate human actions, therefore enabling predictive automation – e.g. in smart homes –, to detect irregular motion patters, and to adapt robot behaviour in view of a human’s intentions.
This project will develop a novel methodology for modelling human-like movement using advanced machine-learning techniques. Specifically, the work will focus on modelling human navigation in indoor environments, and object manipulation. The new methodology will make use of dynamical systems learning and non-linear systems identification as a comparative baseline. The models obtained will be tested in a smart environment setting to predict people’s behaviour and to detect deviation from normal movement.
The goal of this project is to develop, implement and test a novel methodology for the modelling and generation of human-like movement. The expected research outcome is a novel methodology to obtain movement models applied to human motion prediction and comparison in Smart Environments with applications to other areas like human-like motion generation in Robots.
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
As Senior Engineering Manager of Analytics at Seagate Technology I utilise the learning from my PhD ever day
Adrian Johnston - PhD in InformaticsWatch Video
Monday 19 February 2018
9 to 23 March 2018
When applying for this PhD opportunity please quote reference number: