A computational approach to gestural interactions of the upper limb on planar surfaces

Loriette, Antoine (2019) A computational approach to gestural interactions of the upper limb on planar surfaces. PhD thesis, University of Glasgow.

Abstract

There are many compelling reasons for proposing new gestural interactions: one might want to use a novel sensor that affords access to data that couldn’t be previously captured, or transpose a well-known task into a different unexplored scenario. After an initial design phase, the creation, optimisation or understanding of new interactions remains, however, a challenge. Models have been used to foresee interaction properties: Fitts’ law, for example, accurately predicts movement time in pointing and steering tasks. But what happens when no existing models apply?

The core assertion to this work is that a computational approach provides frameworks and associated tools that are needed to model such interactions. This is supported through three research projects, in which discriminative models are used to enable interactions, optimisation is included as an integral part of their design and reinforcement learning is used to explore motions users produce in such interactions.

• Item Type: Thesis (PhD)
• Qualification Level: Doctoral
• Keywords: computational interaction, gestures, modelling, gestural interaction.
• Subjects: T Technology > T Technology (General)
• Colleges/Schools: College of Science and Engineering > School of Computing Science
• Funder's Name: European Commission (EC)
• Supervisor's Name: Williamson, Dr. John and Murray-Smith, Pr. Roderick
• Date of Award: 2019
• Depositing User: m antoine loriette
• Unique ID: glathesis:2019-78981
• Copyright: Copyright of this thesis is held by the author.
• Date Deposited: 27 May 2020 05:31
• Last Modified: 01 Aug 2022 09:24
• Thesis DOI: 10.5525/gla.thesis.78981
• URI: https://theses.gla.ac.uk/id/eprint/78981