English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  In Silico User Testing for Mid-Air Interactions with Deep Reinforcement Learning

Cheema, N. (2019). In Silico User Testing for Mid-Air Interactions with Deep Reinforcement Learning. Master Thesis, Universität des Saarlandes, Saarbrücken.

Item is

Files

show Files
hide Files
:
2019 MSc Thesis Noshaba Cheema - Computer Science.pdf (Any fulltext), 1005KB
 
File Permalink:
-
Name:
2019 MSc Thesis Noshaba Cheema - Computer Science.pdf
Description:
-
Visibility:
Restricted (Max Planck Institute for Informatics, MSIN; )
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Cheema, Noshaba1, Author
Slusallek, Philipp2, Advisor
Hämäläinen, Perttu2, Referee
Lehtinen, Jaakko2, Referee
Slusallek, Philipp2, Referee
Hämäläinen, Perttu2, Referee
Affiliations:
1International Max Planck Research School, MPI for Informatics, Max Planck Society, Campus E1 4, 66123 Saarbrücken, DE, ou_1116551              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: User interface design for Virtual Reality and other embodied interaction contexts has to carefully consider ergonomics. A common problem is that mid-air inter- action may cause excessive arm fatigue, known as the “Gorilla arm” effect. To predict and prevent such problems at a low cost, this thesis investigates user test- ing of mid-air interaction without real users, utilizing biomechanically simulated AI agents trained using deep Reinforcement Learning (RL). This is implemented in a pointing task and four experimental conditions, demonstrating that the sim- ulated fatigue data matches ground truth human data. Additionally, two effort models are compared against each other: 1) instantaneous joint torques commonly used in computer animation and robotics, and 2) the recent Three Compartment Controller (3CC-r) model from biomechanical literature. 3CC-r yields movements that are both more efficient and natural, whereas with instantaneous joint torques, the RL agent can easily generate movements that are unnatural or only reach the targets slowly and inaccurately. This thesis demonstrates that deep RL combined with the 3CC-r provides a viable tool for predicting both interaction movements and user experience in silico, without users.

Details

show
hide
Language(s): eng - English
 Dates: 2019-09-302019-09-302019-09-302019-09-30
 Publication Status: Published in print
 Pages: 65 p.
 Publishing info: Saarbrücken : Universität des Saarlandes
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: Cheema_MSc2019b
 Degree: Master

Event

show

Legal Case

show

Project information

show

Source

show