Please use this identifier to cite or link to this item:
Volltext verfügbar? / Dokumentlieferung
doi:10.22028/D291-39187
Title: | Predicting Mid-Air Interaction Movements and Fatigue Using Deep Reinforcement Learning |
Author(s): | Cheema, Noshaba Frey-Law, Laura A. Naderi, Kourosh Lehtinen, Jaakko Slusallek, Philipp Hämäläinen, Perttu |
Language: | English |
Title: | CHI'20 : Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, April 25-30, 2020, Honolulu, HI, USA |
Pages: | 1-13 |
Publisher/Platform: | ACM |
Year of Publication: | 2020 |
Place of publication: | New York |
Place of the conference: | Honolulu, HI, USA |
DDC notations: | 004 Computer science, internet |
Publikation type: | Conference Paper |
Abstract: | A common problem of mid-air interaction is excessive arm fatigue, known as the "Gorilla arm" effect. To predict and prevent such problems at a low cost, we investigate user testing of mid-air interaction without real users, utilizing biomechanically simulated AI agents trained using deep Reinforcement Learning (RL). We implement this in a pointing task and four experimental conditions, demonstrating that the simulated fatigue data matches human fatigue data. We also compare two effort models: 1) instantaneous joint torques commonly used in computer animation and robotics, and 2) the recent Three Compartment Controller (3CC-) model from biomechanical literature. 3CC- yields movements that are both more efficient and relaxed, whereas with instantaneous joint torques, the RL agent can easily generate movements that are quickly tiring or only reach the targets slowly and inaccurately. Our work demonstrates that deep RL combined with the 3CC- provides a viable tool for predicting both interaction movements and user experiencein silico, without users. |
DOI of the first publication: | 10.1145/3313831.3376701 |
URL of the first publication: | https://dl.acm.org/doi/abs/10.1145/3313831.3376701 |
Link to this record: | urn:nbn:de:bsz:291--ds-391879 hdl:20.500.11880/35330 http://dx.doi.org/10.22028/D291-39187 |
ISBN: | 978-1-4503-6708-0 |
Date of registration: | 1-Mar-2023 |
Faculty: | MI - Fakultät für Mathematik und Informatik |
Department: | MI - Informatik |
Professorship: | MI - Prof. Dr. Philipp Slusallek |
Collections: | SciDok - Der Wissenschaftsserver der Universität des Saarlandes |
Files for this record:
There are no files associated with this item.
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.