Exploring Generative Simulation: Aircraft Pilot Task Modeling via Reinforcement Learning Agents
No Thumbnail Available
URL
Journal Title
Journal ISSN
Volume Title
Sähkötekniikan korkeakoulu |
Master's thesis
Authors
Date
2023-10-09
Department
Major/Subject
Human-Computer Interaction
Mcode
SCI3097
Degree programme
CCIS - Master’s Programme in Computer, Communication and Information Sciences (TS2013)
Language
en
Pages
45 + 5
Series
Abstract
This research thesis explores the potential of generative simulations in Human Computer Interaction (HCI), offering insights into their potential. It explores how simulations, by emulating user behavior, could potentially improve understanding and predictability in HCI, making design processes more rigorous, predictable, and ethical. The study enhances simulation environments with features like a turnable head, omnidirectional eye, and high-fidelity cockpit models, addressing a research gap concerning intricate real-world tasks. It underscores the potential of simulation-based research to reshape HCI evaluations, particularly in aircraft cockpit design assessment. This research promotes simulations as a potential tool for analyzing complex tasks, fostering more robust and informed HCI methodologies.Description
Supervisor
Oulasvirta, AnttiThesis advisor
Nählinder, StaffanOulasvirta, Antti
Keywords
Human-Computer Interface Evaluation, RL-based agents, simulation realism enhancement, cockpit design assessment, human-computer interaction, generative simulation