How people prompt generative AI to create interactive VR scenes

Generative AI tools can provide people with the ability to create virtual environments and scenes with natural language prompts. Yet, how people will formulate such prompts is unclear---particularly when they inhabit the environment that they are designing. For instance, it is likely that a person m...

Full description

Saved in:
Bibliographic Details
Main Authors: AGHEL MANESH, Setareh, ZHANG, Tianyi, ONISHI, Yuki, HARA, Kotaro, BATEMAN, Scott, LI, Jiannan, TANG, Anthony
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8977
https://ink.library.smu.edu.sg/context/sis_research/article/9980/viewcontent/3643834.3661547.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9980
record_format dspace
spelling sg-smu-ink.sis_research-99802024-10-17T07:10:29Z How people prompt generative AI to create interactive VR scenes AGHEL MANESH, Setareh ZHANG, Tianyi ONISHI, Yuki HARA, Kotaro BATEMAN, Scott LI, Jiannan TANG, Anthony Generative AI tools can provide people with the ability to create virtual environments and scenes with natural language prompts. Yet, how people will formulate such prompts is unclear---particularly when they inhabit the environment that they are designing. For instance, it is likely that a person might say, "Put a chair here,'' while pointing at a location. If such linguistic and embodied features are common to people's prompts, we need to tune models to accommodate them. In this work, we present a Wizard of Oz elicitation study with 22 participants, where we studied people's implicit expectations when verbally prompting such programming agents to create interactive VR scenes. Our findings show when people prompted the agent, they had several implicit expectations of these agents: (1) they should have an embodied knowledge of the environment; (2) they should understand embodied prompts by users; (3) they should recall previous states of the scene and the conversation, and that (4) they should have a commonsense understanding of objects in the scene. Further, we found that participants prompted differently when they were prompting in situ (i.e. within the VR environment) versus ex situ (i.e. viewing the VR environment from the outside). To explore how these lessons could be applied, we designed and built Ostaad, a conversational programming agent that allows non-programmers to design interactive VR experiences that they inhabit. Based on these explorations, we outline new opportunities and challenges for conversational programming agents that create VR environments. 2024-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8977 info:doi/10.1145/3643834.3661547 https://ink.library.smu.edu.sg/context/sis_research/article/9980/viewcontent/3643834.3661547.pdf http://creativecommons.org/licenses/by/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University generative ai virtual reality prompting interactive virtual reality multi-modal embodied prompting embodied interaction Artificial Intelligence and Robotics Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic generative ai
virtual reality
prompting
interactive virtual reality
multi-modal
embodied prompting
embodied interaction
Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
spellingShingle generative ai
virtual reality
prompting
interactive virtual reality
multi-modal
embodied prompting
embodied interaction
Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
AGHEL MANESH, Setareh
ZHANG, Tianyi
ONISHI, Yuki
HARA, Kotaro
BATEMAN, Scott
LI, Jiannan
TANG, Anthony
How people prompt generative AI to create interactive VR scenes
description Generative AI tools can provide people with the ability to create virtual environments and scenes with natural language prompts. Yet, how people will formulate such prompts is unclear---particularly when they inhabit the environment that they are designing. For instance, it is likely that a person might say, "Put a chair here,'' while pointing at a location. If such linguistic and embodied features are common to people's prompts, we need to tune models to accommodate them. In this work, we present a Wizard of Oz elicitation study with 22 participants, where we studied people's implicit expectations when verbally prompting such programming agents to create interactive VR scenes. Our findings show when people prompted the agent, they had several implicit expectations of these agents: (1) they should have an embodied knowledge of the environment; (2) they should understand embodied prompts by users; (3) they should recall previous states of the scene and the conversation, and that (4) they should have a commonsense understanding of objects in the scene. Further, we found that participants prompted differently when they were prompting in situ (i.e. within the VR environment) versus ex situ (i.e. viewing the VR environment from the outside). To explore how these lessons could be applied, we designed and built Ostaad, a conversational programming agent that allows non-programmers to design interactive VR experiences that they inhabit. Based on these explorations, we outline new opportunities and challenges for conversational programming agents that create VR environments.
format text
author AGHEL MANESH, Setareh
ZHANG, Tianyi
ONISHI, Yuki
HARA, Kotaro
BATEMAN, Scott
LI, Jiannan
TANG, Anthony
author_facet AGHEL MANESH, Setareh
ZHANG, Tianyi
ONISHI, Yuki
HARA, Kotaro
BATEMAN, Scott
LI, Jiannan
TANG, Anthony
author_sort AGHEL MANESH, Setareh
title How people prompt generative AI to create interactive VR scenes
title_short How people prompt generative AI to create interactive VR scenes
title_full How people prompt generative AI to create interactive VR scenes
title_fullStr How people prompt generative AI to create interactive VR scenes
title_full_unstemmed How people prompt generative AI to create interactive VR scenes
title_sort how people prompt generative ai to create interactive vr scenes
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/8977
https://ink.library.smu.edu.sg/context/sis_research/article/9980/viewcontent/3643834.3661547.pdf
_version_ 1814047947480891392