EmBARDiment: an Embodied AI Agent for Productivity in XR
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912270103085056 |
|---|---|
| author | Bovo, Riccardo Abreu, Steven Ahuja, Karan Gonzalez, Eric J Cheng, Li-Te Gonzalez-Franco, Mar |
| author_facet | Bovo, Riccardo Abreu, Steven Ahuja, Karan Gonzalez, Eric J Cheng, Li-Te Gonzalez-Franco, Mar |
| contents | XR devices running chat-bots powered by Large Language Models (LLMs) have the to become always-on agents that enable much better productivity scenarios. Current screen based chat-bots do not take advantage of the the full-suite of natural inputs available in XR, including inward facing sensor data, instead they over-rely on explicit voice or text prompts, sometimes paired with multi-modal data dropped as part of the query. We propose a solution that leverages an attention framework that derives context implicitly from user actions, eye-gaze, and contextual memory within the XR environment. Our work minimizes the need for engineered explicit prompts, fostering grounded and intuitive interactions that glean user insights for the chat-bot. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08158 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EmBARDiment: an Embodied AI Agent for Productivity in XR Bovo, Riccardo Abreu, Steven Ahuja, Karan Gonzalez, Eric J Cheng, Li-Te Gonzalez-Franco, Mar Human-Computer Interaction Multiagent Systems XR devices running chat-bots powered by Large Language Models (LLMs) have the to become always-on agents that enable much better productivity scenarios. Current screen based chat-bots do not take advantage of the the full-suite of natural inputs available in XR, including inward facing sensor data, instead they over-rely on explicit voice or text prompts, sometimes paired with multi-modal data dropped as part of the query. We propose a solution that leverages an attention framework that derives context implicitly from user actions, eye-gaze, and contextual memory within the XR environment. Our work minimizes the need for engineered explicit prompts, fostering grounded and intuitive interactions that glean user insights for the chat-bot. |
| title | EmBARDiment: an Embodied AI Agent for Productivity in XR |
| topic | Human-Computer Interaction Multiagent Systems |
| url | https://arxiv.org/abs/2408.08158 |