Enabling Real-World Assistive Agents: From Live Vision to Proactive Context-Aware Information Delivery

Figure 1: My dissertation work explores the design of an assistive agent as an always-available companion to assist BVI people in real-world interactions.(a) I first conducted a user study with eight BVI people to probe the design insights for designing assistive agents [11].Based on the insights, (b) I developed a system, WorldScribe, that proactively provides live visual descriptions based on user intent, and visual and sound contexts [10].(c) My ongoing works expand WorldScribe to take natural user interactions to provide corresponding information for BVI people, such as object descriptions for hand-object interactions, and spatial information based on location and mobility.(d) In the future, I aim to draw insights from human assistance to develop an assistive agent that serves as a long-term, context-aware companion in everyday environments.

Authors

Institutions

Publication Details

Published
2025-09-27
DOI
https://doi.org/10.1145/3746058.3758468
Primary Topic
Mobile Crowdsensing and Crowdsourcing
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Enabling Real-World Assistive Agents: From Live Vision to Proactive Context-Aware Information Delivery

Ruei-Che Chang
Mobile Crowdsensing and Crowdsourcing
article

Enabling Real-World Assistive Agents: From Live Vision to Proactive Context-Aware Information Delivery

Ruei-Che Chang
article en

Abstract

Figure 1: My dissertation work explores the design of an assistive agent as an always-available companion to assist BVI people in real-world interactions.(a) I first conducted a user study with eight BVI people to probe the design insights for designing assistive agents [11].Based on the insights, (b) I developed a system, WorldScribe, that proactively provides live visual descriptions based on user intent, and visual and sound contexts [10].(c) My ongoing works expand WorldScribe to take natural user interactions to provide corresponding information for BVI people, such as object descriptions for hand-object interactions, and spatial information based on location and mobility.(d) In the future, I aim to draw insights from human assistance to develop an assistive agent that serves as a long-term, context-aware companion in everyday environments.

University of Michigan (US)
Openalex Percentile: Top 70%
Mobile Crowdsensing and Crowdsourcing
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.