Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

What do Blind and Low-Vision People Really Want from Assistive Smart Devices? Comparison of the Literature with a Focus Study

Bhanuka Gamage, Thanh-Toan Do, Nicholas Seow Chiang Price, Arthur Lowery, Kim Marriott

TL;DR

The paper tackles whether AI-based smart devices for BLV users address real-world needs. It combines a scoping review of 646 recent papers with interviews of 24 BLV participants to map tasks, devices, and interactions and compare them with user priorities. The findings show only a weak link between what researchers study and what BLV users want, limited end-user involvement in most studies, and a clear preference for conversational interfaces and head-mounted wearables, suggesting a shift toward universal, co-designed solutions. These insights provide concrete guidance for prioritizing tasks, interaction modalities, and devices to improve adoption and real-world utility of smart assistive technologies.

Abstract

Over the last decade there has been considerable research into how artificial intelligence (AI), specifically computer vision, can assist people who are blind or have low-vision (BLV) to understand their environment. However, there has been almost no research into whether the tasks (object detection, image captioning, text recognition etc.) and devices (smartphones, smart-glasses etc.) investigated by researchers align with the needs and preferences of BLV people. We identified 646 studies published in the last two and a half years that have investigated such assistive AI techniques. We analysed these papers to determine the task, device and participation by BLV individuals. We then interviewed 24 BLV people and asked for their top five AI-based applications and to rank the applications found in the literature. We found only a weak positive correlation between BLV participants' perceived importance of tasks and researchers' focus and that participants prefer conversational agent interface and head-mounted devices.

What do Blind and Low-Vision People Really Want from Assistive Smart Devices? Comparison of the Literature with a Focus Study

TL;DR

The paper tackles whether AI-based smart devices for BLV users address real-world needs. It combines a scoping review of 646 recent papers with interviews of 24 BLV participants to map tasks, devices, and interactions and compare them with user priorities. The findings show only a weak link between what researchers study and what BLV users want, limited end-user involvement in most studies, and a clear preference for conversational interfaces and head-mounted wearables, suggesting a shift toward universal, co-designed solutions. These insights provide concrete guidance for prioritizing tasks, interaction modalities, and devices to improve adoption and real-world utility of smart assistive technologies.

Abstract

Over the last decade there has been considerable research into how artificial intelligence (AI), specifically computer vision, can assist people who are blind or have low-vision (BLV) to understand their environment. However, there has been almost no research into whether the tasks (object detection, image captioning, text recognition etc.) and devices (smartphones, smart-glasses etc.) investigated by researchers align with the needs and preferences of BLV people. We identified 646 studies published in the last two and a half years that have investigated such assistive AI techniques. We analysed these papers to determine the task, device and participation by BLV individuals. We then interviewed 24 BLV people and asked for their top five AI-based applications and to rank the applications found in the literature. We found only a weak positive correlation between BLV participants' perceived importance of tasks and researchers' focus and that participants prefer conversational agent interface and head-mounted devices.

Paper Structure

This paper contains 20 sections, 10 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Study 1 - Scoping Review
  4. Literature Search and Review Methodology
  5. Data Extraction
  6. Results
  7. Study 2 - Needs of People Who are Blind or have Low-Vision (BLV)
  8. Participants
  9. Procedure
  10. Results
  11. Comparison & Discussion
  12. Which tasks should researchers explore?
  13. Which interaction modalities are preferred?
  14. Which devices are preferred?
  15. Why is Blind and Low-Vision community involvement important in smart assistive device research?
  16. ...and 5 more sections

Figures (10)

  • Figure 1: Breakdown of the counts of papers identified for each types of tasks. Note the height of each sub-box is only indicative of the number of papers in that category.
  • Figure 2: Count of papers identified for the types of devices
  • Figure 3: Count of papers identified for each interaction model
  • Figure 4: Type of participant involvement in research studies and the stages of involvement
  • Figure 5: Participants' Five Most Useful Tasks Ranked by Order of Preference; The identified tasks are presented in order from most to least preferred, with tasks not listed in our review task list indicated in bold font with a [+] symbol next to them.
  • ...and 5 more figures