Navigation Training for Persons With Visual Disability Through Multisensory Assistive Technology: Mixed Methods Experimental Study
Bibliographic record
Abstract
BACKGROUND: Visual disability is a growing problem for many middle-aged and older adults. Conventional mobility aids, such as white canes and guide dogs, have notable limitations that have led to increasing interest in electronic travel aids (ETAs). Despite remarkable progress, current ETAs lack empirical evidence and realistic testing environments and often focus on the substitution or augmentation of a single sense. OBJECTIVE: This study aims to (1) establish a novel virtual reality (VR) environment to test the efficacy of ETAs in complex urban environments for a simulated visual impairment (VI) and (2) evaluate the impact of haptic and audio feedback, individually and combined, on navigation performance, movement behavior, and perception. Through this study, we aim to address gaps to advance the pragmatic development of assistive technologies (ATs) for persons with VI. METHODS: The VR platform was designed to resemble a subway station environment with the most common challenges faced by persons with VI during navigation. This environment was used to test our multisensory, AT-integrated VR platform among 72 healthy participants performing an obstacle avoidance task while experiencing symptoms of VI. Each participant performed the task 4 times: once with haptic feedback, once with audio feedback, once with both feedback types, and once without any feedback. Data analysis encompassed metrics such as completion time, head and body orientation, and trajectory length and smoothness. To evaluate the effectiveness and interaction of the 2 feedback modalities, we conducted a 2-way repeated measures ANOVA on continuous metrics and a Scheirer-Ray-Hare test on discrete ones. We also conducted a descriptive statistical analysis of participants' answers to a questionnaire, assessing their experience and preference for feedback modalities. RESULTS: Results from our study showed that haptic feedback significantly reduced collisions (P=.05) and the variability of the pitch angle of the head (P=.02). Audio feedback improved trajectory smoothness (P=.006) and mitigated the increase in the trajectory length from haptic feedback alone (P=.04). Participants reported a high level of engagement during the experiment (52/72, 72%) and found it interesting (42/72, 58%). However, when it came to feedback preferences, less than half of the participants (29/72, 40%) favored combined feedback modalities. This indicates that a majority preferred dedicated single modalities over combined ones. CONCLUSIONS: AT is crucial for individuals with VI; however, it often lacks user-centered design principles. Research should prioritize consumer-oriented methodologies, testing devices in a staged manner with progression toward more realistic, ecologically valid settings to ensure safety. Our multisensory, AT-integrated VR system takes a holistic approach, offering a first step toward enhancing users' spatial awareness, promoting safer mobility, and holds potential for applications in medical treatment, training, and rehabilitation. Technological advancements can further refine such devices, significantly improving independence and quality of life for those with VI.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".