Research map / Multi-agent systems and games / LLM agents
Navigation and Interaction for Blind Users via a Cognitive Architecture
Oscar J. Romero, Anthony Tomasic, Elizabeth J. Carter, John Zimmerman, Aaron Steinfeld
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Prototypes a smartphone-based conversational assistant for blind and low-vision users that uses a cognitive architecture to integrate AR spatial audio, computer vision, and language technologies for indoor navigation and interaction.
Problem
Navigating unfamiliar indoor spaces and interacting with the environment is hard for blind and low-vision (BLV) people.
Approach
Integrates augmented-reality spatial audio, computer vision, and language technologies inside a cognitive architecture that drives a smartphone conversational assistant for BLV navigation and interaction.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| enable both object detection and spatial anchors instead of object detection only (ablation) | conversational navigation assistant · Task T1 completion time | seconds: 240.0 -> 149.0 | Improved |
| enable both features instead of object detection only (ablation) | conversational navigation assistant · Task T4 completion time | seconds: 289.5 -> 165.5 | Improved |
| enable both features instead of spatial anchors only (ablation) | conversational navigation assistant · Task T2 completion time | seconds: 186.5 -> 105.5 | Improved |
| enable both features instead of spatial anchors only (ablation) | conversational navigation assistant · Task T3 completion time | seconds: 70.5 (C2) vs 73.0 (C3) | No clear effect |
| enable both features instead of object detection only (ablation) | conversational navigation assistant · Task T3 completion time | seconds: 135.0 -> 73.0 | Improved |
Closest papers by meaning
- EgoBlind: Towards Egocentric Visual Assistance for the Blind (NeurIPS 2025 · similarity 0.83)
- Text to Blind Motion (NeurIPS 2024 · similarity 0.82)
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS 2024 · similarity 0.82)
- CitySeeker: How Do VLMs Explore Embodied Urban Navigation with Implicit Human Needs? (ICLR 2026 · similarity 0.82)
- Voila-A: Aligning Vision-Language Models with User's Gaze Attention (NeurIPS 2024 · similarity 0.82)
- LifeEval: A Multimodal Benchmark for Assistive AI in Egocentric Daily Life Tasks (CVPR 2026 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
