NavigateSense: a multimodal smart blind cane system with deep learning for enhanced environmental perception and mobility assistance

According to the World Health Organization (WHO), approximately 285 million people worldwide have visual impairments, including 39 million who are completely blind. These individuals face significant challenges in daily navigation, obstacle detection, and environmental perception. Traditional assistive devices often suffer from limited environmental awareness, unimodal feedback, and poor adaptability to varying conditions. To address these limitations, we have developed a comprehensive assistive system that integrates multiple sensors and delivers multi-modal feedback. The system consists of four core modules: an environmental perception module that utilizes computer vision and depth sensing for real-time detection of surroundings; a data processing module that employs deep learning algorithms for scene understanding and hazard identification; a multi-modal feedback module that combines voice prompts and Braille output to convey intuitive and efficient environmental information; and a power management module that uses intelligent algorithms to optimize energy consumption and ensure stable long-term operation. Through systematic testing in both indoor and outdoor scenarios, the smart blind cane achieved 95% accuracy in obstacle detection, with an average response time of less than 0.5 seconds. User satisfaction evaluations revealed that 92% and 95% of participants reported high satisfaction and convenience rates, which are also kept relatively high in the following 6 months too. A comprehensive market analysis demonstrates the system's competitive advantages in detection range and accuracy compared to existing products, and an economic feasibility analysis also reveals its low production cost and maintenance cost and high scalability potential. These results demonstrate the system’s strong potential for application in daily navigation, emergency alerting, and environmental information acquisition, offering a safe and reliable assistive solution for visually impaired individuals.

Authors

Institutions

Publication Details

Published
2025-09-19
DOI
https://doi.org/10.1117/12.3082704
Primary Topic
Tactile and Sensory Interactions
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

NavigateSense: a multimodal smart blind cane system with deep learning for enhanced environmental perception and mobility assistance

Yuhang Chen
Tactile and Sensory Interactions
article

NavigateSense: a multimodal smart blind cane system with deep learning for enhanced environmental perception and mobility assistance

Yuhang Chen
article en

Abstract

According to the World Health Organization (WHO), approximately 285 million people worldwide have visual impairments, including 39 million who are completely blind. These individuals face significant challenges in daily navigation, obstacle detection, and environmental perception. Traditional assistive devices often suffer from limited environmental awareness, unimodal feedback, and poor adaptability to varying conditions. To address these limitations, we have developed a comprehensive assistive system that integrates multiple sensors and delivers multi-modal feedback. The system consists of four core modules: an environmental perception module that utilizes computer vision and depth sensing for real-time detection of surroundings; a data processing module that employs deep learning algorithms for scene understanding and hazard identification; a multi-modal feedback module that combines voice prompts and Braille output to convey intuitive and efficient environmental information; and a power management module that uses intelligent algorithms to optimize energy consumption and ensure stable long-term operation. Through systematic testing in both indoor and outdoor scenarios, the smart blind cane achieved 95% accuracy in obstacle detection, with an average response time of less than 0.5 seconds. User satisfaction evaluations revealed that 92% and 95% of participants reported high satisfaction and convenience rates, which are also kept relatively high in the following 6 months too. A comprehensive market analysis demonstrates the system's competitive advantages in detection range and accuracy compared to existing products, and an economic feasibility analysis also reveals its low production cost and maintenance cost and high scalability potential. These results demonstrate the system’s strong potential for application in daily navigation, emergency alerting, and environmental information acquisition, offering a safe and reliable assistive solution for visually impaired individuals.

Central South University (CN)
Openalex Percentile: Top 74%
Tactile and Sensory Interactions
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.