An Affordable AI-Integrated Smart Cane for Multimodal Mobility Assistance of Visually Impaired Users

一款面向视障人士、具备多模态移动辅助功能的经济型人工智能智能手杖

Abstract: Visual impairment affects over 2.2 billion people worldwide, yet conventional white canes cannot detect elevated hazards or provide semantic environmental context. Existing AI-assisted navigation systems typically rely on expensive hardware or cloud connectivity, limiting accessibility in resource-constrained settings.

摘要： 全球有超过 22 亿人受到视力障碍的影响，然而传统的盲杖无法探测高处的危险，也无法提供语义化的环境背景信息。现有的 AI 辅助导航系统通常依赖昂贵的硬件或云端连接，这限制了其在资源受限环境下的普及。

This paper presents an affordable ($88 USD), fully offline AI-integrated smart cane designed for multimodal mobility assistance on an ultra-low-power Raspberry Pi Zero 2W. The system fuses RGB vision sensing with Time-of-Flight (ToF) distance estimation, pairing an INT8-quantized SSD MobileNet V1 model with distance-aware vibrotactile feedback and real-time audio alerts.

本文介绍了一款经济实惠（88 美元）、完全离线且集成 AI 的智能手杖，该手杖专为在超低功耗的树莓派（Raspberry Pi）Zero 2W 上实现多模态移动辅助而设计。该系统融合了 RGB 视觉感知与飞行时间（ToF）测距技术，将 INT8 量化的 SSD MobileNet V1 模型与距离感知振动触觉反馈及实时音频警报相结合。

To ensure operational robustness on constrained hardware, a multiprocessing architecture isolates sensor acquisition, neural inference, and haptic feedback into independent processes with fail-safe sensing support. Experimental evaluation across indoor mobility scenarios demonstrates a macro-averaged F1-score of 0.82 (precision: 0.85, recall: 0.81), a mean end-to-end latency of 330,ms, and a peak power draw of 2.8,W.

为了确保在受限硬件上的运行稳定性，系统采用了多进程架构，将传感器采集、神经网络推理和触觉反馈隔离为独立进程，并配备了故障安全传感支持。在室内移动场景下的实验评估显示，其宏平均 F1 分数为 0.82（精确率为 0.85，召回率为 0.81），平均端到端延迟为 330 毫秒，峰值功耗为 2.8 瓦。

A preliminary usability study with 12 participants (SUS: 78.5, NASA-TLX) demonstrated positive user perception and enhanced obstacle awareness. The proposed prototype validates the feasibility of deploying privacy-preserving, edge-native assistive intelligence for cost-sensitive mobility assistance.

一项针对 12 名参与者的初步可用性研究（SUS 得分 78.5，NASA-TLX 指标）表明，用户反馈积极，且障碍物感知能力得到了增强。该原型验证了在成本敏感的移动辅助场景中，部署保护隐私的边缘原生辅助智能的可行性。