{"slug": "an-affordable-ai-integrated-smart-cane-for-multimodal-mobility-assistance-of", "title": "An Affordable AI-Integrated Smart Cane for Multimodal Mobility Assistance of Visually Impaired Users", "summary": "Researchers built an $88 fully offline AI-integrated smart cane for visually impaired users, running on a Raspberry Pi Zero 2W and fusing RGB vision with Time-of-Flight distance estimation. The system pairs an INT8-quantized SSD MobileNet V1 model with distance-aware vibrotactile feedback and real-time audio alerts, achieving a macro-averaged F1-score of 0.82 (precision 0.85, recall 0.81), 330 ms mean end-to-end latency, and 2.8 W peak power draw. A preliminary usability study with 12 participants recorded a System Usability Scale score of 78.5, and the authors state the prototype validates privacy-preserving, edge-native assistive intelligence for cost-sensitive mobility assistance.", "body_md": "arXiv:2609.22277v1 Announce Type: new \nAbstract: 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. 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. 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. 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.", "url": "https://wpnews.pro/news/an-affordable-ai-integrated-smart-cane-for-multimodal-mobility-assistance-of", "canonical_source": "https://arxiv.org/abs/2609.22277", "published_at": "2026-09-23 04:00:00+00:00", "updated_at": "2026-09-23 04:26:19.878575+00:00", "lang": "en", "topics": ["computer-vision", "ai-products", "ai-tools", "ai-research"], "entities": ["Raspberry Pi Zero 2W", "SSD MobileNet V1", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/an-affordable-ai-integrated-smart-cane-for-multimodal-mobility-assistance-of", "markdown": "https://wpnews.pro/news/an-affordable-ai-integrated-smart-cane-for-multimodal-mobility-assistance-of.md", "text": "https://wpnews.pro/news/an-affordable-ai-integrated-smart-cane-for-multimodal-mobility-assistance-of.txt", "jsonld": "https://wpnews.pro/news/an-affordable-ai-integrated-smart-cane-for-multimodal-mobility-assistance-of.jsonld"}}