Researchers unveil $88 AI-integrated smart cane for visually impaired
A new prototype smart cane costs $88 USD and runs entirely offline on an ultra‑low‑power Raspberry Pi Zero 2W. The device combines an RGB camera with a Time‑of‑Flight distance sensor and runs an INT8‑quantized SSD MobileNet V1 model to detect obstacles and provide vibrotactile and audio feedback.
Key points
- The cane costs $88 USD and runs fully offline on a Raspberry Pi Zero 2W.
- It uses an INT8‑quantized SSD MobileNet V1 model achieving 0.82 macro‑averaged F1 (precision 0.85, recall 0.81).
- A 12‑person usability test reported SUS 78.5 and reduced obstacle‑awareness latency to 330 ms with 2.8 W peak power.
Experimental tests in indoor mobility scenarios show 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 recorded a System Usability Scale score of 78.5 and favorable NASA‑TLX ratings, indicating positive user perception and improved obstacle awareness. The authors argue the approach demonstrates the feasibility of privacy‑preserving, edge‑native assistive intelligence for cost‑sensitive mobility assistance.
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- Researchers propose multi-split boundary decision to lower LLM document segmentation cost · 1 src
- GaitVista reduces gait measurement error by 27.7% in lab tests · 1 src
- Megagon Labs releases mawile workbench for auditing LLM judges · 1 src
- AutoGym framework generates verifiable agent gyms · 1 src
- EvidenT improves enterprise assistant evidence verification by 29% · 1 src
Comments
via GitHub Discussions