Lantern: one walk with a phone becomes an offline indoor map, built by Gemma 4
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built My friends can't find the washroom in a crowded stadium where internet and cell networks get blocked. Nobody can find anything at the Kumbh Mela. Entire buildings have no map beyond the gate. Indoor navigation exists, but it needs architect floor plans, Bluetooth beacons or weeks of professional…
Lantern is an AI-powered offline indoor mapping tool created by Gemma 4. The creator's motivation was to provide a simple solution for people struggling to navigate large, unfamiliar buildings without internet connectivity. The tool relies on a single walk-through of the building, where the user films the space and describes what they see.
Gemma 4 then converts this video into a map with photos, floor information, and step-by-step directions. After the first visit, the map works in airplane mode, and no app installation or GPS is required. The design focuses on simplicity, with large buttons, high contrast, and read-aloud functionality for easy use. Lantern aims to assist elderly visitors, first-time smartphone users, non-English speakers, and wheelchair users who need to find stairs or other landmarks.
To demonstrate, the creator mapped their college campus using two iPhone clips totaling three minutes and seventeen seconds. The AI model, Gemma 4, processes the video frames and transcriptions to create an accurate, step-by-step navigation system without any human intervention beyond initial confirmation.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
