Goto

Collaborating Authors

 shift metric


The Invisible Map: Visual-Inertial SLAM with Fiducial Markers for Smartphone-based Indoor Navigation

Ruvolo, Paul, Chakraborty, Ayush, Dave, Rucha, Li, Richard, Mazza, Duncan, Shen, Xierui, Siddique, Raiyan, Suresh, Krishna

arXiv.org Artificial Intelligence

Abstract-- We present a system for creating building-scale, easily navigable 3D maps using mainstream smartphones. In our approach, we formulate the 3D-mapping problem as an instance of Graph SLAM and infer the position of both building landmarks (fiducial markers) and navigable paths through the environment (phone poses). Our results demonstrate the system's ability to create accurate 3D maps. Three of the AprilTags used as fiducial markers by our mapping system. Indoor 3D mapping and navigation are of vital importance To combat the shortcomings of VIO, we use fiducial in a number of applications including autonomous mobile markers (or "tags") with planar patterns that can be readily robots which need to both accurately determine their position identified in a camera image.