Paper ID: 2310.10862

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

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

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. Further, we highlight the importance of careful selection of mapping hyperparameters and provide a novel technique for tuning these hyperparameters to adapt our algorithm to new environments.

Submitted: Oct 16, 2023