Lead University: Carnegie Mellon University
PI: Anthony Rowe, Electrical and Computer Engineering and Bruno Sinopoli, Electrical and Computer Engineering
Co-PI(s): Burcu Akinci, Civil and Environmental Engineering and Anind Dey, HCI

This project aims at developing a cost effective, accurate and resilient indoor localization service to be used in built environments. Unlike existing methods, the proposed method will achieve high accuracy and robustness with respect to disruptions while maintaining low installation and maintenance costs. To achieve these goals the team has devised a system that relies upon several range-free and range-based trilateration techniques to increase accuracy and resilience and an implementation plan that piggybacks on much of the existing infrastructure in typical built environments, namely, audio, light and RF-based communication to minimize installation cost. The partnership will employ a cloud-based architecture to deliver and manage the service where storage and most of the computation will reside in the back-end. The smartphone will act as a relay with the back-end for ranging information and will perform fusion between the relatively low frequency (about 1Hz) position estimate coming from the cloud and the potentially higher one (10Hz) based on inertial data coming from phone, resembling the common GPS-INS (Inertial Navigation System) common in outdoor navigation systems. The proposed location service system targets large indoor facilities owners and managers, such as shopping malls, warehouses, airports, office building etc. The technology could be used in facilities employing a large number of automated mobile robots such as Kiva Systems, because of its capability to perform tracking. Through a partnership with the Sports and Exhibition Authority of Pittsburgh, we have the unique opportunity to deploy and test our platform in the Lawrence David Convention Center in downtown.