CMU wins Microsoft Indoor Localization Competition


April 22, 2015

A Carnegie Mellon team came in first place in the infrastructure-based Microsoft Indoor Localization Competition with 48 submissions from 44 teams all around the world, 12 from industry and 32 from academia. Accurate indoor localization has the potential to transform the way people navigate indoors in a similar way that GPS transformed the way people navigate outdoors. Over the last 15 years, several human-centric approaches to indoor localization have been proposed by both academia and industry, but we have yet to see large scale deployments. This competition aims to bring together real-time or near real-time indoor location technologies and compare their performance.

Each team was asked to take measurements at 20 different unknown locations across a 2,000 square meter area of a conference center and report the x and y position with respect to the corner of the building. The space consisted of multiple rooms with furniture and observers walking around. The CMU team achieved an average accuracy of 31cm using a standard unmodified smartphone as the receiver. The system, called Alps, uses a hybrid ultrasonic and bluetooth low energy approach that computes time-of-flight range values using the audio bandwidth just above the human hearing frequency range where mobile device microphones are still sensitive. The team has been working closely with the Bosch Research and Technology Center in Pittsburgh on the technology since 2012 and also as part of the SRC funded TerraSwarm research center. With the support of a Pennsylvania Infrastructure Technology Alliance (PITA) grant the team will be rolling out a large-scale deployment in the Pittsburgh Convention center over the next year. 

Faculty Advisors: Anthony Rowe and Bruno Sinopoli
Students: Patrick Lazik, Niranjini Rajagopal, Oliver Shih

View the project website here.

winning team