July 26, 2018
CMU Teams Take Top Spots in Microsoft Localization Competition
By Daniel CarrollMedia Inquiries
- College of Engineering
Carnegie Mellon University alumni and students found their way to a first- and second-place finish in the fifth annual Microsoft Indoor Localization Competition, held this year in the Palácio da Bolsa in Porto, Portugal. Knowing how to pinpoint a specific location inside a building has broad applications, from rescue and recovery, augmented reality and manufacturing, to medicine, transportation and tourism.
Contestants were separated into two categories and judged by their devices' ability to report their location in either two or three dimensions. Each device traversed an area of the palace's first and second floors, as well as the large staircase connecting them, and reported their location as they followed the predetermined path.
Their readings were then compared against ground truth readings from a LiDAR sensor, a method similar to radar. This was used to calculate average location error.
The competition, which included teams from industry and academia, was tough, and the palace contributed its own challenges.
"Our ultrasound-based system faced extremely high multipath interference [very long acoustic reverberation, i.e. echoes] due to the stone construction of the space with no sound absorbing materials," said Patrick Lazik, a member of Yodel Labs. "The multistory layout of the space also made surveying the locations of our beacons difficult."
Yodel is a CMU startup spun off by Department of Electrical and Computer Engineering alumni Lazik, who earned his doctorate in 2017, and Nick Wilkerson, who earned his master's degree in 2014. They finished second in the competition.
Indoor localization equipment and beacons are mounted around the competition space of the Palácio da Bolsa in Porto, Portugal.
First place went to ECE Ph.D. candidate Niranjini Rajagopal, ECE Ph.D. student John Miller, ECE master's degree student Krishna Kumar and CyLab Postdoctoral Researcher Anh Luong.
Rajagopal and Lazik are seasoned competitors, having both been on the CMU team that won first place in 2015. They have remained at the leading edge of indoor localization technology, although much has changed since their last win.
"In 2015, the systems at the competition were much more exploratory, and people were trying all sorts of approaches," Rajagopal noted. "While this was exciting and chaotic, the latest version of the competition is much more refined, with more presence from startups. We have also seen most teams converge on technologies like UWB [ultra-wideband], acoustic or ultrasonic beacons."
While thrilled with their win, Rajagopal's team is looking ahead to improve their technology and create solutions that are flexible and user-friendly for widespread deployment.
"A practical system should not require any explicit mapping of beacons or expertise in deploying beacons," Rajagopal said. "These beaconing technologies might end up being embedded in devices deployed indoors such as WiFi routers, phones, or IoT devices. A network of these devices together would be able to provide an accurate localization service."
The team is integrating their technology into several projects. They developed a pilot version of a multiuser AR system that won the Best Demo Award at the 2018 Information Processing in Sensor Networks Conference. Their other project, funded by the National Institute of Standards and Technology, centers around creating an effective method of infrastructure-free (without mounted beacons or sensors) localization for firefighters using sensors in their equipment and devices.
Yodel Labs employs acoustic location processing system (ALPS) technology. Originally developed at CMU, ALPS uses ultrasound waves, Bluetooth signals, and VIO in custom beacons that work with off-the-shelf smartphones and tablets. Yodel Labs is commercializing the technology by using a National Science Foundation Small Business Innovation Research grant of $250,000 to improve methods to automatically localize their custom beacons, in preparation for mass production. The team's ultimate goal is to deploy their localization technology to enable multi-user, persistent AR across large areas.
"For us, the most interesting applications are the ones that require high accuracy, such as multi-user augmented reality and next generation assistive technologies like navigation systems for the visually impaired," Lazik said. "AR especially is an extremely fast-growing field that requires cutting-edge localization at its foundation."
ECE Associate Professor Anthony Rowe served as an adviser for the winning teams in 2018 and 2015. He also served as an organizer of the event, which is sponsored by Microsoft Research and Bosch.