PIL excels once again at the Microsoft Indoor Location Competition



For the second year in a row, the Precise Indoor Location’ (PIL) stood out at the Microsoft Indoor Location Competition - the most renowned competition in the field. Among dozens of participants from industry and academia from all over the world, it was the Fraunhofer AICOS’ PIL solution that won the second place in the 2D Localization Category.


With an average position accuracy of 1.32m, the PIL indoor solution demonstrated the significant improvements achieved from last year's competition (2.6m). A second version of PIL that participated out of the competition even achieved 1.11m average accuracy and would have beaten the winner of the 2D category that provided an average accuracy of 1.23m. The third place achieved 1.86m. So the top teams of the infrastructure free 2D category are consistently achieving an accuracy of less than 2 meters, some even close to just one meter. The detailed results can be found at http://research.microsoft.com/en-us/events/msindoorloccompetition2016/default.aspx.

PIL is an accurate indoor location technology that allows navigation using a smartphone without the need of any infrastructure like beacons or similar. It also does not require efforts to generate and maintain maps of buildings for the purpose of indoor location in order to contribute to the rapid spread of indoor ocation solutions on the consumer level.

PIL has been designed to support several real usage scenarios, such as when the smartphone is in a pocket or while in calling or texting. Target markets are e.g. retail, solutions for public and private safety providers or elderly people. Locating users inside buildings does also provide key information for the interaction between humans and the IoT. It will help buildings to understand their users' activities or businesses to plan better for their customers, combining location information with other in big data scenarios. Accurate indoor localization has a high potential to transform the way people can use applications and services on the micro level (indoors), like location information on the macro level (e.g. outdoors GPS) already changed our lives. For more than 2 decades, several indoor localization technologies have been proposed and experimented by both academia and industry, but we have yet to see large scale deployments.

The main reason for this are costs versus not yet fully understood values and business models. Practically all infrastructure based solutions do require significant investments that rise often linear and sometimes exponentially with the space covered. Thus beacon-based systems that today are the most widely deployed, by far are not as successful as many studies predicted. Looking at the overall results of the competition, it also becomes clear that the accuracy of simple (e.g. Bluetooth) beacon-based systems is not better, or even worse than the top infrastructure-free performers of the competition. In addition, they require energy and maintenance. So, only if significant better accuracy is needed, or tracking of "things" is required, infrastructure based systems (UWB, LIDAR, etc.) justify the related investments.

Fraunhofer AICOS' PIL is a pure SW solution for smartphones that relies on a proprietary sensor fusion algorithm that precisely calculates users' movement in real time. This is performed with an innovative dead reckoning approach, employing filtering techniques based on cyclic human walking patterns. Moreover, PIL measures existing environmental patterns, such as RF signals and magnetic fluctuations, whose unique properties allow them to be used as reference fingerprints. Position history and reference fingerprints are then used to incrementally match the route with floor plan data yielding a more accurate position estimation.

The latest developments on PIL solution led to an innovative approach for generating and maintaining fingerprints that has already been subject of a patent application.

The contest took place on the 10th and 11th of April, during the CPS Week 2016, which this year was held from the 11th to the 14th of April, in Vienna (Austria). Fraunhofer AICOS applied in the 2D Localization Category with its ‘Precise Indoor Location’ (PIL) solution. The Microsoft Indoor Location Competition – IPSN 2016 aims to bring together real-time or near real-time indoor location technologies and compare their performance in the same space.


About Fraunhofer Portugal

Associação Fraunhofer Portugal Research (Fraunhofer Portugal) is a non-profit private association founded by Fraunhofer-Gesellschaft, the largest organization for applied research in Europe. Fraunhofer Portugal promotes and coordinates the cooperation between its research center, other research institutions and Industry partners, with the objective of undertaking applied research of direct utility to private and public enterprises and of wide benefit to society. Fraunhofer Portugal Research Center for Assistive Information and Communication Solutions (Fraunhofer AICOS), located in Porto, is the first research center operated by Fraunhofer Portugal. It aims to enhance people’s living standards by offering them intuitive and useful technology solutions, capable of facilitating their access to Information and Communication Technologies, and therefore leading to the integration of an increasingly large part of the population in the Information and Knowledge Society.