Aircraft Localization Competition - Call for Contesters

The OpenSky Network will co-organise a data science (MLAT / localization) competition at this year's ACM/IEEE IPSN conference in Montreal, Canada. We are looking for competitors with experience and interest in the area of TDOA/RSS-based localization using large-scale databases. The winning solutions will be awarded with cash prizes and the implementations will be open-sourced! More details below.

Overview

    * Date: April 15, 2019
    * Place: Montreal, Canada
    * Registration Deadline: February 15, 2019
    * Co-located with ACM/IEEE IPSN and CPS-IoT Week 2019
    * Website: https://competition.opensky-network.org
    * Student Travel Grants will be available soon
    * Cash Prizes up to 13.500,- EUR
    * Partners/Sponsors: armasuisse, OpenSky Network, SeRo Systems
    * Organisers/Committee:
        * Matthias Schäfer (TU Kaiserslautern / SeRo Systems GmbH, Germany)
        * Martin Strohmeier (University of Oxford, UK / armasuisse, Switzerland)
        * Vincent Lenders (armasuisse, Switzerland)
        * Mauro Leonardi (University of Rome Tor Vergata, Italy)
        * Fabio Ricciato (OpenSky Network, Switzerland)


Goal of the Competition

This competition is about finding the best methods to localize aircraft based on crowdsourced air traffic control communication data. The data is collected by the OpenSky Network, a large-scale sensor network which continuously collects air traffic control data from thousands of aircraft for research. The goal of the competition is to determine the positions of all aircraft which do not have position reporting capabilities or may report wrong locations. To do so, competitors will rely on time of arrival and signal strength measurements reported by many different sensors. Although methods like multilateration are long known, this data poses new challenges because most of the low-cost sensors are not time synchronised or calibrated. Competitors will therefore have to face different kinds of noise, ranging from clock drifts, inaccurate sensor locations, or broken timestamps due to software bugs.


Eligibility

We encourage both individuals and teams from academia and industry to register and participate. We strongly emphasize our openness towards novel approaches (such as machine learning) but also allow competitors to adapt their "traditional" localization models to the peculiarities of the crowdsourced measurement data. The localization algorithms should be able to produce decent results from a fresh 1h data set (~1 GB CSV) in under 3 hours.


Categories

Competitors can choose between four levels of increasing difficulty. The easiest category deals with data from GPS-synchronised receivers only and the competitors are provided with the barometric altitude of the aircraft. In this category, competitors do not have to deal with clock drifts and can limit the effect of a bad vertical dilution of precision by additionally considering the barometric altitude of the target. Category 2 competitors will also have GPS-synchronised data, however, no information about the target’s altitude will be available. Category 3 and 4 competitors will face data from both GPS-synchronised and unsynchronised sensors. In addition, category 3 data sets will include the barometric altitude.


Competition Execution

Competitors are provided with labelled training datasets which include all aircraft location. These labelled data sets can be used by the contesters to train their models. At the competition day, each team has to send at least 1 team member to the conference where they will get access to a non-labelled evaluation data sets. The teams have then 9h to find all locations of aircraft that are missing location information in the data sets. Every 3 hours, the teams have to submit their intermediate results (as a CSV file) to the organizers. The organizers will then calculate an indicator of the accuracy of their solution and provide an intermediate ranking. After 9 hours, the teams submit their final results and the final ranking is determined.


Evaluation and Prizes

On the competition day (April 15), all teams have to submit their intermediate results to the organizers every three hours. These intermediate results will then be rated using an objective error metric and the scores will be published. The teams can then continue to improve their results, e.g., by further pre-filtering the data or improving their models ad hoc. The leading teams of each intermediate evaluation (i.e. after 3h and 6h) will receive increasing cash awards. The awards will reach their maximum at the 9h deadline, when all teams have to submit their final results. The best 3 teams of each category will also receive cash prizes for their final results. The cash prizes are scaled with the level of competition and the difficulty of the category. This means that the more competitors and the higher the difficulty in a category, the higher the prizes. The exact pricing can be found on our website.

The teams with the best final results (after 9h) of each category will have to present their solutions in a short presentation at the conference. In addition, all teams who won cash awards (intermediate or final prizes) will have to publish their code under the GNU GPLv3 on the OpenSky Network's github account. Teams that do not want to publish their code are not eligible for awards. This means that closed-source solution can also compete but they will not be eligible for cash prizes.