The participants were required to run their VIO algorithms on sequences selected from the public UZH-FPV Drone Racing Dataset, which include images, IMU measurements, and event-based camera data recorded with a FPV drone racing quadrotor flown aggressively by an expert pilot. The goal was to estimate the quadrotor motion as accurately as possible, utilizing any desired sensor combinations.details on github
This was the second edition of the competition first held at IROS 2019. The evaluation datasets were exactly the same.
Our mission is to develop autonomous machines that can navigate all by themselves using onboard cameras, without relying on external infrastructure, such as GPS or motion capture systems.