The participants are required to run their VIO algorithms on sequences selected from the UZH FPV 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 is to estimate the quadrotor motion as accurately as possible, utilizing any desired sensor combinations.
This is the third edition of the competition (IROS 2019, ICRA 2020). The evaluation datasets are exactly the same. To obtain the prize money of up to 2000 USD, the winner of this competition will need to outperform the winners from the previous competitions as follows:
- Average translation error below 5% -> 1000 USD
- Average translation error below 2% -> 2000 USD
The prize money will only be awarded to the single team with the best performance. Evaluation details are provided on the leader board page. The winner will also be invited to present their approach at the IROS 2020 Workshop on “Perception, Learning, and Control for Autonomous Agile Vehicles”.
The deadline to submit the estimated trajectories and report is Sunday, September 27th, 2020.
To participate in the IROS 2020 competition, submit an entry to our leader board. All new submissions submitted by September 27th, 2020 will be considered in the competition.
Submissions submitted through the old competition website will also be considered.