RSS 2024 Robust State Estimation Competition

Welcome to the RSS 2024 Robust State Estimation Competition. Participants will run their state estimation algorithms on datasets (including images, IMU measurements, and event data) recorded with an FPV drone racing quadrotor flown by an expert pilot and an autonomous drone with speeds up to 100 km/h. The goal of the competition is to estimate the quadrotor motion as accurately as possible, utilizing any possible sensor combinations. The winner will be selected based on the accuracy of the estimated trajectories and will be rewarded with an invitation to deliver a talk at the workshop.

Sequences

Below are the sequences of the RSS 2024 competition. The entire dataset, containing training sequences with open-source ground truth and calibration files, is available here.

SequenceVideoLength [m]Start Time [s]Download
SplitS Track 1 https://youtu.be/mYKStE7e2aI 246.28 1654544051.569510 bag, zip
SplitS Track 2 https://youtu.be/mYKStE7e2aI 246.38 1654836213.498711 bag, zip
SplitS Track 3 https://youtu.be/mYKStE7e2aI 249.05 1654836718.332698 bag, zip
SequenceVideoLength [m]Start Time SnapdragonStart Time DavisDownload SnapdragonDownload Davis
indoor forward 11 https://youtu.be/mYKStE7e2aI 85.68 1540824001 s 1540824001 s bag, zip bag, zip
indoor forward 12 https://youtu.be/jNlDgN8fdKA 124.07 1540824296 s 1540824296 s bag, zip bag, zip
indoor 45deg 3 https://youtu.be/q6ELgSAjNMY 119.82 1623 s 1545305934 s bag, zip bag, zip
indoor 45deg 16 https://youtu.be/V4OnapxRLD4 58.72 133 s 1545315222 s bag, zip bag, zip
outdoor forward 9 https://youtu.be/ydaMA4Uta9A 314.41 372 s 1540102003 s bag, zip bag, zip
outdoor forward 10 https://youtu.be/G60gls4qeZ4 455.63 674 s 1540102304 s bag, zip bag, zip

Evaluation Method

The submission will be ranked based on the position accuracy. We use the same metric as the one adopted by KITTI. The average translation error (in percentage) over all possible subsequences of a set of certain lengths is used for ranking the submitted results. We use our publicly available trajectory evaluation toolbox to evaluate the estimated trajectories.

For each x in {40m, 60m, 80m, 100m, 120m}, subtrajectories of length x are uniformly sampled (in time) from the entire trajectory. The smaller the subtrajectory, the more samples there are in a given sequence. For each of those subtrajectories is then the relative position and rotation error computed as in the trajectory evaluation toolbox. For the ranking, the average of relative position error and rotation error is taken across all such samples. The length of the sequence affects the amount of samples in that sequence. For example, outdoor_forward_9 has {964, 916, 862, 807, 762} samples for trajectory lengths {40, 60, 80, 100, 120}. If a trajectory is shorter than x, no samples are generated for x.

Submission

Check here the submission format.

Submit here.

Deadline

The deadline is Sunday, June 30rd, 2024.

Contact

For support, please contact Giovanni Cioffi at cioffi (at) ifi (dot) uzh (dot) ch

Other

The submissions to this competition will not appear in the Standing Leader board. If you want to submit to the Standing Leader Board please visit the corresponding page here.