Datasets
Open Access
AirMuseum: a heterogeneous multi-robot dataset for stereo-visual and inertial Simultaneous Localization And Mapping
- Citation Author(s):
- Submitted by:
- Rodolphe Dubois
- Last updated:
- Thu, 09/10/2020 - 13:45
- DOI:
- 10.21227/fq66-4973
- Data Format:
- Links:
- License:
860 Views- Categories:
- Keywords:
Abstract
The AirMuseum dataset is intended for multi-robot stereo-visual and inertial Simultaneous Localization And Mapping (SLAM). It consists in five indoor multi-robot scenarios acquired with ground and aerial robots in a former Air Museum at ONERA Meudon, France. Those scenarios were designed to exhibit some specific opportunities and challenges associated to collaborative SLAM. Each scenario includes synchronized sequences between multiple robots with stereo images and inertial measurements. They also exhibit explicit direct interactions between robots through the detection of mounted AprilTag markers. Ground-truth trajectories for each robot were computed using
Structure-from-Motion algorithms and constrained with the detection of fixed AprilTag markers placed as beacons on the experimental area.
The dataset is organized as follows:
- sensors.zip holds the calibrations of the cameras and the IMU sensors.
- apriltags.zip holds the calibration of the mounted apriltag markers for robots B and C. It consists in the estimated pose of the markers' frames with regard to the reference frame attached to one of the robot's cameras.
- scenarioX_robotY holds the acquisitions of the robotY in scenarioX as ROS .bag files, as well the associated ground-truth trajectories (the ground-truth is provided for the frame attached to cam100 and for the body (inertial) frame).
- scenarioX_trajectories.mp4 is a video of an accelerated (x20) top-view of the robot trajectories (robotA is red, robotB is green, robotC is blue and the drone is orange)
- scenarioX_preview.mp4 is a x1.5 accelerated preview of the visual acquisitions of the robots
Additional updated details may be found on the associated github repository (https://github.com/AirMuseumDataset/AirMuseumDataset.git) and in the associated article: AirMuseum: a heterogeneous multi-robot dataset for stereo-visual and inertial Simultaneous Localization And Mapping - Rodolphe Dubois, Alexandre Eudes and Vincent Frémont - 2020 IEEE International Conference on Multisensor Fusion and Integration (MFI 2020).
Dataset Files
Calibration of the cameras and the IMU sensors sensors.zip (4.25 kB)- Calibration of the mounted apriltag markers mounted_apriltags.zip (2.15 kB)
- Acquisitions and ground-truth trajectories of robot A in scenario 2 scenario2_robotA.zip (3.15 GB)
- Acquisitions and ground-truth trajectories of robot B in scenario 2 scenario2_robotB.zip (3.11 GB)
- Acquisitions and ground-truth trajectories of robot C in scenario 2 scenario2_robotC.zip (3.15 GB)
- Acquisitions and ground-truth trajectories of the drone in scenario 3 scenario3_drone.zip (2.52 GB)
- Acquisitions and ground-truth trajectories of robot A in scenario 3 scenario3_robotA.zip (2.42 GB)
- Acquisitions and ground-truth trajectories of robot B in scenario 3 scenario3_robotB.zip (2.41 GB)
- Acquisitions and ground-truth trajectories of robot C in scenario 3 scenario3_robotC.zip (2.42 GB)
- Acquisitions and ground-truth trajectories of the drone in scenario 4 scenario4_drone.zip (2.68 GB)
- Acquisitions and ground-truth trajectories of robot A in scenario 4 scenario4_robotA.zip (2.54 GB)
- Acquisitions and ground-truth trajectories of robot B in scenario 4 scenario4_robotB.zip (2.63 GB)
- Acquisitions and ground-truth trajectories of robot C in scenario 4 scenario4_robotC.zip (2.47 GB)
- Acquisitions and ground-truth trajectories of the drone in scenario 5 scenario5_drone.zip (2.48 GB)
- Acquisitions and ground-truth trajectories of robot A in scenario 5 scenario5_robotA.zip (2.47 GB)
- Acquisitions and ground-truth trajectories of robot B in scenario 5 scenario5_robotB.zip (2.38 GB)
- Acquisitions and ground-truth trajectories of robot C in scenario 5 scenario5_robotC.zip (2.48 GB)
- Acquisitions and ground-truth trajectories of robot A in scenario 1 scenario1_robotA.zip (3.47 GB)
- Acquisitions and ground-truth trajectories of robot B in scenario 1 scenario1_robotB.zip (3.50 GB)
Pre-view of the scenario 1 scenario1_preview.mp4 (23.90 MB)- Pre-view of the scenario 2 scenario2_preview.mp4 (20.85 MB)
- Pre-view of the scenario 3 scenario3_preview.mp4 (16.34 MB)
- Pre-view of the scenario 4 scenario4_preview.mp4 (16.75 MB)
- Pre-view of the scenario 5 scenario5_preview.mp4 (16.24 MB)
- Top-view accelerated view trajectories of scenario 1 scenario1_trajectories.mp4 (398.94 kB)
- Top-view accelerated trajectories of scenario 2 scenario2_trajectories.mp4 (283.49 kB)
- Top-view accelerated trajectories of scenario 3 scenario3_trajectories.mp4 (326.29 kB)
- Top-view accelerated trajectories of scenario 4 scenario4_trajectories.mp4 (367.12 kB)
- Top-view accelerated trajectories of scenario 5 scenario5_trajectories.mp4 (310.75 kB)
- Acquisitions and ground-truth trajectories of robot C in scenario 1 scenario1_robotC.zip (3.47 GB)
Open Access dataset files are accessible to all logged in users. Don't have a login? Create a free IEEE account. IEEE Membership is not required.
