====== Gazebo (summer) ======
^**Contact**: | [[http://asrl.utias.utoronto.ca/~pomerlef/|Francois Pomerleau]] |
^ | f.pomerleau [at] gmail [dot] com |
^**Date**: | Aug 4, 2011 |
^**Place**: | UniversitätsSpital Park, Zurich, Switzerland |
^**Situation**: | Outdoors |
^**Environments**: | Semi-structured |
^**Dynamics**: | People walking and seasonal changes |
^**Scanner path**: | Mainly on a 2D plane with a small loop |
^**Re-localization**: | 1 |
^**Number of scan**: | 32 |
^**Avg. points/scan**: | 170 000 |
^**Path bounding box**: | 5 x 4 x 0.07 m |
^**Scene bounding box**: | 35 x 45 x 16 m |
The environment is located in a park where there is grass, paved small roads and sparse trees.
The main construction is a gazebo made of rock walls and a wood ceiling covered with vines trees.
People usually walk in the path and take a break under the gazebo.
The main motivation for this dataset was to test registration algorithms against semi-structured environments.
Some people were walking in the area while the scanner was recording.
===== Citation =====
F. Pomerleau, M. Liu, F. Colas, and R. Siegwart, //Challenging data sets for point cloud registration algorithms//, **International Journal of Robotic Research**, vol. 31, no. 14, pp. 1705–1711, Dec. 2012. [[bibtex:challenging_datasets|bibtex]], [[http://intl-ijr.sagepub.com/content/31/14/1705|Publisher Link]]
===== Environment Topology =====
Manually drew map. The photo poses number correspond to the ones used in [[.:#contextual_photographs | Contextual Photographs]].
{{ :laserregistration:gazebo_summer:topo_gazebosummer_notes.png?650 |}}
===== Contextual Photographs =====
You can use right and left arrows keys to navigate once you click on a picture.
Number in the photo titles correspond the those used in the [[.:#environment_topology | Environment Topology]] section(click on the photo to see the numbers).
{{gallery>:laserregistration:gazebo_summer:photo?&lightbox}}
===== Screenshots =====
==== Point Cloud Views ====
Top view of the gazebo and the surroundings:
{{:laserregistration:gazebo_summer:pointcloudstop.png?650|}}
Scan sequence see from above:
file=/datasets/data/media/laserregistration/gazebo_summer/3D_map.flv&image=/datasets/data/media/laserregistration/gazebo_summer/video_preview.png
Side view of the scene:
{{:laserregistration:gazebo_summer:pointcloudsside.png?650|}}
Zoom on the gazebo covered with vines (point cloud manually extracted):
{{:laserregistration:gazebo_summer:gazebo.png?650|}}
Seasonal change - tree with leaves (point cloud manually extracted):
{{:laserregistration:gazebo_summer:tree.png?500|}}
==== Scanner Poses ====
{{:laserregistration:gazebo_summer:poseid_distance.png?650|}}
Overlap between each scan. The graph can be read as the percentage of points in Scan A that are also in Scan B.
The overlap matrix can be downloaded in the section [[.:#point_clouds_in_global_frame| Download Point Clouds in Global Frame]] as a csv file.
{{ :laserregistration:gazebo_summer:overlap_gazebo_summer.png?400 |}}
==== Scanner Orientation ====
{{:laserregistration:gazebo_summer:orientations.png?650|}}
==== Magnetic North ====
{{:laserregistration:gazebo_summer:compass.png?650|}}
==== Gravity ====
{{:laserregistration:gazebo_summer:gravity.png?650|}}
==== Number of Detected Satellites ====
{{:laserregistration:gazebo_summer:nbsats.png?650|}}
===== Downloads =====
All file contents and headers are explained on the page [[hardware:tiltinglaser#file_formats| Tilting Laser - File Formats]].
==== Point Clouds in Base Frame ====
Point clouds of this section have their origin at the scanner center.
2D scans have been transformed using the axis encoder to produce consistent 3D point clouds.
The supporting data (Gravity, Magnetic North and GPS) have been recorded while the scanner was rotating.
If you do not wish to compute the statistics for the supporting data, you can go to the section [[.:#Point Clouds in Global Coordinates|Point Clouds in Global Coordinates]] were single measurements have been selected per pose.
The "**ground truth**" poses can also be downloaded in the section [[.:#Point Clouds in Global Coordinates| Point Clouds in Global Coordinates]].
All csv files have a header explaining each column and consistent timestamps.
**Download all** local files: [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/csv_local/local_frame.zip | local_frame.zip]] (109 MB) [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/csv_local/local_frame.tar.gz | local_frame.tar.gz]] (109 MB)
- or -
Select the specific csv file you want [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/csv_local| here]].
**For Matlab users:**
* Example of how to load and plot the point clouds: [[http://robotics.ethz.ch/~asl-datasets/matlabScripts/plotCloudCsv.m| plotCloudCsv.m]]
----
==== Point Clouds in Global Frame ====
Point clouds of this section has been moved to a global reference frame where the pose of the first 3D scan is the origin.
The supporting data (Gravity, Magnetic North and GPS) has been post-processed to have only one reading per 3D scan.
All csv files have a header explaining what each columns are and consistent timestamps.
**Download all** global files: [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/csv_global/global_frame.zip | global_frame.zip]] (89 MB) [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/csv_global/global_frame.tar.gz | global_frame.tar.gz]] (89 MB)
- or -
Select the specific csv file you want [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/csv_global | here]] or in the list below:
* **"Ground truth"** poses for every point clouds: [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/csv_global/pose_scanner_leica.csv | pose_scanner_leica.csv]]
* Overlap matrix: [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/csv_global/overlap_gazebo_summer.csv | overlap_gazebo_summer.csv]]
* Mean of Gravity for every poses: [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/csv_global/xsens_Gravity_mean.csv | xsens_Gravity_mean.csv]]
* Mean of Magnetic North for every poses: [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/csv_global/xsens_Compass_mean.csv | xsens_Compass_mean.csv]]
* Mean of GPS for every poses: [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/csv_global/xsens_Gps_mean.csv | xsens_Gps_mean.csv]]
**For Matlab users:**
* Example of how to load and plot the point clouds: [[http://robotics.ethz.ch/~asl-datasets/matlabScripts/plotCloudCsv.m| plotCloudCsv.m]]
* Example of how to load and plot the path: [[http://robotics.ethz.ch/~asl-datasets/matlabScripts/plotPathCsv.m| plotPathCsv.m]]
----
==== Visualization Files ====
File type chosen for visualization is VTK legacy in ASCII format.
We suggest to use Paraview to view the files because it can be freely downloaded for Windows, Mac and Ubuntu user and it's supported by Kitware.
All screenshots of this page were realized using this software.
You can download it here: http://www.paraview.org/
**Download all** local files: [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/vtk/vtk_global.zip | vtk_global.zip]] (94 MB) [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/vtk/vtk_global.tar.gz | vtk_global.tar.gz]] (94 MB)
- or -
Select the specific vtk file you want [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/vtk| here]] or in the table below:
* Sequence of poses with supporting data attached to them: [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/vtk/path.vtk | path.vtk]] (8.0 KB)
* Post-processed global map (scanner removed, lower density of points, shadow points removed): [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/vtk/globalMap.vtk | globalMap.vtk]] (46 MB)
----
==== Raw Data ====
This type of data can be useful if you want to do some preprocessing on the 2D scans directly. We used ''ROS'' (www.ros.org) as middleware so the raw recordings can be downloaded and playback using ''rosbag''. One rosbag has been recored per 3D scan. The ground truth poses are not available in the ''rosbags''.
For more information on how to use this format see: www.ros.org/wiki/rosbag
Here is the output of ''rosbag info'' for the first scan. All scans have roughly the same number of messages
path: 0-Tiltlaser.bagversion: 2.0
duration: 18.7s
start: Aug 04 2011 16:14:42.30 (1312467282.30)
end: Aug 04 2011 16:15:00.00 (1312467301.00)
size: 1.7 MB
messages: 5106
compression: none [3/3 chunks]
types: diagnostic_msgs/DiagnosticArray [3cfbeff055e708a24c3d946a5c8139cd]
geometry_msgs/TwistStamped [98d34b0043a2093cf9d9345ab6eef12e]
geometry_msgs/Vector3Stamped [7b324c7325e683bf02a9b14b01090ec7]
sensor_msgs/Imu [6a62c6daae103f4ff57a132d6f95cec2]
sensor_msgs/LaserScan [90c7ef2dc6895d81024acba2ac42f369]
sensor_msgs/NavSatFix [2d3a8cd499b9b4a0249fb98fd05cfa48]
tf/tfMessage [94810edda583a504dfda3829e70d7eec]
xsens_mtig/GPSInfoStatus2 [d4266e982cc9a73c3a1de68763827345]
xsens_mtig/Thermistor [1a7c01d7f495652f5c21d90276c66498]
topics: /diagnostic 413 msgs : diagnostic_msgs/DiagnosticArray
/gravity_vector 376 msgs : geometry_msgs/Vector3Stamped
/imu_data 376 msgs : sensor_msgs/Imu
/info_gps 376 msgs : xsens_mtig/GPSInfoStatus2
/magnetic_vector 376 msgs : geometry_msgs/Vector3Stamped
/position_gps 376 msgs : sensor_msgs/NavSatFix
/scan 188 msgs : sensor_msgs/LaserScan
/temperature 752 msgs : xsens_mtig/Thermistor
/tf 1121 msgs : tf/tfMessage
/velocity 752 msgs : geometry_msgs/TwistStamped
**Download all** bags files: [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/rosbags/rosbags.zip | rosbags.zip]] (16.9 MB), [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/rosbags/rosbags.tar.gz | rosbags.tar.gz]] (16.8 MB)
- or -
Select the specific bag you want [[http://robotics.ethz.ch/~asl-datasets/gazebo_summer_04-Aug-2011-16_13_22/rosbags/ | here]].
----