#################### ### Introduction ### #################### This document describes the format of the files that store odometry, sonar range, laser range and image data of the 'FS2HSC dataset' (From Sensors To Human Spatial Concepts): http://www2.science.uva.nl/sites/cogniron/ The data comes from different indoor home environments. Each home has its own directory Data/Home1, Data/Home2, etc. There were a few runs within each home separated in Data/Home1/run1,Data/Home1/run2, etc. Sensor calibration data and results are available under Data/HomeX/Calibration. If you use any of the datasets please cite the following paper: "From images to rooms" Z. Zivkovic, O. Booij , B. Krose Robotic and Autonomous Systems, vol.55, no.5, pages 411-418, 2007. ##################################### ### Matlab toolbox ### ##################################### In order to allow the researchers a quick start we provide a Matlab toolbox with a set of functions for accessing the data; the data annotations; and the information about sensor calibration and their positioning on the robot. The provided functions can be divided into following groups: Geometrical - we provide a set of functions that can be used to perform various geometric transformations on the sensory data. For example a laser scan can be transformed to 3D world coordinates with respect to the robot and then these points can be projected to the omnidirectional camera image. Annotation - a data annotation tool is provided visualizing and changing the annotation. Demos - we provide a set of demonstration scripts that illustrate usage of the functions from the toolbox. ##################################### ### Odometry and Sonar range data ### ##################################### The file 'OdometryAndSonar.txt' holds both the odometry and sonar range data. The columns hold the following information: column description 1 timestamp of time of measurement, milliseconds since 1970 2 odometry, x coordinate in meters 3 odometry, y coordinate in meters 4 odometry, orientation in radians 5 odometry, translational velocity in meters per second 6 odometry, rotational velocity in radians per second The coordinate system used for the robots odometry is the standard Cartesian coordinate system where 0 orientation corresponds to the direction of the x axis. The orientation increases in anti-clockwise direction. All odometry information is relative to an arbitrary fixed point. column description 7 sonar range information at 0/16 * 2Pi radians in meters 8 sonar range information at 1/16 * 2Pi radians in meters 9 sonar range information at 2/16 * 2Pi radians in meters 10 sonar range information at 3/16 * 2Pi radians in meters 11 sonar range information at 4/16 * 2Pi radians in meters 12 sonar range information at 5/16 * 2Pi radians in meters 13 sonar range information at 6/16 * 2Pi radians in meters 14 sonar range information at 7/16 * 2Pi radians in meters 15 sonar range information at 8/16 * 2Pi radians in meters 16 sonar range information at 9/16 * 2Pi radians in meters 17 sonar range information at 10/16 * 2Pi radians in meters 18 sonar range information at 11/16 * 2Pi radians in meters 19 sonar range information at 12/16 * 2Pi radians in meters 20 sonar range information at 13/16 * 2Pi radians in meters 21 sonar range information at 14/16 * 2Pi radians in meters 22 sonar range information at 15/16 * 2Pi radians in meters All sonar range information is relative to the orientation of the robot where 0 radians corresponds to the forward direction of the robot. Radians increase in the anti-clockwise direction. All sonar cells are mounted on a ring with radius 0.19 meters centered over the center of rotation at a height of 0.26 meters. The sonar sensors do not measure simultaneously, each sonar sensor starts measuring 200 milliseconds after the previous sensor has processed its signal which in turns depends on the time it takes for the sound to come back. Therefore, the sonar measurements include a lot of data that was actually measured in the recent past. ##################################### ### SLAM corrected Odometry ### ##################################### The file 'OdometrySLAM.txt' holds the SLAM corrected odometry. The columns hold the following information: column description 1 timestamp of time of measurement, milliseconds since 1970 2 odometry, x coordinate in meters 3 odometry, y coordinate in meters 4 odometry, orientation in radians The data was produced using line features from range scans as described in: J.Folkesson, P.Jensfelt, H.I.Christensen, "Vision SLAM in the Measurement Subspace", In Proc. of the IEEE Int. Conf. on Robotics and Automation, 2005, Barcelona, Spain. ######################## ### Laser range data ### ######################## The file 'Scans.txt' holds the laser range information. The laser scanner has an opening angle of 180 degrees and measure distances every 0.5 degrees thus one scan consists of 361 measurements. The columns hold the following information: column description 1 timestamp of time of measurement, milliseconds since 1970 2 laser range information at 180/360 * Pi radians in meters 3 laser range information at 179/360 * Pi radians in meters ... ... 181 laser range information at 1/360 * Pi radians in meters 182 laser range information at 0/360 * Pi radians in meters 183 laser range information at -1/360 * Pi radians in meters ... ... 361 laser range information at -179/360 * Pi radians in meters 362 laser range information at -180/360 * Pi radians in meters The laser scanner measured at a height of approximately 0.57 meters from the ground. The scanner was mounted on the robot with an offset of approximately 69mm in the direction of the X axis and -5mm in the direction of the Y axis relative to the center of rotation of the robot (so 69mm forward and 5mm to the right). The maximum range the laser scanner is about 8 meters. ################## ### Image data ### ################## The file 'ImagesOmnicamT.txt' holds the image timestamps in milliseconds since 1970. The corresponding images are available in the corresponding 'ImagesOmnicam' directory in 'jpeg' format.