Interleague Challenge Graz, 2009
The goal is here that teams can easier start to use real robots in the rescue league after they implemented robust algorithms in the simulation.
For this purpose I collected yesterday data with a Matilda Robot (the red robot standing between simulation and robot arena in Graz) in the Rescue Robot arena (the maze).
I drove the entire maze while going up and down all the ramps and rolls. The logfile now contains data from two laser range finders (one horizontal and one vertical), and data
from an IMU.
The two lasers (Hokuyo URG) have the following specifica:
Num ranges: 682
Field of view: 240 Deg
Angular resolution: 0.35 Deg
Maximal Range 5 Meters
The IMU data provides yaw, roll, and pitch. The yaw angle comes from the gyroscope (integrated over time).
I uploaded the logfile and a Player for it. When you execute the player you will have exactly the same as the USARSim server. So all you have to do is to connect
to this server and run your mapping algorithm.
I would like everyone to provide me a file containing each line the estimated pose of the robot and timestamp:
x, y, th, timestamp,
where x,y, are in meters, th in rad, and timestamp in seconds. Please note that the timestamp has to be according to the timestamp of the original data and not of your PC's current time!
The player can be found at:
www.informatik.uni-freiburg.de/~kleiner/matildaInterface.tgz
The logfile can be found at:
www.informatik.uni-freiburg.de/~kleiner/maze_graz09.usar.gz
I would like to collect the results at Friday. Please send them to: kleiner@informatik.uni-freiburg.de
How it works:
Contact: A. Kleiner, University of Freiburg
Description:
The RoboCupRescue initiative, represented by real-robot and simulation league, is designed to foster the research and development of innovative technologies and assistive capabilities to help responders mitigate an emergency response situation. This competition model employed by the RobocupRescue community has proven to be a propitious model, not only for fostering the development of innovative technologies but in the development of test methods used to quantitatively evaluate the performance of these technologies. The Interleague Challenge has been initiated to evaluate real-world performance of algorithms developed in simulation, as well as to drive the development of a common interface to simplify the entry of newcomer teams to the robot league. This page shows the development of emerging test methods used to evaluate robotic-mapping, the development of a common robotic platform, and the development of a novel map evaluation methodology deployed during the RoboCupRescue competition 2009.
Check out our paper at Permis 2009!
