Logo U. Osnabrueck Institute of Computer ScienceKnowledge-Based Systems Research Group

Project Deutschland1

In this project we develop, together with our partners University of Hannover and Fraunhofer AIS, the software for controlling robots in rescue environments. At University of Osnabrück experiments are carried out with Kurt3D. Kurt3D is a mobile robot of type KURT2 that is equipped with a 3D laser scanner.

Partners

The team has its origins in the Fraunhofer AiS' RoboCup Rescue Team "Kurt3D" (2004) and presented the first 3D mapping rescue robot in Lisbon, scoring 2nd place. For more information click here. In 2005 the extended team "Deutschland1" entered the competition and scored sixth (out of 25 teams).
Kurt3D on stepfields

RoboCup Rescue

RoboCup Rescue is an international competition in which a mobile robot has to navigate in a geometrical and sensory challenging environment. The robot has to find, map, and estimate the condition of so called victims. The scientific challenges consist of mobility and autonomy.

Research Focus in Onsabrück

  1. 6D SPLAM. To build a map, the following three tasks have to run in a permanent cycle: (1) Plan and go to the next scan pose, (2) localize yourself in the current environment model, and (3) take a new scan and register it consistently with the previous model. We call this overall process SPLAM (Simultaneous Planning, Localization, and Mapping). At any time, the robot pose is to be determined in 6D, i.e., in coordinates x, y, z and yaw, pitch, and roll angles – wrt. a given coordinate system.
    We are working on the respective algorithms. See also the KURT3D project page.
  2. Autonomous Robot Driving. A hard challenge is to drive mobile robots in rescue environments. University of Osnabrück focusses on mastering the orange and yellow arena with a wheeled robot autonomously. The robot has to determine which surfaces are drivable using its onboard sensors, such as laser scanners, cameras and odometry.
    We are working on the respective algorithms.
  3. Multi Robot 3D Mapping. To build a 3D maps efficiently during the 10 minute competition, several robots have to work together. 3D maps originating from several sources have to be created.
    We are working on the respective algorithms.

Robots

2005 - Kurt3D (with RTS 3D ScanDrive) and RTS Crawler


Kurt3D Rescue Edition   RTS Crawler

2006

RTS Crawler and Kurt3D Rescue Edition
More pictures and videos of the 2006 RoboCup Rescue event can be found here.

Some Results