Andreas Nuechter 24 05 2007

From EECS

Abstract

Digital 3D models of the environment are needed in rescue and inspection robotics, facility managements and architecture. This talk presents an automatic robotic system for gaging, digitalization and interpreting of 3D environments.

Intelligent autonomous acting in unstructured environments requires 3D maps with labeled 3D objects. 3D maps are necessary to avoid collisions with complex obstacles and to self localize in six degrees of freedom (x-, y-, z-position, roll, yaw and pitch angle). Meaning becomes inevitable, if the robot has to interact with its environment. The robot is then able to reason about the objects; its knowledge becomes inspectable and communicable. These arguments lead to requiring automatic and fast semantic environment modeling in robotics. A revolutionary method for gaging environments are 3D scanners, which enable robots to scan objects in a non-contact way in three dimensions. The presented work examines and evaluates the algorithms needed for automatic semantic 3D map building using a 3D laser range finder and a mobile robot, e.g., Kurt3D, RTS Dora or RTS Erkia.

An short overview can be found here: http://kos.informatik.uni-osnabrueck.de/download/Erika/Overview.mpg