In this article, research at Institute of Robotics and Mechatronics, German Aerospace Center (DLR) in the field of robot work-space exploration and modelling are presented. The robot shall be enabled to explore its work-space partially autonomously. Initially, the environment is completely or partially unknown, the robot’s task is to incrementally build up a representation of its surroundings.
Optical sensors like stereo vision, laser-range scanner and laser-stripe profiler are integrated into a multi-purpose vision system, the DLR 3D Modeller. It is mounted on the robot’s tool center point to acquire information about the robot’s environment. Fusion of range data into a consistent representation is performed to allow for safe path planning and view planning. This paper deals with 3D sensor technology, sensor synchronization und model generation. Algorithms for planning the next best views considering measurement noise and occlusion are theorized and evaluated for suitability for exploration.
Print ISSN: 0171-8096
Volume: 74, 03/2007
Pages: 139 - 146