First steps towards a robotic system for flexible volumetric mapping of indoor environments

The problem of building maps of the environment is one of the fundamental problems in mobile robotics. So far, the majority of research has focused on the problem of how to learn two-dimensional maps such as occupancy grids. Robots, however, operate in a three-dimensional world. Accordingly, robots that use tree-dimensional maps can be expected to be more reliable and robust than those relying on 2d maps. In this paper we describe a robotic system that is able to learn volumetric maps of the environment. The robot is equipped with a laser range scanner attached to a manipulator with four degrees of freedom. This allows the robot to scan into arbitrary directions and accurately explore its environment. We also describe the techniques used for 3d collision avoidance and path planning.