Abstract
Although recent (physical) robots have powerful sensors and actuators their abilities to show intelligent behavior is often limited. One key reason is the lack of an appropriate spatial representation. Spatial knowledge plays a crucial role in navigation, (self- and object-)localization, planning and reasoning for physically grounded robots. However, it is a major difficulty of most existing approaches that each of these tasks imposes heterogeneous requirements on the representation. In this paper, we propose an egocentric representation which relies on 1D ordering information that still provides sufficient allocentric information to solve navigation and (self- and object-)localization tasks. Furthermore, we claim that our approach supports an efficient, incremental process based on a simple 1D-representation.
