A Hierarchic World Model Supporting Video-based Localization, Exploration and Object Identification

Abstract

The design of mobile robots which can cope with unexpected disturbances like obstacles or misplaced objects is an active field of research. Such an autonomous robot assesses the situation by comparing data from one or more sensors with an internal representation of its environment. In this paper we present a hierarchically structured world model that combines a general geometric object representation with sensor- and task-specific features and therefore can be used for various sensors and perception tasks. A symbolic layer enables communication with planning instances or other robots. 1 Introduction This work is part of a research project towards development of autonomous mobile robots (AMR) which can fulfil service and transport tasks in structured environments like office buildings and industrial plants. For planning its actions such an autonomous robot needs an internal representation of its environment (environ- mental or world model). To keep this representation up to date it co...