Hybrid Metric-Topological 3D Occupancy Grid Maps for Large-scale Mapping

This paper presents a large-scale 3D environment mapping solution for mobile robots that is based on hybrid metric-topological maps. If a robot performs simultaneous localization and mapping (SLAM) while exploring an unknown environment, sometimes loops are closed and the whole SLAM graph has to be optimized. If a conventional occupancy grid mapping algorithm using a monolithic map is used, the whole occupancy grid map has to be rebuilt after optimization, which for large maps can easily become too time consuming for real-time operation. In the same way, path planning on very large occupancy grid maps can become computationally too expensive. Hybrid metric-topological maps can solve both problems. The global metric map is divided into sub-maps and a global topological graph is formed on the map. This allows recomputing only isolated areas of the map, whereas others can remain unchanged. The topological graph allows efficient path planning on the hybrid map. We show that the hybrid mapping approach presented here is considerably faster than conventional methods. Within the same time, it can generate more detailed maps of large environments. The computation time for maps with identical level of detail can be improved by up to two orders of magnitude.