Navigation and mapping in large-scale space
AI Magazine
Topological mapping for mobile robots using a combination of sonar and vision sensing
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
Learning metric-topological maps for indoor mobile robot navigation
Artificial Intelligence
Artificial intelligence and mobile robots: case studies of successful robot systems
Artificial intelligence and mobile robots: case studies of successful robot systems
Robot Motion Planning
Globally Consistent Range Scan Alignment for Environment Mapping
Autonomous Robots
Integration of reactive behaviors and enhanced topological map for robust mobile robot navigation
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Mathematical morphology and binary geodesy for robot navigation planning
ICAPR'05 Proceedings of the Third international conference on Advances in Pattern Recognition - Volume Part I
| Hi-index | 0.00 |
Autonomous mobile robots need to use spatial information about the environment in order to effectively plan and execute navigation tasks. The information can be represented at different levels of abstraction, ranging from detailed geometric maps to coarse topological maps. Each level is adequate for some sub-task, but not for others. In this paper, we consider the representation of spatial knowledge at two different levels of abstraction, which are commonly considered in the robotics literature : the geometric level, and the topological level. We propose to represent the environment by local metric maps connected into a topological network. This technique allows us to use maps that are not metrically consistent on the global scale, although they are metrically consistent locally. The structure allows also the combination of abstract global reasoning and precise local geometric computations. Moreover, this structure reflects the typical organization of indoor environments, where rooms and hallways define independent but connected local working spaces. To navigate in the environment, the robot uses the topological information to plan a sequence of sectors to traverse, and uses the metric information in each sector to locally move within the sector and to the next one. The functioning of the proposed system with respect to omnidirectional mobile robots and results of simulated experiments are presented.