Localization plays a vital role in the mobile robot navigation system and is a fundamental capability for the following path planning task. In an indoor environment where the global positioning system signal fails or becomes weak, the wireless sensor network (WSN) or simultaneous localization and mapping (SLAM) scheme gradually becomes a research hot spot. WSN method uses received signal strength indicator (RSSI) values to determine the position of the target signal node, however, the orientation of the target node is not clear. Besides, the distance error is large when the indoor signal receives interference. The laser SLAM-based method usually uses a 2D laser Lidar to build an occupancy grid map, then locates the robot according to the known grid map. Unfortunately, this scheme only works effectively in those areas with salient geometrical features. The traditional particle filter always fails for areas with similar structures, such as a long corridor. To solve their shortcomings, this paper proposes a novel coarse-to-fine paradigm that uses WSN to assist mobile robot localization in a geometrically similar environment. Firstly, the fingerprints database is built in the offline stage to get reference distance information. The distance data is determined by the statistical mean value of multiple RSSI values. Secondly, a hybrid map with grid cells and RSSI values is constructed when the mobile robot moves from a starting point to the ending place. Thirdly, the RSSI values are thought of as a basic reference to get a coarse localization. Finally, an improved particle filtering method is presented to achieve fine localization. Experimental results demonstrate that our approach is effective and robust for global localization. The localization success rate reaches 97.0% and the average moving distance is only 0.74 meters, while the traditional method always fails. In addition, the method also works well when the mobile robot is kidnapped to another position in the environment.
Localization is a fundamental capability for an autonomous mobile robot, especially in the navigation process. The commonly used laser-based simultaneous localization and mapping (SLAM) method can build a grid map of the indoor environment and realize localization task. However, when a robot comes to a long corridor where there exists many geometrically symmetrical and similar structures, it often fails to position itself. Besides, the environment is not represented to a semantic level that the robot cannot interact well with users. To solve these crucial issues, in this paper, we propose an improved visual SLAM approach to realize a robust and precise global localization. The system is divided into two main steps. The first step is to construct a topological semantic map using visual SLAM, text detection and recognition, and laser sensor data. The second step is the localization which repeats part work of the first step but makes the best use of the prebuilt semantic map. Experiments show that our approach and solutions perform well and localize successfully almost everywhere in the corridor environment while traditional methods fail.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.