Park, Soonyong Park, Mignon Park, Sung-Kee 2024-01-20T21:02:19Z 2024-01-20T21:02:19Z 2021-09-03 2009-08 1598-6446 https://pubs.kist.re.kr/handle/201004/132266 This paper presents new object-spatial layout-route based hybrid map representation and global localization approaches using a stereo camera. By representing objects as high-level features in a map, a robot can deal more effectively with different contexts such as dynamic environments, human-robot interaction, and semantic information. However, the use of objects alone for map representation has inherent problems. For example, it is difficult to represent empty spaces for robot navigation, and objects are limited to readily recognizable things. One way to overcome these problems is to develop a hybrid map that includes objects and the spatial layout of a local space. The map developed in this research has a hybrid structure that combines a global topological map and a local hybrid map. The topological map represents the spatial relationships between local spaces. The local hybrid map combines the spatial layout of the local space with the objects found in that space. Based on the proposed map, we suggest a novel coarse-to-fine global localization method that uses object recognition, point cloud fitting and probabilistic scan matching. This approach can accurately estimate robot pose with respect to the correct local space. English INST CONTROL ROBOTICS & SYSTEMS, KOREAN INST ELECTRICAL ENGINEERS REPRESENTATION SLAM Object-Spatial Layout-Route based Hybrid Map and Global Localization for Mobile Robots Article 10.1007/s12555-009-0411-5 1 INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS, v.7, no.4, pp.598 - 614 INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS 7 4 598 614 scie scopus kci ART001365964 000268509200011 2-s2.0-69749101797 Automation & Control Systems Automation & Control Systems Article REPRESENTATION SLAM Global localization hybrid map object recognition stereo vision