Global Monocular Indoor Positioning of a Robotic Vehicle with a Floorplan
This paper presents a global monocular indoor positioning system for a robotic vehicle starting from a known pose. The proposed system does not depend on a dense 3D map, require prior environment exploration or installation, or rely on the scene remaining the same, photometrically or geometrically....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/3/634 |
| _version_ | 1797999265498267648 |
|---|---|
| author | John Noonan Hector Rotstein Amir Geva Ehud Rivlin |
| author_facet | John Noonan Hector Rotstein Amir Geva Ehud Rivlin |
| author_sort | John Noonan |
| collection | DOAJ |
| description | This paper presents a global monocular indoor positioning system for a robotic vehicle starting from a known pose. The proposed system does not depend on a dense 3D map, require prior environment exploration or installation, or rely on the scene remaining the same, photometrically or geometrically. The approach presents a new way of providing global positioning relying on the sparse knowledge of the building floorplan by utilizing special algorithms to resolve the unknown scale through wall⁻plane association. This <i>Wall Plane Fusion</i> algorithm presented finds correspondences between walls of the floorplan and planar structures present in the 3D point cloud. In order to extract planes from point clouds that contain scale ambiguity, the <i>Scale Invariant Planar RANSAC</i> (SIPR) algorithm was developed. The best wall⁻plane correspondence is used as an external constraint to a custom Bundle Adjustment optimization which refines the motion estimation solution and enforces a global scale solution. A necessary condition is that only <i>one</i> wall needs to be in view. The feasibility of using the algorithms is tested with synthetic and real-world data; extensive testing is performed in an indoor simulation environment using the <i>Unreal Engine</i> and <i>Microsoft Airsim</i>. The system performs consistently across all three types of data. The tests presented in this paper show that the standard deviation of the error did not exceed 6 cm. |
| first_indexed | 2024-04-11T11:01:53Z |
| format | Article |
| id | doaj.art-67017e04e1d046f4ab99153ab0549da2 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T11:01:53Z |
| publishDate | 2019-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-67017e04e1d046f4ab99153ab0549da22022-12-22T04:28:30ZengMDPI AGSensors1424-82202019-02-0119363410.3390/s19030634s19030634Global Monocular Indoor Positioning of a Robotic Vehicle with a FloorplanJohn Noonan0Hector Rotstein1Amir Geva2Ehud Rivlin3Department of Computer Science, Technion—Israel Institute of Technology, Haifa 3200003, IsraelDepartment of Electrical Engineering, Technion—Israel Institute of Technology, Haifa 3200003, IsraelDepartment of Computer Science, Technion—Israel Institute of Technology, Haifa 3200003, IsraelDepartment of Computer Science, Technion—Israel Institute of Technology, Haifa 3200003, IsraelThis paper presents a global monocular indoor positioning system for a robotic vehicle starting from a known pose. The proposed system does not depend on a dense 3D map, require prior environment exploration or installation, or rely on the scene remaining the same, photometrically or geometrically. The approach presents a new way of providing global positioning relying on the sparse knowledge of the building floorplan by utilizing special algorithms to resolve the unknown scale through wall⁻plane association. This <i>Wall Plane Fusion</i> algorithm presented finds correspondences between walls of the floorplan and planar structures present in the 3D point cloud. In order to extract planes from point clouds that contain scale ambiguity, the <i>Scale Invariant Planar RANSAC</i> (SIPR) algorithm was developed. The best wall⁻plane correspondence is used as an external constraint to a custom Bundle Adjustment optimization which refines the motion estimation solution and enforces a global scale solution. A necessary condition is that only <i>one</i> wall needs to be in view. The feasibility of using the algorithms is tested with synthetic and real-world data; extensive testing is performed in an indoor simulation environment using the <i>Unreal Engine</i> and <i>Microsoft Airsim</i>. The system performs consistently across all three types of data. The tests presented in this paper show that the standard deviation of the error did not exceed 6 cm.https://www.mdpi.com/1424-8220/19/3/634indoor positioningrobotic vehiclevision-based navigationfloorplan |
| spellingShingle | John Noonan Hector Rotstein Amir Geva Ehud Rivlin Global Monocular Indoor Positioning of a Robotic Vehicle with a Floorplan Sensors indoor positioning robotic vehicle vision-based navigation floorplan |
| title | Global Monocular Indoor Positioning of a Robotic Vehicle with a Floorplan |
| title_full | Global Monocular Indoor Positioning of a Robotic Vehicle with a Floorplan |
| title_fullStr | Global Monocular Indoor Positioning of a Robotic Vehicle with a Floorplan |
| title_full_unstemmed | Global Monocular Indoor Positioning of a Robotic Vehicle with a Floorplan |
| title_short | Global Monocular Indoor Positioning of a Robotic Vehicle with a Floorplan |
| title_sort | global monocular indoor positioning of a robotic vehicle with a floorplan |
| topic | indoor positioning robotic vehicle vision-based navigation floorplan |
| url | https://www.mdpi.com/1424-8220/19/3/634 |
| work_keys_str_mv | AT johnnoonan globalmonocularindoorpositioningofaroboticvehiclewithafloorplan AT hectorrotstein globalmonocularindoorpositioningofaroboticvehiclewithafloorplan AT amirgeva globalmonocularindoorpositioningofaroboticvehiclewithafloorplan AT ehudrivlin globalmonocularindoorpositioningofaroboticvehiclewithafloorplan |