Abstract
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 Wall Plane Fusion 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 Scale Invariant Planar RANSAC (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 one 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 Unreal Engine and Microsoft Airsim. 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.
Highlights
Global localization for robotic vehicles is an essential backbone for robust autonomous navigation.In outdoor applications, the Global Positioning System (GPS) can be used to compute an accurate and inexpensive position solution, which is either not available or substantially degraded in indoor environments due to the blocking of signals by the building structure
The rest of the paper is organized as follows: Section 2 discusses current related work in the area of monocular vision localization; Section 3 provides a simple example of the entire positioning system; Section 4 provides details about the initialization framework and its design; Section 5 presents how the system produces continual positioning updates; Section 6 describes how a wall–plane association can be exploited as an external constraint to refine the camera motion via Bundle Adjustment optimization and enforce a global scale solution; Section 7 discusses the computational runtime of the system; Section 8 provides results running synthetic, simulation, and real-world tests on the localization system; and Section 9 concludes the paper
The Structure from Motion relative camera positions and 3D points are subsequently scaled by k∗, and this best wall–plane pair is used as an external constraint for a constrained Bundle Adjustment optimization
Summary
Global localization for robotic vehicles is an essential backbone for robust autonomous navigation. The approach pursued in this paper is to complement the visual information acquired by a monocular camera with the knowledge of the building floorplan The latter is accessible for many indoor environments and requires no prior equipment installation or exploration. The rest of the paper is organized as follows: Section 2 discusses current related work in the area of monocular vision localization; Section 3 provides a simple example of the entire positioning system; Section 4 provides details about the initialization framework and its design; Section 5 presents how the system produces continual positioning updates; Section 6 describes how a wall–plane association can be exploited as an external constraint to refine the camera motion via Bundle Adjustment optimization and enforce a global scale solution; Section 7 discusses the computational runtime of the system; Section 8 provides results running synthetic, simulation, and real-world tests on the localization system; and Section 9 concludes the paper
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
