Abstract
High-precision 3D maps play an important role in autonomous driving. The current mapping system performs well in most circumstances. However, it still encounters difficulties in the case of the Global Navigation Satellite System (GNSS) signal blockage, when surrounded by too many moving objects, or when mapping a featureless environment. In these challenging scenarios, either the global navigation approach or the local navigation approach will degenerate. With the aim of developing a degeneracy-aware robust mapping system, this paper analyzes the possible degeneration states for different navigation sources and proposes a new degeneration indicator for the point cloud registration algorithm. The proposed degeneracy indicator could then be seamlessly integrated into the factor graph-based mapping framework. Extensive experiments on real-world datasets demonstrate that the proposed 3D reconstruction system based on GNSS and Light Detection and Ranging (LiDAR) sensors can map challenging scenarios with high precision.
Highlights
Rapid progress has been witnessed in the field of unmanned ground vehicles (UGVs) [1,2]
These include the Global Navigation Satellite System (GNSS) factor produced by the GNSS information; the local odometry factor produced by the wheel odometer and IMU, and the scan matching factor generated by the preprocessed Light Detection and Ranging (LiDAR) scans
Each platform is equipped with a multi-channel LiDAR, an IMU, a wheel encoder, and a Novatel Propack 7 GNSS/Inertial Navigation System (INS) system
Summary
Rapid progress has been witnessed in the field of unmanned ground vehicles (UGVs) [1,2]. For the global navigation information, the GNSS signal might become inaccurate due to the blockage of tall buildings or the well-known multi-path effect [10] It may even become unavailable in certain scenarios, such as under bridges, in tunnels, in underground parking lots, etc. A factor graph-based fusion framework is proposed which could suitably integrate the global navigation information with local navigation information in a probabilistic way. A new robust degeneration indicator is proposed for the local navigation approach which could reliably estimate the degeneration state of the scan matching algorithm. The proposed mapping system has been extensively tested on real-world datasets in several challenging scenarios, including busy urban scenarios, featureless off-road scenarios, high bridges, highways, and large-scale settings.
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.
