The fusion framework based on Light Detection and Ranging (LiDAR) and vision is susceptible to environmental constraints. Therefore, they are unable to adapt to complex and challenging environments. In response to this, this paper proposes a tightly coupled framework based on Global Navigation Satellite System (GNSS) data, which tightly couples GNSS, inertial, LiDAR and visual data. The experimental results demonstrate that, using publicly available challenging environment datasets, the proposed fusion system can achieve a 52.68% improvement in positioning accuracy compared to some existing fusion algorithms.
GVIL: Tightly Coupled GNSS-Visual-Inertial-Lidar for Position Estimation in Challenging Environments
24.06.2024
1209671 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Unified multi-modal landmark tracking for tightly coupled lidar-visual-inertial odometry
BASE | 2022
|