From a paper by P. Ji et al.
The algorithm employs a tightly coupled SLAM framework integrating LiDAR and inertial measurement unit (IMU). In the process of dynamic obstacle removal, the point cloud data is first gridded. To more comprehensively represent the point cloud information, the point cloud within the perception area is linearly discretized by height to obtain the distribution of the point cloud at different height layers, which is then encoded to construct a linear discretized height descriptor for dynamic region extraction.
To preserve more static feature points without altering the original point cloud, the Random Sample Consensus (RANSAC) ground fitting algorithm is employed to fit and segment the ground point cloud within the dynamic regions, followed by the removal of dynamic obstacles.
Finally, accurate point cloud poses are obtained through static feature matching. The proposed algorithm has been validated using open-source datasets and self-collected campus datasets. The results demonstrate that the algorithm improves dynamic point cloud removal accuracy by 12.3% compared to the ERASOR algorithm and enhances overall mapping and localization accuracy by 8.3% compared to the LIO-SAM algorithm, thereby providing a reliable environmental description for intelligent mobile vehicles.
Simultaneous Localization and Mapping (SLAM) technology represents one of the pivotal technologies that enables intelligent mobile vehicles to achieve autonomous navigation within unknown environments [1]. Vehicles employ onboard sensors to collect information pertaining to their surroundings, constructing environmental maps to ascertain their own positions.
As a high-precision spatial sensor, LiDAR has garnered widespread application in SLAM technology in recent years, owing to its high ranging accuracy and insensitivity to variations in lighting conditions. In comparison to visual-based approaches, LiDAR demonstrates substantial improvements in both robustness and accuracy [2]. Nonetheless, the majority of LiDAR SLAM systems presuppose that the surrounding environment is static. In practical applications, however, real-world environments are frequently replete with numerous dynamic obstacles, including pedestrians and moving vehicles.
For the complete paper CLICK HERE.
