Pole-Like Object Extraction and Pole-Aided GNSS/IMU/LiDAR-SLAM System in Urban Area

Abstract

Vision-based sensors such as LiDAR (Light Detection and Ranging) are adopted in the SLAM (Simultaneous Localization and Mapping) system. In the 16-beam LiDAR aided SLAM system, due to the difficulty of object detection by sparse laser data, neither the grid-based nor feature point-based solution can avoid the interference of moving objects. In an urban environment, the pole-like objects are common, invariant and have distinguishing characteristics. Therefore, it is suitable to bring more robust and reliable positioning results as auxiliary information in the process of vehicle positioning and navigation. In this work, we proposed a scheme of a SLAM system using a GNSS (Global Navigation Satellite System), IMU (Inertial Measurement Unit) and LiDAR sensor using the position of pole-like objects as the features for SLAM. The scheme combines a traditional preprocessing method and a small scale artificial neural network to extract the pole-like objects in environment. Firstly, the threshold-based method is used to extract the pole-like object candidates from the point cloud, and then, the neural network is applied for training and inference to obtain pole-like objects. The result shows that the accuracy and recall rate are sufficient to provide stable observation for the following SLAM process. After extracting the poles from the LiDAR point cloud, their coordinates are added to the feature map, and the nonlinear optimization of the front end is carried out by utilizing the distance constraints corresponding to the pole coordinates; then, the heading angle and horizontal plane translation are estimated. The ground feature points are used to enhance the elevation, pitch and roll angle accuracy. The performance of the proposed navigation system is evaluated through field experiments by checking the position drift and attitude errors during multiple two-min mimic GNSS outages without additional IMU motion constrain such as NHC (Nonholonomic Constrain). The experimental results show that the performance of the proposed scheme is superior to that of the conventional feature point grid-based SLAM with the same back end, especially in congested crossroads where slow-moving vehicles are surrounded and pole-like objects are rich in the environment. The mean plane position error during two-min GNSS outages was reduced by 38.5%, and the root mean square error was reduced by 35.3%. Therefore, the proposed pole-like feature-based GNSS/IMU/LiDAR SLAM system can fuse condensed information from those sensors effectively to mitigate positioning and orientation errors, even in a short-time GNSS denied environment.

LiDAR Odometry by Deep Learning-based Feature Points with Two-step Pose Estimation

“…The information from adjacent scan lines is not fully utilized. In [19], [20], common landmarkers extracted from infrastructures in urban areas such as poles and traffic boards are also employed for LiDAR scan matching. These types of method are constrained in some certain areas, and might be ineffective in country or highway.…”

Lidar-Inertial Navigation Based on Map Aided Distance Constraint and Factor Graph Optimization

“…On the other hand, featurebased algorithms extract geometric and semantic features and register the corresponding features with the prior LiDAR maps. For example, in (Chen et al, 2019;Liu et al, 2020;Schaefer et al, 2019), semantic patches (e.g., pole like objects) are considered as stable points to provide environmental context for localization tasks. In (Cho et al, 2022;Yan et al, 2019), feature spaces consist of semantic descriptors generated from the vectorized models of roads and building boundaries, representing the distribution of traffic elements.…”

Sensors and Sensor’s Fusion in Autonomous Vehicles

“…Liu T. et al [ 12 ] proposed a SLAM (simultaneous localization and mapping) scheme using GNSS (global navigation satellite system), IMU (inertial measurement unit) and LiDAR (light detection and ranging) sensor, using the position of pole-like objects as features for SLAM. The scheme combines a traditional preprocessing method and a small-scale artificial neural network to extract pole-like objects in the environment.…”