Real-time localization is a crucial task in various applications, such as automatic vehicles (AV), robotics, and smart city. This study proposes a framework for map-aided LiDAR-inertial localization, with the objective of accurately estimating the trajectory in a point clouds map. The proposed framework addresses the localization problem through a factor graph optimization (FGO), enabling the fusion of homogenous measurements for sensor fusion and designed absolute and relative constraints. Specifically, the framework estimates the light detection and ranging (LiDAR) odometry by leveraging inertial measurement unit (IMU) and registering corresponding featured points. To eliminate the accumulative error, this paper employs a ground plane distance and a map matching error to constraint the positioning error along the trajectory. Finally, local odometry and constraints are integrated using a FGO, including LiDAR odometry, IMU pre-integration, and ground constraints, map matching constraints, and loop closure. Experimental results were evaluated on an open-source dataset, UrbanNav, with an overall localization accuracy of 2.29 m (root mean square error, RMSE).

Recently, HD maps have various merits for achieving the highest level of self-localization accuracy, keeping track of the state of the road infrastructure and maintenance, and providing an indication if any repairs are required. Therefore, it is essential to keep the HD map up to date. However, the process of updating the HD map is exorbitant because the HD map is created using expensive sensor setups, and updating the map frequently via these setups will be costly. In this paper, a full pipeline is proposed for updating the HD map via a crowdsourced dataset that is collected with low-cost smartphone sensors. Furthermore, an Android application is developed and installed on a smartphone to collect the raw data. Once the dataset is collected from the area of interest, it will be uploaded automatically to the cloud server that is connected to the HD map database. Then, object detection, depth estimation, and matching algorithms are triggered on the cloud server to keep updating the HD map database. The positions of the detected objects from the crowdsourced dataset are estimated by using fused outputs of deep learning models and the Global navigation satellite system (GNSS) of a smartphone and then compared with the objects in the HD map through matching algorithms. The proposed model is considered the first comprehensive pipeline approach for updating HD maps with high a cost-effective and efficient solution.