Recent advances in precise navigation have extensively utilized the integration of Global Navigation Satellite System (GNSS) and Inertial Navigation System (INS), particularly in the domain of intelligent vehicles. However, the efficacy of such navigation systems is considerably compromised by the reflection and multipath disruptions of non-light-of-sight (NLOS) signals. Light Detection and Ranging (LiDAR)-based odometry, an active perception-based sensor known for its precise 3D measurements, has become increasingly prevalent in augmenting navigation systems. Nonetheless, the assimilation of LiDAR odometry with GNSS/INS systems presents substantial challenges. Addressing these challenges, this study introduces a two-phase sensor fusion (TPSF) approach that synergistically combines GNSS positioning, LiDAR odometry, and IMU pre-integration through a dual-stage sensor fusion process. The initial stage employs an Extended Kalman Filter (EKF) to amalgamate the GNSS solution with IMU Mechanization, facilitating the estimation of IMU biases and system initialization. Subsequently, the second stage integrates scan-to-map LiDAR odometry with IMU mechanization to support continuous LiDAR factor estimation. Factor graph optimization (FGO) is then utilized for the comprehensive fusion of LiDAR factors, IMU pre-integration, and GNSS solutions. The efficacy of the proposed methodology is corroborated through rigorous testing on a demanding trajectory from an urbanized open-source dataset, with the system demonstrating a notable enhancement in performance compared to the state-of-the-art algorithms, achieving a translational Standard Deviation (STD) of 1.269 meters.

Object-level simultaneous localization and mapping (SLAM) has gained popularity in recent years since it can provide a means for intelligent robot-to-environment interactions. However, most of these methods assume that the distribution of the errors is Gaussian. This assumption is not valid under many circumstances. Further, these methods use a delayed initialization of the objects in the map. During this delayed period, the solution relies on the motion model provided by an inertial measurement unit (IMU). Unfortunately, the errors tend to accumulate quickly due to the dead-reckoning nature of these motion models. Finally, the current solutions depend on a set of salient features on the object’s surface and not the object’s shape. This research proposes an accurate object-level solution to the SLAM problem with a 4.1 to 13.1 cm error in the position (0.005 to 0.021 of the total path). The developed solution is based on Rao–Blackwellized Particle Filtering (RBPF) that does not assume any predefined error distribution for the parameters. Further, the solution relies on the shape and thus can be used for objects that lack texture on their surface. Finally, the developed tightly coupled IMU/camera solution is based on an undelayed initialization of the objects in the map.

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).

Accurate, reliable and infrastructure-free indoor positioning using a smartphone is considered an essential topic for applications such as indoor emergency response and indoor path planning. While the inertial measurement units (IMU) offer continuous and high-frequency motion data, pedestrian dead reckoning (PDR) based on IMU data suffers from significant and accumulative errors. Map-aided particle filters (PFs) are important pose estimation frameworks that have exhibited capabilities to eliminate drifts by incorporating additional constraints from a pre-built floor map, without relying on other wireless or perception-based infrastructures. However, despite the recent approaches, a key challenging issue remains: existing map-aided PF-PDR solutions are computationally demanding, as they typically rely on a large number of particles and require map boundaries to eliminate non-matching particles. This process introduces substantial computational overhead, limiting efficiency and real-time performance on resource-constrained platforms such as smartphones. To address this key issue, this work proposes a novel map-aided PF-PDR framework that leverages a smartphone’s IMU data and a pre-built vectorized floor plan map. The proposed method introduces an adaptive PF-PDR solution that detects particle convergence using a cross-entropy distance of the particles and a Gaussian distribution. The number of particles is reduced significantly after a convergence is detected. Further, in order to reduce the computational cost, only the heading is included in particle attitude sampling. The heading is estimated accurately by levelling gyroscope measurements to a virtual plane, parallel to the ground. Experiments are performed using a dataset collected on a smartphone and the results demonstrate improved performance, especially in drift reduction, achieving an mean position error of 0.9 m and a processing rate of 37.0 Hz.

Object-level Simultaneous Localization and Mapping (SLAM) has gained popularity in recent years since it can provide a means for intelligent robot-to-environment interactions. However, most of these methods assume that the distribution of the errors is gaussian. This assumption is not valid under many circumstances. Further, these methods use a delayed initialization of the objects in the map. During this delayed period, the solution relies on the motion model provided by an Inertial Measurement Unit (IMU). Unfortunately, the errors tend to accumulate quickly due to the dead-reckoning nature of these motion models. Finally, the current solutions depend on a set of salient features on the object’s surface and not the object’s shape. This research proposes an accurate object-level solution to the SLAM problem with a 4.1 to 13.1 cm error in the position (0.005 to 0.021 of the total path). The developed solution is based on Rao-blackwellized Particle Filtering (RBPF) that does not assume any predefined error distribution for the parameters. Further, the solution relies on the shape and thus can be used for objects that lack texture on their surface. Finally, the developed tightly coupled IMU/camera solution is based on an undelayed initialization of the objects in the map.

Lane Detection is a critical component of an autonomous driving system that can be integrated alongside with High-definition (HD) map to improve accuracy and reliability of the system. Typically, lane detection is achieved using computer vision algorithms such as edge detection and Hough transform, deep learning-based algorithms, or motion-based algorithms to detect and track the lanes on the road. However, these approaches can contain incorrectly detected line segments with outliers. To address these issues, we proposed a vanishing point aided lane detection method that utilizes both camera and LiDAR sensors, and then employs a RANSAC-based post-processing method to remove potential outliers to improve the accuracy of the detected lanes. We evaluated this method on four datasets provided from the KITTI Benchmark Suite and achieved a total precision of 87%.