Global navigation satellite system (GNSS) positioning can be significantly degraded due to multipath and non-line-of-sight (NLOS) signals in urban areas. Cellular vehicle-to-everything (C-V2X) technology provides new opportunities to enhance GNSS performance from a single intelligent vehicle by leveraging roadside GNSS (RSG) and C-V2X. Inspired by this, we propose an RSG-aided GNSS/LiDAR/IMU (RSG-GLIO) method to achieve reliable odometry and mapping, which leverages the high-quality double-differenced (DD) measurements provided by nearby RSG, effectively mitigating shared random errors such as multipath and NLOS. Our RSG-GLIO first estimates the absolute state of the vehicle using onboard sensors. Utilizing this initial positioning estimate, the proposed method introduces a coarse-to-fine selection scheme to identify consistent DD observations from available RSG measurements. Finally, the consistent roadside DD constraints are jointly optimized into factor graph optimization (FGO). Static and dynamic data are extensively evaluated using multiple RSG receivers deployed in the Hong Kong C-V2X testbed to evaluate the effectiveness of roadside-aided positioning. The results demonstrate a significant 36.6% improvement in terms of absolute positioning accuracy compared to the state-of-the-art GLIO method. Furthermore, we showcase the potential for employing RSG as low-cost base stations in dense urban areas. The data of our work is publicly accessible at https://github.com/DarrenWong/RSG-GLIO.

Pedestrian location tracking in emergency responses and environmental surveys of indoor scenarios tend to rely only on their own mobile devices, reducing the usage of external services. Low-cost and small-sized inertial measurement units (IMU) have been widely distributed in mobile devices. However, they suffer from high-level noises, leading to drift in position estimation over time. In this work, we present a graph-based indoor 3D pedestrian location tracking with inertial-only perception. The proposed method uses onboard inertial sensors in mobile devices alone for pedestrian state estimation in a simultaneous localization and mapping (SLAM) mode. It starts with a deep vertical odometry-aided 3D pedestrian dead reckoning (PDR) to predict the position in 3D space. Environment-induced behaviors, such as corner-turning and stair-taking, are regarded as landmarks. Multi-hypothesis loop closures are formed using statistical methods to handle ambiguous data association. A factor graph optimization fuses 3D PDR and behavior loop closures for state estimation. Experiments in different scenarios are performed using a smartphone to evaluate the performance of the proposed method, which can achieve better location tracking than current learning-based and filtering-based methods. Moreover, the proposed method is also discussed in different aspects, including the accuracy of offline optimization and proposed height regression, and the reliability of the multi-hypothesis behavior loop closures. The video (YouTube) or (BiliBili) is also shared to display our research.

We propose Stacked Deep Sets and Quantile Pooling for learning tasks on set data. We introduce Quantile Pooling, a novel permutation-invariant pooling operation that synergizes max and average pooling. Just like max pooling, quantile pooling emphasizes the most salient features of the data. Like average pooling, it captures the overall distribution and subtle features of the data. Like both, it is lightweight and fast. We demonstrate the effectiveness of our approach in a variety of tasks, showing that quantile pooling can outperform both max and average pooling in each of their respective strengths. We also introduce a variant of deep set networks that is more expressive and universal. While Quantile Pooling balances robustness and sensitivity, Stacked Deep Sets enhances learning with depth.