Pose estimation is a crucial problem in simultaneous localization and mapping (SLAM). However, developing a robust and consistent state estimator remains a significant challenge, as the traditional extended Kalman filter (EKF) struggles to handle the model nonlinearity, especially for inertial measurement unit (IMU) and light detection and ranging (LiDAR). To provide a consistent and efficient solution of pose estimation, we propose Eq-LIO, a robust state estimator for tightly coupled LIO systems based on an equivariant filter (EqF). Compared with the invariant Kalman filter based on the SE2(3) group structure, the EqF uses the symmetry of the semi-direct product group to couple the system state including IMU bias, navigation state, and LiDAR extrinsic calibration state, thereby suppressing linearization error and improving the behavior of the estimator in the event of unexpected state changes. The proposed Eq-LIO owns natural consistency and higher robustness, which is theoretically proven with mathematical derivation and experimentally verified through a series of tests on both public and private datasets.

Visual semantic SLAM integrates geometric measurements with semantic perception, making it widely applicable in autonomous driving and robotics. Semantic-assisted localization and dynamic object perception are two critical tasks in visual semantic SLAM. However, many existing state-of-the-art methods address only one of these tasks in isolation. To address issues of functional limitations and insufficient information utilization in a single framework, we propose a unified visual semantic SLAM framework, SDS-SLAM, which tightly couples static and dynamic semantic information to handle the motion estimation of both the camera and observed objects in driving scenarios. A multi-task network for driving perception is employed to extract semantic information, including drivable areas, lanes, and vehicles. Based on various information obtained, we propose semantic local ground manifolds (SLGMs) to represent the geometric structure and semantic features, enabling the online generation of a lightweight semantic map. Subsequently, we integrate SLGM-based constraints such as lane alignment and planar motion to promote camera and object pose estimation. We evaluated our method on the public KITTI dataset and self-collected real-world data. The results demonstrate that our method effectively perceives both dynamic and static semantic elements in driving scenarios, achieving high accuracy in estimating the poses of the camera and objects.

Edge computing is considered as a promising paradigm to support vehicular applications in the upcoming sixth-generation (6G) vehicular networks. In the context of vehicular edge computing (VEC), the self-interested vehicular users and edge servers work towards incongruous goals. Such mixed-motive setting is detrimental to the collective good, sometimes leading to social dilemmas. To resolve such a conflict, we first formulate a bi-level optimization problem to model mixed-motive task offloading. In this case, vehicular users aim to improve energy efficiency under strict low-latency requirements, whereas edge servers attempt to increase serving efficiency. To address it, we propose a scheme based on bi-level reinforcement learning, i.e., bi-level multi-agent actor-critic (BLMAAC) framework. Specifically, upper-level edge servers make iterative optimization under the best responses of lower-level vehicular users, which can be regarded as a Stackelberg game. Theoretically, we identify the conditions and prove the convergence of the framework that is able to reach Stackelberg equilibrium strategy. By numerical evaluation, the high-utilization edge servers and energy-efficient vehicular users demonstrate the superiority of the bi-level structure. Moreover, the proposed scheme outperforms other actor-critic based learning algorithms and two-stage methods exploring Nash equilibrium strategy.

Continuous and highly accurate positioning of land vehicles continues to be a substantial challenge in urban GNSS-denied environments. Although the vehicle motion model (VMM) is fused to mitigate the positioning error, the problems of position error accumulation over a distance remain. Hence, we introduce an innovative multi-information integrated navigation approach that leverages visual semantics in conjunction with a lightweight high-definition (LHD) map for absolute position refinement. This method enhances the navigation solution by integrating a vehicle-mounted GNSS/INS system with the precise localization capabilities of road semantics, such as lane lines and poles, through camera vision. We establish a comprehensive road semantic measurement model in the pixel frame to directly use raw pixel data for a tightly coupled integration process. Additionally, we examine the distinct contributions of lane lines and poles to the estimation of navigation error states using a simplified measurement model. Field tests with land vehicles demonstrate the efficacy of our proposed method and show that the longitudinal and lateral positioning errors decrease to 0.43 meters and approximately 0.27 meters, which are significant enhancements due to road semantic cues.

The goal of visual navigation is steering an agent to find a given target object with current observation. It is crucial to learn an informative visual representation and robust navigation policy in this task. Aiming to promote these two parts, we propose three complementary techniques, heterogeneous relation graph (HRG), a value regularized navigation policy (VRP), and gradient-based meta learning (ML). HRG integrates object relationships, including object semantic closeness and spatial directions, e.g., a knife is usually co-occurrence with bowl semantically or located at the left of the fork spatially. It improves visual representation learning. Both VRP and gradient-based ML improve robust navigation policy, regulating this process of the agent to escape from the deadlock states such as being stuck or looping. Specifically, gradient-based ML is a type of supervision method used in policy network training, which eliminates the gap between the seen and unseen environment distributions. In this process, VRP maximizes the transformation of the mutual information between visual observation and navigation policy, thus improving more informed navigation decisions. Our framework shows superior performance over the current state-of-the-art (SOTA) in terms of success rate and success weighted by length (SPL). Our HRG outperforms the Visual Genome knowledge graph on cross-scene generalization with$\approx$$56\%$and$\approx$$39\%$improvement on Hits@$5^{*}$(proportion of correct entities ranked in top 5) and MRR$^{*}$(mean reciprocal rank), respectively. Our code and HRG datasets will be made publicly available in the scientific community.

Spectrum sharing in cellular vehicle-to-everything (C-V2X) has been conceived as a promising solution to improve spectrum efficiency. However, the co-channel interference incurred with it may cause severe performance degradation to vehicular links. Thereby, radio resource management (RRM) is motivated and designed to ensure communication reliability and increase system capacity. One challenge is that RRM involves channel allocation and power control, which are tightly coupled and hard to optimize simultaneously. Another challenge for this is the difficulty adapting centralized RRM schemes, requiring global channel state information (CSI) and causing high signaling overhead. To tackle these challenges, we propose the hybrid centralized-distributed RRM scheme and the distributed RRM scheme. Specifically, we prove a decoupling method that provides a theoretical lower bound so that channel allocation and power control can be optimized independently. Given the decoupling method, the hybrid centralized-distributed RRM scheme is based on graph matching and reinforcement learning (GMRL) to maximize system capacity and guarantee reliability requirements. Further, to decrease computation complexity and signaling overhead, the distributed RRM scheme that only requires local CSI with hybrid-framework reinforcement learning (HFRL) is exploited. Finally, both schemes are numerically evaluated through experiments and outperform other deep Q-network (DQN)-based schemes.

Acquiring accurate and reliable pedestrian trajectories is essential for providing indoor location-based services. Although a foot-mounted inertial navigation system (Foot-INS) can acquire pedestrian trajectories in multistory buildings, it will inevitably encounter heading divergence because the constraint information is not always valid. Therefore, we proposed an accurate and convenient postprocessing indoor pedestrian positioning system (IPPS) to acquire pedestrian trajectories in multistory buildings such as shopping malls. Based on the hypotheses that the start and end points of the pedestrian trajectories on a single floor were closed, and the horizontal position of the closing point on each floor was identical. Therefore, in the single floor of multistory buildings, we use the closing point to control the trajectory drift error caused by the Foot-INS, and use a smoothing algorithm to reasonably distribute the drift error to the entire trajectory. Heading divergence is unavoidable with the Foot-INS, result in the pedestrian trajectories acquired on different floors were rotationally offset. Because pedestrian trajectories can epitomize the building orientation and provide an opportunity to align those trajectories on multistory buildings, an algorithm was proposed to match the trajectories acquired on different floors. A hybrid simulation experiment was conducted using an accurate reference object to evaluate the positioning performance of the proposed IPPS. The effectiveness of acquiring pedestrian trajectories was also confirmed by various experimental tests in a large shopping mall. The study findings suggest that the proposed IPPS is self-contained, low cost, and has the potential for large-scale applications.

The assumption of static scenes limits the performance of traditional visual SLAM. Many existing solutions adopt deep learning methods or geometric constraints to solve the problem of dynamic scenes, but these schemes are either low efficiency or lack of robustness to a certain extent. In this paper, we propose a solution combining object detection and semantic segmentation to obtain the prior contours of potential dynamic objects. With this prior information, geometric constraints techniques are utilized to assist with removing dynamic feature points. Finally, the evaluation with the public datasets demonstrates that our proposed method can improve the accuracy of pose estimation and robustness of visual SLAM with no efficiency loss in high dynamic scenarios.

Individual driving final destination prediction supports location-based services such as personalized service recommendations, traffic navigation, and public transport dispatching. However, real-time destination prediction is challenging due to the complexity of temporal dependencies, and the strong influence of travel spatiotemporal semantics and spatial correlations. Besides temporal context, the nearby urban functionalities of traveling zones and departure regions, and the crucial positions on the road network where trajectory points located would reflect the travel intentions of drivers. However, these spatial factors are rarely considered in existing studies. To fill this gap, we propose a real-time individual driving destination prediction model LSI-LSTM based on an attention-aware Long Short-Term Memory (LSTM) by taking Location Semantics and Location Importance of trajectory points into account. More specifically, a trajectory location semantics extraction method (t-LSE) enriches feature description with prior knowledge for implicit travel intentions learning. t-LSE represents urban functionality through Points of Interest (POIs) using Term Frequency-Inverse Document Frequency (TF-IDF). Meanwhile, a novel trajectory spatial attention mechanism (t-SAM) captures the trajectory points that strongly correlate to candidate destinations based on the location importance inferred from the driving status, i.e., turning angle, driving speed, and traveled distance. Comparative experiments with three baseline methods, i.e., Hidden Markov Model, Random Forest, and LSTM, demonstrate significant prediction accuracy improvements of LSI-LSTM on four individual trajectory datasets. Further analyses validate the effectiveness of the proposed semantic extraction method and attention mechanism, and also discuss the factors that may affect the prediction results.

Vehicle and pedestrian detection is one of the critical tasks in autonomous driving. Since heterogeneous techniques have been proposed, the selection of a detection system with an appropriate balance among detection accuracy, speed and memory consumption for a specific task has become very challenging. To deal with this issue and to provide guidance for model selection, this paper analyzes several mainstream object detection architectures, including Faster R-CNN, R-FCN, and SSD, along with several typical feature extractors, such as ResNet50, ResNet101, MobileNet_V1, MobileNet_V2, Inception_V2 and Inception_ResNet_V2. By conducting extensive experiments using the KITTI benchmark, which is a commonly used street dataset, we demonstrate that Faster R-CNN ResNet50 obtains the best average precision (AP) (58%) for vehicle and pedestrian detection, with a speed of 8.6 FPS. Faster R-CNN Inception_V2 performs best for detecting cars and detecting pedestrians respectively (74.5% and 47.3%). ResNet101 consumes the highest memory (9907 MB) and has the largest number of parameters (64.42 millions), and Inception_ResNet_V2 is the slowest model (3.05 FPS). SSD MobileNet_V2 is the fastest model (70 FPS), and SSD MobileNet_V1 is the lightest model in terms of memory usage (875 MB), both of which are suitable for applications on mobile and embedded devices.

The demand for library books has been growing year by year, and manual methods for purchasing books have been unable to keep with these ever-increasing Chinese book demands. As deep learning techniques have developed, they have achieved remarkable results in various fields. In this study, we applied a convolution neural network (CNN)-based model to the book purchasing task. We also built a Chinese book dataset based on historical data from the Wuhan University Library. Experimental results on this dataset show that our CNN-BOOK model can reach an accuracy of 83% on the book purchasing task. This method greatly improves the efficiency of book purchases and can provide new ideas for how library purchasing is conducted in the future.

Location-Based Services based on thematic information have become commonplace. Thematic indoor navigation services are also increasingly pervasive with the development of indoor positioning technologies. Extending these technologies, we designed and implemented icon Cube, a mobile cloud computing system integrating Location-Based Services and indoor navigation for meeting organizers and participants. For meeting organizers, our system provides a template library to efficiently customize meeting portal websites for different topics and meeting types, such as academic conferences or art exhibitions. For meeting participants, the Android application in our system not only provides indoor navigation in a meeting space, but also enhances communication among participants through online-to-offline social network services. The system also extracts information from the Internet related to users' location and pushes it to users in sequence based on similarity to location's social attributes. Our system has been used for many academic conferences such as China Satellite Navigation Conference (CSNC), demonstrating its utility.

This paper combines the results of research on social psychology, and has designed a trust model for rumor spreading. It is considered that when information exchanges between people, the trust of information is related to the interpersonal closeness. In addition, this paper uses Monte Carlo method to find the key source nodes in rumor spreading by comparing the total number of spread nodes and spreading time. We find that the key nodes that impact the rumor spreading are not necessarily those with higher degree or betweeness. Our work will provide algorithm support for maintaining the credibility of network information and ensuring the security of network information content.

Fitting a circle to a set of data points arranged in a circular pattern is a common problem in many fields of science and engineering. Specific applications in metrology include center position and circularity measurements. The fitting criteria usually depends on the application and varies with the statistical error model. Chebyshev fits, also known as minmax or least L-infinity fits, are of particular interest in metrology where they quantify the form error in addition to yielding an allegedly more objective position assessment. The paper offers further empirical evidence to support this conjecture. The Chebyshev circular fit problem can be solved using common computational geometry tools but the computational complexity of the algorithm is prohibitive for real-time applications. A substitute heuristic marching algorithm was developed and implemented. After a comprehensive state of the art review, the paper presents the marching algorithm and evaluates its convergence properties for full and partial circular data sets. A comparative study of convergence rate and accuracy is presented with respect to exhaustive computational geometry solutions and other fitting criteria.