Achieving accurate and flexible localization in global navigation satellite system (GNSS)-denied underground spaces is critical for Internet of Things (IoT)-enabled logistics and personnel operations. To this end, this paper proposes a scalable multimodal localization framework requiring only a single ultra-wideband (UWB) transmitter connected to a distributed antenna system, avoiding the deployment of multiple additional anchors. An adjacency-masked, change-point-aware hidden Markov model (AC-HMM) is developed for region identification using only two-path UWB measurements, which avoids full channel impulse response (CIR) processing and reduces computational complexity. A multi-scale factor-graph maximum a posteriori inference method (MS-FGM) is then proposed for dynamic localization by fusing UWB and magnetic-field residuals with region and motion constraint factors. Multi-scale temporal aggregation is further introduced to mitigate motion-induced fluctuations and improve localization accuracy and stability. Experiments conducted along the roadways of an underground parking lot demonstrate an average region classification accuracy of 96.81% and a mean positioning error of 0.88 m, outperforming existing methods by up to 42.19%.

Deep reinforcement learning (DRL)-based traffic signal control (TSC) algorithms often suffer from overfitting to static training environments and perform poorly in unseen traffic scenarios. Two major challenges remain in previous methods: the scarcity and homogeneity of training data, and the limited adaptability to harsh or challenging traffic environments. To address these issues, we propose RAW-MetaRL, a Robust Adversarial Weighted Meta-Reinforcement Learning framework. RAW-MetaRL introduces an adversarial environment agent that adaptively generates increasingly challenging and diverse traffic environments based on the current policy’s performance, where synthetic environments are optimized to expose weaknesses in the current control policy. Furthermore, we design a weighted meta-learning framework that alternates between local-level adaptation on individual tasks and global-level adaptation across a sampled set of tasks, aiming to effectively train the meta-agent. A meta weight generator is incorporated to prioritize rare and critical environments, enabling the meta agent to generalize effectively across diverse and previously unseen environments. Extensive experiments on real-world and synthetic datasets demonstrate that RAW-MetaRL significantly outperforms existing methods in adaptability and performance across diverse traffic environments.

Multiple target tracking (MTT) on the roadside is an important technology for achieving environmental perception in intelligent transportation systems (ITS). The existing 4D millimeter-wave radar provides low-cost and enhanced resolution capability to detect small and distant objects, but it also poses significant challenges in associating measurements with targets during tracking, especially for spatially adjacent targets. This paper proposes a novel vision-assisted point cloud data association method for MTT. Firstly, we utilize the back-projection information of visual detection to assist in partitioning the measurement set, which effectively handles situations involving multiple closely spaced targets. In addition, to mitigate the impact of radar missed detection on association and tracking performance, we present a point cloud measurement supplementation method based on the combination of the unmatched back-projection point of visual detection with the predicted state information of the corresponding target. Finally, the Murty algorithm is introduced to obtain the association subset and implement global hypothesis updates in MTT. Experimental results from real-world show our method’s superior performance and robustness in handling diverse and complex scenarios.

In the sixth generation (6G) Internet of Things (IoT), integrated sensing and communication (ISAC) emerges as a key technology, which is expected to significantly enhance the perception capabilities and spectrum efficiency of base stations (BSs). It holds potential for applications in unmanned aerial vehicle (UAV) monitoring, vehicle positioning, and crowd detection. However, developing an integrated waveform that efficiently conserves spectrum resources while maintaining lower complexity remains challenging. This paper designs an ISAC system that utilizes orbital angular momentum (OAM) waves generated by a uniform circular array (UCA), which enhances communication and sensing capabilities by allocating distinct modes. This paper proposes a multimode multiplexing communication scheme based on a single UCA and an OAM-circular reception method (OAM-CRM) for the two-dimensional direction-of-arrival (DOA) estimation of targets, encompassing both azimuth and elevation angles. Additionally, an OAM-different modes (OAMDM) algorithm is designed to optimize communication and sensing performance across various mode sets. Simulation results verify the effectiveness of the OAM ISAC system and demonstrate the superior performance of the proposed algorithms compared to conventional methods.

Owing to the inherent advantages of high flexibility and strong Line of Sight (LoS) links, as well as the continuous power supply, tethered autonomous aerial vehicle (TUAV) connected to ground charging stations (GCSs) is regarded as a feasible and effective solution to support stable emergency communications. One of the key issues in the TUAV network deployment is to ensure the flight safety considering the potential risk of tether tangling as well as collision along with TUAVs’ movements. In this article, we propose a theoretical method for analyzing mobile TUAV networks with spacial repulsion constrain. Under the nearest association criterion, we apply the Matérn hard-core point process (MHCPP) to derive the steady-state spacial distance distribution between the TUAV and the reference ground user equipment (GUE). In the vertical direction, we assume that all TUAVs dynamically adjust their altitude following a random waypoint (RWP) mobility model. Then, closed-form expressions for the network performance metrics, such as coverage probability and handover probability are presented, jointly considering the path loss model and generalized Nakagami-m fading channels. Our analytical results, validated through Monte Carlo simulations, demonstrate the efficiency and accuracy of the proposed method.

Low Earth Orbit (LEO) satellite communication systems can provide wide-coverage and low-latency communication services, making them suitable for global mobile communications, navigation positioning, military operations, remote sensing, and resource exploration, etc. Recently, LEO satellite constellation are gaining increasing attention, consequently facing with the challenge of scarcity of spectrum and space resources. As satellite frequency bands follow the principle of “first come, first served”, countries that started late in the satellite field are more eager to seize space resources. In this paper, we derive analytical model for the coverage probability under multi-altitude orbits for a multi-layer LEO satellite constellation based on stochastic geometry. The distribution of the satellite constellation along the latitude at different inclinations angles is non-homogeneous, we compensate for this phenomenon by calculating the effective number of satellites in the constellation. We then perform simulations of the VLEO (very low Earth orbit) constellation in the presence of interference from other satellite constellations, and the results provide insights into the selection of parameters such as constellation density, altitude range, inclination angle and minimum elevation angle which can help to launch the VLEO constellation more efficiently.

Coordinated Multi-Point (CoMP) transmission enhances the reliability and throughput of communication systems. However, its reliance on precise CSI feedback and retransmission introduces undesirable delays, limiting its applicability in Ultra-Reliable Low Latency Communication (URLLC). To address this challenge, we propose an enhanced RaptorQ-based downlink CoMP scheme that optimizes the decoding process. This scheme utilizes a limited number of Belief Propagation (BP) iterations and a self-adaptive Ordered Statistics Decoder (OSD) to reconstruct ordered information sequences based on the accumulated Log-Likelihood Ratio (LLR) transitions of variable nodes. Simulations demonstrate an average 38.2 % improvement in resource utilization compared to traditional CoMP schemes under a Block Error Rate (BLER) of 10–5in low Signal-to-Noise Ratio (SNR) scenarios.

Orbital angular momentum (OAM) multiplexing techniques have great potential in high-speed and high-capacity short-range wireless communication. However, the divergence angle of OAM waves changes with mode and frequency, increasing the receiver complexity. This paper proposes a Bessel constraint method for generating OAM waves with the same divergence angle. Specifically, this paper first analyzes the factors affecting the divergence angle by combining two uniform circular arrays (UCAs) as uniform concentric circular arrays (UCCAs). Then, this paper defines the intensity proportion between the two UCAs to analyze constraint conditions. Additionally, two algorithms are designed to generate multimode OAM waves with equal divergence angles, considering scenarios with and without multiple frequency bands. Simulation results demonstrate the effectiveness of these algorithms in generating OAM waves with matching maximum strength ring radii, enabling the receiver to fully receive OAM waves of multiple modes and frequencies with just one UCA. Furthermore, the proposed approach facilitates the adjustment of OAM waves with different modes and frequencies by flexibly modifying the intensity proportion without necessitating alterations to the antenna radius.

Detours are inevitable in on-demand customized bus (CB) systems. Previous studies alleviate the impact of detours by predefining high-spatial–temporal similarity of travel orders for CB. However, this assumption is clearly inconsistent with orders’ distribution at the urban level and leads to low-bus occupancy rate in practical use. In this article, we propose a novel service policy to achieve cost-effective CB, which consists of dynamically deployed bus stops and a spatial–temporal heterogeneous-order service. Then, to address the challenge of computational complexity, we provide an order-oriented graphic model named order correlation network (OCN) to formulate the CB design problem. By introducing OCN, we propose a near-optimal computationally efficient solution to the problem, which is scalable and suitable for real-time implementation. Finally, comparative experiments based on the real-world taxi trajectory data set in San Francisco are implemented to verify the performance of our proposed CB in terms of service coverage and travel efficiency.

The connected and autonomous vehicles combined with deep reinforcement learning (DRL) are capable of handling complex driving scenarios. However, due to the random exploration feature of reinforcement learning (RL), unexpected actions and collisions that would be inevitable in the real world occur during training, resulting in property damage, injury, and loss of life. To address this issue, in this article, we propose a sophisticated safe DRL in autonomous lane changing that benefits from both exploration and optimization capabilities. The key idea is first to integrate the safety constraints into the RL algorithm to limit the actions that the agent can take during training, which is implemented by designing a vehicle convex occupancy approximation to estimate the candidate action set. Then, adaptive exploration strategies are used, in which an imaginary environment based on domain randomization is built to explore areas of the action–state space where it is uncertain about the outcomes. We present a Monte Carlo tree search to replace unsafe with safe action. The twin-delayed deep deterministic policy gradient is used as the RL algorithm to train action space agents. Experimental results show that our proposed framework significantly enhances safety during the lane-change process with faster and more stable learning than the other methods.

The intersection network constitutes the basic skeleton of the urban traffic environment, and informative representation of the intersection plays an important role in supporting the wide variety of applications in the intelligent transportation system. In this paper, we propose the Intersection to Vector model, named Intersec2vec, to achieve an accurate, efficient, and low-dimensional representation of each intersection in the large-scale intersection network. It introduces structural and temporal modules with attention mechanisms to specifically represent the evolution of intersection features in the spatiotemporal dimension, ensuring that intersections with stronger correlations have a higher probability of co-occurrence. Furthermore, our proposed Intersec2vec model is integrated into a traffic signal control method based on deep reinforcement learning by supporting more precise sub-area divisions, named Intersec2vec-TSC. For each sub-area, Intersec2vec-TSC adopts a hierarchical structure to design agents, where the upper agent determines the common cycle length based on the overall states of the sub-area, and lower agents jointly train a centralized evaluation network to achieve optimization of green time for each intersection. We conduct the experiment on 108 signalized intersections using real online car-hailing data, and the experimental results show that our proposed method significantly improves the stability of sub-area division and reduces the waiting time of cars during peak hours compared with other comparison methods.

The continuous development of intelligent traffic control systems has a profound influence on urban traffic planning and traffic management. Indeed, as big data and artificial intelligence continue to evolve, the traffic control strategy based on deep reinforcement learning (RL) has been proven to be a promising method to improve the efficiency of intersections and save people's travel time. However, the existing algorithms ignore the temporal and spatial characteristics of intersections. In this article, we propose a multiagent RL based on the deep spatiotemporal attentive neural network (MARL-DSTAN) to determine the traffic signal timing in a large-scale road network. In this model, the state information captures the spatial dependency of the entire road network by leveraging the graph convolutional network (GCN) and integrates the information based on the importance of intersections via the attention mechanism. Meanwhile, to accumulate more valuable samples and enhance the learning efficiency, the recurrent neural network (RNN) is introduced in the exploration stage to constrain the action search space instead of fully random exploration. MARL-DSTAN decomposes the large-scale area into multiple base environments, and the agents in each base environment use the idea of "centralized training and decentralized execution" to learn to accelerate the algorithm convergence. The simulation results show that our algorithm significantly outperforms the fixed timing scheme and several other state-of-the-art baseline RL algorithms.

Multi-target detection and tracking based on fusion of millimeter-wave (MMW) radar and camera play an important role in intelligent transportation system (ITS). However, most previous studies rely heavily on the information from one sensor and assisted by another, or require some additional measurement work. To address this issue, in this paper, we propose a radar-camera fusion method based on position deducing, where the camera and radar serve as mutual reference to deduce the position of the object. Since the azimuth accuracy and target detection rate of visual positioning algorithm are higher than those of radar, the proposed method improve the accuracy of the lateral positioning and reduce the missed detection. Experiments illustrate that the proposed method achieves highprecision positioning with an accuracy of 0. 110m. In addition, when there is at least one reference target, the detection rate and the false alarm rate are approximately 99.15% and 0.03%, respectively.

Due to the limited energy of the Internet of Things (IoT) device, unmanned aerial vehicle (UAV) as a mobile fusion center can effectively prolong the lifetime of IoT device via supporting communication with the device directly. Moreover, since UAV's energy constrained, it will be a good measure to take multiple UAVs to collect data from devices in large areas. In this paper, we investigate multi-UAV collaborative data collection system, where multiple UAVs collect data from two-dimensional distributed devices on flying mode or hovering mode. The objective is to minimize UAVs' total flight time while allowing each device to complete data upload successfully with limited energy. To this end, firstly, a cell partition based on Voronoi diagram is used to allocate the collection areas of each UAV. Then, in each associated area, UAV determines the whole trajectory to serve devices. Lastly, given load requirement of ground devices and energy limitation, the optimal data collection mode of each device is decided to minimize flight time of each UAV. Simulation results show that the proposed multi-UAV data collection scheme can shorten collection task completion time significantly.

In this article, we study the co-channel problem in the 2-tier architecture of vehicular networks [i.e., vehicle-to-vehicle (V2V) communication and vehicle-to-infrastructure (V2I) communication]. The communication technology we consider here is dedicated to short-range radio communication (DSRC), cellular vehicle-to-everything (C-V2X), or a hybrid of both. The V2I communication will interfere V2V communication, and vice versa, because the roadside unit (RSU) cannot sense V2V communication during the downlink period when the V2V communication is in the coverage of RSU. We note that V2V communication will have higher priority since it conveys critical messages for road safety in connected and automated vehicle (CAV) systems. We propose a p-opportunity channel access scheme (p-OCAS) for the RSU to solve the problem. Simulation results validate the correctness of the analytical model. The investigation showed that p-OCAS can substantially minimize the interference from RSU to V2V communications according to the V2V session arrival rate to automated vehicles as well as maintain a high throughput of RSU.

As average user load in wireless local area network (WLAN) becomes heavy, the fundamental CSMA/CA mechanism based on binary exponential backoff (BEB) in the 802.11 protocol is under stress. When a large number of users associate with WLAN, the network suffers from severe throughput deterioration and poor short-term fairness due to the inappropriate BEB algorithm. In this paper, we provide an enhanced backoff (EBO) algorithm to improve the performance of WLANs. Our main motivation is based on the observation that disjointing backoff intervals in different backoff stage can greatly reduce the collision probability. In EBO, the size of backoff interval increases by the initial value of contention window after an unsuccessful transmission, and backoff intervals in different backoff stage are disjoint. Meanwhile, to improve the short-term fairness, we slow down the decrement of contention window by resetting the contention window to initial value after consecutive successful transmissions. Simulation results show that EBO improves the throughput and short-term fairness effectively comparing with BEB in heavy user loaded WLANs.

This paper investigates proportional-fair energy-efficient radio resource allocation problem for the uplink transmission of OFDMA smallcell networks. Instead of the fairness measured by users' achievable data rates, this paper concentrates on the fairness in terms of energy efficiency (EE) and aims to provide EE-based proportional fairness guarantee among all users in smallcell networks. Specifically, EE-based global proportional fairness utility optimization problem is formulated, taking into account both the minimum data rates requirements and the cross-tier interference constraints. In order to make the problem more tractable, it is transformed into a weighted sum maximization problem of each user's instantaneous EE utility. Then, a two-step scheme is adopted, which solves subchannel allocation and power allocation separately, and the corresponding algorithms are devised. The proposed subchannel allocation algorithm is heuristic and low-complexity. The power allocation scheme is optimal, and is devised based on a novel method which can solve the sum of ratios problems efficiently. Numerical results verify the effectiveness of the proposed algorithms, especially the good capability of ensuring high level EE fairness among all users in the smallcell network.

WiFi offloading is a cost-effective and practical solution to alleviate the problem of highly congested cellular networks. Recent theoretical and experimental studies show that delayed WiFi offloading where traffic can be delayed to increase the chance of meeting WiFi can significantly improve offloading efficiency. Nevertheless, there is no exact analytic model to analyze the offloading benefits with different types of traffic. In this paper, we propose a preemptive priority queuing analytic model for delayed offloading with multi-level priority traffic and derive expressions for the average delay and offloading efficiency of traffic with different priorities as a function of the WiFi availability, deadlines, and other key parameters. At last, we validate the accuracy of our queuing model by simulation in different scenarios and clarify how to choose a suitable deadline for traffic of different priorities.

The unforeseen mobile data explosion poses a major challenge to the performance of today's cellular networks, and cellular network is in urgent need of original solutions to handle such voluminous mobile data. Obviously, data offloading through third-party WiFi access points (APs) can effectively alleviate the issue of overload in the cellular networks with a low operational and capital expenditure. In this paper, we study the network selection problem in operator-initiate offloading in ultradense wireless networks. To enhance the mobile data offloading, a dynamic and self-adaptive method for network selection is proposed, using the attractor selection mechanism described in biological system. In our proposed algorithm, the operator enables users to dynamically select an appropriate APs according to the dynamic conditions of various available networks. Simulation results show that the proposed algorithm decreases the service delay and achieve a high offloading efficiency in delay offloading.

In this paper, we consider the problem of interference mitigation in the downlink of multicell networks via base station coordination. In this paper, a simple and efficient scheme for interference management based on potential game is proposed. The main emphasis of this paper is placed on the problem of users' quality of service (QoS) in order to maximize the efficient throughput of system. Meanwhile, a pricing factor is introduced which is proportion to the co-channel interference to other base stations. Furthermore, an improved gradient projection rule with variable step size and Jacobi iterative algorithm are utilized to solve the optimization problem. Pareto optimal is verified by using "price of anarchy" as an optimize performance indicators in potential game. Simulation results show that our proposed scheme can significantly improve the performance of multicell networks.