Collaborative perception leveraging intermediate feature fusion has emerged as a leading paradigm to significantly enhance the environmental perception capabilities of autonomous driving systems. However, existing methods typically rely on discriminative supervision guided by downstream tasks. This paradigm compels models to learn minimal, task-specific representations, which conflicts with the goal of cooperative perception to capture comprehensive information, thereby limiting generalization. To address this issue, we propose DiGS-CP, a novel two-stage generative supervised collaborative perception framework. Specifically, we introduce a diffusion-based generative task that conditions on fused object-level features to generate representations of object-level point clouds. The proposed generative supervision provides fine-grained, task-agnostic signals that encourages the fusion module to learn comprehensive representations beyond task-specific requirements. By preserving and integrating complementary information from collaborative agents, our approach overcomes the limitations of task-specific learning and enhances the generalizability of the learned features. Furthermore, our two-stage architecture requires agents to transmit only object-level features, significantly reducing communication overhead. Extensive experiments on three benchmark datasets demonstrate that DiGS-CP achieves state-of-the-art performance in 3D object detection, while maintaining low bandwidth requirements and exhibiting excellent generalization ability.

Collaborative perception can significantly enhance the perceptual capabilities of autonomous vehicles by sharing sensing information through vehicular communications. However, large-scale sharing of sensing information often results in unsustainable network loads, making it challenging to maximize perception performance with limited communication resources in complex environments. To address this challenge, we propose FullPerception, an innovative cooperative perception framework that jointly orchestrates sensing information sharing and communication resource allocation at the network level. FullPerception advocates for the sharing of semantic information (neural network features) within critical areas, i.e., blind spots. With limited communication resources, FullPerception strategically eliminates these blind spots to maximize the accumulated perception performance. We formulate this strategy as a weighted optimization problem and prove its NP-hardness. We propose a simple yet effective algorithm, Proactive Conflict-free Scheduling (PCS), which guarantees a good performance ratio by considering broader contexts. PCS is meticulously combined with recursive structure, accounting for both the overall and future contexts to determine link scheduling and resource allocation. We demonstrate that FullPerception improves perception accuracy by 20% relative to single-vehicle systems and by 10% compared to existing scheduling methods through large-scale comprehensive joint simulation experiments.

Collaborative perception in autonomous driving significantly enhances the perception capabilities of individual agents. Immutable heterogeneity, where agents have different and fixed perception networks, presents a major challenge due to the semantic gap in exchanged intermediate features without modifying the perception networks. Most existing methods bridge the semantic gap through interpreters. However, they either require training a new interpreter for each new agent type, limiting extensibility, or rely on a two-stage interpretation via an intermediate standardized semantic space, causing cumulative semantic loss. To achieve both extensibility in immutable heterogeneous scenarios and low-loss feature interpretation, we propose PolyInter, a polymorphic feature interpreter. It provides an extension point where new agents integrate by overriding only their specific prompts, which are learnable parameters that guide interpretation, while reusing PolyInter’s remaining parameters. By leveraging polymorphism, our design enables a single interpreter to accommodate diverse agents and interpret their features into the ego agent’s semantic space. Experiments on the OPV2V dataset demonstrate that PolyInter improves collaborative perception precision by up to 11.1% compared to SOTA interpreters, while comparable results can be achieved by training only 1.4% of PolyInter’s parameters when adapting to new agents. Code is available at https://github.com/yuchen-xia/PolyInter.

Heterogeneous collaborative perception enables interconnected agents to share and fuse intermediate features extracted from multimodal sensor data, thereby enhancing robustness and reducing perception blind spots. However, shared high-dimensional features often contain redundant and modality-specific information, leading to semantic inconsistencies and excessive communication overhead. To address these challenges, we propose an efficient communication framework for heterogeneous collaborative perception. This framework integrates a shared-private feature decoupling module that disentangles cross-modal features into shared and private components, sharing only shared feature to improve communication efficiency. Additionally, we design a spatial redundancy elimination module to remove background information from transmitted features, further reducing bandwidth consumption. Collectively, these modules enable compact and communication-efficient perception capabilities across heterogeneous modalities, models, and tasks. Experimental results demonstrate that the proposed framework significantly reduces communication overhead in complex heterogeneous scenarios while maintaining perception accuracy.

Collaborative perception improves task performance by expanding the perception range through information sharing among agents. Immutable heterogeneity poses a significant challenge in collaborative perception, as participating agents may employ different and fixed perception models. This leads to domain gaps in the intermediate features shared among agents, consequently degrading collaborative performance. Aligning the features of all agents to a common representation can eliminate domain gaps with low training cost. However, in existing methods, the common representation is designated as the representation of a specific agent, making it difficult for agents with significant domain discrepancies from this specific agent to achieve proper alignment. This paper proposes NegoCollab, a heterogeneous collaboration method based on the negotiated common representation. It introduces a negotiator during training to derive the common representation from the local representations of each modality's agent, effectively reducing the inherent domain gap with the various local representations. In NegoCollab, the mutual transformation of features between the local representation space and the common representation space is achieved by a pair of sender and receiver. To better align local representations to the common representation containing multimodal information, we introduce structural alignment loss and pragmatic alignment loss in addition to the distribution alignment loss to supervise the training. This enables the knowledge in the common representation to be fully distilled into the sender. The experimental results demonstrate that NegoCollab significantly outperforms existing methods in common representation-based collaboration approaches. The mechanism of obtaining common representations through negotiation provides a more reliable and flexible option for common representations in heterogeneous collaborative perception.

Multi-agent collaborative perception enhances perception performance by enabling information sharing and complementary data fusion among agents. However, this process inevitably requires a trade-off between perception performance, computing resources, and communication bandwidth to ensure overall collaboration efficiency. To address these challenges, we propose a joint resource and intelligence optimization method for multi-vehicle collaborative perception, named C3I-JO. Based on slimmable network and accuracy-awareness, the method performs joint optimization over collaborative mode, resource allocation, and intelligent elasticity. C3I-JO minimizes overall resource consumption while satisfying both perception accuracy and delay constraints, thereby improving the overall system efficiency. Simulation results demonstrate that, compared with baseline methods, the proposed method achieves superior performance in terms of both resource consumption and perception quality.

Collaborative perception enables connected and autonomous vehicles (CAVs) to overcome individual viewpoint limitations by exchanging perception data, making effective resource allocation crucial for timely transmission. However, existing studies focus on resource allocation within a single collaborative perception group (CPG), limiting their effectiveness in multi-group collaborative perception systems. In such a system, each CPG contributes differently to the overall collaborative perception performance, and it is challenging to evaluate and represent CPG system-level utilities. Meanwhile, competition for shared spectrum resources leads to interference and complicates the joint optimization of collaboration mechanisms and spectrum allocation, which is intensified by their temporal scale misalignment. To address these challenges, we propose a Utility-Aware Hierarchical Reinforcement Learning method (UAHRL) to jointly optimize collaboration mechanisms and spectrum allocation. Specifically, we introduce a hierarchical framework to handle temporally misaligned decisions through joint training. The upper layer optimizes the collaborative relationship and granularity over a longer time scale to enhance system-level collaborative performance, while the lower layer allocates spectrum resources over a shorter time interval to fulfill individual CPG transmission demand and enhance system transmission efficiency. To represent and utilize system-level utility, we leverage a feature-based confidence map to assess CAVs’ perception capability and complementarity. A mixing network in the upper layer further decomposes global performance into individual CPG utilities, enabling utility-aware resource allocation. Simulations show that UAHRL outperforms baseline methods in system-level collaborative perception in multi-group systems.

Intelligent connected vehicles are integrated equipment with communication, computing, and control capabilities. The diversity of communication demands and high-speed mobility of intelligent connected vehicles leads to the challenge of wireless resource allocation and performance evaluation. To manage wireless resources efficiently in complex environments, this paper proposes an attentional value factorization (AVF) based cooperative resource allocation and performance evaluation method, which is built on top of the actor-critic-based multiagent deep reinforcement learning (MADRL) framework. Specifically, AVF is constructed with hierarchical and heterogeneous critics to accurately evaluate the performance and then fed back to the resource allocation policy. The individual task-specific critics and the global critic are exploited to trade off local optimum against global optimum. In addition, a meticulously designed attentional action-value mixing network is used by the global critic to assign different credits for individual critics, factorizing the overall reward to each agent and further to each agent’s sub-tasks. Extensive experimental results show that AVF can promote cooperative resource allocation among agents by evaluating which agents and what actions have been contributing most to the overall quality of communication, achieving optimal resource efficiency and accurate evaluation.

Vehicle platooning has emerged as a promising solution for efficient traffic management. Multiple platoons traveling in a cooperative way can alleviate congestion and enhance driving safety by information sharing and consensus. To address the data security and privacy concerns, blockchain could be applied to enable secure data sharing and consensus across multiple platoons. However, existing performance of blockchain is insufficient to ensure reliable and efficient data consensus among multiple platoons. First, the hierarchical structure of platoons with different roles of vehicles complicates the trust establishment between platoons, making it challenging to evaluate their trustworthiness and ensure consensus reliability. Additionally, data sharing in vehicle platooning networks demands timely information and efficient consensus-building. To tackle above challenges, we design a role-adaptive trust model for trust evaluation of platoons in consideration of different roles of vehicles within a platoon. Based on the proposed model, we formulate a blockchain consensus optimization problem to facilitate both reliability and efficiency of data consensus among multiple platoons. Leveraging Generative Artificial Intelligence (GenAI) techniques, we then propose the Diffusion Enhanced Soft Actor-Critic (DESAC) by integrating the diffusion model and SAC, to further improve the performance of blockchain consensus. Experiment results demonstrate the effectiveness and efficiency of the proposed consensus optimization approach.

Recent multi-agent deep reinforcement learning (MADRL) approaches have shown notable benefits in multi-intersection traffic signal control (M-TSC). However, spatial-temporal coupling and action heterogeneity are often overlooked. Interactions among traffic states and signal actions introduce complex coupling and hysteresis across space and time, while local actions vary due to fluctuating flows. We proposeAsyn-Light, a MADRL-based M-TSC model that captures spatial-temporal traffic features and leverages action repetition for asynchronous cooperative control. To address spatial-temporal coupling,Asyn-Lightemploys a feature extraction framework based on a spatial-temporal Transformer with a stacked spatial graph module. To handle action heterogeneity, it uses a repetition-enabled MADRL to generate asynchronous multi-step policies for each intersection. We evaluateAsyn-Lighton both synthetic and real-world datasets, analyzing each component’s contribution. Results show thatAsyn-Lightconsistently outperforms baselines in diverse settings, effectively balancing action smoothness with policy adaptability.

Efficient wireless resource allocation is essential for supporting multi-vehicle cooperation. The service data exchanged among intelligent vehicles is typically diverse, with varying transmission requirements that shift according to applications and traffic conditions, leading to major fluctuation in communication situations. Existing multi-agent reinforcement learning based resource allocation methods are often inefficient in handling such nonstationary communication situations due to their rigid cooperation patterns. To this end, we propose a ROle-TRansformable multi-agent resource allocation method, named ROTR. This method adopts a hierarchical decision-making process, where a high-level agent at a base station (BS) dynamically plans and distributes cooperation roles (CRs) and cooperation behaviors (CBs) in response to fluctuating communication situations. The Low-level agents within the transmitting vehicles (TVs) perform role transformations based on the assigned CRs and subsequently receive behavioral guidance according to CBs, enabling dynamic adjustments in cooperation patterns to adapt to variable communication situations and make resource allocation decisions. Additionally, we introduce a non-BS-assisted mode based on policy distillation, which enables a seamless transition to independent operation without the BS, relying solely on local states to generate CRs and CBs, thereby facilitating global resource cooperation. Extensive simulation experiments demonstrate that the proposed framework optimizes resource efficiency in nonstationary vehicular communications.

Vehicle platooning is a promising traffic model in intelligent transportation systems (ITSs), which can effectively improve resource utilization and reduce traffic congestion. The resource allocation for vehicle-to-everything (V2X) communications that consist of intraplatoon communications and interplatoon communications is crucial for safe operation of multiple vehicular platoons. Considering dynamic coordination pattern of vehicular platoons and layered architecture of vehicle platooning networks, a hierarchical resource decision-making framework is proposed in this article. In the proposed framework, the resource decision-making process is divided into two levels. The high level that generates and distributes coordination meta policy is deployed on base station (BS), and the low level that generates ego resource decisions is deployed in each platoon. To deal with optimization of resource allocation for multiplatoon V2X communications, a hierarchical reinforcement learning method (HierNet) is designed based on the proposed hierarchical decision-making framework. In HierNet, meta policy of the high level can be preserved and needs to be updated only when cooperative conditions of multiple platoons undergo distinct changes. Simulation experiments have demonstrated that our proposed method not only optimizes resource efficiency but also reduces the communication costs for resource decision making of vehicle platooning networks.

To support safety driving and various on-board services, efficient resource allocation is crucial for the promising implement of vehicle platooning in intelligent transportation systems (ITSs). The resource allocation of vehicle-to-everything (V2X) communications for vehicular platoons is studied in this article. First, a multiobjective function is formulated to jointly optimize sub-band and power allocation to satisfy Quality-of- Service (QoS) in vehicular networks. With the advantage of dealing with complex decision-making problems in multiagent systems, distributed multiagent deep reinforcement learning (MADRL) stands out for resource allocation of vehicular networks. However, it faces the challenge of cooperation aging when every agent is only learning from information of others to form a cooperation model in the training process. Considering the random and dynamic combination of vehicles in vehicle platooning, a tactic-interactive MADRL method named as TacNet is then proposed to improve the cooperation efficiency of multiple agents. In TacNet, the tactics of other agents will be encoded and transmitted through interactive communications among agents. In addition, with the development of vehicular edge computing (VEC), digital twin (DT) networks are constructed to assist offloading computation-intensive resource allocation tasks in vehicles to the edge. The superiority of the proposed method is verified through extensive simulation results, which refers to convergence and performance of satisfying diversified QoS requirements compared with state-of-the-art MADRL methods.

Autonomous driving vehicle (ADV) that is ready to transform our society and economy, is in desperate need of precise positioning over itself as well as surrounding environments. However, it is still a challenging issue for ADV to retrieve real-time positioning knowledge over road participants and dynamic surrounding environments, due to unsatisfied perception accuracy caused by sparse observations and limited perception range. Cooperative perception, which advocates cooperatively disseminating perception data among vehicles, has the potential to overcome the above limitations. To this end, this article proposes a novel edge-assisted multi-vehicle perception system to enhance vehicles’ awareness over surrounding environments, which is termed as EdgeCooper. EdgeCooper first schedules vehicles to share complementarity-enhanced and redundancy-minimized raw sensor data with an edge server, using multi-hop cooperative 5G V2X communications. Then, EdgeCooper merges vehicles’ individual views to form a holistic view with a higher resolution, thus enhancing perception robustness and enlarging perception range. We formulate multi-vehicle multi-hop cooperative data sharing as a minimum cost flow problem with conflict, and further prove that there exists no polynomial-time approximation algorithm with a constant performance ratio unless P = NP. Furthermore, a two-dimension graph coloring algorithm with guaranteed performance is proposed to eliminate conflict. We evaluate EdgeCooper by building a comprehensive simulation platform through a joint manipulation of SUMO, CARLA, NS3, and PyTorch. The experiment results show that, compared to a single vehicle’s perception, EdgeCooper performs effective and efficient in enhancing vehicular awareness, e.g., extending up to 3.6 times detection range and improving perception accuracy by 20%.

Traffic prediction is a keystone for building smart cities in the new era and has found wide applications in traffic scheduling and management, environment policy making, public safety, and so on. Instead of creating a traffic predictor for each city, this article focuses on designing a unified network model that could be directly applied for traffic prediction in any city, by learning the essential spatial-temporal dependencies, i.e., the mutual relationship between traffic and the corresponding fine-grained road network. To achieve this goal, this article proposes a joint knowledge- and data-driven mechanism that novelly divides dependencies into three kinds of correlations, i.e., road segment, intra-intersection, and inter-intersection correlation, which capture the microcosmic, middle, and macroscopic dependencies between traffic and the road network, respectively. Specifically, we first construct traffic datasets that could cover all road segments from real-world trajectory datasets, which makes it possible to model the whole road network as a graph, with the help of fine-grained road topology. Then, we propose meta road segment learner, connection-aware spatial-temporal graph convolutional network (GCN), and multiscale residual networks for capturing the microcosmic, middle, and macroscopic dependencies, respectively. Our experiments on three real-world datasets demonstrate that our proposed method could: 1) achieve better prediction accuracy compared with several approaches and 2) capture the mutual relationship between traffic and the fine-grained road network since our model trained only using data from the source city achieves good performance when it is directly applied for traffic prediction in the target city, without any fine-tuning. The codes will be made publicly available.

This paper proposes AlphaRoute, an AlphaGo inspired algorithm for coordinating large-scale routes, built upon graph attention reinforcement learning and Monte Carlo Tree Search (MCTS). We first partition the road network into regions and model large-scale coordinated route planning as a Markov game, where each partitioned region is treated as a player instead of each driver. Then, AlphaRoute applies a bilevel optimization framework, consisting of several region planners and a global planner, where the region planner coordinates the route choices for vehicles located in the region and generates several strategies, and the global planner evaluates the combination of strategies. AlphaRoute is built on graph attention network for evaluating each state and MCTS algorithm for dynamically visiting and simulating the future state for narrowing down the search space. AlphaRoute is capable of 1) bridging user fairness and system efficiency, 2) achieving higher search efficiency by alleviating the curse of dimensionality problems, and 3) making an effective and informed route planning by simulating over the future to capture traffic dynamics. Comprehensive experiments are conducted on two real-world road networks as compared with several baselines to evaluate the performance, and results show that AlphaRoute achieves the lowest travel time, and is efficient and effective for coordinating large-scale routes and alleviating the traffic congestion problem. The code will be publicly available.

The use of multi-agent reinforcement learning (MARL) methods in coordinating traffic lights (CTL) has become increasingly popular, treating each intersection as an agent. However, existing MARL approaches either treat each agent absolutely homogeneous, i.e., same network and parameter for each agent, or treat each agent completely heterogeneous, i.e., different networks and parameters for each agent. This creates a difficult balance between accuracy and complexity, especially in large-scale CTL. To address this challenge, we propose a grouped MARL method named GPLight. We first mine the similarity between agent environment considering both real-time traffic flow and static fine-grained road topology. Then we propose two loss functions to maintain a learnable and dynamic clustering, one that uses mutual information estimation for better stability, and the other that maximizes separability between groups. Finally, GPLight enforces the agents in a group to share the same network and parameters. This approach reduces complexity by promoting cooperation within the same group of agents while reflecting differences between groups to ensure accuracy. To verify the effectiveness of our method, we conduct experiments on both synthetic and real-world datasets, with up to 1,089 intersections. Compared with state-of-the-art methods, experiment results demonstrate the superiority of our proposed method, especially in large-scale CTL.

Multi-agent collaborative perception depends on sharing sensory information to improve perception accuracy and robustness, as well as to extend coverage. However, most collaborative perception methods ignore the limitations of communication networks, such as limited bandwidth and the possibility of wireless conflicts. To fill this gap, this paper proposes BlindSpotEliminator, a conflict-free scheduler over the cellular-V2X networks for supporting practical collaborative point cloud perception to eliminate blind spots. BlindSpotEliminator first identifies the blind spots for each vehicle, then lists the corresponding conflict relationships based on the distribution of the blind spots and communication conflicts, and finally designs an optimized point cloud data transmission strategy to eliminate the blind spots of each vehicle. Extensive experiments show that compared with greedy algorithm and random methods, BlindSpotEliminator achieves better efficiency, i.e., transmitting 20% more point cloud data.

In this paper, we propose a masked and sparse transformer to address the problem of point cloud registration with low overlap. The mask mechanism reduces the overall data, increasing the corresponding point ratio in the overlap region, while also reducing the computational cost to accelerate the algorithm's execution speed. Moreover, we combine spatial position encoding and sparse self-attention to establish relationships within the source point cloud, as well as the relationships and attention scores between the source and target point clouds. This approach is specifically designed for the task of point cloud registration. Finally, we search for the maximum overlap area by matching the spatial consistency between points and calculate the 3D transformation matrix to complete the registration process. Our method achieves an improvement in the inlier ratio and performs well on the 3DMatch and 3DLoMatch datasets, demonstrating high registration efficiency.

Traffic forecasting aims to capture complex spatial-temporal dependencies and non-linear dynamics, which plays an indispensable role in intelligent transportation systems and other domains like neuroscience, climate, etc. Most recent works rely on graph convolutional networks (GCN) to model the dependencies and the dynamics. However, the over-smoothing issue of GCN would produce indistinguishable features among nodes, leading to poor expressivity and weak capability of modeling complex dependencies and dynamics. To address this issue, we present a novel clustering spatial-temporal (ClusterST) unit, which incorporates unsupervised learning into GCN for extracting discriminative features. Specifically, we first exploit a neural network to learn a dynamic clustering, i.e., learning to partition the neighbors of each node into clusters at each time step. Two probabilistic losses are proposed to improve the separability of clusters. Then, the extracted features of different clusters can be distinguished. Based on the dynamically formed clusters, a vanilla GCN is applied to aggregate features within each cluster. By purely exploiting such a ClusterST unit, large improvements over the state-of-the-art are achieved. Furthermore, ClusterST units with a different number of clusters can be regarded as basic components to construct an inception-like ClusterST network for going deeper. We evaluate the framework on two real-world large-scale traffic datasets and observe an average improvement of 18.19% and 7.62% over state-of-the-art baselines, respectively. The code and models will be publicly available.

Multi-agent collaborative perception depends on sharing sensory information to improve perception accuracy and robustness, as well as to extend coverage. The cooperative shared information between agents should achieve an equilibrium between redundancy and complementarity, thus creating a concise and composite representation. To this end, this paper presents a complementarity-enhanced and redundancy-minimized collaboration network (CRCNet), for efficiently guiding and supervising the fusion among shared features. Our key novelties lie in two aspects. First, each fused feature is forced to bring about a marginal gain by exploiting a contrastive loss, which can supervise our model to select complementary features. Second, mutual information is applied to measure the dependence between fused feature pairs and the upper bound of mutual information is minimized to encourage independence, thus guiding our model to select irredundant features. Furthermore, the above modules are incorporated into a feature fusion network CRCNet. Our quantitative and qualitative experiments in collaborative object detection show that CRCNet performs better than the state-of-the-art methods.

Accurate spatial-temporal prediction is a fundamental building block of many real-world applications such as traffic scheduling and management, environment policy making, and public safety. This problem is still challenging due to nonlinear, complicated, and dynamic spatial-temporal dependencies. To address these challenges, we propose a novel embedded spatial-temporal network (ESTNet), which extracts efficient features to model the dynamic correlations and then exploits three-dimension convolution to synchronously model the spatial-temporal dependencies. Specifically, we propose multi-range graph convolution networks for extracting multi-scale static features from the fine-grained road network. Meanwhile, dynamic features are extracted from real-time traffic using a gated recurrent unit network. These features can be applied to identify the dynamic and flexible correlations among sensors and make it possible to exploit a three-dimension convolution unit (3DCon) to simultaneously model the spatial-temporal dependencies. Furthermore, we propose a residual network by stacking multiple 3DCon to capture the nonlinear and complicated dependencies. The effectiveness and superiority of ESTNet are verified on two real-world datasets, and experiments show ESTNet outperforms the state-of-the-art with a significant margin. The code and models will be publicly available.

3D object detection has attracted a significant amount of attention and interest from both academia and industry due to its indispensable role in understanding 3D environments. By fusing the camera and LiDAR sensors, it is expected to improve both the accuracy and robustness of 3D object detection. However, existing fusion approaches are either limited by cascading processing, or easy to be influenced by the interference information in multi-sensors. To this end, this paper incorporates meta learning to fuse the camera and LiDAR data. Specifically, we first extract meta knowledge from images, and then apply it to generate the parameter weights of a set of convolution kernels, which are further exploited for feature extraction on LiDAR point clouds. Furthermore, we propose a meta fusion network (MF -Net), enabling accurate and robust 3D object detection. The superiority and effectiveness of MF -Net have been demonstrated by extensive experiments on KITTI 3D object detection dataset.

As artificial intelligence and the internet of vehicles are becoming mature, multi-agent reinforcement learning is utilized as an efficient way to coordinate vehicles to achieve safer and more efficient transportation. Communication between vehicles is essential for multi-vehicle cooperation to enhance the understanding of the environment state and the intentions of other vehicles. However, with limited communication resources, how to compress the message and reduce the number of messages that need to be transmitted while ensuring the coordination performance is an urgent problem to be solved. And evaluating whether the message is useful and identifying the valuable information from the received messages are huge challenges for the vehicle communication system. To this end, we propose an efficient communication method that can guarantee coordination performance with limited communication resources. In particular, the efficient communication method using the algorithm in variational auto-encoder to compress the message while guaranteeing the valuable information of the message is preserved in the compressed message. Additionally, the multi-head attention mechanism is utilized to extract valuable information from the received messages and help the vehicle to make the driving decision. To avoid contention of communication resources, the message will be scored before transmitted to other vehicles. So that communication resources can be reserved for valuable messages. The efficient communication method is evaluated in an unsignalized intersections scenario. Experimental results show that the efficient communication method achieves better performance under the bandwidth-constrained environment than the baselines.

Artificial intelligence-empowered smart things (e.g., robots, autonomous vehicles, and unmanned aerial vehicles) have been transforming the world. The “brains” of smart things can be abstracted as the agents or cybertwins residing on end devices and edge servers. The next-generation communication networks (i.e., 6G) will become the nervous system for these agents and natively support multiagent cooperation. By sharing local observations and intentions via communication channels, the agents could better understand the environments and make right decisions. Due to the limited channel bandwidth, the communication is considered as a bottleneck of multiagent cooperation. In this article, we propose a graph convolutional communication method (GraphComm) for multiagent cooperation to relive the bottleneck. Specifically, a variational information bottleneck is used to encode the observations and intentions compactly. Furthermore, a graph information bottleneck with the attention-based neighbor sampling mechanism is utilized to improve the effectiveness and robustness of the multiround communication process. The experimental results show that GraphComm can improve the effectiveness, robustness, and efficiency of communication in multiagent cooperative tasks as compared to baseline methods.

Internet of Everything (IoE) brings unprecedented challenges regarding scability, mobility, availability, and security to wireless communications. Cybertwin emerges as a promising paradigm for the next-generation mobile network, i.e., 6G. Basically, it serves as the communication anchor of a user at the edge and performs fundamental authentication and network resources control functionalities. Cybertwin is also an indispensable enabler of the cloud native network paradigm and can efficiently support the digital twin and metaverse. With cybertwin, heterogeneous access networks can be easily exploited in a synergic manner, such that advanced applications, such as multiscreen multistream rich media delivery, can be realized with guaranteed QoS. Furthermore, a user’s activities in cyberspace can be recorded naturally which becomes his/her/its digital asset. In the future, cybertwin may become the personal assistant and even an immortal second life of the user.

With a massive number of Internet-of-Things (IoT) devices connecting with the Internet via 5G or beyond 5G (B5G) wireless networks, how to support massive access for coexisting cellular users and IoT devices with quality-of-service (QoS) guarantees over limited radio spectrum is one of the main challenges. In this paper, we investigate the multi-operator dynamic spectrum sharing problem to support the coexistence of rate guaranteed cellular users and massive IoT devices. For the spectrum sharing among mobile network operators (MNOs), we introduce a wireless spectrum provider (WSP) to make spectrum trading with MNOs through the Stackelberg pricing game. This framework is inspired by the active radio access network (RAN) sharing architecture of 3GPP, which is regarded as a promising solution for MNOs to improve the resource utilization and reduce deployment and operation cost. For the coexistence of cellular users and IoT devices under each MNO, we propose the coexisting access rules to ensure their QoS and the priority of cellular users. In particular, we prove the uniqueness of the Stackelberg equilibrium (SE) solution, which can maximize the payoffs of MNOs and WSP simultaneously. Moreover, we propose an iterative algorithm for the Stackelberg pricing game, which is proved to achieve the unique SE solution. Extensive numerical simulations demonstrate that, the payoffs of WSP and MNOs are maximized and the SE solution can be reached. Meanwhile, the proposed multi-operator dynamic spectrum sharing algorithm can support more than almost 40% IoT devices compared with the existing no-sharing method, and the gap is less than about 10% compared with the exhaustive method.

It is widely recognized that connected vehicles have the potential to further improve the road safety, transportation intelligence and enhance the in-vehicle entertainment. By leveraging the 5G enabled Vehicular Ad hoc NETworks (VANET) technology, which is referred to as 5G-VANET, a flexible software-defined communication can be achieved with ultra-high reliability, low latency, and high capacity. Many enabling applications in 5G-VANET rely on sharing mobile data among vehicles, which is still a challenging issue due to the extremely large data volume and the prohibitive cost of transmitting such data using 5G cellular networks. This article focuses on efficient cooperative data sharing in edge computing assisted 5G-VANET. First, to enable efficient cooperation between cellular communication and Dedicated Short-Range Communication (DSRC), we first propose a software-defined cooperative data sharing architecture in 5G-VANET. The cellular link allows the communications between OpenFlow enabled vehicles and the Controller to collect contextual information, while the DSRC serves as the data plane, enabling cooperative data sharing among adjacent vehicles. Second, we propose a graph theory based algorithm to efficiently solve the data sharing problem, which is formulated as a maximum weighted independent set problem on the constructed conflict graph. Specifically, considering the continuous data sharing, we propose a balanced greedy algorithm, which can make the content distribution more balanced. Furthermore, due to the fixed amount of computing resources allocated to this software-defined cooperative data sharing service, we propose an integer linear programming based decomposition algorithm to make full use of the computing resources. Extensive simulations in NS3 and SUMO demonstrate the superiority and scalability of the proposed software-defined architecture and cooperative data sharing algorithms.

With the expansion of the mobile communication technology, telecommunication fraud is increasing dramatically which results in the loss of billions of dollars worldwide every year. In recent years, some detection methods utilize data mining and statistical techniques to detect fraud from large amount of subscriber content data, and some methods transform the social relation into a set of topological features, such as degree, k-core etc. However, both content and relation have not been fully explored for identifying fraudsters. In this paper, we propose the Multi-Range Gated Graph Neural Network (MRG-GNN) for learning latent features of social network. Specifically, we first model a social network as a directed graph where vertices with subscriber features represent subscribers and edges with relational features represent activities between them. Then, a novel method based on efficient short walks and node-merging is proposed to structure the convolutions, and graph convolution block captures content information and relation information between users. The multi-range gated readout operation is proposed to aggregate informative features in multiple nodes and automatically learns the representation of user social network. Finally, experiments on a real-world telecommunication network show that our MRG-GNN achieves the state-of-the-art results.

Urban traffic congestion has a great impact on commute time, energy consumption, and carbon emissions. To deal with traffic congestion, the vehicle cooperative routing method coordinates the routing behavior of vehicles according to dynamic traffic demands. However, city-wide cooperative routing is faced with extremely high communication and computing complexity, which makes it difficult to guarantee real-time performance. To this end, we propose a hierarchical traffic-balanced route planning method for connected vehicles based on edge computing. Specifically, the road network is divided into grids, and an improved back-pressure algorithm is used to guide the inter-grid traffic flow. Furthermore, to balance the intra-grid traffic flow, the vehicle routing is scheduled by evolutionary game method at each intersection. The simulation results show that the algorithm can effectively balance the utilization of road network resources, increase the throughput of the road network and reduce the total traffic time.

Intelligent and connected vehicles rely on edge computing to offload their perception and planning tasks, so the scheduling of communication and computing resources is critical to the driving safety and efficiency. However, the imbalanced distribution of road traffic and offloading demands impedes the quality of vehicular edge computing. In this paper, we propose a multi-timescale load balancing approach to improve the service quality and resource utility of vehicular edge computing. Specifically, vehicle mobility optimization is leveraged to perform long-term load balancing, and resource allocation is used to achieve real-time load balancing. As the multi-timescale optimization is confronted with the curse of dimensionality, multi-agent deep reinforcement learning is utilized to optimized vehicle mobility and resource allocation in parallel. Experimental results show that the proposed method can significantly reduce the service delay of vehicular edge computing.

The existing end-to-end methods make driving decisions mainly based on the vehicle's own perceived data, which cannot avoid hazards in blind zones. To fill this gap, vehicles should cooperate to construct a comprehensive environment perception by sharing information among each other, equipping each vehicle with see-through ability. While bringing more perceived information, data from other sources may also interfere feature selection and make decision making more difcult. To solve this problem, we propose a dual-attention-based neural network by utilizing two different attention modules. The first module is designed for each source to eliminate redundant features in perception and generate cognitive information for sharing. Since the influences of different cognition on the decision making are different under different circumstances, the second module is used to discriminate the importance of different cognition and focus on the dominant one as needed. Guided by the dual-attention-weighted features, the proposed network extracts the most salient features from the multi-source data, which leads to a signicant reduction of false response in steering angle controlling. Extensive experiments have demonstrated the superior performance of our proposed method, as compared with several state-of-the-arts.

Traffic congestion is a serious social issue confronting modern cities. To improve traffic efficiency, route planning for the individual vehicle based on dynamic traffic conditions has been well investigated. However, existing studies usually model the vehicles with perfect rationality and omit the complex routing interaction among multiple vehicles, causing that the routing performance dramatically deviates from the system optimum. Considering the mutual influence in multi-vehicle routing, we propose an edge-assisted distributed routing framework, which enables virtual agents on behalf of vehicles to interact with others to make real-time routing decisions. In the framework, we model the agent interaction as a population game and propose a scalable multiagent learning algorithm to efficiently find the Nash equilibria. Specifically, the multiagent learning algorithm takes the bounded rationality of individuals into account and uses a stage learning algorithm based on best-response dynamics to plan a route for vehicles. The simulation results show that the algorithm efficiently converges to Nash equilibria, and achieves the maximum throughput at the intersection and the minimum average travel time for vehicles.

Guiding vehicles to their destination is an essential service. Nowadays navigation systems are mainly relying on the traffic conditions of road network, and other influence factors are not taken into account accurately, which is easy to lead to imbalance between the supply and demand of roads, resulting in congestion. In this paper, we introduce an online guiding approach via value iteration network on road graphs, R-VIN for short, which is an end-to-end planning model. In R-VIN, a large-scale real GPS trajectories are mapped via map-matching based road topology, which enables R-VIN to catch the experienced driving knowledge. Then we propose a conversion method from irregular road graphs to regular grid images to formalize the learning model. For a global optimum, ConvLSTM is used to predict the future traffic situation to form prediction reward of R-VIN. Combining with current reward, a double rewarded VIN is used to solve the plan-involved function. Lastly, we train and evaluate R-VIN on planning problem in road networks, showing that R-VIN can achieve segment-based autonomous navigation with high top-k accuracy and less commuting time.

The infrastructure to vehicle (I2V) communication boosts a large number of prevailing vehicular services, which can provide vehicles with external information, storage, and computing power located at both mobile edge server (MES) and remote cloud. However, vehicle distribution is imbalanced due to the spatial inhomogeneity and temporal dynamics. As a consequence, the communication load for MES is imbalanced and vehicles may suffer from poor I2V communications where the MES is overloaded. In this paper, we propose a novel proactively load balancing approach that enables efficient cooperation among MESs, which is referred to as end-to-end load balancer (E2LB). E2LB schedules the cached data among MESs based on the predicted road traffic situation. First, a convolutional neural network (CNN) is applied to efficiently learn the spatio-temporal correlation in order to predict the road traffic situation. Then, we formulate the load balancing problem as a nonlinear programming (NLP) problem and a novel framework based on CNN is adopted to approximate the NLP optimization. Finally, we connect the above neural networks into an end-to-end neural network to jointly optimize the performance, where the input is the historical traffic situation while the output is the balanced scheduling solution. E2LB can guarantee the real-time scheduling, since the calling of a well-trained neural network only requires a small number of simple operations. Experiments on the trajectories of taxis and buses in Beijing demonstrate the efficiency and effectiveness of E2LB.

In vehicular sensor networks, vehicles can act as mobile sensors to monitor the dynamic features of the physical world such as traffic flow, air quality, and temperature. However, the conventional full-coverage sensing approach is neither realizable nor cost-effective since the sensor-equipped vehicles are unevenly distributed and the environmental data are spatio-temporally correlated. To this end, we propose a cost-effective urban environment sensing solution (CESense), that exploits the sensing data correlations to improve the sensing accuracy and efficiency. CESense gathers data only at some specific areas of the whole sensing space and reliably infers the status of unsensed areas. Particularly, CESense uses a probabilistic matrix factorization model to reveal the latent features that impact the environmental status. Then, an appropriate set of sensing areas can be selected by fully taking advantage of these latent features and the sensing resource distribution patterns. In addition, to be adaptive to the dynamic environment, a checkpoint mechanism is designed to supervise the data gathering progress. Extensive experiments, which are based on the real taxicab mobility traces and air quality data collected in Beijing city, demonstrate that CESense can significantly improve the accuracy and efficiency of vehicular sensing.

Predicting traffic conditions for road segments is the prelude of working on intelligent transportation. Many existing methods can be used for short-term or long-term traffic prediction, but they focus more on regions than on road segments. The lack of fine-grained traffic predicting approach hinders the development of ITS. Therefore, MapLSTM, a spatio-temporal long short-term memory network preluded by map-matching, is proposed in this paper to predict fine-grained traffic conditions. MapLSTM first obtains the historical and real-time traffic conditions of road segments via map-matching. Then LSTM is used to predict the conditions of the corresponding road segments in the future. Breaking the single-index forecasting, MapLSTM can predict the vehicle speed, traffic volume, and the travel time in different directions of road segments simultaneously. Experiments confirmed MapLSTM can not only achieve prediction for road segments based a large scale of GPS trajectories effectively but also have higher predicting accuracy than GPR and ConvLSTM. Moreover, we demonstrate that MapLSTM can serve various applications in a lightweight way, such as cognizing driving preferences, learning navigation, and inferring traffic emissions.

The performance of a vehicular ad hoc network (VANET) largely depends on the underlying medium access control (MAC), as it determines the schedule utility of physical resources. However, in existing time-division multiple access (TDMA)-based MAC protocols, a node usually acquires slots based on what each node senses, which is typically the coupling of the control and data plane. This coupling makes the TDMA protocols unable to rapidly and agilely deal with the challenges in VANETs, such as high mobility and dynamic network densities. Inspired by the software-defined network (SDN), we propose a novel SDN-based MAC protocol, named sdnMAC, to handle these challenges. A novel roadside openflow switch (ROFS) is designed as the roadside unit, controlled by the openflow controller. The sdnMAC can be divided into two tiers, the management of ROFSes (MA-ROFS) by the controller and the management of vehicles (MA-VEH) by ROFSes. In MA-ROFS, the controller schedules the cooperative sharing of time slot information among ROFSes. In MA-VEH, each ROFS allocates slots based on this shared information, thus decoupling of the control and data plane. This decoupling provides great rapidness and agility to sdnMAC, thus handling the rapid mobility and varying vehicle densities. Extensive simulations using network simulator NS3 and traffic simulator SUMO are performed. It is shown that the sdnMAC protocol can better meet the requirements of cooperative safety in VANETs.

Group sensing is a kind of crowdsensing service where HD map producers motivate private cars in a local region to collect data from real world. Group sensing needs vehicles to communicate physically and drivers to collaborate strategically in a mobile or edge‐assisted environment. First, we consider collaboration module that motivates drivers to be participants; centralized and distributed motivating methods are discussed. Secondly, we consider communication module; two VANET‐based methods are proposed to achieve message relaying in edge infrastructure. To accomplish participants’ selection, three combinations of two modules are proposed and simulated based on a flexible framework. The results show that centralized selection could motivate collaboration at a low price but brings heavy communication overhead. Clustered selection requires more incentives and less communication overhead than centralized selection. Distributed selection is usually the first class choice because of its fine performances on both communicating and motivating.

In vehicular sensor networks, probe vehicles can act as mobile sensors to monitor physical world and report to an urban sensing center. However, the distribution of probe vehicles is uneven over space and time. Data redundancy and vacancy are common phenomena for different spatiotemporal positions, which seriously degrade sensing efficiency and accuracy. To address this issue, we propose an adaptive and compressive data gathering scheme (AC-Sense) based on matrix completion theory. The scheme adaptively determines the locations where to obtain samples from so that the principal features of physical world can be captured with a reduced number of probe vehicles. The spatio-temporal correlation between sensor data is exploited to estimate the un-sampled data. Furthermore, we introduce a feedback mechanism to stabilize sensing performance according to the evaluation of data error. We perform extensive experiments based on real taxicab mobility traces and air quality data in Beijing. The experimental results show that the proposed scheme largely improves sensing efficiency while ensuring required data quality.