Spatiotemporal forecasting plays a vital role in modeling and managing complex dynamic systems, such as traffic networks, power grids, and industrial diagnostic systems. However, most existing spatiotemporal models focus primarily on improving prediction accuracy within fixed scenarios, while overlooking the challenge of adapting to dynamically changing forecasting demands. As a result, when prediction requirements shift, these models often need to be retrained to remain accurate—leading to resource inefficiency, production delays, and heightened safety risks. To address this issue, we propose a novel spatiotemporal prediction framework that effectively captures dynamic spatiotemporal dependencies and can be directly applied to spatiotemporal prediction tasks with varying prediction lengths and arbitrary starting points, requiring only a single training phase. Specifically, we introduce the spatiotemporal Date2Vec embedding method, which generates past and future timestamp embeddings by explicitly modeling intrinsic spatiotemporal relationships. Furthermore, we design a fusion module to model the direct mapping relationship between past and future timestamp embeddings, thereby enabling rapid adaptation to dynamic prediction demands. Extensive experiments on seven real-world public datasets show that our model exhibits superior adaptability across four distinct domains and higher predictive accuracy—achieving an average 4.55% improvement over the best-performing baseline on the fixed-horizon prediction task and an average 9.10% improvement on the free-form prediction task—while also providing lower computational complexity and faster inference compared with state-of-the-art methods.

The Low-Altitude Wireless Networks (LAWNs) has emerged as a cornerstone of next-generation mobile due to their flexibility and adaptability in providing on-demand connectivity. However, ensuring reliable and high-throughput aerial drone communication remains a major challenge, mainly due to the dynamic mobility of aerial drones and the complexity of the wireless propagation environment. Traditional LAWNs rely heavily on channel sampling and real-time feedback, which introduce latency and communication overhead. In this work, we proposeRadioRS, a novel sampling-free aerial drone communication framework that combines Radio Map (RM) prediction with Rate-Splitting Multiple Access (RSMA) to enable robust and efficient communication without requiring explicit channel estimation during flight. RadioRS leverages a RM that provides location-aware predictions of channel state. To enhance the accuracy and generalization of these predictions under complex propagation conditions, we develop a generative model based on the Mamba architecture, which efficiently captures fine-grained correlations in the radio environment. Building on the RM, RSMA is employed to flexibly manage interference and improve spectral efficiency. In addition, we design a Mamba-powered controller that adapts beamforming strategies from the RM directly, further improving link reliability and throughput. Comprehensive simulation results demonstrate that the proposed RadioRS framework significantly outperforms conventional channel-sampling-based approaches in terms of both communication reliability and throughput.

Mesh watermark embeds secret messages in 3D meshes and decodes the message from watermarked meshes for ownership verification. Current watermarking methods directly hide secret messages in vertex and face sets of meshes. However, mesh is a discrete representation that uses vertex and face sets to describe a continuous signal, which can be discretized in other discrete representations with different vertex and face sets. This raises the question of whether the watermark can still be verified on the different discrete representations of the watermarked mesh. We conduct this research in an attack-then-defense manner by proposing a novel function space mesh watermark removal attack FuncEvade and then mitigating it through function space mesh watermarking FuncMark. In detail, FuncEvade generates a different discrete representation of a watermarked mesh by extracting it from the signed distance function of the watermarked mesh. We observe that the generated mesh can evade ALL previous watermarking methods. FuncMark mitigates FuncEvade by watermarking signed distance function through message-guided deformation. Such deformation can survive isosurfacing and thus be inherited by the extracted meshes for further watermark decoding. Extensive experiments demonstrate that FuncEvade achieves 100% evasion rate among all previous watermarking methods while achieving only 0.3% evasion rate on FuncMark. Besides, our FuncMark performs similarly on other metrics compared to state-of-the-art mesh watermarking methods.

Cooperative autonomous driving (AD) systems have increasingly become key elements of future intelligent transportation systems owing to the provisioning of dependable, safe, and effective urban mobility operations. In particular, the utilization of motion prediction can contribute to achieving a high-performance cooperative AD planning strategy of the vehicle platoon system. However, realizing accurate spatial-temporal motion prediction is a challenge since most existing work unilaterally considers the spatial or temporal feature in predicting vehicle motion trajectories. To address the problem, we design a novel spatial-temporal Transformer (ST-Transformer) motion prediction model to predict vehicle motion trajectories with highfidelity simulator. In particular, we integrate both the convolutional and transformer-based networks to capture the spatial-temporal feature of vehicle states. Case studies demonstrate the superiority of the proposed model in predicting autonomous vehicle (AV) trajectories over the existing baseline models, which can greatly support AV motion planning tasks.

The recovery of coarsely sampled trajectories considering the road network topology characteristics is a crucial task for many downstream applications in intelligent transportation systems. Existing approaches in this domain primarily focus on extracting spatio-temporal correlations for the observed trajectory points but neglect the critical role of road network topology characteristics in making the recovery results more accurate and realistic. In addition, too many road segments in cities undermine the model inference performance. To address these challenges, we propose a novel Map-informed Adaptive Spatio-Temporal Autoencoder, which follows an encoder-decoder architecture for trajectory recovery. Specifically, we utilize a pre-trained attributed network embedding module to incorporate the road segment characteristics into the input data to make it easier for the model to extract the spatio-temporal dependencies from coarse trajectories. Furthermore, we construct a novel adaptive mask inference module that contains a distance-based mask matrix and a learnable adaptive mask matrix to assist the model in making segment inferences by weighting each candidate segment adaptively in the recovery process. To evaluate the performance of the proposed model, we conduct a series of comprehensive case studies on two representative real-world trajectory datasets. The experimental results demonstrate that the proposed model consistently outperforms state-of-the-art approaches.

As one of the most promising elements in Intelligent Transportation Systems (ITSs), connected electric vehicles (CEVs) can be collectively utilized to improve the quality of essential transportation services. However, involving CEVs to provide vehicle-to-grid (V2G) services becomes a crucial problem since they are selfish and belong to different parties. To solve this problem, we propose an efficient federated CEV scheduling framework that implements noncooperative online incentive approach. In particular, the proposed system is designed for providing privacy-preserving power grid signals to each CEV aggregator (CEVA) within the citywide region. To motivate the CEVs to participate in V2G services, a noncooperative interaction scheme is designed between the selfish CEVs and each CEVA. The purpose of the game is to let the CEVA to determine the real-time electricity trading prices, while the CEVs decide their own real-time service schedules. Case studies assess the feasibility and effectiveness of proposed noncooperative incentive approach, in which the efficient motivation on the CEVs contribute to a high quality V2G services. Additionally, the use of sufficient online parking allocation method can further increase the quality of V2G services.

In the evolving field of urban development, precise traffic prediction is essential for optimizing traffic and mitigating congestion. While traditional graph learning-based models effectively exploit complex spatial-temporal correlations, their reliance on trivially generated graph structures or deeply intertwined adjacency learning without supervised loss significantly impedes their efficiency. This paper presents Contrastive Learning of spatial-tEmporal trAffic data Representations (CLEAR) framework, a comprehensive approach to spatial-temporal traffic data representation learning aimed at enhancing the accuracy of traffic predictions. Employing self-supervised contrastive learning, CLEAR strategically extracts discriminative embeddings from both traffic time-series and graph-structured data. The framework applies weak and strong data augmentations to facilitate subsequent exploitations of intrinsic spatial-temporal correlations that are critical for accurate prediction. Additionally, CLEAR incorporates advanced representation learning models that transmute these dynamics into compact, semantic-rich embeddings, thereby elevating downstream models’ prediction accuracy. By integrating with existing traffic predictors, CLEAR boosts predicting performance and accelerates the training process by effectively decoupling adjacency learning from correlation learning. Comprehensive experiments validate that CLEAR can robustly enhance the capabilities of existing graph learning-based traffic predictors and provide superior traffic predictions with a straightforward representation decoder. This investigation highlights the potential of contrastive representation learning in developing robust traffic data representations for traffic prediction.

Autonomous cooperative planning (ACP) is a promising technique to improve the efficiency and safety of multi-vehicle interactions for future intelligent transportation systems. However, realizing robust ACP is a challenge due to the aggregation of perception, motion, and communication uncertainties. This paper proposes a novel multi-uncertainty aware ACP (MUACP) framework that simultaneously accounts for multiple types of uncertainties via regularized cooperative model predictive control (RC-MPC). The regularizers and constraints for perception, motion, and communication are constructed according to the confidence levels, weather conditions, and outage probabilities, respectively. The effectiveness of the proposed method is evaluated in the Car Learning to Act (CARLA) simulation platform. Results demonstrate that the proposed MUACP efficiently performs cooperative formation in real time and outperforms other benchmark approaches in various scenarios under imperfect knowledge of the environment.

DNN-based watermarking methods are rapidly developing and delivering impressive performances. Recent advances achieve resolution-agnostic image watermarking by reducing the variant resolution watermarking problem to a fixed resolution watermarking problem. However, such a reduction process can potentially introduce artifacts and low robustness. To address this issue, we propose the first, to the best of our knowledge, Resolution-Agnostic Image WaterMarking (RAIMark) framework by watermarking the implicit neural representation (INR) of image. Unlike previous methods, our method does not rely on the previous reduction process by directly watermarking the continuous signal instead of image pixels, thus achieving resolution-agnostic watermarking. Precisely, given an arbitrary-resolution image, we fit an INR for the target image. As a continuous signal, such an INR can be sampled to obtain images with variant resolutions. Then, we quickly fine-tune the fitted INR to get a watermarked INR conditioned on a binary secret message. A pre-trained watermark decoder extracts the hidden message from any sampled images with arbitrary resolutions. By directly watermarking INR, we achieve resolution-agnostic watermarking with increased robustness. Extensive experiments show that our method outperforms previous methods with significant improvements: averagely improved bit accuracy by 7%~29%. Notably, we observe that previous methods are vulnerable to at least one watermarking attack (e.g. JPEG, Crop, or Resize), while ours are robust against all watermarking attacks.

Large Language Models (LLMs) have demonstrated remarkable capabilities, surpassing human experts in various benchmark tests and playing a vital role in various industry sectors. Despite their effectiveness, a notable drawback of LLMs is their inconsistent moral behavior, which raises ethical concerns. This work delves into symmetric moral consistency in large language models and demonstrates that modern LLMs lack sufficient consistency ability in moral scenarios. Our extensive investigation of twelve popular LLMs reveals that their assessed consistency scores are influenced by position bias and selection bias rather than their intrinsic abilities. We propose a new framework tSMC, which gauges the effects of these biases and effectively mitigates the bias impact based on the Kullback–Leibler divergence to pinpoint LLMs' mitigated Symmetric Moral Consistency. We find that the ability of LLMs to maintain consistency varies across different moral scenarios. Specifically, LLMs show more consistency in scenarios with clear moral answers compared to those where no choice is morally perfect. The average consistency score of 12 LLMs ranges from $60.7\%$ in high-ambiguity moral scenarios to $84.8\%$ in low-ambiguity moral scenarios.

Exploiting spatial–temporal correlations has long been regarded as the cornerstone of traffic state prediction. Among existing techniques, temporal graph neural networks (TGNNs) have recently emerged as a prominent solution for modeling complex spatial–temporal traffic data correlations. Existing studies on TGNNs mainly focus on developing new building blocks to embed hidden correlations into a unified latent representation, which is mapped to predictions of distinct horizons. However, mapping the same latent features to distinct scalar predictions makes the gradient computation challenging for updating model parameters in the relevant directions. Besides, TGNNs are biased towards the shared temporal patterns while neglecting the complex dependencies within each data series, which can be captured to enrich latent features. To handle these problems jointly, we propose a novel feature projection scheme for the traffic prediction framework of TGNNs. The proposed projection scheme is based on spatial convolutions that first generate horizon-specific feature maps and then transform them into scalar predictions of the corresponding horizons. These horizon-specific feature maps establish interactions between the unified latent representation and the corresponding output values to bring the predictions closer to the true values. Besides, the proposed scheme also serves as a pattern modeling phase that enhances the expressivity of TGNNs by enriching latent features with data source-wise patterns of distinct time steps. Comprehensive experiments on two real-world traffic datasets demonstrate that the proposed scheme enhances the predictive performance and reduces the model parameters of TGNNs.

Travel time estimation (TTE) aims to predict travel duration and provide reliable planning for residential travel schedules. Trajectories naturally contain sequential features in form of GPS points with temporal precedence, which can be leveraged to improve prediction performance. Besides, the spatial information, i.e., the graph structure of the road network, can well represent the road highly and is commonly used to capture spatial information in traffic networks. However, extracting regional spatial information from trajectory data, in addition to its latitude and longitude information, poses a significant challenge due to the inherent format in which the trajectory data is recorded. In light of this, we propose a graph-transformer for TTE (GT-TTE) to utilize a Graph Transformer to adapt effectively to trajectories’ sequential and spatial characteristics for improved TTE performance. By traversing the trajectory nodes with GT-TTE, we construct a graph structure for all trajectory points, thereby obtaining the relative spatial information of each point. Further, we obtain a region adjacency empirically more feature-rich over the sequential data. We evaluate GT-TTE on three real-world representative data sets and observe improvement by approximately 17% compared to the state-of-the-art baselines.

The growth of vehicular applications will inevitably require Base Stations (BSs) to simultaneously serve more Connected Vehicles (CVs) within limited bandwidth resources, which imposes a great challenge in interference management. Effective management of this interference is crucial for reliable Vehicle-to-Everything (V2X) communication, and necessitates accurate Channel State Information at the Transmitter (CSIT). In practice, the dynamic and unpredictable nature of CV movements prevents BS from obtaining perfect CSIT, leading to outdated information and threatening communication performance. In this study, we propose a Rate-Splitting Multiple Access (RSMA)-enabled V2X communication system to efficiently manage interference channels. We leverage a 1-layer RSMA scheme to relax the stringent requirement for perfect CSIT and enhance robustness to outdated information. Furthermore, we introduce Gruformer, a transformer-based model for improved CSIT prediction utilizing historical data. While longer forecasting horizons decrease accuracy, we present a game theory-based approach that significantly reduces processing time for power allocation, enabling timely decisions before CSIT becomes outdated. Simulation results reveal that Gruformer allows for more accurate predictions during rapid changes in channel conditions. Leveraging this high-quality CSIT, the proposed V2X system achieves a 20% increase in Weighted Ergodic Sum-Rate (WESR). Furthermore, the game theory-based approach delivers a 60% reduction in processing time while maintaining near-optimal performance.

Existing Rate-Splitting Multiple Access (RSMA) techniques offer a promise for Non-Terrestrial Networks (NTNs) by managing interference and ensuring reliable data transmission. However, precoder design remains a crucial bottleneck, demanding accurate Channel State Information (CSI) feedback and complex optimization, which are challenging in practical deployment. Motivated by this, this paper proposes a novel Deep Learning (DL)-based method to predict the precoder design from the historical CSI directly. In particular, we first establish a predictive beamforming protocol for precoder design using historical CSI, bypassing the need for constant feedback and reducing complexity. Subsequently, we formulate a general problem for precoder design, with the Weighted Ergodic Sum Rate (WESR) serving as the objective function. Solving this problem is particularly challenging due to the dynamic nature of wireless channels in NTNs. To address this, we designed a fusion model, named TranCN, which harnesses the strengths of Transformers and Convolutional Neural Networks (CNNs) to extract spatial-temporal features from historical CSI, thereby enhancing precoder performance. Simulation results demonstrate that our predictive beamforming scheme enables RSMA to adapt to dynamic channel conditions using historical CSI, surpassing baseline methods and improving data transmission resilience.

Pervasive integration of GPS-enabled devices and data acquisition technologies has led to an exponential increase in GPS trajectory data, fostering advancements in spatial-temporal data mining research. Nonetheless, GPS trajectories contain personal geolocation information, rendering serious privacy concerns when working with raw data. A promising approach to address this issue is trajectory generation, which involves replacing original data with generated, privacy-free alternatives. Despite the potential of trajectory generation, the complex nature of human behavior and its inherent stochastic characteristics pose challenges in generating high-quality trajectories. In this work, we propose a spatial-temporal diffusion probabilistic model for trajectory generation (DiffTraj). This model effectively combines the generative abilities of diffusion models with the spatial-temporal features derived from real trajectories. The core idea is to reconstruct and synthesize geographic trajectories from white noise through a reverse trajectory denoising process. Furthermore, we propose a Trajectory UNet (Traj-UNet) deep neural network to embed conditional information and accurately estimate noise levels during the reverse process. Experiments on two real-world datasets show that DiffTraj can be intuitively applied to generate high-fidelity trajectories while retaining the original distributions. Moreover, the generated results can support downstream trajectory analysis tasks and significantly outperform other methods in terms of geo-distribution evaluations.

The use of trajectory data with abundant spatial-temporal information is pivotal in Intelligent Transport Systems (ITS) and various traffic system tasks. Location-Based Services (LBS) capitalize on this trajectory data to offer users personalized services tailored to their location information. However, this trajectory data contains sensitive information about users’ movement patterns and habits, necessitating confidentiality and protection from unknown collectors. To address this challenge, privacy-preserving methods like K-anonymity and Differential Privacy have been proposed to safeguard private information in the dataset. Despite their effectiveness, these methods can impact the original features by introducing perturbations or generating unrealistic trajectory data, leading to suboptimal performance in downstream tasks. To overcome these limitations, we propose a Federated Variational AutoEncoder (FedVAE) approach, which effectively generates a new trajectory dataset while preserving the confidentiality of private information and retaining the structure of the original features. In addition, FedVAE leverages Variational AutoEncoder (VAE) to maintain the original feature space and generate new trajectory data, and incorporates Federated Learning (FL) during the training stage, ensuring that users’ data remains locally stored to protect their personal information. The results demonstrate its superior performance compared to other existing methods, affirming FedVAE as a promising solution for enhancing data privacy and utility in location-based applications.

Autonomous vehicles (AVs) have become an emerging crucial component of the intelligent transportation system (ITS) in modern smart cities. In particular, coordinated operations of AVs can potentially enhance the quality of public services, e.g., logistic and AV charging services. However, the joint logistic and AV charging scenario involves the sophisticated interactions between a large number of complicated agents, dynamic logistics, and electricity prices in real-world systems. Since AVs are individuals owned by different parties, the design of attractive incentive to motivate them to provide multiple public services becomes a fundamental issue. In this article, we develop an urban intelligent system (UIS) by exploiting the efficient incentive mechanisms, e.g., noncooperative and cooperative game-theoretic approaches, to motivate the AVs to provide logistic and charging services in UIS. For the noncooperative game approach, we formulate the interaction between the selfish AVs and the aggregator as a Stackelberg game. Meanwhile, the aggregator, known as the leader in the game, aims to decide the logistic and electricity trading prices, and then the AVs, executed as the followers, determine their service schedules. Furthermore, considering that all the players are willing to cooperate, we develop a cooperative potential game for the selfless AVs to maximize the social welfare of the UIS. These case studies demonstrate the effectiveness and practicability of proposed incentive mechanisms that can motivate EVs to provide high-quality logistic and charging services by maximizing their utilities. Also, both the proposed schemes provide significant system revenues than that of conventional system optimization-based approaches.

Rate-Splitting Multiple Access (RSMA) has recently found favour in the multi-antenna-aided wireless downlink, as a benefit of relaxing the accuracy of Channel State Information at the Transmitter (CSIT), while in achieving high spectral efficiency and providing security guarantees. These benefits are particularly important in high-velocity vehicular platoons since their high Doppler affects the estimation accuracy of the CSIT. To tackle this challenge, we propose an RSMA-based Internet of Vehicles (IoV) solution that jointly considers platoon control and FEderated Edge Learning (FEEL) in the downlink. Specifically, the proposed framework is designed for transmitting the unicast control messages within the IoV platoon, as well as for privacy-preserving FEEL-aided downlink Non-Orthogonal Unicasting and Multicasting (NOUM). Given this sophisticated framework, a multi-objective optimization problem is formulated to minimize both the latency of the FEEL downlink and the deviation of the vehicles within the platoon. To efficiently solve this problem, a Block Coordinate Descent (BCD) framework is developed for decoupling the main multi-objective problem into two sub-problems. Then, for solving these non-convex sub-problems, a Successive Convex Approximation (SCA) and Model Predictive Control (MPC) method is developed for solving the FEEL-based downlink problem and platoon control problem, respectively. Our simulation results show that the proposed RSMA-based IoV system outperforms both the popular Multi-User Linear Precoding (MU–LP) and the conventional Non-Orthogonal Multiple Access (NOMA) system. Finally, the BCD framework is shown to generate near-optimal solutions at reduced complexity.

Recent studies indicate that Graph Neural Networks (GNNs) are vulnerable to adversarial attacks. Particularly, adversarially perturbing the graph structure, e.g., flipping edges, can lead to salient degeneration of GNNs’ accuracy. In general, efficiency and stealthiness are two significant metrics to evaluate an attack method in practical use. However, most prevailing graph structure-based attack methods are query intensive, which impacts their practical use. Furthermore, while the stealthiness of perturbations has been discussed in previous studies, the majority of them focus on the attack scenario targeting a single node. To fill the research gap, we present a global attack method against GNNs, Saturation adversarial Attack with Meta-gradient, in this article. We first propose an enhanced meta-learning-based optimization method to obtain useful gradient information concerning graph structural perturbations. Then, leveraging the notion of saturation attack, we devise an effective algorithm to determine the perturbations based on the derived meta-gradients. Meanwhile, to ensure stealthiness, we introduce a similarity constraint to suppress the number of perturbed edges. Thorough experiments demonstrate that our method can effectively depreciate the accuracy of GNNs with a small number of queries. While achieving a higher misclassification rate, we also show that the perturbations developed by our method are not noticeable.

In modern traffic management, one of the most essential yet challenging tasks is accurately and timely predicting traffic. It has been well investigated and examined that deep learning-based Spatio-temporal models have an edge when exploiting Spatio-temporal relationships in traffic data. Typically, data-driven models require vast volumes of data, but gathering data in small cities can be difficult owing to constraints such as equipment deployment and maintenance costs. To resolve this problem, we propose TrafficTL, a cross-city traffic prediction approach that uses big data from other cities to aid data-scarce cities in traffic prediction. Utilizing a periodicity-based transfer paradigm, it identifies data similarity and reduces negative transfer caused by the disparity between two data distributions from distant cities. In addition, the suggested method employs graph reconstruction techniques to rectify defects in data from small data cities. TrafficTL is evaluated by comprehensive case studies on three real-world datasets and outperforms the state-of-the-art baseline by around 8 to 25 percent.

Traffic speed prediction based on real-world traffic data is a classical problem in intelligent transportation systems (ITS). Most existing traffic speed prediction models are proposed based on the hypothesis that traffic data are complete or have rare missing values. However, such data collected in real-world scenarios are often incomplete due to various human and natural factors. Although this problem can be solved by first estimating the missing values with an imputation model and then applying a prediction model, the former potentially breaks critical latent features and further leads to the error accumulation issues. To tackle this problem, we propose a graph-based spatio-temporal autoencoder that follows an encoder-decoder structure for spatio-temporal traffic speed prediction with missing values. Specifically, we regard the imputation and prediction as two parallel tasks and train them sequentially to eliminate the negative impact of imputation on raw data for prediction and accelerate the model training process. Furthermore, we utilize graph convolutional layers with a self-adaptive adjacency matrix for spatial dependencies modeling and apply gated recurrent units for temporal learning. To evaluate the proposed model, we conduct comprehensive case studies on two real-world traffic datasets with two different missing patterns and a wide and practical missing rate range from 20% to 80%. Experimental results demonstrate that the model consistently outperforms the state-of-the-art traffic prediction with missing values methods and achieves steady performance in the investigated missing scenarios and prediction horizons.

The existing Federated Learning (FL) systems encounter an enormous communication overhead when employing GNN-based models for traffic forecasting tasks since these models commonly incorporate enormous number of parameters to be transmitted in the FL systems. In this paper, we propose a FL framework, namely, C lustering-based hierarchical and T wo-step- optimized FL (CTFL), to overcome this practical problem. CTFL employs a divide-and-conquer strategy, clustering clients based on the closeness of their local model parameters. Furthermore, we incorporate the particle swarm optimization algorithm in CTFL, which employs a two-step strategy for optimizing local models. This technique enables the central server to upload only one representative local model update from each cluster, thus reducing the communication overhead associated with model update transmission in the FL. Comprehensive case studies on two real-world datasets and two state-of-the-art GNN-based models demonstrate the proposed framework’s outstanding training efficiency and prediction accuracy, and the hyperparameter sensitivity of CTFL is also investigated.

Electric vehicle (EV) dynamic wireless charging system has become an emerging application in the area of the intelligent transportation system (ITS). However, an integrated design of the EV dynamic wireless charging system requires the considerations of both the economical and technical perspectives of a smart city. Specifically, most of the existing researches unilaterally consider the application of either placement strategy for power tracks (PTs) or dynamic vehicle-to-grid (V2G) scheduling. In this article, we propose a multistage system framework to account for an integrated EV dynamic wireless charging system in a smart city. First of all, an optimal placement strategy for PTs is developed based on city traffic information and EV energy demand. Then, having the optimal locations of PTs through the previous stage approach, the proposed dynamic V2G scheduling scheme is formulated to coordinate the schedules of EVs with the provision of daytime V2G ancillary services. Our simulation results present that the proposed multistage system model achieves improvements on both the placement strategy and V2G scheduling scheme. In addition, relatively low economic system costs can be obtained through our proposed model.

Accurate long-term origin-destination demand (OD) prediction can help understand traffic flow dynamics, which plays an essential role in urban transportation planning. However, the main challenge originates from the complex and dynamic spatial-temporal correlation of the time-varying traffic information. In response, a graph deep learning model for long-term OD prediction (ST-GDL) is proposed in this paper, which is among the pioneering work that obtains both short-term and long-term OD predictions simultaneously. ST-GDL avoids the conventional multi-step forecasting and thus prevents learning from prediction errors, rendering better long-term forecasts. The proposed method captures time attributes from multiple time scales, namely closeness, periodicity, and trend, to study the features with temporal dynamics. Besides, two gate mechanisms are introduced over the vanilla convolution operation to alleviates the error accumulation issue of typical recurrent forecast in long-term OD prediction. A method based on graph convolution is proposed to capture the dynamic spatial relationship, which projects the transportation network into a graphical time-series. Finally, the long-term OD prediction results are obtained by combining the extracted spatio-temporal features with external features from the meteorological information. Case studies on a practical dataset show that the proposed model is superior to existing methods in long-term OD prediction problems.

Traffic speed prediction is among the foundations of advanced traffic management and the gradual deployment of internet of things sensors is empowering data-driven approaches for the prediction. Nonetheless, existing research studies mainly focus on short-term traffic prediction that covers up to one hour forecast into the future. Previous long-term prediction approaches experience error accumulation, exposure bias, or generate future data of low granularity. In this paper, a novel data-driven, long-term, high-granularity traffic speed prediction approach is proposed based on recent development of graph deep learning techniques. The proposed model utilizes a predictor-regularizer architecture to embed the spatial-temporal data correlation of traffic dynamics in the prediction process. Graph convolutions are widely adopted in both sub-networks for geometrical latent information extraction and reconstruction. To assess the performance of the proposed approach, comprehensive case studies are conducted on real-world datasets and consistent improvements can be observed over baselines. This work is among the pioneering efforts on network-wide long-term traffic speed prediction. The design principles of the proposed approach can serve as a reference point for future transportation research leveraging deep learning.

Autonomous vehicles (AVs), as one of the cores in future intelligent transportation systems (ITSs), can facilitate reliable and safe traffic operations and services. The ability to automatically perform effective AV motion planning and deploy efficient perception systems is vital for advancing the quality of core transportation services. However, existing research studies have only considered the applications of either of these approaches, which neglect their necessary interactions in real-world AV motion planning systems. To address this problem, we design an AV motion planning strategy based on motion prediction and V2V communication. Specifically, we propose the perception system and V2V communication module to provide real-time traffic and vehicular information to the participated AVs. Then, we formulate the AV lane-change motion planning problem through the scope of model predictive control based problem, as well as proposing the method on learning optimal motion planning by means of a novel deep learning technique. We conduct extensive case studies to evaluate the performance of the proposed system model. Our experimental results demonstrate the effectiveness of the proposed system model under various traffic conditions. In addition, the robustness of the perception system is guaranteed by utilizing the Car Learning to Act (CARLA) system with available V2V communication.

In a smart grid integrated with vehicle-to-grid (V2G) technique, electric vehicles (EVs) fleets under effective coordination can be considered as a massive aggregated power storage to provide frequency regulation service. In this article, we propose a hierarchical system model to jointly optimize power flow routing and V2G scheduling for providing regulation service. First of all, by installing power flow routers (PFRs) inside the power grid, we formulate the problem of optimal power flow (OPF) routing at the grid level. Through the utilization of the semidefinite programming (SDP) relaxation, we can transform the original non-deterministic polynomial-time hard (NP-hard) problem into a convex problem. The tree decomposition method is then used to further reduce the complexity of the system network. After solving the grid-level OPF routing problem, a forecast-based scheduling problem is formulated at the EV level to coordinate EVs by providing the V2G regulation service. To cope with the forecast uncertainties, an online scheduling problem is in turn formulated. In order to solve these problems in a scalable manner, decentralized algorithms are then devised to control the EV schedules. The simulation results show that the devised online scheduling algorithm can outperform the existing algorithms, which is able to flatten the power fluctuations at the buses with EVs attached. Additionally, we show that grid stability issue can be alleviated through the proposed model. Finally, for different power systems, the uses of PFRs can reduce the system power loss in a great manner while providing voltage regulation.

Autonomous vehicle (AV) integration poses a significant challenge for intelligent transportation systems (ITSs). The ability to automatically coordinate complex AV operations at scale is crucial for advancing the quality of core transportation services, such as ride-sharing and parcel delivery. However, existing studies have only considered either of these two services independently from the other, disregarding the potential benefits of their combined optimization. To address this open problem, we design an autonomous vehicle intelligent system (AVIS) providing joint ride-sharing and parcel delivery services under realistic ride and route constraints. We formulate the joint optimization problem through the scope of mixed-integer linear programming and solve it using the Lagrangian dual decomposition method to ensure scalability. We conduct extensive case studies to evaluate the performance of the proposed AVIS and its constituting components. Our experimental results demonstrate that AVIS can effectively provide both ride-sharing and parcel delivery services while satisfying service requests in transportation networks of various scales. In addition, the distributed method is shown to generate near-optimal solutions in reduced computation time.