Chao Wang

Vehicle-to-everything (V2X) communication plays an essential role in the Internet-of-Vehicles (IoV) systems. However, in practice the diverse decision objectives of different users and the highly dynamic nature of IoV cause great challenges in realizing efficient data transmission. This paper investigates a sequential power control problem in a typical V2X communication network formed by multiple data delivery links, and proposes a novel decision framework from the perspective of dynamic multi-objective optimization (DMO). The framework is developed based on the dynamic multi-objective optimization evolutionary algorithm (DMOEA). When the variation of channel fading state is detected, an innovative environment change response mechanism is implemented to predict the centroid change of the Pareto optimal set (PS) in the new environment. This allows to properly generate the initial population for the subsequent evolutionary search process, and rapidly track the time-varying Pareto optimal front (PF). The effectiveness and advantages of the proposed framework over conventional solutions are validated by simulation results.

Traffic status monitoring is essential to support intelligent transportation, and demands for highly efficient and secure processing and transmission of massive data. Inspired by recent information-theoretic study, the traffic status monitoring is formulated as a privacy-preserving semantic coding problem in this work to characterize the fundamental trade-off among data compression, traffic image reconstruction, segmentation of traffic participants, and preservation of pixel regions of traffic participants. Grounded on the theoretic results, a novel generative semantic coding scheme is further developed for data-driven semantic coding design with the aid of attention mechanisms to capture correlations between sparse information. Experiments on the RCooper dataset demonstrate the effectiveness of the proposed generative semantic coding scheme and its advantages over the benchmark compression methods.

This paper proposes a semantic Sparse Code Multiple Access (SCMA) broadcast framework for Unmanned Aerial Vehicle (UAV)-assisted Internet of Vehicles (IoV) networks, integrating structural state optimization with Lyapunov-guided Deep Reinforcement Learning (DRL). The UAV acts as a semantic-aware aerial Base Station (aBS) that extracts and encodes high-level semantic features before mapping them onto the SCMA factor graph. A state-optimization module designs the semantic projection and energy-mapping matrices to preserve semantic fidelity under power and sparsity constraints. On top of this structure, a Lyapunov-constrained DRL controller adapts the UAV’s transmit-power policy based on instantaneous semantic reliability, channel dynamics, and network conditions. Simulation results demonstrate that the proposed Lyapunov-guided learning approach significantly improves energy efficiency and long-term stability while maintaining semantic reliability above the required threshold, with negligible throughput degradation compared to unconstrained SCMA-based learning schemes.

The advent of 6G networks necessitates fundamental advancements in Radio Access Network (RAN) slicing to accommodate unprecedented service demands with highly dynamic traffic patterns. Existing AI-driven approaches for RAN slicing face critical limitations: they typically require model retraining when slice configurations change, lack scalability for concurrent slice management, or overlook the significant computational overhead from frequent resource reconfigurations. This paper addresses these significant challenges by introducing a novel RAN Partially Observable Stochastic Game (RAN-POSG) framework that enables parallel decision-making while effectively incorporating global resource constraints. Firstly, we propose an Adaptive Retention Framework (ARF) that strategically balances stability and adaptability through an innovative Conditional Accumulative Reward mechanism, significantly reducing reconfiguration overhead while maintaining high Service Level Agreement (SLA) compliance. Our proposed Statistic-Field Deep Truncated Monte Carlo (SF-DTMC) algorithm leverages multi-agent reinforcement learning where agents make independent yet coordinated decisions, ensuring both flexibility with varying slice counts and scalability under large-scale networks. Lastly, a custom-built high-fidelity RAN slicing simulator based on NS-3 simulator with PettingZoo interfaces is developed for comprehensive evaluations across multiple test scenarios. The simulation results demonstrate the significant advantages of the proposed framework, including superior user satisfaction, resource utilization, and lower resource reconfiguration overhead compared to state-of-the-art methods, representing a crucial advancement toward Native-AI in 6G networks.

Parking scenarios present huge challenges for the prediction of intentions and situational awareness of autonomous vehicles. Unlike urban roads, parking scenarios feature greater freedom of movement, denser interactions, and more diverse intents. To address this issue, we propose the Parking Memory Interaction Transformer (PMI-Transformer) for predicting vehicle intent and trajectory based on cooperative vehicle-infrastructure systems (CVIS). Our model utilizes long-term semantic observation data and short-term historical trajectories to predict a target vehicle’s future intentions and trajectories from roadside perception units in CVIS. Based on global spatiotemporal features, a memory encoding strategy extracts essential information from the vehicle’s long-term history. At the same time, a hypergraph-based multiscale interaction module captures dense, diverse interactions in multi-vehicle environments. We incorporate parking occupancy data and calculate affinities between the vehicle and nearby spots to better characterize vehicle intent within the parking context. Experimental results show that our model outperforms state-of-the-art methods in intent and trajectory prediction, with visualizations confirming that PMI-Transformer effectively captures key historical information and social interactions in parking scenarios.

Semantic communication is envisioned as a promising solution for tackling the data transmission challenges in future wireless communication systems. In this paper, we propose a novel semantic importance-enhanced multi-hop semantic communication (SIMSC) framework that integrates semantic communication with a map-and-forward (MF) relaying scheme. To enhance transmission reliability, the framework employs a semantic importance (SI) calculation module to aid in training joint source-channel coding (JSCC) with relays, thereby better protecting the delivery of crucial semantic information over wireless channels with long-distance signal propagation. Different from conventional amplify-and-forward (AF) and decode-and-forward (DF) relaying schemes, the proposed MF scheme leverages a deep neural network (DNN) to adaptively transform the received signal, optimizing it for multi-hop transmission. This enhances robustness and flexibility in varying relay conditions. Numerical results demonstrate that the proposed SIMSC framework performs notably better than conventional solutions that do not utilize semantic coding or relays. Moreover, the MF relaying scheme outperforms the AF and DF schemes, especially when relay distances vary across hops.

This paper presents a novel, high-performance multi-vehicle detection and tracking (MVDT) framework to extract vehicle trajectories from roadside 3D point clouds. First, we developed a vehicle detector called the deep evidential occupancy grid model. This model uses PointNet to extract features from vertically organized point cloud pillars, generating a bird’s-eye view (BEV) grid feature map, followed by a 2D convolutional neural network to capture both local and global spatial features. The detection head uses a Dirichlet distribution to gather “evidence” from gathered features that indicate grid occupancy or vacancy, quantifying the model’s “confidence” through a probabilistic representation of uncertainty. An adaptive post-processing method is applied to output detection results with associated uncertainty. Second, we integrated uncertainty into the tracker, developing an uncertainty-aware multi-vehicle tracking (UMVT) model. This model manages the trajectory initialization and termination strategies, enhancing tracking robustness in complex scenarios. Comprehensive experiments on two real-world datasets, DAIR-V2X and V2X-Real, demonstrate that the proposed MVDT framework outperforms state-of-the-art methods in roadside perception, achieving improvements in both detection and tracking tasks. The effectiveness has also been validated using point cloud data from the Shanghai-Nanjing Expressway, showcasing its excellent practical applicability.