Traffic flow prediction is a key component of Intelligent Transportation Systems (ITS), crucial for alleviating urban congestion, optimizing traffic management, and improving the overall efficiency of road networks. With the rapid growth in vehicle numbers and the increasing complexity of urban traffic patterns, accurate short-term traffic flow prediction has become increasingly important. This paper comprehensively reviews the latest advancements in traffic flow prediction methods, focusing on graph neural network (GNN)-based approaches and hybrid deep learning frameworks. First, we introduce the fundamental theoretical foundations, including graph neural networks, deep learning algorithms, heuristic optimization methods, and attention mechanisms. Subsequently, we summarize GNN-based prediction methods into four paradigms: (1) federated learning and privacy-preserving methods, enabling cross-regional collaboration while protecting sensitive data; (2) dynamically adaptive graph structure methods, capturing time-varying spatial dependencies; (3) multi-graph fusion and attention mechanism methods, enhancing feature representations from multiple perspectives; and (4) cross-domain technology integration methods, fusing novel architectures and interdisciplinary technologies. Furthermore, we investigate hybrid methods combining signal decomposition, heuristic optimization, and attention mechanisms with LSTM networks to address challenges related to non-stationarity and model optimization. For each category, we analyzed representative works and summarized their core innovations, strengths, and limitations using a systematic comparative table. Finally, we discussed current challenges, including computational complexity, model interpretability, and generalization ability, and outlined future research directions such as lightweight model design, uncertainty quantification, multimodal data fusion, and integration with traffic control systems. This review provides researchers and practitioners with a systematic understanding of the latest advances in traffic flow prediction and offers guidance for methodological selection and future research.

Autonomous racing requires fast, anticipatory, and interaction-aware trajectory planning, where the ego vehicle must interpret complex track geometries while reasoning about the future behavior of multiple competitive agents. Existing approaches typically treat static and dynamic obstacles separately or rely heavily on global perception, limiting their robustness and scalability in realistic multi-agent racing environments. This work presents a unified prediction–planning framework that jointly addresses static and dynamic challenges through three key mechanisms. First, a grid-based track discretization and static risk field are constructed to model proximity to boundaries and fixed obstacles through smooth spatial potentials, enabling efficient safety-aware path shaping. Second, an interaction-aware prediction module based on Mean Field Games (MFG) captures the collective, density-driven behavior of surrounding vehicles, providing anticipatory and rational multi-agent motion forecasts. Third, these components are integrated into a hierarchical trajectory optimizer using piecewise-jerk quadratic programming (PJPO) for path and speed planning, followed by spline smoothing to ensure continuity and dynamic feasibility. Extensive evaluations across nine racetrack segments and diverse dynamic obstacle configurations demonstrate that the proposed planner achieves superior collision avoidance, smoother trajectories, and improved lap times compared to MPC, RRT*, and A*+Profiling baselines. The results confirm the framework’s strong generalization to both static and multi-agent dynamic environments, highlighting its suitability for real-time, high-speed autonomous racing.

In recent years, achieving safety, efficiency, and comfort among interactive automated driving has been a formidable challenge. Model-based approaches, such as game-theoretic and robust control methods, often result in overly cautious decisions or suboptimal solutions. In contrast, learning-based techniques typically demand high computational resources and lack interpretability. At the same time, simpler strategies that rely on static assumptions tend to underperform in rapidly evolving traffic environments. To address these limitations, we propose a novel game-based MPC-DDP framework that integrates game-theoretic predictions of human-driven vehicle (HDV) with a Dynamic Differential Programming (DDP) solver under a receding-horizon setting. Our method dynamically adjusts the autonomous vehicle’s (AV) control inputs in response to real-time human-driven vehicle (HDV) behavior. This enables an effective balance between safety and efficiency. Experimental evaluations on lane-change and intersection scenarios demonstrate that the proposed approach achieves smoother trajectories, higher average speeds when needed, and larger safety margins in high-risk conditions. Comparisons against state-of-the-art baselines confirm its suitability for complex, interactive driving environments.

Aiming at the problem of random environment interference in the process of strategy interaction and the behavioral evolution of an aerial attack–defense game, this paper considers the influence of the difference in the performance and value between both game players in terms of strategy evolution; explores the randomness of the complex battlefield environment, the uncertainty of the behavioral state of game players, and the limitations of the emergent situation; constructs a mathematical model of the stochastic evolution of an aerial-coordinated attack–defense game in uncertain environments; and studies the stability of the strategy interaction and behavioral decision-making process of both players of the aerial attack–defense game. Simulation results show that many factors of the performance and value between both game players have a greater impact on the strategy evolution trend in both game players, which not only causes changes in the results of the strategy selection but also affects the rate of strategy evolution for the game players. In addition, random environmental factors cause a certain degree of interference to the strategy evolution process of the game players, which usually accelerates the game players’ strategy evolution rate and greatly affects the evolution process of the game players’ strategy. This study can provide a theoretical basis and feasible reference for improving mission decision-making, response mechanisms, and system modeling of an aerial attack–defense game, which has important theoretical value and practical significance.

To address the risks of centralized single-point failures and data privacy leaks associated with massive data storage in Intelligent Transportation Systems (ITS) and Vehicle-to-Everything (V2X) environments, this paper proposes a distributed secure storage architecture based on blockchain. However, traditional Practical Byzantine Fault-Tolerant (PBFT) algorithms suffer from scalability bottlenecks in large-scale dynamic networks, such as high communication overhead and low consensus efficiency. Therefore, this paper designs a hierarchical and reputation-aware improved consensus mechanism (H-PBFT). First, this mechanism introduces a geographical location grouping strategy, dividing all network nodes into several local consensus groups and leveraging edge computing characteristics to achieve rapid consensus within each group. Second, a multi-dimensional reputation evaluation model (comprehensively considering historical behavior, performance, and availability) is constructed to dynamically elect representative nodes from each group to participate in global consensus, thereby significantly reducing the communication complexity from O(N2). Simulation results show that compared with standard PBFT, Q-PBFT, and APBFT, H-PBFT exhibits significant advantages in consensus latency, throughput, and view switching recovery time, and maintains high system robustness even in complex network environments with malicious nodes.

Unmanned aerial vehicles (UAVs) require reliable and efficient path planning to navigate complex three-dimensional (3D) environments. However, conventional sampling-based planners such as RRT* typically produce irregular trajectories characterized by redundant waypoints and abrupt directional changes, which compromise flight efficiency and control performance. This paper proposes RRT*-CEC-AEB, a two-stage trajectory refinement framework that integrates an Adaptive Elastic Band (AEB) optimizer and a Collision-aware Efficient Compression (CEC) strategy atop the RRT* global planner. AEB treats the initial path as a deformable elastic curve and iteratively balances internal smoothing forces against external obstacle repulsion with adaptive weighting, thereby enhancing trajectory smoothness and safety clearance. CEC subsequently eliminates geometrically redundant waypoints through segment-level collision detection and minimum clearance verification, yielding a compact and executable flight trajectory. Four known static 3D sphere maps are evaluated with 30 comparison trials per method and scene, and 100 paired ablation trials per scene. Relative to the implemented RRT* initializer, the ratio of four-scene macro means gives reductions of 7.51% in length, 55.02% in the sum of squared turning angles and 41.38% in waypoint count. The proposed framework provides an effective and computationally efficient solution for autonomous UAV path planning in complex 3D environments.