The real-time path optimization for heterogeneous vehicle fleets in large-scale road networks presents significant challenges due to conflicting traffic demands and imbalanced resource allocation. While existing vehicle-to-infrastructure coordination frameworks partially address congestion mitigation, they often neglect priority-aware optimization and exhibit algorithmic bias toward dominant vehicle classes—critical limitations in mixed-priority scenarios involving emergency vehicles. To bridge this gap, this study proposes a preference game-theoretic coordination framework with adaptive strategy transfer protocol, explicitly balancing system-wide efficiency (measured by network throughput) with priority vehicle rights protection (quantified via time-sensitive utility functions). The approach innovatively combines (1) a multi-vehicle dynamic routing model with quantifiable preference weights, and (2) a distributed Nash equilibrium solver updated using replicator sub-dynamic models. The framework was evaluated on an urban road network containing 25 intersections with mixed priority ratios (10%–30% of vehicles with priority access demand), and the framework showed consistent benefits on four benchmarks (Social routing algorithm, Shortest path algorithm, The comprehensive path optimisation model, The emergency vehicle timing collaborative evolution path optimization method) showed consistent benefits. Results show that across different traffic demand configurations, the proposed method reduces the average vehicle traveling time by at least 365 s, increases the road network throughput by 48.61%, and effectively balances the road loads. This approach successfully meets the diverse traffic demands of various vehicle types while optimizing road resource allocations. The proposed coordination paradigm advances theoretical foundations for fairness-aware traffic optimization while offering implementable strategies for next-generation cooperative vehicle-road systems, particularly in smart city deployments requiring mixed-priority mobility guarantees.

Accurate trajectory forecasting is essential for enabling autonomous vehicles to navigate safely in complex traffic environments. Current models typically assume that predictions are latency-free, an idealistic simplification that fails in real-world settings, where processing, computation, and transmission inevitably introduce delays. During this latency window, target agents continue to move, which renders early predictions obsolete, thus degrading system performance. To address this challenge, we introduce latency-aware trajectory prediction, a new task that explicitly accounts for latency and repurposes it as a useful signal. We present LatenAux, a consolidated auxiliary learning paradigm that first decouples prediction into two tasks: a primary task that predicts valid-horizon trajectories from historical data, and an auxiliary task that utilizes latency-inclusive observations. By allowing the auxiliary branch access to latency-crafted inputs, LatenAux is then committed to transferring latency-aware knowledge to the primary branch via a progressive feature alignment strategy. This enables the primary model to internalize latency cues without explicit reliance on latency data. Our method departs from conventional auxiliary learning by introducing a soft feature-consistency function, which gradually incorporates auxiliary representations across both scene context and query state levels, enriching features while avoiding overconstraint. In addition, auxiliary queries act as informative priors for the primary branch to further enhance prediction accuracy. Extensive experiments on two large-scale real-world datasets demonstrate the effectiveness and superiority of LatenAux, showing that it consistently supports latency-aware modeling and delivers more accurate and reliable trajectory forecasts.

Autonomous driving technology is becoming increasingly popular, transforming transportation systems worldwide. However, its perception modules are highly vulnerable to adversarial attacks, which exploit weaknesses in deep neural networks, leading to potential safety risks and compromised decision-making in autonomous systems. In this study, we propose AdvGLOW, a novel adversarial attack model tailored for covert attacks on autonomous driving perception modules in traffic scenarios. Leveraging an information exchange network within a flow-based model, AdvGLOW introduces reversible data transformations to achieve high attack success with minimal perturbation visibility. By optimizing a combined global-local loss, our model preserves structural details while embedding adversarial features, resulting in robust yet visually imperceptible adversarial samples. We conduct extensive experiments on traffic-related datasets, demonstrating that the generated adversarial samples are challenging for both humans and algorithms to detect. Additionally, this method exhibits strong attack robustness and transferability.