With the increasing frequency of natural disasters, terrestrial communication infrastructure is often severely damaged, leading to interruptions in edge computing and data delivery. This paper proposes a Post-Disaster Adaptive Deep Deterministic Policy Gradient algorithm (PD-DDPG) to jointly optimize the Unmanned Aerial Vehicle (UAV)'s trajectory and vehicle task offloading in such disrupted environments. The PD-DDPG framework enhances traditional DDPG by incorporating a probabilistic Roadside Unit (RSU) failure model and real-time UAV-vehicle communication constraints into the environment state, enabling informed decision-making in uncertain post-disaster conditions. The proposed model employs a multi-objective reward function that simultaneously minimizes Age of Information (AoI), transmission delay, and system-wide energy consumption. To improve exploration and convergence under non-stationary dynamics, PD-DDPG uses an adaptive noise mechanism during training. Simulation experiments across different RSU damage rates validate the robustness and generalization ability of the proposed method. Comparative evaluations with Twin Delayed Deep Deterministic Policy Gradient (TD3) and random baseline strategies demonstrate that PD-DDPG achieves lower delay and energy costs while maintaining comparable AoI levels. In addition, the UAV trained via PD-DDPG autonomously adjusts its trajectory to compensate for RSU outages and maximize service coverage. This study provides an effective framework for emergency offloading coordination and offers insights into UAV-assisted edge computing in post-disaster scenarios.

Multi-Agent Reinforcement Learning (MARL) has demonstrated significant potential for cooperative decision-making in connected and autonomous vehicles (CAVs). However, existing approaches often fail to address the task-specific characteristics and varying requirements of vehicles in high-dynamic, unsignalized intersection scenarios. In these environments, vehicles are frequently exposed to conflict zones where risks, such as collisions, are difficult to perceive, particularly in the absence of traffic signals. Additionally, current methods lack effective mechanisms for balancing learning performance across multiple tasks. To overcome these challenges, we propose a novel multi-task MARL framework tailored for unsignalized intersections. The framework incorporates a hybrid-attention network that captures the influence of surrounding vehicles on different driving tasks, improving multi-agent decision-making. A multi-task diversity priority sampling mechanism is introduced to prioritize high-quality episodes from more complex tasks, enhancing performance in dynamic intersection settings. Furthermore, a risk-aware local decision corrector optimizes decision-making in high-risk conflict zones by enabling vehicles to predict and adapt to surrounding traffic behaviors. The proposed framework is evaluated through simulations, demonstrating superior performance compared to state-of-the-art baselines. A miniature intelligent vehicle testbed further validates its effectiveness and potential for real-world deployment.

In complex traffic environments, autonomous vehicles must simultaneously cope with multi-source potential risks arising from road boundaries, lane structures, and both dynamic and static traffic participants. These risks interact and overlap across spatial and temporal dimensions, increasing the safety challenges of trajectory planning. Existing methods face limitations in handling high-dimensional obstacle avoidance constraints and dynamic environmental factors, often resulting in degraded trajectory quality and reduced safety. To overcome these challenges, this paper proposes a safety-enhanced trajectory planning method, which improves trajectory quality through the recursive generation of the Spatio-Temporal Risk Map (STRM) and the Dynamic Safety Corridor (DSC). First, based on potential field theory, a risk modeling approach is applied to various traffic elements, such as road boundaries, lane markings, and both dynamic and static obstacles, to generate the STRM, thereby mapping the traffic environment information into a unified risk space. Subsequently, a method for constructing the DSC is proposed, considering boundary risk thresholds. This approach effectively decouples the relationship between complex environmental factors and driving tasks, thereby simplifying collision constraints. Finally, an Optimal Control Problem (OCP) is formulated, taking into account factors such as trajectory smoothness, comfort, and collision risk, in order to generate safe optimized trajectories. The effectiveness of the proposed method in various multi-lane scenarios was evaluated through simulation experiments. The results show that the proposed method significantly enhances the safety of trajectory planning, especially in highly dynamic and high-risk environments.

With the rapid advancement of Vehicle-to-Everything (V2X) communication and automated driving technologies, connected and automated vehicle (CAV) platoons have emerged as a promising solution for enhancing road capacity, energy efficiency, and traffic safety. Unlike the ideal fully CAV environment, real-world traffic will remain in a mixed traffic phase for an extended period, where CAVs and human-driven vehicles (HDVs) coexist. Factors such as cut-in by surrounding vehicles, HDV leader disturbances, and communication delay significantly increase the complexity of platoon control. This paper provides a systematic review of CAV platoon control methods under mixed traffic from three interrelated perspectives: control architecture, HDV interaction mecha nisms, and control methods. From the architectural perspective, centralized management, distributed cooperation, and hybrid hierarchical architectures are comparatively examined in terms of decision efficiency, communication dependency, and scalability. Regarding HDV interaction mechanisms, HDV behavior modeling and prediction approaches based on model-driven, data-driven, and game-theoretic frameworks are synthesized, highlighting the trade-offs between modeling fidelity and uncertainty quantification capability. In terms of control methods, the technical characteristics and applicability limits of model-driven control, data-driven control, and hybrid model-data-driven control are systematically analyzed. Building upon this comparative assessment, the advantages, limitations, and application scenarios of these approaches are summarized to provide guidance for control strategy design and selection. Finally, future research directions for CAV platoon control under mixed traffic flow are outlined, aiming to provide theoretical support for establishing safe, stable, and efficient CAV platoons in complex mixed traffic environments.

Reliable perception of taillight signals is essential for robust driving intention recognition in autonomous vehicles. However, real-world conditions, such as varying illumination and adverse weather, often degrade image quality and obscure visual cues, leading to detection errors and poor generalization in traditional vision-based methods. To address these challenges, this article proposes the multiscene preceding vehicle intention recognition network (MS-PVIRNet), a framework designed for adaptive intention recognition across diverse driving environments. Central to the method is a global-local attention-guided CLAHE module (GLA-CLAHE), which employs an attention fusion mechanism to combine global illumination context and local texture cues, allowing adaptive regression of CLAHE parameters. This strategy significantly improves taillight visibility under complex environmental conditions. MS-PVIRNet adopts a you only look once (YOLO)-based detection architecture, enhanced with multiscale feature fusion and omni-dimensional dynamic convolution (ODConv) to improve robustness and efficiency in intention recognition. Extensive experiments are conducted on a self-constructed multiscene driving intention dataset. Results show that MS-PVIRNet outperforms other methods under various lighting and weather conditions, providing a practical solution for intention recognition in real-world autonomous driving scenarios. Furthermore, sensitivity analysis on vehicle distance and relative velocity shows that the proposed method maintains high recognition accuracy within 0-30 m and 0-25 km/h, validating its effectiveness in dynamic and complex environments.

Mixed platoons comprising connected automated vehicles (CAVs) and human-driven vehicles (HDVs) are subject to dual-layer disturbances arising from unpredictable traffic oscillations and stochastic communication delays. To address these disturbances, this study proposes Resilience-Physics Enhanced Residual Learning (R-PERL), a resilience-oriented control framework that integrates model predictive control with communication-quality-aware residual learning. R-PERL establishes a unified system model that couples knowledge-guided longitudinal dynamics with a comprehensive stochastic communication-delay model as a fixed foundation, ensuring inter-pretability and constraint satisfaction. A gating mechanism adaptively regulates residual learning to compensate for model-reality mismatch under degraded information quality, while resilience operations leverage aggregated HDV and macroscopic traffic information to prevent overreaction and accelerate disturbance attenuation. This architecture enables the controller to absorb oscillations, maintain core functionality during communication deterioration, and rapidly restore nominal conditions. Comparative simulations indicate that R-PERL outperforms baseline methods in string stability, ride comfort, tracking accuracy, and resilience-related metrics. During communication interruptions, performance degrades smoothly without abrupt collapse and resynchronizes rapidly after recovery. Across varying CAV penetration rates, consistent improvements in traffic operation and oscillation suppression are observed. Generalization validation over repeated random delay trials confirms bounded tracking behavior in the tested scenarios and supports safe operation with effective oscillation attenuation under the considered conditions.

Automated vehicles (AVs) are transforming urban transportation systems, as end-to-end autonomous driving models show great promise in enhancing traffic safety and operational efficiency. Despite these advances, their performance in highly interactive driving scenarios remains limited due to insufficient decision-making diversity and the absence of explicit safety guarantees. To address these challenges, we propose NavDrive, a safety-enhanced end-to-end autonomous driving framework that formulates planning as a multi-modal generative process.Specifically, NavDrive integrates navigation-based guidance into a diffusion policy. To focus on decision-critical information, a Decision-Aware Channel Fusion (DCF) module adaptively emphasizes regions involving key interactions between the ego vehicle and surrounding agents. Furthermore, a safety-aware generative planner refines trajectory samples toward feasible regions via the Target-Prior Diffusion Transformer (TDiT), which explicitly embeds physical constraints to ensure safe and human-aligned driving behaviors. Extensive experiments on the NAVSIM and nuScenes benchmarks demonstrate that NavDrive consistently outperforms existing baselines, delivering substantial gains in planning quality, safety, and robustness under complex and adverse conditions. The details will be available at https://github.com/zgchongbo/NavDrive

Virtual Coupling (VC) technology is expected to increase railway capacity and enable flexible coordinated train formations in complex scenarios. A representative VC operation occurs at track junctions, where trains merge and transition among coupling, coupled, and decoupled states. This paper investigates the problem of integrating the sideline train into mainline virtually coupled train set (VCTS) while maintaining coupling-state continuity, and proposes an MPC-based virtual pilot injection (VPI) strategy. A virtual pilot trajectory is planned, and distributed MPC controllers are designed under a leader-follower information framework to achieve smooth merging and recoupling. Robustness and stability are theoretically established to account for disturbances and unreliable communication. Extensive simulation results demonstrate that, compared with existing methods, the proposed approach significantly reduces the coupling time under both ideal operating conditions and scenarios with disturbances and delays, while maintaining effective safety protection even in extreme cases.

Unmanned aerial vehicles (UAVs) play a pivotal role in air-ground collaborative mobile edge computing (MEC) systems. They function as aerial cloudlets, deploying flexibly closer to ground users (GUs) to provide enhanced computational capacity in edge computing scenarios. While extensive studies have optimized resource allocation and UAV trajectories collaboratively to improve energy and offloading efficiency, few have simultaneously addressed the system's communication security and reliability. This paper proposes a joint optimization model to ensure both security and reliability in an energy-efficient UAV-assisted MEC system. Specifically, we introduce an artificial noise generation technique to enhance system security and derive a closed-form expression for the optimal ratio between the generated noise and the data transmission power to ensure secure communication. Additionally, we propose a probabilistic model to characterize the reliability of data transmission and derive the worst-case transmission rate. Furthermore, we present an energy-efficient model for optimizing resource allocation and UAV trajectory planning, with the goal of improving the overall energy efficiency of the UAV-assisted MEC system. Finally, we design an optimization algorithm with polynomial-time complexity based on the augmented Lagrangian multiplier method. Simulation results demonstrate that the proposed method outperforms existing approaches in terms of both global secure energy efficiency and average secure energy efficiency.

Real-time prediction of road adhesion conditions ahead of the vehicle is critical for emergency braking, stability control, and trajectory planning in advanced driver-assistance systems (ADAS). To overcome the limitations of conventional vehicle-dynamics-based methods, which mainly rely on tire–road contact responses and lack preview perception capability, this article proposes a real-time road adhesion prediction method based on onboard lidar point clouds. First, point cloud data were collected from four typical road surface conditions, including dry asphalt, wet asphalt, dry concrete, and wet concrete. Random sample consensus (RANSAC)-based ground segmentation and reflectivity filtering were then applied to remove nonroad points and highly reflective outliers. Subsequently, a speed-adaptive dynamic region of interest (ROI) was constructed by incorporating a vehicle safety distance model, enabling preview perception of the target road surface ahead. On this basis, the processed point clouds were converted into multichannel pseudoimages, and a convolutional neural network (CNN)-vision transformer classification model was developed to enhance local reflectance texture feature extraction and global context modeling. Finally, based on the empirical mapping relationship between road surface type and friction coefficient, the road surface recognition results were converted into road adhesion prediction results. Experimental results show that the proposed method achieves a better tradeoff between recognition accuracy and real-time performance. Compared with conventional vehicle-dynamics-based estimation methods, the proposed method significantly reduces the mean absolute error and mean absolute percentage error in both homogeneous road and transition road scenarios, verifying its effectiveness for real-time forward road adhesion prediction in ADAS.

Deep Reinforcement Learning (DRL) has demonstrated significant potential in tackling the complex challenges of autonomous vehicles, particularly in decision-making and motion planning. However, many existing DRL methods optimize individual components in isolation, leading to a lack of integration across modules. Additionally, current reinforcement learning methods often focus on high-reward samples while neglecting the valuable information contained in low-reward samples. Furthermore, the efficiency of action search requires further improvement. To overcome these challenges, we propose a novel closed-loop DRL framework that utilizes feedback to simultaneously optimize both decision-making and motion planning. To address these, we propose a novel closed-loop DRL framework that leverages closed-loop feedback to optimize both decision-making and motion planning concurrently. The feedback framework refines the DRL process by utilizing the deviation between real and predicted trajectories, enabling continuous improvement of the system’s decision-making capabilities. The framework also incorporates a dual-value priority sampling strategy, which enhances the utilization of low-reward samples by prioritizing the sampling of high-value samples across categories. Additionally, the framework integrates a hybrid action selection mechanism that combines rule-based and learning-based mechanism, effectively reducing exploration inefficiencies in the early stages of DRL while maintaining long-term optimization through experience-driven learning. Experimental results demonstrate that the proposed framework outperforms state-of-the-art models, showing strong potential for real-world applications.

This paper presents a systematic evaluation framework to assess the performance of the Segment Anything Model (SAM) in traffic scene image segmentation under diverse meteorological conditions. Addressing the critical challenge of environmental perception in autonomous driving systems, this study makes three primary contributions. First, we construct a traffic scene dataset comprising 1,350 high-resolution images (1920 × 1080) with pixel-level annotations, covering nine distinct weather-light combinations, including various conditions of rain, fog, and illumination. Second, this paper designs a novel evaluation system that incorporates adaptive preprocessing and optimized prompting strategies to thoroughly examine SAM’s zero-shot segmentation capability. The experimental results demonstrate that SAM performs remarkably well across a variety of complex scenarios, especially in daytime rainy conditions, where the mean Intersection over Union (mIoU) for vehicle segmentation reaches 82.8

In environments characterized by low texture or sparse LiDAR returns, conventional LiDAR-IMU fusion systems are prone to drift and significant loss of accuracy over time. To address these limitations, we propose a robust, lightweight, and efficient multi-sensor localization framework that tightly integrates a sliding-window filtering approach with vision-based incremental motion compensation. This design enables real-time correction of both translational and rotational errors without the need for computationally expensive global optimization. The system also retains full compatibility with multi-agent collaborative localization frameworks, enhancing scalability. Additionally, we introduce an exponentially weighted moving average (EMA)-based IMU filter and a visual motion estimation pipeline that leverages ORB feature matching and essential matrix decomposition for robust relative pose estimation. Experimental validation conducted on a high-precision, synchronized motion capture platform shows a root mean square positioning error of only 0.0710 m. These results confirm the effectiveness of the proposed method in challenging scenarios with degraded visual or geometric features. The approach is well-suited for real-time deployment in autonomous, GPS-denied, and dynamic multi-robot environments.

Autonomous aerial vehicles (AAVs) have gained considerable attention in data collection due to their mobility and flexibility. These capabilities are crucial in time-sensitive missions (e.g., disaster response, military reconnaissance). In such cases, tasks are often subject to tight deadlines and require timely access to information. To address these challenges, this paper investigates collaborative data collection and task offloading in multi-AAV systems, aiming to maximize mission area coverage while minimizing total energy consumption. To overcome the limited computing power of data collection AAVs, we propose a heterogeneous multi-tier AAV system. In this design, an assisted AAV with strong computing capabilities is introduced to handle data offloading and processing. This enhances energy efficiency and enables timely task execution. Consequently, we develop an integrated optimization model to jointly design trajectory planning and task offloading under communication, energy, and deadline constraints. We propose a deep reinforcement learning algorithm called data collection optimized proximal policy optimization (DCOPPO). This approach optimizes both AAV trajectories and offloading decisions. Simulation results demonstrate that DCOPPO significantly outperforms baseline DRL approaches in terms of energy efficiency and task completion performance.

Multimodal large language models (MLLMs) have been well acknowledged as the generalist across a broad spectrum of vision-language understanding tasks. Despite notable advancements, their potential for autonomous-driving perception remains largely underexplored. In response, we conduct an in-depth investigation of image-text-point interaction and propose a versatile paradigm of vision-language supervision (VLS) for 3D object detection, where multi-sensory proposals are primarily refined with meticulously-designed text-referred expression, and multimodal correspondences are further incorporated in a contrastive-learning manner. Moreover, VLS holds great advantages. (1) No complicated engineering. It could be seamlessly integrated into a camera-LiDAR 3D detector without troublesome hand-crafted engineering. (2) No extra computation. It provides auxiliary guidance only during training. (3) No additional data. It derives multimodal pairs from ground-truth label instead of a laborious annotation pipeline. Empirical study on publicly available KITTI and nuScenes benchmarks demonstrates the state-of-the-art detection performance against a wide span of counterparts, suggesting its effectiveness and advancement. We hope this work could pave a substantial path towards multimodal feature fusion and object detection for autonomous driving.

An integrated UGV-UAV cooperative navigation framework is proposed to support multiple unmanned ground vehicles (UGVs) operating with limited onboard perception. In this system, a LiDAR-equipped unmanned aerial vehicle (UAV) autonomously explores unknown environments and builds a global occupancy map through simultaneous localization and mapping (SLAM). The UGVs, lacking their own perception capabilities, rely on external motion capture systems for precise localization and receive the shared map information from the UAV to perform trajectory planning with obstacle avoidance. To ensure safe and efficient navigation, the UAV dynamically assesses potential collision risks along UGV-predicted paths and provides targeted perception support by visiting critical areas. A vehicle routing problem with time windows (VRPTW) model is formulated to optimize the UAV’s assistance schedule. The framework is validated through real-world indoor experiments, demonstrating its efficacy in enabling reliable multi-UGV navigation under constrained sensing conditions. The proposed system is particularly well-suited for structured environments such as warehouses, laboratories, and testbeds.

In complex and unknown environments, uncrewed ground vehicles (UGVs) with no perception capability or degraded sensing struggle to achieve efficient and safe autonomous navigation. To address this challenge, this letter proposes a low-cost aerial-ground collaborative autonomous navigation system designed for unknown environments, which supports efficient navigation of perception-denied ground platforms while minimizing hardware requirements. In the proposed system, an uncrewed aerial vehicle (UAV) equipped with a lightweight camera provides the UGV with relative position observations and semantic bird & sacute;-eye-view (BEV) maps. The semantic BEV is designed as a unified intermediate representation for UAV-UGV collaboration. While reducing communication overhead, semantic risk information is explicitly incorporated into the diffusion inference process, enabling the planner to satisfy geometric feasibility constraints during path generation while proactively avoiding semantically high-risk regions. Both simulation and real-world experiments validate the effectiveness of the proposed framework. In particular, within an unknown obstacle-filled space of 7 m & times; 4 m & times; 3 m, the UAV enables efficient and safe collaborative navigation for perception-denied UGVs, demonstrating strong application potential in complex and unknown environments.