Search Results (1,801)

To enhance road-testing safety for autonomous driving robotic vehicles (ADRVs), collision avoidance with sudden obstacles is essential during testing processes. This paper proposes an upper-level collision avoidance strategy integrating model predictive control (MPC) and improved artificial potential field (APF). The kinematic model of the driving robot is established, and a vehicle dynamics model considering road curvature is used as the foundation for vehicle control. The improved APF constraints are constructed. The boundary constraint uses a three-circle vehicle shape suitable for roads with arbitrary curvatures. A unified obstacle potential field constraint is designed for static/dynamic obstacles to generate collision-free trajectories. An auxiliary attractive potential field is designed to ensure stable trajectory recovery after obstacle avoidance completion. A multi-objective MPC framework coupled with artificial potential fields is designed to achieve obstacle avoidance and trajectory tracking while ensuring accuracy, comfort, and environmental constraints. Results from Carsim-Simulink and semi-physical experiments validate that the proposed strategy effectively avoids various obstacles under different road conditions while maintaining reference trajectory tracking. Full article

Efficient task offloading for delay-sensitive applications, such as autonomous driving, presents a significant challenge in multi-hop Vehicular Edge Computing (VEC) networks, primarily due to high vehicle mobility, dynamic network topologies, and complex end-to-end congestion problems. To address these issues, this paper proposes a graph attention-based reinforcement learning algorithm, named GAPO. The algorithm models the dynamic VEC network as an attributed graph and utilizes a graph neural network (GNN) to learn a network state representation that captures the global topological structure and node contextual information. Building on this foundation, an attention-based Actor–Critic framework makes joint offloading decisions by intelligently selecting the optimal destination and collaboratively determining the ratios for offloading and resource allocation. A multi-objective reward function, designed to minimize task latency and to alleviate link congestion, guides the entire learning process. Comprehensive simulation experiments and ablation studies show that, compared to traditional heuristic algorithms and standard deep reinforcement learning methods, GAPO significantly reduces average task completion latency and substantially decreases backbone link congestion. In conclusion, by deeply integrating the state-aware capabilities of GNNs with the decision-making abilities of DRL, GAPO provides an efficient, adaptive, and congestion-aware solution to the resource management problems in dynamic VEC environments. Full article

Critical Internet of Things (IoT) data in Fifth Generation Vehicular Ad Hoc Networks (5G VANETs) demands Ultra-Reliable Low-Latency Communication (URLLC) to support mission-critical vehicular applications such as autonomous driving and collision avoidance. Achieving the stringent Quality of Service (QoS) requirements for these applications remains a significant challenge. This paper proposes a novel framework integrating Software-Defined Networking (SDN) and Network Functions Virtualisation (NFV) as embedded functionalities in connected vehicles. A lightweight SDN Controller model, implemented via vehicle on-board computing resources, optimised QoS for communications between connected vehicles and the Next-Generation Node B (gNB), achieving a consistent packet delivery rate of 100%, compared to 81–96% for existing solutions leveraging SDN. Furthermore, a Software-Defined Wide-Area Network (SD-WAN) model deployed at the gNB enabled the efficient management of data, network, identity, and server access. Performance evaluations indicate that SDN and NFV are reliable and scalable technologies for virtualised and distributed 5G VANET infrastructures. Our SDN-based in-vehicle traffic classification model for dynamic resource allocation achieved 100% accuracy, outperforming existing Artificial Intelligence (AI)-based methods with 88–99% accuracy. In addition, a significant increase of 187% in flow rates over time highlights the framework’s decreasing latency, adaptability, and scalability in supporting URLLC class guarantees for critical vehicular services. Full article

Real-time traffic light detection is essential for the safe navigation of autonomous vehicles, where timely and accurate recognition of signal states is critical. YOLOv8, a state-of-the-art object detection model, offers enhanced speed and precision, making it well-suited for real-time applications in complex driving environments. This study presents a modified YOLOv8 architecture optimized for traffic light detection by integrating Depth-Wise Separable Convolutions (DWSCs) throughout the backbone and head. The model was first pretrained on a public traffic light dataset to establish a strong baseline and then fine-tuned on a custom real-time dataset consisting of 480 images collected from video recordings under diverse road conditions. Experimental results demonstrate high detection performance, with precision scores of 0.992 for red, 0.995 for yellow, and 0.853 for green lights. The model achieved an average mAP@0.5 of 0.947, with stable F1 scores and low validation losses over 80 epochs, confirming effective learning and generalization. Compared to existing YOLO variants, the modified architecture showed superior performance, especially for red and yellow lights. Full article

The safe and reliable operation of autonomous vehicles is contingent on comprehensive testing. However, the operational scenarios are inexhaustible. Corner cases, which critically influence autonomous vehicle safety, occur at an extremely low probability and follow a long-tail distribution. Corner cases can be defined as combinations of driving task and scenario elements. These scenarios are characterized by low probability, high risk, and a tendency to reveal functional limitations inherent to autonomous driving systems, triggering anomalous behavior. This study constructs a novel corner case dataset using naturalistic driving data, specifically tailored for autonomous vehicle testing. A scenario marginality quantification method is designed to analyze multi-source naturalistic driving data, enabling efficient extraction of corner cases. Heterogeneous scenarios are systematically transformed, resulting in a dataset characterized by diverse interaction behaviors and standardized formatting. The results indicate that the scenario marginality of the dataset constructed in this study is 2.78 times that of mainstream naturalistic driving datasets, and the scenarios exhibit considerable diversity. The trajectory and velocity fluctuations, quantified at 0.013 m and 0.021 m/s, respectively, are consistent with the kinematic characteristics of real-world driving scenarios. These results collectively demonstrate the dataset’s high marginality, diversity, and applicability. Full article

GPSs typically have an accuracy ranging from a few meters to several tens of meters. However, when corrected using various methods, they can achieve an accuracy of several tens of centimeters. In autonomous driving, a positioning accuracy of less than 50 cm is required for lane-level positioning, route generation, and navigation. However, in environments where GPS signals are blocked, such as tunnels and underground roads, absolute positioning is impossible. Instead, relative positioning methods integrating IMU, IVN, and cameras are used. These methods are influenced by numerous variables, however, such as vehicle speed and road conditions, resulting in lower accuracy. In this study, we conducted experiments on current vehicle navigation technologies using an autonomous driving simulation vehicle in the Suri–Suam Tunnel of the Seoul Metropolitan Area 1st Ring Expressway. To recognize objects (lane markings/2D/3D) for position correction inside the tunnel, data on tunnel and underground road infrastructure in Seoul and Gyeonggi Province was collected, processed, refined, and trained. Additionally, a Loosely Coupled-based Kalman Filter was designed and applied for the fusion of GPSs, IMUs, and IVNs. As a result, an error of 113.62 cm was observed in certain sections. This suggests that while the technology is applicable for general vehicle lane-level navigation in ultra-long tunnels spanning several kilometers for public service, it falls short of meeting the precision required for autonomous driving systems, which demand lane-level accuracy. Therefore, it was concluded that infrastructure-based absolute positioning technology is necessary to enable precise navigation inside tunnels. Full article

Vehicle-to-everything (V2X) communication is a fundamental technology in the development of intelligent transportation systems, encompassing vehicle-to-vehicle (V2V), infrastructure (V2I), and pedestrian (V2P) communications. This technology enables connected and autonomous vehicles (CAVs) to interact with their surroundings, significantly enhancing road safety, traffic efficiency, and driving comfort. However, as V2X communication becomes more widespread, it becomes a prime target for adversarial and persistent cyberattacks, posing significant threats to the security and privacy of CAVs. These challenges are compounded by the dynamic nature of vehicular networks and the stringent requirements for real-time data processing and decision-making. Much research is on using novel technologies such as machine learning, blockchain, and cryptography to secure V2X communications. Our survey highlights the security challenges faced by V2X communications and assesses current ML and blockchain-based solutions, revealing significant gaps and opportunities for improvement. Specifically, our survey focuses on studies integrating ML, blockchain, and multi-access edge computing (MEC) for low latency, robust, and dynamic security in V2X networks. Based on our findings, we outline a conceptual framework that synergizes ML, blockchain, and MEC to address some of the identified security challenges. This integrated framework demonstrates the potential for real-time anomaly detection, decentralized data sharing, and enhanced system scalability. The survey concludes by identifying future research directions and outlining the remaining challenges for securing V2X communications in the face of evolving threats. Full article

This paper introduces a robust and efficient Localized Spline-based Path-Planning (LSPP) algorithm designed to enhance autonomous vehicle navigation on highways. The LSPP approach prioritizes smooth maneuvering, obstacle avoidance, passenger comfort, and adherence to road constraints, including lane boundaries, through optimized trajectory generation using quintic spline functions and a dynamic speed profile. Leveraging real-time data from the vehicle’s sensor fusion module, the LSPP algorithm accurately interprets the positions of surrounding vehicles and obstacles, creating a safe, dynamically feasible path that is relayed to the Model Predictive Control (MPC) track-following module for precise execution. The theoretical distinction of LSPP lies in its modular integration of: (1) a finite state machine (FSM)-based decision-making layer that selects maneuver-specific goal states (e.g., keep lane, change lane left/right); (2) quintic spline optimization to generate smooth, jerk-minimized, and kinematically consistent trajectories; (3) a multi-objective cost evaluation framework that ranks competing paths according to safety, comfort, and efficiency; and (4) a closed-loop MPC controller to ensure real-time trajectory execution with robustness. Extensive simulations conducted in diverse highway scenarios and traffic conditions demonstrate LSPP’s effectiveness in delivering smooth, safe, and computationally efficient trajectories. Results show consistent improvements in lane-keeping accuracy, collision avoidance, enhanced materials wear performance, and planning responsiveness compared to traditional path-planning methods. These findings confirm LSPP’s potential as a practical and high-performance solution for autonomous highway driving. Full article

In intelligent vehicular networks, the accuracy of semantic segmentation in road scenes is crucial for vehicle-mounted artificial intelligence to achieve environmental perception, decision support, and safety control. Although deep learning methods have made significant progress, two main challenges remain: first, the difficulty in balancing global and local features leads to blurred object boundaries and misclassification; second, conventional convolutions have limited ability to perceive irregular objects, causing information loss and affecting segmentation accuracy. To address these issues, this paper proposes a global–local collaborative attention module and a spider web convolution module. The former enhances feature representation through bidirectional feature interaction and dynamic weight allocation, reducing false positives and missed detections. The latter introduces an asymmetric sampling topology and six-directional receptive field paths to effectively improve the recognition of irregular objects. Experiments on the Cityscapes, CamVid, and BDD100K datasets, collected using vehicle-mounted cameras, demonstrate that the proposed method performs excellently across multiple evaluation metrics, including mIoU, mRecall, mPrecision, and mAccuracy. Comparative experiments with classical segmentation networks, attention mechanisms, and convolution modules validate the effectiveness of the proposed approach. The proposed method demonstrates outstanding performance in sensor-based semantic segmentation tasks and is well-suited for environmental perception systems in autonomous driving. Full article

Autonomous vehicles (AVs) have emerged as a promising sustainable urban mobility solution, expected to lead to enhanced road safety, smoother traffic flows, less traffic congestion, improved accessibility, better energy utilization and environmental performance, as well as more efficient passenger and freight transportation, in terms of time and cost, due to better fleet management and platooning. However, challenges also arise, mostly related to data privacy, security and cyber-security, high acquisition and infrastructure costs, accident liability, even possible increased traffic congestion and air pollution due to induced travel demand. This paper presents the results of a survey conducted among 654 residents who experienced an autonomous bus (AB) service in the city of Trikala, Greece, in order to assess their willingness to use (WTU) and willingness to pay (WTP) for ABs, through testing a range of factors based on a literature review. Results useful to policy-makers were extracted, such as that the intention to use ABs was mostly shaped by psychological factors (e.g., users’ perceptions of usefulness and safety, and trust in the service provider), while WTU seemed to be positively affected by previous experience in using ABs. In contrast, sociodemographic factors were found to have very little effect on the intention to use ABs, while apart from personal utility, users’ perceptions of how autonomous driving will improve the overall life standards in the study area also mattered. Full article

Automated vehicles controlled by artificial intelligence are becoming capable of making moral decisions independently. This study investigates the differences in participants’ perceptions of the moral decision-maker’s permissibility when viewing scenarios (pre-test) and after witnessing the outcomes of moral decisions (post-test). It also investigates how permissibility, ten typical moral emotions, and perceived moral agency fluctuate when AI and the human driver make deontological or utilitarian decisions in a pedestrian-sacrificing dilemma (Experiment 1, N = 254) and a driver-sacrificing dilemma (Experiment 2, N = 269) from a third-person perspective. Moreover, by conducting binary logistic regression, this study examined whether these factors could predict the non-decrease in permissibility ratings. In both experiments, participants preferred to delegate decisions to human drivers rather than to AI, and they generally preferred utilitarianism over deontology. The results of perceived moral emotions and moral agency provide evidence. Moreover, Experiment 2 elicited greater variations in permissibility, moral emotions, and perceived moral agency compared to Experiment 1. Moreover, deontology and gratitude could positively predict the non-decrease in permissibility ratings in Experiment 1, while contempt had a negative influence. In Experiment 2, the human driver and disgust were significant negative predictor factors, while perceived moral agency had a positive influence. These findings deepen the comprehension of the dynamic processes of autonomous driving’s moral decision-making and facilitate understanding of people’s attitudes toward moral machines and their underlying reasons, providing a reference for developing more sophisticated moral machines. Full article

Autonomous driving systems have the potential to reduce traffic accidents dramatically; however, conventional modules often struggle to accurately detect risks in complex environments. This study presents a novel risk recognition system that integrates the reasoning capabilities of a large language model (LLM), specifically GPT-4, with traffic engineering domain knowledge. By incorporating surrogate safety measures such as time-to-collision (TTC) alongside traditional sensor and image data, our approach enhances the vehicle’s ability to interpret and react to potentially dangerous situations. Utilizing the realistic 3D simulation environment of CARLA, the proposed framework extracts comprehensive data—including object identification, distance, TTC, and vehicle dynamics—and reformulates this information into natural language inputs for GPT-4. The LLM then provides risk assessments with detailed justifications, guiding the autonomous vehicle to execute appropriate control commands. The experimental results demonstrate that the LLM-based module outperforms conventional systems by maintaining safer distances, achieving more stable TTC values, and delivering smoother acceleration control during dangerous scenarios. This fusion of LLM reasoning with traffic engineering principles not only improves the reliability of risk recognition but also lays a robust foundation for future real-time applications and dataset development in autonomous driving safety. Full article

In recent years, a growing number of real-time semantic segmentation networks have been developed to improve segmentation accuracy. However, these advancements often come at the cost of increased computational complexity, which limits their inference efficiency, particularly in scenarios such as autonomous driving, where strict real-time performance is essential. Achieving an effective balance between speed and accuracy has thus become a central challenge in this field. To address this issue, we present a lightweight semantic segmentation model tailored for the perception requirements of autonomous vehicles. The architecture follows an encoder–decoder paradigm, which not only preserves the capability for deep feature extraction but also facilitates multi-scale information integration. The encoder leverages a high-efficiency backbone, while the decoder introduces a dynamic fusion mechanism designed to enhance information interaction between different feature branches. Recognizing the limitations of convolutional networks in modeling long-range dependencies and capturing global semantic context, the model incorporates an attention-based feature extraction component. This is further augmented by positional encoding, enabling better awareness of spatial structures and local details. The dynamic fusion mechanism employs an adaptive weighting strategy, adjusting the contribution of each feature channel to reduce redundancy and improve representation quality. To validate the effectiveness of the proposed network, experiments were conducted on a single RTX 3090 GPU. The Dynamic Real-time Integrated Vision Encoder–Segmenter Network (DriveSegNet) achieved a mean Intersection over Union (mIoU) of 76.9% and an inference speed of 70.5 FPS on the Cityscapes test dataset, 74.6% mIoU and 139.8 FPS on the CamVid test dataset, and 35.8% mIoU with 108.4 FPS on the ADE20K dataset. The experimental results demonstrate that the proposed method achieves an excellent balance between inference speed, segmentation accuracy, and model size. Full article

In modern vehicles, Autonomous Driving Systems (ADSs) are designed to operate partially or fully without human intervention. The ADS pipeline comprises multiple layers, including sensors, perception, localization, mapping, path planning, and control. The Robot Operating System (ROS) is a widely adopted framework that supports the modular development and integration of these layers. Among them, the path-planning and control layers remain particularly challenging due to several limitations. Classical path planners often struggle with non-smooth trajectories and high computational demands. Meta-heuristic optimization algorithms have demonstrated strong theoretical potential in path planning; however, they are rarely implemented in real-time ROS-based systems due to integration challenges. Similarly, traditional PID controllers require manual tuning and are unable to adapt to system disturbances. This paper proposes a ROS-based ADS architecture composed of eight integrated nodes, designed to address these limitations. The path-planning node leverages a meta-heuristic optimization framework with a cost function that evaluates path feasibility using occupancy grids from the Hector SLAM and obstacle clusters detected through the DBSCAN algorithm. A dynamic goal-allocation strategy is introduced based on the LiDAR range and spatial boundaries to enhance planning flexibility. In the control layer, a modified Pure Pursuit algorithm is employed to translate target positions into velocity commands based on the drift angle. Additionally, an adaptive PID controller is tuned in real time using the Differential Evolution (DE) algorithm, ensuring robust speed regulation in the presence of external disturbances. The proposed system is practically validated on a four-wheel differential drive robot across six scenarios. Experimental results demonstrate that the proposed planner significantly outperforms state-of-the-art methods, ranking first in the Friedman test with a significance level less than 0.05, confirming the effectiveness of the proposed architecture. Full article