Search Results (302)

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

Unmanned platforms such as unmanned aerial vehicles, unmanned ground vehicles, and autonomous underwater vehicles often face challenges of data, device, and model heterogeneity when performing collaborative data processing tasks. Existing research does not simultaneously address issues from these three aspects. To address this issue, this study designs an unmanned platform cluster architecture inspired by the cloud-edge-end model. This architecture integrates federated learning for privacy protection, leverages the advantages of distributed model training, and utilizes edge computing’s near-source data processing capabilities. Additionally, this paper proposes a federated edge intelligence method (DSIA-FEI), which comprises two key components. Based on traditional federated learning, a data sharing mechanism is introduced, in which data is extracted from edge-side platforms and placed into a data sharing platform to form a public dataset. At the beginning of model training, random sampling is conducted from the public dataset and distributed to each unmanned platform, so as to mitigate the impact of data distribution heterogeneity and class imbalance during collaborative data processing in unmanned platforms. Moreover, an intelligent model aggregation strategy based on similarity measurement and loss gradient is developed. This strategy maps heterogeneous model parameters to a unified space via hierarchical parameter alignment, and evaluates the similarity between local and global models of edge devices in real-time, along with the loss gradient, to select the optimal model for global aggregation, reducing the influence of device and model heterogeneity on cooperative learning of unmanned platform swarms. This study carried out extensive validation on multiple datasets, and the experimental results showed that the accuracy of the DSIA-FEI proposed in this paper reaches 0.91, 0.91, 0.88, and 0.87 on the FEMNIST, FEAIR, EuroSAT, and RSSCN7 datasets, respectively, which is more than 10% higher than the baseline method. In addition, the number of communication rounds is reduced by more than 40%, which is better than the existing mainstream methods, and the effectiveness of the proposed method is verified. Full article

Autonomous drones may be called on to perform search-and-rescue operations in environments without access to signals from the global navigation satellite system (GNSS), such as underground mines, subterranean caverns, or confined tunnels. While technology to perform such missions has been demonstrated at events such as DARPA’s Subterranean (Sub-T) Challenge, the hardware deployed for these missions relies on heavy and expensive sensors, such as LiDAR, carried by costly mobile platforms, such as legged robots and heavy-lift multicopters, creating barriers for deployment and training with this technology for all but the wealthiest search-and-rescue organizations. To address this issue, we have developed a custom four-rotor aerial drone platform specifically built around low-cost low-weight sensors in order to minimize costs and maximize flight time for search-and-rescue operations in GNSS-denied environments. We document the various issues we encountered during the building and testing of the vehicle and how they were solved, for instance a novel redesign of the airframe to handle the aggressive yaw maneuvers commanded by the FUEL exploration framework running onboard the drone. The resulting system is successfully validated through a hardware autonomous flight experiment performed in an underground environment without access to GNSS signals. The contribution of the article is to share our experiences with other groups interested in low-cost search-and-rescue drones to help them advance their own programs. Full article

The Internet of Vehicles (IoVs) uses vehicles as the main carrier to communicate with other entities, promoting efficient transmission and sharing of traffic data. Using real identities for communication may leak private data, so pseudonyms are commonly used as identity credentials. However, existing anonymous authentication schemes have limitations, including large vehicle storage demands, information redundancy, time-dependent pseudonym updates, and public–private key updates coupled with pseudonym changes. To address these issues, we propose a certificateless strong anonymous privacy protection authentication scheme that allows vehicles to autonomously generate and dynamically update pseudonyms. Additionally, the trusted authority transmits each entity’s partial private key via a session key, eliminating reliance on secure channels during transmission. Based on the elliptic curve discrete logarithm problem, the scheme’s existential unforgeability is proven in the random oracle model. Performance analysis shows that it outperforms existing schemes in computational cost and communication overhead, with the total computational cost reduced by 70.29–91.18% and communication overhead reduced by 27.75–82.55%, making it more suitable for privacy-sensitive and delay-critical IoV environments. Full article

The integration of shared autonomous vehicles into historic urban areas presents both opportunities and challenges. In heritage-rich environments like very old Asian (such as Suzhou old town, which serves as a use case example) or European (especially Mediterranean coastal cities) areas—characterized by narrow alleys, dense development, and sensitive cultural landscapes—shared autonomous vehicle adoption raises critical spatial and social questions. This study employs a qualitative, user-centered approach based on the ripple model to examine residents’ perceptions across four dimensions: residential patterns, parking land use, regional accessibility, and street-level infrastructure. Semi-structured interviews with 27 participants reveal five key findings: (1) public trust depends on transparent decision-making and safety guarantees; (2) shared autonomous vehicles may reshape generational residential clustering; (3) the short-term parking demand remains stable, but the long-term reuse of space is feasible; (4) shared autonomous vehicles could enhance accessibility in historic cores; (5) transport systems may evolve toward intelligent, human-centered designs. Based on these insights, the study proposes three strategies: (1) transparent risk assessment using explainable artificial intelligence and digital twins; (2) polycentric development to diversify land use; (3) hierarchical street retrofitting to balance mobility and preservation. While this study is limited by its qualitative scope and absence of simulation, it offers a framework for culturally sensitive, small-scale interventions supporting sustainable mobility transitions in historic urban contexts. Full article

Passengers’ trust in Shared Autonomous Vehicles (SAVs) can be affected by different factors, such as their attitudes toward new technologies and perceptions of the vehicles’ reputation. While the existing literature has begun to explore these issues, there is limited research investigating how industrial design in SAVs can enhance passengers’ trust levels. To address this gap, this study responds to the central question: How can passengers’ trust in the vehicle itself and in fellow passengers be enhanced through design intervention? This question conceptualises trust in the vehicle and trust in strangers as an integrated trust issue within the SAV context. To fill this gap, this study adopts a project-grounded methodology. The design work is guided by five trust principles: anthropomorphic design, a defensible space, system transparency, personalisation features, and a restorative environment. Drawing on insights from an auto-ethnography of current ride-sharing services, these principles are further explored and applied to identify design opportunities for both the physical and digital elements of SAVs. The final conceptual SAV design demonstrates how different design elements can be orchestrated to engender user trust. The outcome contributes to ongoing design practices and helps researchers and designers better understand trust design for SAVs. Full article

Path planning and collision avoidance are essential components of an autonomous driving system (ADS), ensuring safe navigation in complex environments shared with other road users. High-quality planning and reliable obstacle avoidance strategies are essential for advancing the SAE autonomy level of autonomous vehicles, which can largely reduce the risk of traffic accidents. In daily driving scenarios, lane changing is a common maneuver used to avoid unexpected obstacles such as parked vehicles or suddenly appearing pedestrians. Notably, lane-changing behavior is also widely regarded as a key evaluation criterion in driver license examinations, highlighting its practical importance in real-world driving. Motivated by this observation, this paper aims to develop an autonomous lane-changing system capable of dynamically avoiding obstacles in multi-lane traffic environments. To achieve this objective, we propose a hierarchical decision-making and control framework in which a Double Deep Q-Network (DDQN) agent operates as the high-level planner to select lane-level maneuvers, while a High-Order Control Lyapunov Function–High-Order Control Barrier Function–based Quadratic Program (HOCLF-HOCBF-QP) serves as the low-level controller to ensure safe and stable trajectory tracking under dynamic constraints. Simulation studies are used to evaluate the planning efficiency and overall collision avoidance performance of the proposed hierarchical control framework. The results demonstrate that the system is capable of autonomously executing appropriate lane-changing maneuvers to avoid multiple obstacles in complex multi-lane traffic environments. In computational cost tests, the low-level controller operates at 100 Hz with an average solve time of 0.66 ms per step, and the high-level policy operates at 5 Hz with an average solve time of 0.60 ms per step. The results demonstrate real-time capability in autonomous driving systems. Full article

The Controller Area Network (CAN) protocol is one of the important communication standards in autonomous vehicles, enabling real-time information sharing across in-vehicle (IV) components to realize smooth coordination and dependability in vital activities. Without encryption and authentication, CAN reveals several vulnerabilities related to message attacks within the IV Network (IVN). Traditional centralized Intrusion Detection Systems (IDS) where all the historical data is grouped on one node result in privacy risks and scalability issues, making them unsuitable for real-time intrusion detection. To address these challenges, we propose a Deep Federated Learning (FL) architecture for intrusion detection in IVN. We propose a Bidirectional Long Short Term Memory (BiLSTM) architecture to capture temporal dependencies in the CAN bus and ensure enhanced feature extraction and multi-class classification. By evaluating our framework on three real-world datasets, we show how our proposal outperforms a baseline LSTM model from the state of the art. Full article

The market share of Last-Mile Delivery Robots (LMDRs) has grown rapidly over the past few years. These robots are mostly autonomous and supported remotely by human operators. As part of a broader shift toward sustainable urban logistics, LMDRs are seen as a promising low-emission alternative to conventional delivery vehicles. While there is a large body of literature about the technology, little is known about the real-world experiences of operating these robots. This study investigates the operational challenges faced by remote operators (ROs) of LMDRs, aiming to enhance their efficiency and safety. Through interviews with industry professionals, we explore the scenarios requiring human intervention, the strategies employed by ROs, and the unique challenges they encounter. Our findings not only identify key intervention scenarios but also provide a thorough examination of the teleoperation ecosystem, operational workflows, and how they affect the ways the ROs manage their interactions with robots. We found that ROs’ involvement varies from monitoring to active intervention to support the robots in completing their tasks when they face connectivity issues, blocked routes, and various other interruptions on their journeys. The findings highlight the importance of intuitive user interfaces (UIs) and decision-support systems to reduce cognitive load and improve situational awareness. This research contributes to the literature by offering a detailed examination of real-world teleoperation practices and focusing on the human factors influencing LMDR scalability, sustainability, and integration into future-ready logistics systems. Full article

The rapid evolution of the transport industry requires a deep understanding of user preferences for emerging mobility solutions, particularly carsharing (CS) and autonomous vehicles (AVs). This study employs machine learning techniques to model transport mode choice, with a focus on traffic safety perceptions of people towards CS and privately shared autonomous vehicles (PSAVs). A stated preference (SP) survey is conducted to collect data on travel behavior, incorporating key attributes such as trip time, trip cost, waiting and walking time, privacy, cybersecurity, and surveillance concerns. Sociodemographic factors, such as income, gender, education, employment status, and trip purpose, are also examined. Three gradient boosting models—CatBoost, XGBoost, and LightGBM are applied to classify user choices. The performance of models is evaluated using accuracy, precision, and F1-score. The XGBoost demonstrates the highest accuracy (77.174%) and effectively captures the complexity of mode choice behavior. The results indicate that CS users are easily classified, while PSAV users present greater classification challenges due to variations in safety perceptions and technological acceptance. From a traffic safety perspective, the results emphasize that companionship, comfort, privacy, cybersecurity, safety in using CS and PSAVs, and surveillance significantly influence CS and PSAV acceptance, which leads to the importance of trust in adopting AVs. The findings suggest that ensuring public trust occurs through robust safety regulations and transparent data security policies. Furthermore, the envisaged benefits of shared autonomous mobility are alleviating congestion and promoting sustainability. Full article

As autonomous vehicles (AVs) are gradually integrated into existing traffic systems, understanding their impact on freeway operations becomes essential for effective infrastructure planning and policy design. This study explores how AV penetration rates, behavior profiles, and freeway geometry interact to influence traffic performance and safety. Using microscopic simulations in VISSIM (a high-fidelity traffic simulation tool), four typical freeway segment types—basic sections, weaving zones, on-ramp merging areas, and AV-exclusive lanes—were modeled under diverse traffic demands and AV behavior settings. The findings indicate that, while AVs can improve flow stability in simple environments, their performance may deteriorate in complex merging scenarios without supportive design or behavior coordination. AV-exclusive lanes offer some mitigation when AV share is high. These results underscore that AV integration requires context-specific strategies and cannot be universally applied. Adaptive, behavior-aware traffic management is recommended to support a smooth transition toward mixed autonomy. Full article

With the rapid advancement in artificial intelligence, autonomous driving has emerged as a prominent research frontier. Autonomous vehicles rely on high-precision high-definition map data, necessitating timely map updates by map companies to accurately reflect road conditions. This paper proposes an efficient and fair map-data-sharing mechanism for vehicular networks. To encourage vehicles to share data, we introduce a reputation unit to resolve the cold-start issue for new vehicles, effectively distinguishing legitimate new vehicles from malicious attackers. Considering both the budget constraints of map companies and heterogeneous data collection capabilities of vehicles, we design a fair incentive mechanism based on the proposed reputation unit and a reverse auction algorithm, achieving an optimal balance between data quality and procurement costs. Furthermore, the scheme has been developed to facilitate mutual authentication between vehicles and Roadside Unit(RSU), thereby ensuring the security of shared data. In order to address the issue of redundant authentication in overlapping RSU coverage areas, we construct a Merkle hash tree structure using a set of anonymous certificates, enabling single-round identity verification to enhance authentication efficiency. A security analysis demonstrates the robustness of the scheme, while performance evaluations and the experimental results validate its effectiveness and practicality. Full article

Rapid progress in lithium-ion batteries and AI-powered autonomous driving is poised to propel electric vehicles to a 50% share of the global automotive market by the year 2035. Today, there is a major focus on recycling electric vehicle motors, particularly on extracting rare earth elements (REEs) from NdFeB permanent magnets (PMs). This research is based on a single-furnace process concept designed to separate metal components within PM motors by exploiting the varying melting points of the constituent materials, simultaneously extracting REEs present within the PMs and transferring them into the slag phase. Thermodynamic modeling, via Factsage Equilib stream calculations, optimized the experimental process. Simulated materials substituted the PM motor, which optimized modeling-directed melting within an induction furnace. The 2FeO·SiO₂ fayalite flux can oxidize rare earth elements, resulting in slag. The neodymium oxidation reaction by fayalite exhibits a ΔG° of −427 kJ when subjected to an oxygen partial pressure ($P_{O_2}$) of 1.8 × 10⁻⁹, which is lower than that required for FeO decomposition. Concerning the FeO–SiO₂ system, neodymium, in Nd³⁺, exhibits a strong bonding with the ${\mathrm{S}\mathrm{i}\mathrm{O}}_4^{4^{-}}$ matrix, leading to its incorporation within the slag as the silicate compound, Nd₂Si₂O₇. When 30 wt.% fayalite flux was added, the resulting experiment yielded a neodymium extraction degree of 91%, showcasing the effectiveness of this fluxing agent in the extraction process. Full article

This paper addresses the resource allocation challenges in autonomous vehicle (AV) networks for delay-sensitive perception tasks. Current vehicular networks face sub-optimal resource distribution and excessive communication overhead, hindering the performance of AVs. We propose an integrated approach that combines a platoon-based system model with optimization techniques using Deep Q-Networks (DQN) and Particle Swarm Optimization (PSO). The platoon-based model enables AVs to share resources effectively, while the DQN and PSO models optimize task offloading and reduce overhead. Simulation results across various traffic scenarios demonstrate that the PSO algorithm outperforms traditional methods in task completion rates, overhead minimization, and platoon formation. This approach offers a significant advancement in enhancing AV network performance and ensuring timely task execution. Full article

The Department of Veterans Affairs’ (VA’s) transportation system plays an important role in ensuring access to transportation services for veterans, particularly those in rural or underserved areas. However, concerns remain regarding the effectiveness of collaboration among the various VA transportation stakeholders. Persistent transportation challenges hinder veterans’ access to essential healthcare services and resources. Electric autonomous ride-sharing services (ARSSs) offer a promising opportunity to enhance transportation access; however, their current limitations and the perspectives of VA transportation personnel must be considered. This study explored the current perspectives of the VA transportation system and assessed ARSSs as an innovative and sustainable alternative through interviews with eight VA transportation stakeholders representing seven transportation sectors. Our findings revealed the VA’s strengths, including personalized service, flexible accommodations, and collaborative care models, but also identified challenges, including limited funding, staff shortages, volunteer constraints, and restrictive eligibility criteria. The introduction of ARSSs was identified as an opportunity to alleviate some of these constraints by reallocating human resources and improving access to essential services, although concerns remain regarding ARSSs’ ability to accommodate veterans with disabilities and address rural route complexities. Effective communication strategies and streamlined coordination were key recommendations for improving service delivery and expanding transportation access for veterans. Full article