Non-contact palm-vein recognition has been widely adopted in security-critical applications owing to its contact-free acquisition paradigm and exceptional discriminative power. However, these systems remain susceptible to a spectrum of presentation attacks (PAs), creating significant security risks that require urgent mitigation. Progress on palm-vein anti-spoofing is currently impeded by three fundamental gaps: (i) the absence of an open-source, end-to-end pipeline for preprocessing liveness-detection data; (ii) a lack of publicly available datasets specifically tailored to anti-spoofing evaluation; and (iii) the unavailability of benchmark studies employing standardized protocols and reference implementations. In light of these key issues, we make the following four contributions. Firstly, we propose a new open-source preprocessing pipeline that can significantly improve model performance, reducing errors by up to 53.3%. Secondly, we introduce PVASD, a new largest known dataset comprised of 1,187,519 images belonging to 5,515 subjects, which consists of 880,241 live palm vein images along with 307,278 spoof attack images including 16 different attack types – both 2d (printed stuff) and 3d (gloves and prosthesis models) attacks captured under a variety of environments using off-the-shelf commercial-grade sensors at five resolutions. Lastly, comprehensive benchmarks are also created by evaluating three types of representative methods namely classical image classification models, face anti-spoofing methods adapted from face domain and anomaly-detection-based approaches, while our experimental results reveal unique characteristics intrinsic only to palm vein spoof attacks, which will hopefully provide valuable guidance to researchers for further investigation. Furthermore, we also expanded PVASD by adding 20,000 spoof samples generated by artificial intelligence, and evaluated the vulnerability of the existing models to deepfake attacks. We will release our preprocessing pipeline, dataset, and benchmark codes at https://github.com/valhongli/PVASD to advance future reproducible studies and accelerate palm-vein anti-spoofing algorithmic research.

Under the impetus of Industry 4.0, oil and gas is undergoing an unprecedented digital transformation, and many innovative ideas are proposed. However, the achieved higher efficiency comes at the expense of reduced social consideration, which necessitates more society-related research and calls for a technological paradigm shift. To meet this challenge, this article introduces parallel oil and gas within the framework of parallel intelligence-based Industry 5.0, providing a pivotal transition from cyber–physical systems (CPS) to cyber–physical–social systems (CPSS). A comprehensive review of oil and gas industrial chain that covers upstream, midstream, and downstream is first outlined. Grounded in Industry 5.0, the main principles of parallel oil and gas are then provided, where three kinds of workers (biological workers, digital workers, and robotic workers) and three operation modes (autonomous modes, parallel modes, and expert/emergency modes) collaborate to develop more human-oriented and resilient systems. To realize the desired vision, some enabling technologies, including blockchain, smart contracts, and industrial foundation models, are thereafter listed. Furthermore, computational experiments on fault diagnosis of sucker rod pumps are conducted to illustrate the feasibility and effectiveness of our proposed mechanism. Finally, the future trend toward imaginative intelligence is envisaged.

The safety of different categories of road users comprising motorized vehicles and vulnerable road users (VRUs) such as pedestrians and cyclists is one of the priorities of automated driving and smart infrastructure services. Three-dimensional (3-D) LiDAR-based object detection has been a promising approach to perceiving road users. Despite accurate 3-D geometry information, the point cloud from LiDAR is usually nonuniform, and learning the effective point cloud abstract representations for diverse road users remains challenging for 3-D object detection, particularly for small objects such as VRUs. For inclusive object detection (IDetect), we propose a general foundation convolution component, called geometry-aware convolution (GA Conv) toward a foundation feature extraction model, to serve as basic convolution operations of the neutral network for inclusive 3-D object detection. Further, the GA Conv operations are then utilized as the elementary feature extraction layers to build a novel elegant and pyramid network for IDetect. It learns the effective geometric-related features from the unstructured point cloud data by implicitly learning the distribution property and geometry-related features from different categories of road users in particular for VRUs. The proposed IDetect is comprehensively evaluated on the large-scale benchmark Waymo open datasets with all categories of road users. The qualitative and quantitative experiment results demonstrate that IDetect can effectively consider the nonuniform distributed point clouds and learn the geometric features to assist the different categories of road user detection. In addition, the GA Conv has been integrated with other state-of-the-art neural networks and a performance boost for VRU detection has been demonstrated, showing the foundation functionality of the GA Conv and making it a general component in the future inclusive 3-D object detection foundation model.

Modern perception systems of autonomous vehicles are known to be sensitive to occlusions and lack the capability of long perceiving range. It has been one of the key bottlenecks that prevents Level 5 autonomy. Recent research has demonstrated that the Vehicle-to-Vehicle (V2V) cooperative perception system has great potential to revolutionize the autonomous driving industry. However, the lack of a real-world dataset hinders the progress of this field. To facilitate the development of cooperative perception, we present V2V4Real, the first large-scale real-world multi-modal dataset for V2V perception. The data is collected by two vehicles equipped with multi-modal sensors driving together through diverse scenarios. Our V2V4Real dataset covers a driving area of 410 km, comprising 20K LiDAR frames, 40K RGB frames, 240K annotated 3D bounding boxes for 5 classes, and HDMaps that cover all the driving routes. V2V4Real introduces three perception tasks, including cooperative 3D object detection, cooperative 3D object tracking, and Sim2Real domain adaptation for cooperative perception. We provide comprehensive benchmarks of recent cooperative perception algorithms on three tasks. The V2V4Real dataset can be found at research.seas.ucla.edu/mobility-lab/v2v4real/.

Vehicle control is one of the most critical challenges in autonomous vehicles (AVs) and connected and automated vehicles (CAVs), and it is paramount in vehicle safety, passenger comfort, transportation efficiency, and energy saving. This survey attempts to provide a comprehensive and thorough overview of the current state of vehicle control technology, focusing on the evolution from vehicle state estimation and trajectory tracking control in AVs at the microscopic level to collaborative control in CAVs at the macroscopic level. First, this review starts with vehicle key state estimation, specifically vehicle sideslip angle, which is the most pivotal state for vehicle trajectory control, to discuss representative approaches. Then, we present symbolic vehicle trajectory tracking control approaches for AVs. On top of that, we further review the collaborative control frameworks for CAVs and corresponding applications. Finally, this survey concludes with a discussion of future research directions and the challenges. This survey aims to provide a contextualized and in-depth look at the state of the art in vehicle control for AVs and CAVs, identifying critical areas of focus and pointing out the potential areas for further exploration.