Sergio Alberto Salguero-LunaKelsey Alejandra Ramírez-GutiérrezAlfonso Martínez-Cruz
22-42页
查看更多>>摘要：Autonomous vehicles rely on their perception systems to understand their surroundings. However, the evolution of autonomous navigation technologies has led to new security issues. LiDAR sensors are crucial for autonomous vehicles, and this paper presents the first study that focuses exclusively on attacks and defense mechanisms on this device. This survey comparatively analyzes the attacks and mitigation techniques in state-of-the-art according to their complexity and robustness. The main LiDAR datasets in the literature are described, and trending approaches for future research directions based on the included solutions are discussed. Overall, this work provides a comprehensive overview of LiDAR attacks and their potential threats. It is an essential contribution to LiDAR security and will help to inform the development of countermeasures.
John Roar Ventura SolaasEnrico MaricontiNilufer Tuptuk
43-58页
查看更多>>摘要：This systematic literature review provides a structured and detailed overview of research on anomaly detection for connected and autonomous vehicles, focusing on the Artificial Intelligence methods employed, training approaches, and testing and evaluation techniques. The initial database search identified 2,160 articles, of which 203 were included in this review after rigorous screening and assessment. This study revealed that the most commonly used anomaly detection techniques employed are deep learning networks such as LSTM, CNN, and autoencoders, alongside one-class SVM. Most detection models were trained using real-world operational vehicle data, although anomalies, such as attacks and faults, were often injected artificially into the datasets. The models were evaluated primarily using five key evaluation metrics: recall, accuracy, precision, F1-score, and false positive rate. The most frequently used set of evaluation metrics for detection models were accuracy, precision, recall, and F1-score. The review makes several recommendations to improve future work related to anomaly detection models. It recommends providing comprehensive assessment of the anomaly detection models and emphasise the importance to share models publicly to facilitate collaboration within the research community and enable further validation. Recommendations also include the need for benchmarking datasets with predefined anomalies or cyberattacks (with comprehensive threat modelling) to test and improve the effectiveness of the proposed anomaly detection models. Future research should focus on the deployment of anomaly based detection in vehicles to evaluate their performance in real-world driving conditions, and explore systems using communication protocols beyond CAN, such as Ethernet and FlexRay.
查看更多>>摘要：Vehicle trajectory data is essential for analyzing and modeling complex traffic behaviors. Although extraction of vehicle trajectory from aerial video data is not a new problem, obtaining trajectories with heading information across various road types, such as intersections or long road segments, requires further research. In this paper, we propose OpenVTER, a generalized Open-source Vehicle Trajectory Extraction framework based on Rotated bounding boxes (RBBs). This framework includes several key components: video stabilization, image division, vehicle detection, vehicle tracking, and data post-processing. Specifically, the rotated vehicle detection model, named YOLOX-R, is applied to detect the small and rotated vehicles using RBBs that provide vehicle heading information. A base-frame video stabilization method is proposed to reduce error accumulation in the transformation matrix and improve the computational efficiency. The rotated vehicle tracking model, named SORT-R, is proposed to enable real-time tracking of RBBs. The performance of YOLOX-R is evaluated on two datasets, showing that vehicle detection challenges are well addressed. Ablation experiments were also conducted to analyze the effectiveness of different modules. Subsequently, we evaluate the completeness of the extracted trajectories under various road types and lighting conditions. The extracted trajectories are also compared with the NGSIM dataset, focusing on internal and platoon consistency. These evaluations demonstrate both the effectiveness and practicality of the proposed framework. Additionally, the visualization analyses of different road types demonstrate the advantages of the trajectories extracted by OpenVTER in various road scenarios for traffic research. The code and dataset are available online for non-commercial research purposes.
查看更多>>摘要：Due to limited mileage and high schedule constraints, electric buses need to maximize not only energy efficiency but also mobility flexibility, especially in lanes where multiple bus lines merge. Connected-autonomous electric buses (CAEBs) indeed reduce inter-vehicle gaps to minimize the impact of bus stops on road capacity, but lead to frequent acceleration and deceleration to ensure safety. Therefore, this paper regards the CAEBs in the merged lane of bus lines as a whole platoon to study the cooperative control algorithm aiming at the tradeoff between energy saving and mobility. Model predictive control and optimal control are combined to design CAEB control inputs where saturation inputs, safe inter-vehicle spacing constraints, and external disturbances are integrated. This paper finds sufficient conditions for the unique solution of the non-convex optimization objective caused by the higher-order energy terms. In addition, this paper proves the semi-negative characterization of the symmetry matrix of higher-order energy terms to realize the asymptotic stability of CAEB platoons. Comparative simulations show that the cooperative control algorithm effectively trades off mobility and energy consumption even in emergency scenarios, and achieves a 25% reduction in energy consumption with only a 2.2% reduction in mobility.
查看更多>>摘要：Fast and accurate three-dimensional (3D) Multiple Object Detection and Tracking (3DMODT) is a critical task for autonomous vehicles to perceive their surroundings and make safe decisions. However, many existing works focus on academic research to address individual problems rather than overall real-world applications, which are more generalizable and applicable to daily life. To address this gap, this paper presents a lightweight and efficient 3D object understanding framework for real-life autonomous vehicles from scratch. We introduce PHE3D, a new large-scale, complex Light Detection and Ranging (LIDAR) dataset that captures Vietnamese streets, notable for its distinct characteristics and wide variety of object classes. Additionally, this study discusses the entire process for 3D object understanding, from data collection to data handling to 3DMODT. To address the computational demands, we propose a suitable lightweight and informative Convolutional Neural Network (CNN) architecture for 3D Multi-Object Detection (3DMOD) and a mathematical-based approach for 3D Multi-Object Tracking (3DMOT). Extensive experiments on the dataset show that the system can precisely detect and track attributes of multiple objects while running at up to 100, and 2000 Frames Per Second (FPS), respectively.
查看更多>>摘要：The recovery of coarsely sampled trajectories considering the road network topology characteristics is a crucial task for many downstream applications in intelligent transportation systems. Existing approaches in this domain primarily focus on extracting spatio-temporal correlations for the observed trajectory points but neglect the critical role of road network topology characteristics in making the recovery results more accurate and realistic. In addition, too many road segments in cities undermine the model inference performance. To address these challenges, we propose a novel Map-informed Adaptive Spatio-Temporal Autoencoder, which follows an encoder-decoder architecture for trajectory recovery. Specifically, we utilize a pre-trained attributed network embedding module to incorporate the road segment characteristics into the input data to make it easier for the model to extract the spatio-temporal dependencies from coarse trajectories. Furthermore, we construct a novel adaptive mask inference module that contains a distance-based mask matrix and a learnable adaptive mask matrix to assist the model in making segment inferences by weighting each candidate segment adaptively in the recovery process. To evaluate the performance of the proposed model, we conduct a series of comprehensive case studies on two representative real-world trajectory datasets. The experimental results demonstrate that the proposed model consistently outperforms state-of-the-art approaches.
NETL
NSTL
IEEE