Search

The vehicular ad hoc network has great potential in improving traffic safety. One of the most important and interesting issues in the research community is the safety evaluation with limited penetration rates of vehicles equipped with inter-vehicular communications. In this paper, a stochastic model is proposed for analyzing the vehicle chain collisions. It takes into account the influences of different penetration rates, the stochastic nature of inter-vehicular distance distribution, and the different kinematic parameters related to driver and vehicle. The usability and accuracy of this model is tested and proved by comparative experiments with Monte Carlo simulations. The collision outcomes of a platoon in different penetration rates and traffic scenarios are also analyzed based on this model. These results are useful to provide theoretical insights into the safety control of a heterogeneous platoon. [ABSTRACT FROM AUTHOR]

Vehicular ad hoc networks (VANETs) is an emerging technology that can support many vehicular safety and comfort applications through intervehicle communications. However, VANETs could face a great challenge arising from rapidly varying network topology. It is an essential issue to design an efficient and reliable solution for message dissemination in dynamic VANETs. In this paper, we propose an epidemic routing method with capability of self-adapting to the highly dynamic nature of VANETs. To ensure a good trade-off between reachability and efficiency of message dissemination, an adaptive probabilistic infection and an adaptive limited-time forwarding mechanisms are also proposed for the epidemic broadcasting. Moreover, inspired by the self-adaptability and robustness of the cellular gene regulatory networks, we use the attractor selection mechanism to enhance routing messages in dynamic VANETs. Through comparative simulations under different traffic scenarios, we validate our proposed method and prove that it can guarantee message reachability and achieve high delivery efficiency in terms of message delivery ratio, average routing latency and cost. [ABSTRACT FROM AUTHOR]

This article considers mixed platoons consisting of both human‐driven vehicles (HVs) and automated vehicles (AVs). The uncertainties and randomness in human driving behaviors highly affect the platoon safety and stability. However, most existing control strategies are either for platoons of pure AVs, or for special formations of mixed platoons with known HV models. This article addresses the control of mixed platoons with more general formations and unknown HV models. An innovative data‐driven policy learning strategy is proposed to design the controllers for AVs based on vehicle‐to‐vehicle (V2V) communications. The policy learning strategy is embedded with the constraints of control input, inter‐vehicular distance error and V2V communication topology. The strategy establishes a safe and robustly stable mixed platoon using prescribed communication topologies. The design efficacy is verified through simulations of a mixed platoon with different communication topologies and leader velocity profiles. [ABSTRACT FROM AUTHOR]

Message exchange among vehicles plays an important role in ensuring road safety. Emergency message dissemination is usually carried out by broadcasting. However, high vehicle density and mobility lead to challenges in message dissemination such as broadcasting storm and low probability of packet reception. This paper proposes a federated learning based blockchain-assisted message dissemination solution. Similar to the incentive-based Proof-of-Work consensus in blockchain, vehicles compete to become a relay node (miner) by processing the proposed Proof-of-Federated-Learning (PoFL) consensus which is embedded in the smart contract of blockchain. Both theoretical and practical analysis of the proposed solution are provided. Specifically, the proposed blockchain based federated learning results in more vehicles uploading their models in a given time, which can potentially lead to a more accurate model in less time as compared to the same solution without using blockchain. It also outperforms other blockchain approaches in reducing 65.2% of time delay in consensus, improving at least 8.2% message delivery rate and preserving privacy of neighbor vehicle more efficiently. The economic model to incentivize vehicles participating in federated learning and message dissemination is further analyzed using Stackelberg game. The analysis of asymptotic complexity proves PoFL as the most scalable solution compared to other consensus algorithms in vehicular networks. [ABSTRACT FROM AUTHOR]

Privacy has gradually developed into a serious concern. Although some privacy protection mechanisms are available, it is still a prerequisite to develop an objective and universal evaluation criterion. In fact, we have to know how much the privacy quantity has been already exposed through a human‐understandable way. For this purpose, we proposed a series of brand‐new concepts about so‐called "habitual privacy" to quantitatively analyze privacy exposure behavior. It should be emphasized that habitual privacy is an inherent property of the user and is correlated with their habitual behaviors. Joint privacy quantity is a measurement of the exposed privacy of two habitual behaviors occurring simultaneously on the same occasion. Moreover, cumulative privacy is the accumulative quantity of privacy exposure within a considerable temporal and/or spatial interval. The presented computing framework has been applied to four different empirical data sets. These data sets consisted of massive sample sets obtained from moving trajectories, Bluetooth connections, velocity preferences, and call data records. The results disclosed the characteristics hidden in different conditions of the presented quantification framework and showed the effects of combinations of various related parameters. The proposed computational habitual privacy quantity is expected to establish a theoretical cornerstone for the design of more effective and efficient privacy protection mechanisms. With reference to the inverse concept of the Shannon information, "Habitual privacy" defines and quantifies a type of privacy information with habitual properties. The definition of "Habitual privacy" is conceived from the standpoint of the data owner, and aims to provide a brand new perspective for privacy computation and protection. The proposed framework is expected to apply to the majority of daily behaviors. [ABSTRACT FROM AUTHOR]

An increasing number of image perception models are being utilized in the field of autonomous driving. During nighttime driving, the visual perception capabilities of a single-modality RGB sensor become compromised. To address this issue, image fusion methods that utilize multi-modality data to provide a more comprehensive visual representation for nighttime scenes. Nevertheless, the existing image fusion methods are limited by poor generalization abilities and lighting conditions, resulting in inadequate handling of the contrast and spectral corruption. In this paper, we propose a cross-sensor low-light enhancement algorithm that provides more accurate visual perceptions. Our approach employs multiple sensors as preceptors for nighttime driving scenes. Compared with typical fusion algorithms that use a simple one-stage workflow for cross-sensor data, our proposed method adopts an advanced content-enhancement strategy by recursively and interactively scaling up informative pixels. More specifically, our approach employs information measurement to describe the information and then utilizes a cross-sensor content enhancement module to dynamically enhance the mutual information between the infrared spectrum and the RGB streams. Our experiments show that CROSE effectively preserves texture details, resulting in clearer and more solid fusion results for nighttime driving scenes. [ABSTRACT FROM AUTHOR]

Recent advances in cross-modal 3D object detection rely heavily on anchor-based methods, and however, intractable anchor parameter tuning and computationally expensive postprocessing severely impede an embedded system application, such as autonomous driving. In this work, we develop an anchor-free architecture for efficient camera-light detection and ranging (LiDAR) 3D object detection. To highlight the effect of foreground information from different modalities, we propose a dynamic fusion module (DFM) to adaptively interact images with point features via learnable filters. In addition, the 3D distance intersection-over-union (3D-DIoU) loss is explicitly formulated as a supervision signal for 3D-oriented box regression and optimization. We integrate these components into an end-to-end multimodal 3D detector termed 3D-DFM. Comprehensive experimental results on the widely used KITTI dataset demonstrate the superiority and universality of 3D-DFM architecture, with competitive detection accuracy and real-time inference speed. To the best of our knowledge, this is the first work that incorporates an anchor-free pipeline with multimodal 3D object detection.

Prior convolution-based road crack detectors typically learn more abstract visual representation with increasing receptive field via an encoder-decoder architecture. Despite the promising accuracy, progressive spatial resolution reduction causes semantic feature blurring, leading to coarse and incontiguous distress detection. To these ends, an alternative sequence-to-sequence perspective with a transformer network termed TransCrack is introduced for road crack detection. Specifically, an image is decomposed into a grid of fixed-size crack patches, which is flattened with position embedding into a sequence. We further propose a pure transformer-based encoder with multi-head reduced self-attention modules and feed-forward networks for explicitly modelling long-range dependencies from the sequential input in a global receptive field. More importantly, a simple decoder with cross-layer aggregation architecture is developed to incorporate global with local attentions across different regions for detailed feature recovery and pixel-wise crack mask prediction. Empirical studies are conducted on three publicly available damage detection benchmarks. The proposed TransCrack achieves a state-of-the-art performance over all counterparts by a substantialmargin, and qualitative results further demonstrate its superiority in contiguous crack recognition and fine-grained profile extraction. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.