Search Results (214)

The integration of connected autonomous vehicles (CAVs), advanced driver assistance systems (ADAS), and conventional vehicles necessitates the development of robust methodologies to enhance traffic efficiency and ensure safety across heterogeneous traffic streams. A comprehensive understanding of vehicle interactions and operating speed variability is essential to support informed decision-making in traffic management and infrastructure design. This study presents operating speed models aimed at estimating the 85th percentile speed (V₈₅) on straight road segments, utilizing floating car data (FCD) for both calibration and validation purposes. The dataset encompasses approximately 2000 km of the Italian road network, characterized by diverse geometric features. Speed observations were analyzed under three traffic conditions: general traffic, free-flow, and free-flow with dry pavement. Results indicate that free-flow conditions improve the model’s explanatory power, while dry pavement conditions introduce greater speed variability. Initial models based exclusively on geometric parameters exhibited limited predictive accuracy. However, the inclusion of posted speed limits significantly enhanced model performance. The most influential predictors identified were the V₈₅ on the preceding curve and the length of the straight segment. These findings provide empirical evidence to inform road safety evaluations and geometric design practices, offering insights into driver behavior in mixed-traffic environments. The proposed model supports the development of data-driven strategies for the seamless integration of automated and non-automated vehicles. Full article

The health of road tunnel linings directly impacts traffic safety and requires regular inspection. Appearance defects on tunnel linings can be measured through images scanned by cameras mounted on a car to avoid disrupting traffic. Existing tunnel lining mobile scanning methods often fail in image stitching due to the lack of corresponding feature points in the lining images, or require complex, time-consuming algorithms to eliminate stitching seams caused by the same issue. This paper proposes a mobile scanning method aided by collimated lasers, which uses lasers as corresponding points to assist with image stitching to address the problems. Additionally, the lasers serve as structured light, enabling the measurement of image projection relationships. An inspection car was developed based on this method for the experiment. To ensure operational flexibility, a single checkerboard was used to calibrate the system, including estimating the poses of lasers and cameras, and a Laplace kernel-based algorithm was developed to guarantee the calibration accuracy. Experiments show that the performance of this algorithm exceeds that of other benchmark algorithms, and the proposed method produces nearly seamless, measurable tunnel lining images, demonstrating its feasibility. Full article

With the rapid development of intelligent transportation systems, voice assistants are increasingly integrated into driving environments, providing an effective means to mitigate the risks of fatigued driving. This study explored drivers’ interaction preferences with voice assistants under different fatigue states and proposed a fatigue-state-based dialogue-awakening mechanism. Using Grounded Theory and the Stimulus–Organism–Response (SOR) framework, in-depth interviews were conducted with 25 drivers from diverse occupational backgrounds. To validate the qualitative findings, a driving simulation experiment was carried out to examine the effects of different voice interaction styles on driver fatigue arousal across various fatigue levels. Results indicated that heavily fatigued drivers preferred highly stimulating and interactive voice communication; mildly fatigued drivers tended toward gentle and socially supportive dialogue; while drivers in a non-fatigued state preferred minimal voice interference, activating voice assistance only when necessary. Significant occupational differences were also observed: long-haul truck drivers emphasized practicality and safety in voice assistants, taxi drivers favored voice interactions combining navigation and social content, and private car owners preferred personalized and emotional support. This study enriches the theoretical understanding of fatigue-sensitive voice interactions and provides practical guidance for the adaptive design of intelligent voice assistants, promoting their application in driving safety. Full article

The automotive industry is fully shifting towards autonomous connected vehicles. By advancing vehicles’ intelligence and connectivity, the industry has enabled innovative functions such as advanced driver assistance systems (ADAS) in the direction of driverless cars. Such functions are often referred to as cyber-physical features, since almost all of them require collecting data from the physical environment to make automotive operation decisions and properly actuate in the physical world. However, increased functionalities result in increased complexity, which causes serious security vulnerabilities that are typically a result of mushrooming functionality and hence complexity. In a world where we keep seeing traditional mechanical systems shifting to x-by-wire solutions, the number of connected sensors, processing systems, and communication buses inside the car exponentially increases, raising several safety and security concerns. Because there is no safety without security, car manufacturers start struggling in making lightweight sensor and processing systems while keeping the security aspects a major priority. This article surveys the current technological challenges in securing autonomous vehicles and contributes a cross-layer analysis bridging hardware security primitives, real-world side-channel threats, and redundancy-based fault tolerance in automotive electronic control units (ECUs). It combines architectural insights with an evaluation of commercial support for TrustZone, trusted platform modules (TPMs), and lockstep platforms, offering both academic and industry audiences a grounded perspective on gaps in current hardware capabilities. Finally, it outlines future directions and presents a forward-looking vision for securing sensors and processing systems in the path toward fully safe and connected autonomous vehicles. Full article

Driver factors are the main cause of road traffic accidents. For the research of automotive active safety, an identification method for road hypnosis of a driver of a car with dynamic human–vehicle heterogeneous data fusion calculation is proposed. Road hypnosis is an unconscious driving state formed by the combination of external environmental factors and the psychological state of the car driver. When drivers fall into a state of road hypnosis, they cannot clearly perceive the surrounding environment and make various reactions in time to complete the driving task. The safety of humans and cars is greatly affected. Therefore, the study of the identification of drivers’ road hypnosis is of great significance. Vehicle and virtual driving experiments are designed and carried out to collect human and vehicle data. Eye movement data and EEG data of human data are collected with eye movement sensors and EEG sensors. Vehicle speed and acceleration data are collected by a mobile phone with AutoNavi navigation, which serves as an onboard sensor. In order to screen the characteristics of human and vehicles related to the road hypnosis state, the characteristic parameters of the road hypnosis in the preprocessed data are selected by the method of independent sample T-test, the hidden Markov model (HMM) is constructed, and the identification of the road hypnosis of the Ridge Regression model is combined. In order to evaluate the identification performance of the model, six evaluation indicators are used and compared with multiple regression models. The results show that the hidden Markov-Ridge Regression model is the most superior in the identification accuracy and effect of the road hypnosis state. A new technical scheme reference for the development of intelligent driving assistance systems is provided by the proposed comprehensive road hypnosis state identification model based on human–vehicle data can provide, which can effectively improve the life recognition ability of automobile intelligent cockpits, enhance the active safety performance of automobiles, and further improve traffic safety. Full article

As urbanization continues to expand, the design and structure of urban spaces increasingly influence the experiences of individuals, whether intentionally or inadvertently. These effects can result in both positive and negative experiences, with urban facilities generally designed to enhance the comfort and well-being of citizens. However, in certain cases, these spaces can provoke adverse emotional reactions, such as anxiety. Anxiety, a prevalent mental health disorder, is more commonly observed in urban environments than in rural areas. Among various urban settings, rail transport in large cities is often cited as one of the most stressful environments for passengers. In light of the significance of this issue, this study seeks to explore how physical and perceptual components can reduce anxiety and encourage greater use of intra-urban rail transportation. Utilizing a qualitative research approach, the study employed directional content analysis to investigate this topic. Data were collected and analyzed through an exploratory methodology with the assistance of MAXQDA software. The analysis began with guided content coding, drawing on theoretical frameworks pertinent to the research. Through this process, 2387 initial codes were identified, which were then categorized into nine main themes, with the relationships between these codes clarified. The findings were inductively derived from the raw data, leading to the development of a foundational theoretical framework. The study, employing a personalized strategy, identified three key factors that contribute to anxiety: physical, perceptual, and environmental components. Physical factors, such as accessibility, lighting, and signage, were found to have a significant impact on passengers’ psychological well-being. Perceptual factors, including personal perceptions, stress, and fear, played a crucial role in exacerbating anxiety. Additionally, environmental factors, particularly the design of metro networks, rail lines, and flexible transportation lines, such as car-sharing and micromobility, were found to significantly contribute to the overall anxiety experienced by passengers. Moreover, the study suggests that anxiety triggers can be mitigated effectively through the implementation of well-designed policies and management practices. Enhancing the sense of security within transit spaces was found to increase citizens’ willingness to utilize rail transportation. These findings indicate that targeted interventions aimed at improving both the physical and perceptual aspects of the transit environment could enhance the commuter experience and, in turn, foster greater use of rail systems. Full article

This study proposes an advanced intelligent vehicle path-following control system using deep reinforcement learning, with a particular focus on the role of road geometry perception in motion planning and control. The system is structured around a three-degree-of-freedom (3-DOF) vehicle model, which facilitates the extraction of critical dynamic features necessary for robust control. The longitudinal control architecture integrates a Deep Deterministic Policy Gradient (DDPG) agent to optimise longitudinal velocity and acceleration, while lateral vehicle control is handled by a Deep Q-Network (DQN). To enhance situational awareness and adaptability, the system incorporates key input variables, including ego vehicle speed, speed error, lateral deviation, lateral error, and safety distance to the preceding vehicle, all in the context of road geometry and vehicle dynamics. In addition, the influence of road curvature is embedded into the control framework through perceived acceleration (sensed by vehicle occupants), allowing for more accurate and responsive adaptation to varying road conditions. The vehicle control system is tested in a simulated environment with a lead car in front with realistic speed profiles. The system outputs continuous values for acceleration and steering angle. The results of this study suggest that the proposed intelligent control system not only improves driver assistance but also has potential applications in autonomous driving. This framework contributes to the development of more autonomous, efficient, safety-aware, and comfortable vehicle control systems. Full article

Efficient pedestrian detection plays an important role in many practical daily life applications, such as autonomous cars, video surveillance, and intelligent driving assistance systems. The main goal of pedestrian detection systems, especially in vehicles, is to prevent accidents. By recognizing pedestrians in real time, these systems can alert drivers or even autonomously apply brakes, minimizing the possibility of collisions. However, occlusion is a major obstacle to pedestrian detection. Pedestrians are typically occluded by trees, street poles, cars, and other pedestrians. State-of-the-art detection methods are based on fully visible or little-occluded pedestrians; hence, their performance declines with increasing occlusion level. To meet this challenge, a pedestrian detector capable of handling occlusion is preferred. To increase the detection accuracy for occluded pedestrians, we propose a new method called the Discriminative Deformable Part Model (DDPM), which uses the concept of breaking human image into deformable parts via machine learning. In existing works, human image breaking into deformable parts has been performed by human intuition. In our novel approach, machine learning is used for deformable objects such as humans, combining the benefits and removing the drawbacks of the previous works. We also propose a new pedestrian dataset based on Eastern clothes to accommodate the detector’s evaluation under different intra-class variations of pedestrians. The proposed method achieves a higher detection accuracy on Pascal VOC and VisDrone Detection datasets when compared with other popular detection methods. Full article

The risk of serious crashes is notably higher among young and novice drivers. This increased risk is due to several factors, including a lack of recognition of dangerous situations, an overestimation of driving skills, and vulnerability to peer pressure. Recently, advanced driver assistance systems (ADAS) have been integrated into vehicles to help mitigate crashes linked to these factors. While numerous studies have examined ADAS broadly, few have specifically investigated its effects on young and novice drivers. This study aimed to address that gap by exploring ADAS’s impact on these drivers. Most studies in this review conclude that ADAS is beneficial for young and novice drivers, though some research suggests its impact may be limited or even negligible. Tailoring ADAS to address the unique needs of young drivers could enhance both the system’s acceptance and reliability. The review also found that unimodal warnings (e.g., auditory or visual) are as effective as multimodal warnings. Of the different types of warnings, auditory and visual signals proved the most effective. Additionally, ADAS can influence young drivers’ car-following behavior; for instance, drivers may maintain greater safety buffers or drive closely to avoid alarm triggers, likely due to perceived system unreliability. Aggressive drivers tend to benefit most from active ADAS, which actively intervenes to assist the driver. Future research could explore the combined effects of multiple ADAS functions within a single vehicle on young and novice drivers to better understand how these systems interact and impact driver behavior. Full article

Peer-to-peer car-sharing systems are an evolving branch of urban mobility, aligning with global trends focused on sustainable development and reducing congestion in cities. A research gap has been identified concerning the specific vehicle attributes that would encourage the public to potentially use these services. Addressing this gap, and in the context of launching a new peer-to-peer car-sharing service in Katowice, Poland, this article investigates the technical features influencing the choice of vehicles in peer-to-peer car-sharing systems, particularly from the perspective of individuals who currently do not use such platforms. The study employs Social Network Analysis (SNA) to examine the interrelationships between vehicle attributes. The analysis reveals that key factors influencing users’ decisions include fuel/energy consumption, safety features, and technological advancement, with a particular emphasis on driver assistance systems, including autonomous driving capabilities. The network structure, characterized by a relatively low density (0.2536) and a short average path length (1.872), suggests that a few central vehicle features dominate user decisions, and improvements in these key areas can quickly propagate through the decision-making process, enhancing overall user satisfaction. To validate the findings, a Gradient Boosting Regression (GBR) analysis was conducted, confirming the significance of the key factors identified by the SNA, such as fuel efficiency, battery capacity, and safety systems, thus strengthening the reliability of the results. This study underscores the growing importance of sustainability and technological innovation in the automotive industry, particularly in the context of the sharing economy. It suggests that car-sharing platforms and vehicle manufacturers should prioritize these features to meet user expectations and preferences. These findings provide valuable insights for the strategic and operational management of peer-to-peer car-sharing services, emphasizing the importance of targeted vehicle selection and user-centered innovations to improve platform performance and scalability. Full article

Despite the implementation of numerous interventions to enhance urban traffic safety, the estimation of the risk of traffic crashes resulting in life-threatening and economic costs remains a significant challenge. In light of the above, an online inference method for traffic crash risk based on the self-developed TAR-DETR and WOA-SA-SVM methods is proposed. The method’s robust data inference capabilities can be applied to autonomous mobile robots and vehicle systems, enabling real-time road condition prediction, continuous risk monitoring, and timely roadside assistance. First, a self-developed dataset for urban traffic object detection, named TAR-1, is created by extracting traffic information from major roads around Hainan University in China and incorporating Russian car crash news. Secondly, we develop an innovative Context-Guided Reconstruction Feature Network-based Urban Traffic Objects Detection Model (TAR-DETR). The model demonstrates a detection accuracy of 76.8% for urban traffic objects, which exceeds the performance of other state-of-the-art object detection models. The TAR-DETR model is employed in TAR-1 to extract urban traffic risk features, and the resulting feature dataset was designated as TAR-2. TAR-2 comprises six risk features and three categories. A new inference algorithm based on WOA-SA-SVM is proposed to optimize the parameters (C, g) of the SVM, thereby enhancing the accuracy and robustness of urban traffic crash risk inference. The algorithm is developed by combining the Whale Optimization Algorithm (WOA) and Simulated Annealing (SA), resulting in a Hybrid Bionic Intelligent Optimization Algorithm. The TAR-2 dataset is inputted into a Support Vector Machine (SVM) optimized using a hybrid algorithm and used to infer the risk of urban traffic crashes. The proposed WOA-SA-SVM method achieves an average accuracy of 80% in urban traffic crash risk inference. Full article

At present, achieving efficient, sustainable, and safe transportation has led to increasing attention on driving behavior recognition and advancements in autonomous driving. Identifying diverse driving styles and corresponding types is crucial for providing targeted training and assistance to drivers, enhancing safety awareness, optimizing driving costs, and improving autonomous driving systems responses. However, current studies mainly focus on specific driving scenarios, such as free driving, car-following, and lane-changing, lacking a comprehensive and systematic framework to identify the diverse driving styles. This study proposes a novel, data-driven approach to driving-style recognition utilizing naturalistic driving data NGSIM. Specifically, the NGSIM dataset is employed to categorize car-following and lane-changing groups according to driving-state extraction conditions. Then, characteristic parameters that fully represent driving styles are optimized through correlation analysis and principal component analysis for dimensionality reduction. The K-means clustering algorithm is applied to categorize the car-following and lane-changing groups into three driving styles: conservative, moderate, and radical. Based on the clustering results, a comprehensive evaluation of the driving styles is conducted. Finally, a comparative evaluation of SVM, Random Forest, and KNN recognition indicates the superiority of the SVM algorithm and highlights the effectiveness of dimensionality reduction in optimizing characteristic parameters. The proposed method achieves over 97% accuracy in identifying car-following and lane-changing behaviors, confirming that the approach based on naturalistic driving data can effectively and intelligently recognize driving styles. Full article

People with hearing impairments often face increased risks related to traffic accidents due to their reduced ability to perceive surrounding sounds. Given the cost and usage limitations of traditional hearing aids and cochlear implants, this study aims to develop a sound alert assistance system (SAAS) to enhance situational awareness and improve travel safety for people with hearing impairments. We proposed the VAS-Compass Net (Vehicle Alert Sound–Compass Net), which integrates three lightweight convolutional neural networks: EfficientNet-lite0, MobileNetV3-Small, and GhostNet. Through employing a fuzzy ranking ensemble technique, our proposed model can identify different categories of vehicle alert sounds and directions of sound sources on an edge computing device. The experimental dataset consisted of images derived from the sounds of approaching police cars, ambulances, fire trucks, and car horns from various directions. The audio signals were converted into spectrogram images and Mel-frequency cepstral coefficient images, and they were fused into a complete image using image stitching techniques. We successfully deployed our proposed model on a Raspberry Pi 5 microcomputer, paired with a customized smartwatch to realize an SAAS. Our experimental results demonstrated that VAS-Compass Net achieved an accuracy of 84.38% based on server-based computing and an accuracy of 83.01% based on edge computing. Our proposed SAAS has the potential to significantly enhance the situational awareness, alertness, and safety of people with hearing impairments on the road. Full article

To validate active human body models for investigating occupant safety in autonomous cars, it is crucial to comprehend the responses of vehicle occupants during evasive maneuvers. This study sought to quantify the behavior of midsize male and small female passenger seat occupants in both upright and reclined postures during three types of vehicle maneuvers. Volunteer tests were conducted using a minivan, where vehicle kinematics were measured with a DGPS sensor and occupant kinematics were captured with a stereo-vision motion capture system. Seatbelt loads, belt pull-out, and footrest reaction forces were also documented. The interior of the vehicle was 3D-scanned for modeling purposes. Results indicated that seatback angles significantly affected occupant kinematics, with small female volunteers displaying reduced head and torso movements, except during emergency braking with a upright posture seatback. Lane-change maneuvers revealed that maximum lateral head excursions varied depending on the maneuver’s direction. The study concluded that seatback angles were crucial in determining the extent of occupant movement, with notable variations in head and torso excursions observed. The collected data assist in understanding occupant behavior during evasive maneuvers and contribute to the validation of human body models, offering essential insights for enhancing safety systems in autonomous vehicles. Full article

Secondary actions in vehicles are activities that drivers engage in while driving that are not directly related to the primary task of operating the vehicle. Secondary Action Recognition (SAR) in drivers is vital for enhancing road safety and minimizing accidents related to distracted driving. It also plays an important part in modern car driving systems such as Advanced Driving Assistance Systems (ADASs), as it helps identify distractions and predict the driver’s intent. Traditional methods of action recognition in vehicles mostly rely on RGB videos, which can be significantly impacted by external conditions such as low light levels. In this research, we introduce a novel method for SAR. Our approach utilizes depth-video data obtained from a depth sensor located in a vehicle. Our methodology leverages the Convolutional Neural Network (CNN), which is enhanced by the Spatial Enhanced Attention Mechanism (SEAM) and combined with Bidirectional Long Short-Term Memory (Bi-LSTM) networks. This method significantly enhances action recognition ability in depth videos by improving both the spatial and temporal aspects. We conduct experiments using K-fold cross validation, and the experimental results show that on the public benchmark dataset Drive&Act, our proposed method shows significant improvement in SAR compared to the state-of-the-art methods, reaching an accuracy of about 84% in SAR in depth videos. Full article