Search Results (99)

Accurate side road detection is essential for traffic management, urban planning, and vehicle navigation. However, existing research mainly focuses on road network construction, lane extraction, and intersection identification, while fine-grained side road detection remains underexplored. Therefore, this study proposes a road segment-level side road detection method based on crowdsourced trajectory data: First, considering the geometric and dynamic characteristics of trajectories, SRDet introduces a trajectory lane-change pattern recognition method based on mutation intervals to distinguish the heterogeneity of lane-change behaviors between main and side roads. Secondly, combining geometric features with spatial statistical theory, SRDet constructs multimodal features for trajectories and road segments, and proposes a potential side road segment classification model based on random forests to achieve precise detection of side road segments. Finally, based on mutation intervals and potential side road segments, SRDet utilizes density peak clustering to identify main and side road access points, completing the fitting of side roads. Experiments were conducted using 2021 Beijing trajectory data. The results show that SRDet achieves precision and recall rates of 84.6% and 86.8%, respectively. This demonstrates the superior performance of SRDet in side road detection across different areas, providing support for the precise updating of urban road navigation information. Full article

Trajectory prediction under multimodal information is critical for autonomous driving, necessitating the integration of dynamic vehicle states and static high-definition (HD) maps to model complex agent–scene interactions effectively. However, existing methods often employ static scene encodings and unstructured latent spaces, limiting their ability to capture evolving spatial contexts and produce diverse yet contextually coherent predictions. To tackle these challenges, we propose MS-SLV, a novel generative framework that introduces (1) a time-aware scene encoder that aligns HD map features with vehicle motion to capture evolving scene semantics and (2) a structured latent model that explicitly disentangles agent-specific intent and scene-level constraints. Additionally, we introduce an auxiliary lane prediction task to provide targeted supervision for scene understanding and improve latent variable learning. Our approach jointly predicts future trajectories and lane sequences, enabling more interpretable and scene-consistent forecasts. Extensive evaluations on the nuScenes dataset demonstrate the effectiveness of MS-SLV, achieving a 12.37% reduction in average displacement error and a 7.67% reduction in final displacement error over state-of-the-art methods. Moreover, MS-SLV significantly improves multi-modal prediction, reducing the top-5 Miss Rate (${\mathrm{MR}}_5$) and top-10 Miss Rate (${\mathrm{MR}}_{10}$) by 26% and 33%, respectively, and lowering the Off-Road Rate (ORR) by 3%, as compared with the strongest baseline in our evaluation. Full article

This study optimizes the deployment of autonomous taxis for safety at skewed intersections through a simulation-based approach, identifying an optimal penetration rate and control strategies. Here, we investigate the safety impacts of autonomous taxis (ATs) at such intersections using a simulation-based approach, leveraging the VISSIM traffic simulation tool and the Surrogate Safety Assessment Model (SSAM). Our study identifies an optimal AT penetration rate of approximately 0.5–0.7, as exceeding this range may lead to a decline in safety metrics such as TTC and PET. We find that connectivity among ATs does not linearly correlate with safety improvements, suggesting a nuanced approach to AT deployment is necessary. The “Normal” control strategy, which mimics human driving, shows a direct proportionality between AT penetration and TTC, indicating that not all levels of automation enhance safety. Our conflict analysis reveals distinct patterns for crossing, lane-change, and rear-end conflicts under various control strategies, underscoring the need for tailored approaches at skewed intersections. This research contributes to the discourse on AT safety and informs the development of traffic management strategies and policy frameworks that prioritize safety and efficiency in the context of skewed intersections. Full article

In an ever-changing driving environment where vehicles are becoming smarter, more autonomous, and more connected, a paradigmatic change in signals for drivers might be required. This need is correlated with road safety (social sustainability). There are several factors affecting road safety, and one of these, especially important on rural roads, is speed. One way to actively influence drivers’ speed is to intervene with regard to speed limit signs by providing credible and effective limits. This goal can be pursued by working on variable speed limits that align with the boundary conditions of the installation site. In this research, an analysis was conducted on the rural road network within the Metropolitan City of Bari (Italy) that involved collecting the speeds on each of the investigated two-way, two-lane rural roads of the network. In addition to the speeds, all the most relevant geometric details of the roads were considered, together with environmental factors like rainfall. A generalized linear model was developed to correlate the operating speed limits and other variables together with information about rainfall, which degrades tire–pavement friction and thus, road safety. After the development of this model, safety performance functions, depending on the amount of rain or number of days of rain, were calculated with the intent of predicting crash frequency, starting with the operative speed and rain conditions. Operative speed, speed limit, percentage of non-compliant drivers, traffic level, and site length were found to be associated with all typologies and locations of crashes investigated. Full article

The rapid growth of e-bikes has intensified traffic conflicts on slow-moving shared paths in China. This study analyzed traffic safety of pedestrians and non-motorized vehicles and examined the factors influencing conflict severity utilizing traffic conflict techniques. Video-based surveys were conducted on six shared paths in Shenzhen, and conflict trajectory was extracted by Petrack software (Version 0.8). The minimum Time to Collision and Yaw Rate Ratio were selected as conflict indicators. Fuzzy c-means clustering was employed to classify conflicts into three severity levels: 579 potential conflicts, 435 minor conflicts, and 150 serious conflicts. Nineteen feature variables related to road environment, traffic operation, conflict sample information, and conflict behavior were considered. A SMOTE random forest model was constructed to explore critical influencing factors systematically. The results identified ten key factors affecting conflict severity. The increase in conflict severity is associated with the rise in pedestrian proportion and flow, and the decrease in e-bike proportion and flow. Male participants and pedestrians are more likely to engage in serious conflicts, while illegal lane occupation and wrong-way travel further elevate the severity level. These findings can provide references for traffic engineers and planners to enhance the safety management of shared paths and contribute to sustainable non-motorized transport. Full article

Cycling significantly contributes to improving metro accessibility; however, the quality of bicycle environments surrounding metro stations remains insufficiently studied. This study develops a criteria–indicators assessment framework that incorporates both objective characteristics of bicycle infrastructure and subjective perceptions of bicycle access to metro stations. The framework consists of four primary criteria—accessibility, convenience, safety, and comfort—along with eighteen sub-level indicators. Taking central Tianjin as the study area, the study evaluated the cycling environment quality around eight representative metro stations by employing information entropy and the analytic hierarchy process, with cosine similarity used to compare the outcomes against human–machine adversarial scoring result to ensure analytical robustness. The findings reveal substantial disparities in cycling infrastructure, with safety and accessibility exhibiting higher scores than convenience and comfort. Additionally, cycling environment quality is higher around comprehensive and public-service stations compared to residential stations, while commercial stations exhibit the lowest quality. The study underscores the necessity of expanding protected bike lanes, enhancing route directness, and improving parking and wayfinding facilities to promote cycling as an effective first- and last-mile metro access mode. Full article

This investigation analyses driving behaviors that lead to accidents on overly sharp mountain road curves in Nanjing Province, China. We collected information through field observations and driving simulations while analyzing key indicators like the mean speed of vehicles and spacing between vehicles. The FP-Growth algorithm was used to identify frequent behavioral patterns and measure their relationship with traffic conflicts. The findings showed that unsafe driver behavior on sharp turns was common, while the combination of “speeding–tailgating–frequent lane changing” behavior increased conflict risk by 3.7 times. A predictive LSTM neural network model was developed with driver, vehicle, road, and environmental factors. Testing on 4795 samples achieved 83.7% accuracy in foreseeing conflict risk levels. The model, which distinguishes between safety conditions and three severity levels of potential conflict, can provide the most fundamental level of safety needed. The research provides quantitative tools for improved road safety management aimed at supporting real evidence-based “safe roads” approaches. Full article

This study proposes a design method for the evaluation and redesign of product–service systems (PSSs) from the perspective of social sustainability, one that applies Max-Neef’s framework of fundamental human needs. The proposed method systematically connects PSS functions and requirements—identified through service blueprints and value graphs—to “satisfiers” and “barriers” extracted via needs-based workshops. This connection enables the identification of functions that either contribute to or hinder the fulfillment of fundamental human needs and guide the generation of redesign proposals aimed at sufficiency-oriented outcomes. A case study involving a smart-cart system in Osaka, Japan, was conducted to demonstrate the applicability of the method. Through an online workshop, satisfiers and barriers related to both physical and online shopping experiences were identified. The analysis revealed that existing functions such as promotional information and automated checkout processes negatively impacted needs such as understanding and affection due to information overload and reduced human interaction. In response, redesign concepts were developed, including filtering options for information, product background storytelling, and optional slower checkout lanes with human assistants. The redesigned functions contribute to the fulfillment of fundamental human needs, indicating that the proposed method can enhance social sustainability in PSS design. This study offers a novel framework that extends beyond traditional customer requirement-based approaches by explicitly incorporating human needs into function-level redesign. Full article

To address the challenges of lane line recognition failure and insufficient segmentation accuracy in complex autonomous driving scenarios, this paper proposes a dual-branch instance segmentation method that integrates multi-scale modeling and dynamic feature enhancement. By constructing an encoder-decoder architecture and a cross-scale feature fusion network, the method effectively enhances the feature representation capability of multi-scale information through the integration of high-level feature maps (rich in semantic information) and low-level feature maps (retaining spatial localization details), thereby improving the prediction accuracy of lane line morphology and its variations. Additionally, hierarchical dilated convolutions (with dilation rates 1/2/4/8) are employed to achieve exponential expansion of the receptive field, enabling better fusion of multi-scale features. Experimental results demonstrate that the proposed method achieves F1-scores of 76.0% and 96.9% on the CULane and Tusimple datasets, respectively, significantly enhancing the accuracy and reliability of lane detection. This work provides a high-precision, real-time solution for autonomous driving perception in complex environments. Full article

High-definition (HD) maps aim to provide detailed road information with centimeter-level accuracy, essential for enabling precise navigation and safe operation of autonomous vehicles (AVs). Traditional offline construction methods involve several complex steps, such as data collection, point cloud generation, and feature extraction, but these methods are resource-intensive and struggle to keep pace with the rapidly changing road environments. In contrast, online HD map construction leverages onboard sensor data to dynamically generate local HD maps, offering a bird’s-eye view (BEV) representation of the surrounding road environment. This approach has the potential to improve adaptability to spatial and temporal changes in road conditions while enhancing cost-efficiency by reducing the dependency on frequent map updates and expensive survey fleets. This survey provides a comprehensive analysis of online HD map construction, including the task background, high-level motivations, research methodology, key advancements, existing challenges, and future trends. We systematically review the latest advancements in three key sub-tasks: map segmentation, map element detection, and lane graph construction, aiming to bridge gaps in the current literature. We also discuss existing challenges and future trends, covering standardized map representation design, multitask learning, and multi-modality fusion, while offering suggestions for potential improvements. Full article

This research aims to optimize corridors in Hyderabad, Sindh, to promote modal choice, reduce congestion, and enhance livability. This study focused on developing and evaluating multimodal wide corridor routing methods, analyzing the modal choice behavior of travelers using a generalized cost model and a mixed constant and separate user balance model, and implementing and assessing innovative road space management strategies. The data were collected using GIS (Geographical Information System) to compare the performance and impacts of the proposed methods and techniques with existing ones, such as shortest path, minimum interference, maximum capacity, and lane addition, using various performance measures, such as travel time, modal share, congestion level, environmental impact, safety, and equity. This research aims to optimize corridors in Hyderabad, Sindh, to encourage various transportation options, such as the BRT system and Peoples Bus Service, to reduce congestion and enhance livability by developing and accessing different methods and strategies. This study analyzed available data through a geospatial perspective to optimize corridors in Hyderabad, Sindh, focusing on multimodal routing methods, modal choice behavior, and innovative road space management strategies to enhance urban livability rather than relying on simulation software or field-collected data. Full article

This paper focuses on a method of rearview camera-based blind-spot detection and a lane change assistance system for autonomous vehicles, utilizing a convolutional neural network and lane detection. In this study, we propose a method for providing real-time warnings to autonomous vehicles and drivers regarding collision risks during lane-changing maneuvers. We propose a method for lane detection to delineate the area for blind-spot detection and for measuring time to collision—both utilized to ascertain the vehicle’s location and compensate for vertical vibrations caused by vehicle movement. The lane detection method uses edge detection on an input image to extract lane markings by employing edge pairs consisting of positive and negative edges. Lanes were extracted through third-polynomial fitting of the extracted lane markings, with each lane marking being tracked using the results from the previous frame detections. Using the vanishing point where the two lanes converge, the camera calibration information is updated to compensate for the vertical vibrations caused by vehicle movement. Additionally, the proposed method utilized YOLOv9 for object detection, leveraging lane information to define the region of interest (ROI) and detect small-sized objects. The object detection achieved a precision of 90.2% and a recall of 82.8%. The detected object information was subsequently used to calculate the collision risk. A collision risk assessment was performed for various objects using a three-level collision warning system that adapts to the relative speed of obstacles. The proposed method demonstrated a performance of 11.64 fps with an execution time of 85.87 ms. It provides real-time warnings to both drivers and autonomous vehicles regarding potential collisions with detected objects. Full article

With the rise in the intelligence levels of automated vehicles, increasing numbers of modules of automated driving systems are being combined to achieve better performance and adaptability by reducing information loss. In this study, an integrated decision and motion planning system is designed for multi-object highways. A two-layer structure is presented to decouple the influence of the traffic environment and the dynamic control of ego vehicles using the cognitive safety area, the size of which is determined by naturalistic driving behavior. The artificial potential field method is used to comprehensively describe the influence of all external objects on the cognitive safety area, the lateral motion dynamics of which are determined by the attention mechanism of the human driver during lane changes. Then, the interaction between the designed cognitive safety area and the ego vehicle can be simplified into a spring-damping system, and the desired dynamic states of the ego vehicle can be obtained analytically for better computational efficiency. The effectiveness of this on improving traffic efficiency, driving comfort, safety, and real-time performance was validated using several comparative tests utilizing complicated scenarios with multiple vehicles. Full article

This study is based on an investigation of shared mobility in Chinese cities, which identifies the factors affecting the sustainable development of shared mobility based on the theoretical framework of TDM (travel demand management). Through a literature review and expert interviews, the FUZZY-DEMATEL-ISM-MICMAC integration model was used to screen 21 influencing factors from aspects that fit the research theme. Triangular fuzzy numbers are used to quantify the subjective scores of nine expert groups and weaken the subjective influence of expert scores. The logical relationships among DEMATEL technology-building factors and ISM technology-based factors are divided into levels. The MICMAC technique is used to divide the types of factors according to the driving power and dependency. The results show that (1) the influence factors of the “soft strategy” and “hard strategy” in the framework of TDM are determined. In the soft strategy, we should focus on “shared mobility education” (shared mobility education, shared mobility publicity and shared mobility “environment” information) and “community organization” (community organization and advocacy and organizational interaction). In the hard strategy, we should focus on “traffic planning and measures”, “dedicated lanes”, “parking facilities”, and “financial subsidies”. (2) The ISM recursive structure model is divided into five layers. Among them, shared mobility education, shared mobility operating technology, and organizational interaction are at the deep root level, which can continuously influence other factors in the long run. (3) In MICMAC, the number of related factors is large. When making decisions on these factors, managers should comprehensively consider the correlation of factors and adjust the use of factors from an overall perspective. This study can help managers identify the key factors affecting the sustainability of shared mobility and make targeted recommendations. Full article

In autonomous driving, environmental perception technology often encounters challenges such as false positives, missed detections, and low accuracy, particularly in detecting small objects and complex scenarios. Existing algorithms frequently suffer from issues like feature redundancy, insufficient contextual interaction, and inadequate information fusion, making it difficult to perform multi-task detection and segmentation efficiently. To address these challenges, this paper proposes an end-to-end multi-task environmental perception model named YOLO-Mg, designed to simultaneously perform traffic object detection, lane line detection, and drivable area segmentation. First, a multi-stage gated aggregation network (MogaNet) is employed during the feature extraction process to enhance contextual interaction by improving diversity in the channel dimension, thereby compensating for the limitations of feed-forward neural networks in contextual understanding. Second, to further improve the model’s accuracy in detecting objects of various scales, a restructured weighted bidirectional feature pyramid network (BiFPN) is introduced, optimizing cross-level information fusion and enabling the model to handle object detection at different scales more accurately. Finally, the model is equipped with one detection head and two segmentation heads to achieve efficient multi-task environmental perception, ensuring the simultaneous execution of multiple tasks. The experimental results on the BDD100K dataset demonstrate that the model achieves a mean average precision (mAP50) of 81.4% in object detection, an Intersection over Union (IoU) of 28.9% in lane detection, and a mean Intersection over Union (mIoU) of 92.6% in drivable area segmentation. The tests conducted in real-world scenarios show that the model performs effectively, significantly enhancing environmental perception in autonomous driving and laying a solid foundation for safer and more reliable autonomous driving systems. Full article