This study assessed the feasibility of deploying mobile safety-sign robots to replace human flaggers in highway work zones and determined the optimal Dynamic Message Display (DMD) configurations. The study consisted of two phases. The first phase involved a pilot test on a test road in Yeoju, where the work zone conditions were replicated by following the highway work zone traffic management guidelines. Eight drivers participated in a pilot test. All four driving behavior indicators demonstrated improvements in driving safety under the robotbased scenario compared with the conventional human flagger scenario. The second phase adopted a Virtual Reality (VR)-integrated Driving Simulator (DS) to analyze the driver behavior across various DMD types. Six robot-based scenarios were designed by combining three DMD message types with two display sizes along with one baseline scenario based on existing guidelines for comparison. Twenty drivers participated in this experiment. A rank-based comparative analysis incorporating five evaluation indicators was performed to derive the optimal DMD display type. Scenario 3 (vertical ‘60’ display) and Scenario 6 (horizontal ‘감속60’ display, ‘Reduce speed to 60’ in English) were identified as the optimal DMD display types. These findings establish a foundation for the development of traffic management standards for safety sign robots in highway work zones.

This study investigated the impact of rainfall on the network performance and video transmission quality of smart CCTV systems deployed across 16 bridges over the Han River in Seoul. Using operational logs collected from September 22 to October 6, 2025 (n=254), a comparative analysis was performed between the wired (n=5) and wireless (n=11) network architectures. The results reveal that under rainfall conditions, wireless networks experienced critical performance degradation. Specifically, at a heavy rainfall intensity of 10 mm/h, the average latency (Ping) surged from 22.5 ms to 355.2 ms, while video frame rates (FPS) plummeted from 19.8 to 6.4. Notably, at a maximum rainfall intensity of 15 mm/h, the wireless network performance exhibited a 78.8% degradation compared with clear weather conditions, severely compromising real-time monitoring reliability. Conversely, the wired networks exhibited robustness, maintaining a Ping of approximately 20 ms and an FPS within the 19–20 range, regardless of weather conditions. A significant negative correlation (r = -0.81, p < 0.01) between Ping and FPS was identified, establishing increased network latency as the primary driver of video quality degradation. These findings provide a technical basis for implementing real-time operational thresholds at Ping 40 ms and FPS 15 as leading indicators to ensure surveillance reliability in a smart city infrastructure.

This study evaluated the effects of image preprocessing techniques on detection of Fire Department Connection (FDC) in road view images using a YOLOv8s-based framework. Six preprocessing techniques were applied under identical training and evaluation settings, and their performances were assessed using precision, recall, mAP@50, and mAP@50–95. Geometric correction produced the largest improvement, increasing mAP@50–95 from 0.419 to 0.543 and also improving recall, indicating enhanced localization and detection stability. HSV (Hue, Saturation, Value)-based red restoration achieved the highest average precision among color-based methods, whereas Retinex-based illumination correction degraded the performance across all metrics. Bottom-region cropping improved localization accuracy but reduced recall owing to limited spatial coverage. These results demonstrate that distortion mitigation and selective color enhancement are effective preprocessing strategies for robust FDC detection in road view environments. The study provides practical guidelines for intelligent road asset management, contributing to optimized road network operation and accessibility by reducing emergency vehicle positioning time in complex urban road environments.

The National Highway Traffic Safety Administration (NHTSA) and the California Department of Motor Vehicles (CA DMV) collect and utilize data from traffic accidents caused by Automated Driving Systems (ADS) driving on real roads, as a policy. Leading autonomous driving technology companies such as Tesla and Waymo collect their own driving and accident data and use them for technology advancement. ADS traffic accident data that occur when driving on real roads are valuable for identifying problems in unexpected situations. This study analyzes the risk of traffic accidents by Operational Design Domain (ODD) on ADS traffic accident data that occurred while driving on an actual road and aims to present a road traffic law-based driving ability evaluation scenario in a complex ODD configuration in high-risk situations, wherein an ADS can be particularly vulnerable in mixed traffic situations. The actual road traffic accident data of ADS from 2,289 accidents as provided by the NHTSA were analyzed. Analysis of the characteristics of ADS traffic accidents revealed that accidents occurred mainly on ordinary ODDs with high traffic demand during actual road driving, that is, on dry roads during clear days and daylight. In traffic situations including ADS and Human Driving Vehicle(HDV), approximately 40% of traffic accidents were confirmed to have occurred because of HDV colliding with stationary ADS and occurred in unexpected situations, such as changing the HDV when driving straight ahead of the ADS. Results of analyzing the risk of traffic accidents on the driving status of ADS by ODD, showed that the risk of traffic accidents that occurred while the ADS was driving straight ahead was 2.27, with dry road conditions, sunny weather, and a road speed limit of 21 to 30 mph at night when streetlights were turned on. Thus, the ADS road traffic law-based driving ability evaluation scenario can be used to evaluate whether to recognize and respond to accident risk situations by developing ADS road traffic law-based driving ability evaluation scenarios for situations vulnerable to accidents due to HDV cut-in in traffic situations that include ADS and HDV. In future, this can be used as basic data for preparing related regulations and institutional devices, such as traffic accident investigations and driving ability evaluations by ADS.

Potholes on urban expressways are a critical pavement maintenance problem because they threaten driving safety, generate vehicle-damage claims, and require repeated emergency repairs. However, network-level evidence integrating climate, traffic, maintenance execution, and detection practice remains limited. This study addressed this gap through a stage-1 empirical assessment of pothole occurrence and pavement maintenance response on the Seoul urban expressway network. The novelty lies in integrating six years of operational data, including pothole repair records, compensation cases, monthly rainfall, monthly average temperature, route-level traffic volume, maintenance budget and execution records, detection pathways, and repeated pothole locations. A total of 28,821 pothole repairs were recorded between 2020 and 2025, with Olympic-daero (11,330 cases), Dongbu Trunk Road (6,594 cases), and Gangbyeonbuk-ro (5,067 cases) accounting for approximately 79.8% of the total. The compensation burden was also concentrated, with 158 cases and a total payout of KRW 48,592,000. Pothole occurrence showed a clear dual-season pattern, with high counts during the thawing period and a stronger summer peak, increasing from 1950, 3100, and 3773 cases in June, July, and August when rainfall rose from 174.60 mm to 333.68 mm and 352.15 mm, respectively. Traffic remained consistently high (48,576–96,700 vehicles/day) but varied by only approximately 5.1% annually, indicating that climate governed outbreak timing, while traffic acted mainly as a chronic aggravating factor. Artificial intelligence (AI)-based Camera Detection System (CDS) detection contributed to 54.3% and 57.2% of external detections in 2024 and 2025, respectively, while repeated repairs accounted for 3,957 cases across 783 locations (13.7% of total repairs). These findings support seasonal preventive maintenance, route-based prioritization, AI-assisted detection, and hotspot-focused management.