In the early stages of the development of autonomous driving technology, autonomous vehicles (AVs) and manually driven vehicles (MVs) will both be present on the roads, and the interaction of AVs and MVs will affect driving safety. This study aims to evaluate driving safety for car-following scenarios involving AVs and MVs on urban roads and to identify the driving safety vulnerability sections for each road. In this study, the AV behavior control algorithm and the urban interrupted road were implemented using SCANeR ^TM , and longitudinal, lateral, and inter-vehicle driving safety indicators were derived. As a result of the analysis, the driving safety of the AV-AV pair was the highest in all safety indicators, and the mixed pair (AV-MV) was safer than the MV-MV pair. The driving safety evaluation index for each analysis section was analyzed by the rate of change. As a result of analysis of variance, the null hypothesis that the section was the same in all mixed pairs of evaluation indicators was rejected. Post hoc analysis shows that the section with the greatest difference from the straight line was selected as a vulnerable area. As a result of the post hoc analysis, the non-signal intersection was analyzed as the most vulnerable area in the case of the mixed pair. Using this, it is possible to select a driving safety vulnerability section when AVs and MVs are mixed on actual urban roads.

To guarantee the right to move for residents in areas where public transportation is insufficient, research is needed to identify vulnerable areas and prepare measures. This paper defines the vulnerable regions of public transportation within various city types in Korea. In order to identify appropriate areas to apply the Demand Responsive Transit (DRT), the regions with vulnerability were compared with a specific city (Yangsan-si) which already the DRT system was successfully adopted. To collect monthly bus data, web-data crawling method was performed and processed with coordinating program by matching GPS coordinate. The public transportation demand was predicted for each grid cell size (100 m, 250 m, and 500 m) by different methodologies. Various data mining models based on regression were analyzed to predict bus demand of vulnerable areas. Among models, a modified model was suggested to combine Automated machine learning models for high prediction performance. The modified model outperformed other methods as 0.685 and prediction performance was appropriate at 100 m rectangle grid. Regional characters of DRT bus allocation areas were extracted by K-means clustering method and differentiate urban and suburban types. The findings of this study provide valuable insights into conditions that DRT bus stop can be installed. The urban bus stop areas located in metropolitan cities and the suburban bus stop allocation areas located in countryside. The study results can be used as policy data for the successful introduction to prevent social exclusion and improve resident welfare in the future.

Public transportation networks are well established in main cities, but there are some inconveniences in using public transportation in some cities. Public transportation is less accessible and walking distance of getting to public transportation is too long in some cities. Compared to other cities, Seoul has a higher satisfaction rate with public transportation. There are many cases, however, where short-distance taxis are used because walking to destinations after using public transportation is inconvenient; instead, Personal mobility (PM) devices can be used for these short-distances trip. This study aims to find the optimal PM service area using GIS(Geographic Information System)-based public transportation big data analyses. Variables were generated by collecting socio-economic factors, public transportation data, and geographic data and Extreme gradient boosting and Random forest, which are representative ensemble methods, were used for evaluation. We divided Seoul into a hexagonal grid and developed the optimal PM location service model by creating hexagonal cell data units and analyzing the areas with the models. We found that residential complexes, parks, and near subway stations (all areas with high foot traffic) are best suited for optimal placement. We also determined deployment should be in lower sloped areas. We expect this work to help determine public transportation stop and shared mobility station locations as well as contribute to public transportation demand surveys and accessibility analyses.

Conflicting driving behaviours between automated vehicles and manually driven vehicles may compromise driving safety. The aim of this study is to analyse the safety of mixed traffic on urban roads. The driving simulation tests were conducted using a multi‐agent driving simulator, which allows real‐time synchronization of multiple simulators. These data were further processed to derive the driving behaviour parameters of manually driven vehicles in VISSIM traffic simulations. Driving safety evaluation indicators included conflict‐related indicators, as well as individual safety indicators. The safety evaluation indicators were normalized through min–max normalization, and the risk scores were summed to evaluate the urban roads. The analysis revealed that driving safety was poor at unsignalized intersections with a market penetration rate of 10% and 50% and at signalized intersections with traffic islands and a market penetration rate of 100%, where conflicts arise from the deceleration of leading vehicles and lane changes. This finding is about the driving behaviour of automated vehicles, which maintain a greater distance from the leading vehicle than manually driven vehicles, resulting in poorer driving safety due to lane changes rather than deceleration. Using the findings of this study, criteria for assessing the safety of mixed traffic situations in existing road infrastructures can be established.

In this study, a novel methodology is proposed to evaluate automated driving safety in mixed traffic environments, including autonomous vehicles (AVs) and manually driven vehicles (MVs). An open-source AV dataset obtained from a real-world autonomous mobility testbed in Korea was used for methodology development and evaluations. The driving behavior was evaluated using well-known promising indicators, including the standard deviation of the vehicle speed, acceleration noise, standard deviation of the lane offset, time to collision (TTC), and deceleration to avoid a crash (DRAC). Min-max and max-min normalization was performed to unify the units of the evaluation indicators. The importance of each driving safety indicator was derived through the Analytical Hierarchy Process (AHP) performed by traffic experts, and the weights were estimated based on the average of the collected importance. The normalized indicators were integrated to obtain the automated driving risk score (ADRS), which is regarded as a measure of automated driving safety. The automated driving safety degraded considerably in road sections where right turns were made at intersections and that had a bus stop. Hazardous driving events of AVs were visualized, which is useful for monitoring mixed traffic safety and developing effective countermeasures for proactive road safety management.