PURPOSES : For autonomous vehicles, abnormal situations, such as sudden changes in driving speed and sudden stops, may occur when they leave the operational design domain. This may adversely affect the overall traffic flow by affecting not only autonomous vehicles but also the driving environment of manual vehicles. Therefore, to minimize the traffic problems and adverse effects that may occur in mixed traffic situations involving manual and autonomous vehicles, an autonomous vehicle driving support system based on traffic operation optimization is required. The main purpose of this study was to build a big-data-classification system by specifying data classification to support the self-driving of Lv.4 autonomous vehicles and matching it with spatio-temporal data. METHODS : The research methodology is explained through a review of related literature, and a traffic management index and big-dataclassification system were built. After collecting and mapping the ITS history traffic information data of an actual Living Lab city, the data were classified using the traffic management indexing method. An AI-based model was used to automatically classify traffic management indices for real-time driving support of Lv.4 autonomous vehicles. RESULTS : By evaluating the AI-based model performance using the test data from the Living Lab city, it was confirmed that the data indexing accuracy was more than 98% for the KNN, Random Forest, LightGBM, and CatBoost algorithms, but not for Logistics Regression. The data were severely unbalanced, and it was necessary to classify very low probability nonconformities; therefore, precision is also important. All four algorithms showed similarly good performances in terms of accuracy. CONCLUSIONS : This paper presents a method for efficient data classification by developing a traffic management index to easily fuse and analyze traffic data collected from various institutions and big data collected from autonomous vehicles. Additionally, EdgeRSU is presented to support the driving of Lv.4 autonomous vehicles in mixed autonomous and manual vehicles traffic situations. Finally, a database was established by classifying data automatically indexed through AI-based models to quickly collect and use data in real-time in large quantities.
운전 시뮬레이션을 통해 3-수준 자율주행 중 차량 전방에 장애물이 출현하는 상황에서 서로 다른 연령대의 운전자 들이 보이는 제어권 전환 반응시간과 상황인식, 그리고 차량통제 수행에서의 차이를 장애물 회피 이전(before the obstacle avoidance: BOA)과 이후(after the obstacle avoidance: AOA) 구간으로 구분하여 분석하였다. 본 연구의 결 과를 요약하면 다음과 같다. 첫째, 실험참가자들의 상황인식은 AOA 구간에 비해 BOA 구간에서, 그리고 청년운전자 집단에 비해 고령운전자 집단에서 더 낮았는데, 이러한 경향은 AOA 구간에 비해 BOA 구간에서 더 뚜렷하였다. 둘째, 제어권 인수 시간은 청년운전자 집단에 비해 고령운전자 집단에서 유의하게 더 느렸다. 셋째, 네 가지 차량통 제 측정치 모두에서 BOA 구간보다는 AOA 구간에서, 그리고 청년운전자 집단보다는 고령운전자 집단에서 더 저하 된 수행이 관찰되었으나 차량통제 수행에서의 연령집단간 차이는 BOA 구간보다는 AOA 구간에서 더 컸다. 이러한 결과는 자율주행 중 제어권을 인수받아 수동으로 운전하여 장애물을 회피하는 상황에서 운전자의 상황인식과 차량 통제는 BOA 구간과 AOA 구간에 따라 달라질 수 있음을 시사한다.
PURPOSES : This study is to develop an comprehensive validation methodology for autonomous mobility-on-demand system with level 4 automated driving system. METHODS : The proposed method includes the quantitative techniques for validating both automated driving system and center system using each optimal indicators. In addition, a novel method for validating the whole system applying multi-criteria decision methodology is suggested. RESULTS : The relative weights for the vehicle system was higher than the center systems. Moreover, the relative weights of failure rate for validating the vehicle system was the highest, in addition to, a relative weight for accuracy of dynamic routing algorithm within center system was the highest. CONCLUSIONS : The proposed methodology will be applicable to validate the autonomous mobility on demand system quantitatively considering the relative weights for each systems.
PURPOSES : An automated driving guidance framework was developed for automated vehicles based on cooperation between infrastructure and automated vehicles. The proposed automated driving guidance framework is assumed to function only when an automated vehicle encounters situations in which it cannot safely pass through without cooperation with the infrastructure.
METHODS : A four-step concept of automated driving guidance levels was employed, and the decision criteria, such as moving object, event, and externality, were defined as the criteria for determining the automated driving guidance level. The judgment criteria of each stage and procedure for determining the autonomous driving guidance level were determined based on successive judgments, and the proposed automated driving guidance framework was designed based on an expert survey. The survey was aimed at experts with experience related to automated driving system research or technology development.
RESULTS : The resulting framework shows the steps and criteria for determining whether automated driving guidance is required under a specific situation and what the guidance should be.
CONCLUSIONS : The proposed automated driving guidance framework is designed to function only when an automated vehicle encounters situations in which it cannot safely pass through without cooperation with the infrastructure.
Background
Our usage of technology and the continuous adoption of technological innovations has implications for our lives that go beyond traditional marketing questions such as product quality, customer satisfaction, and customer loyalty. The psychological consequences of new technology affect our lives and our well-being as individuals. A current technological advancement is the ongoing development of automated driving capabilities. The recent advances have led to the diffusion of semi-autonomous driving systems, such as Teslas autopilot or Daimlers DISTRONIC PLUS. These commercially available technologies correspond to the second level of SAE international’s J3016 standard for automated driving, which ranges from 0 (“No Automation”) to 5 (“Full Automation”, no human needed). SAE level 2 (“Partial Automation”) is defined as “the driving mode-specific execution by one or more driver assistance systems of both steering and acceleration/deceleration using information about the driving environment and with the expectation that the human driver performs all remaining aspects of the dynamic driving.” (SEA On-Road Automated Driving (ORAD) committee, 2014). First of all, qualities of mobility such as safety and comfort influence well-being directly and autonomous driving has a potential impact on these qualities. Furthermore, advances in autonomous driving have particularly social but also ecological and economic benefits. On the one hand, social benefits result from increased social participation by improving mobility of the non-driving, elderly or people with travel-restrictive medical conditions (Harper, Hendrickson, Mangones, & Samaras, 2016; Wadud, MacKenzie, & Leiby, 2016). On the other hand, social benefits result from increasing road safety, less congestions as well as from a reduced number of accidents (Fagnant & Kockelman, 2015). Individual social or personal benefits such as improved safety and comfort or reduced stress levels are also widely perceived by potential users (Bansal, Kockelman, & Singh, 2016; Karlsson & Pettersson, 2015). Additionally, ecological benefits can be realized due to more efficient driving of vehicles and a smoother traffic flow (Wadud et al., 2016). Economic benefits are mainly a result of decreased travel times and of the fact that at high automation levels driving time could be used more productively. Accordingly, this research tends to answer the following research questions:
• How does automated driving impact consumers’ well-being?
• What qualities of mobility (e.g. safety) mediate the impact of automated driving on consumers’ well-being?
Conceptual Model
As argued above, automated driving potentially has both a direct and an indirect (mediated) impact on well-being. Subjective well-being (SWB) describes one’s well-being through the global evaluation of life satisfaction (LS), positive affect (PA), and negative affect (NA) (Diener, 1984). This tripartite concept of well-being has been widely adopted by researchers, even though the relationship of the three aspects remains in question (Busseri & Sadava, 2011). Busseri and Sadava (2011) provide an overview of five prominent conceptualizations: As three separate components, as a hierarchical construct, as a causal system, as a composite, and as configurations of components. We adhere to Diener’s original model that describes LS, PA, and NA as three separate components. Accordingly, the correlations among the three components are not of primary interest in this model. Therefore, the impact of automated driving on LS, PA, and NA is assessed separately in order to provide a full image of SWB. This leads to the following hypotheses:
H1a. Semi-autonomous driving has a positive impact on the level of SWB by increasing positive affect.
H1a. Semi-autonomous driving has a positive impact on the level of SWB by decreasing negative affect.
H1c. Semi-autonomous driving has a positive impact on the level of SWB by increasing life satisfaction.
Driving influences subjective well-being through different mediators. One potential mediating factor, discussed quite controversially in literature, is fun. While non-automated driving shows a higher level of fun than automated driving, still a large majority is fascinated by automated driving (Kyriakidis, Happee, & Winter, 2015) and also a discharge from the actual driving could be perceived as fun. The most relevant perceived benefit of automated driving studied in literature is safety, followed by stress (e.g. Bansal et al., 2016; Karlsson & Pettersson, 2015; Kyriakidis et al., 2015). Therefore, we formulate the following hypotheses:
H2a. The impact of semi-autonomous driving well-being is mediated by fun.
H2b. The impact of semi-autonomous driving well-being is mediated by stress.
H2c. The impact of semi-autonomous driving well-being is mediated by security.
Design/methodology/approach
Our sample comprises of two groups with a total of 259 respondents. Group 1 contains 111 respondents using automated driving while group 2 contains 148 respondents not using automated driving. In a first step, to test hypotheses H1a to H1c, we use ANOVA to analyse the group’s differences regarding positive affect, negative effect, and life satisfaction. We analyse both the aggregated values and the single items for all three aspects of subjective well-being. ANOVA was conducted using SPSS version 25. In a second step, to test hypotheses H2a to H2c, three multiple parallel mediation models were estimated with ordinary least squares path analysis. Each model consisted of one of the aspects of SWB as the dependent variable as well as the three mediators. The models were estimated using PROCESS version 3.0 (Hayes, 2013) and SPSS version 25.
Findings
ANOVA shows a highly significant interaction between semi-automated driving and well-being for negative affect, but not for positive affect and life satisfaction. Looking at the items that amount to positive affect, we see that drivers with the new technology have more excitement, pride and interest. But these effects are counterweighted by significantly less activity, determination and attention. In the context of semi-autonomous driving, being less active, attentive and determined can be interpreted as a positive thing (driving more relaxed). Therefore, we adjust the positive affect scale and remove these three items to from the scale for further analysis. Cronbach’s alpha for all three aspects of subjective well-being is 0.73 or above, thus indicating adequate convergence. Mediation analysis (process model 4) on positive affect reveals a significant indirect effect of semi-automated driving moderated by fun. There is no significant mediation effect for safety and stress as well as no significant direct effect of semi-automated driving on positive affect. The parallel mediation model using negative affect as the dependent variable, shows a significant direct effect of semi-automated driving as well as significant indirect effects mediated by safety and stress. Semi-automated driving reduces negative affect directly as well as by increasing safety, which reduces negative affect. It also reduces negative affect by decreasing stress, which is positively linked to negative affect. Fun, however, has no significant effect on negative affect. Last, life satisfaction shows a combination of the effects mentioned above: Automated-driving has a significant positive direct effect on life satisfaction. Furthermore, life satisfaction is influenced positively through increased fun, safety, and decreased stress.
Implications
ANOVA and mediation analysis show a positive impact of semi-automated driving on subjective well-being, thus contributing to the investigation of new technologies on consumers’ well-being. Using Diener’s tripartite model of subjective well-being, analyses revealed that the positive effect is especially driven by reducing negative affect. Further research is needed to investigate the transformative impact of (semi-) autonomous driving more deeply and broadly. Especially investigations differentiating between target groups of the new technology might be an interesting path to follow, since the impact on the different aspects of SWB might differ (e.g. increase of positive affect for early adopters vs. decrease of negative affect for people with reduced mobility). Furthermore, our investigation contributes to the conceptual discussion about the structure of the tripartite model of subjective well-being. The fact that life satisfaction as a dependent variable, to some extent, combines the effects observed for positive and negative affect indicates that the three aspects are causally linked instead of being separate. Researchers have promoted a system where positive affect and negative affect are conceptualized as inputs to life satisfaction before (Busseri & Sadava, 2011). Last, our findings give directions to marketing executives for marketing new technologies in general and (semi-)automated driving specifically. First, practitioners need to think about the well-being impact of their technology, i.e. evaluate if it increases well-being by increasing positive affect or by decreasing negative affect. The two paths lead to different marketing measures and ways to promote the technology. More specifically, for semi-autonomous driving a mixed strategy commends itself. It is essential to demonstrate that the new technology reduces the pains of driving while being fun at the same time.