摘要
为了探求人们对自动驾驶巴士的信任程度,文章从乘客的角度构建了自动驾驶巴士信任度分析模型。首先以自动驾驶巴士潜在用户为研究对象,并提取相关群体特征,综合利用显变量和潜在变量的相关关系,量化分析各个影响因素之间的关系以及对信任度的影响程度;其次对模型的信度进行了检验并计算了模型适配度和各个变量之间的影响标准化系数;最后根据分群研究路径系数对模型结果进行分析。研究结果表明:影响乘客信任度的最主要因素是安全性和便捷性,其中技术安全是影响安全性的主要因素,包括硬件基础设施和软件安全工程。此外,不同群体所选择因素的影响程度也不同,但是在不同群体中安全性对乘客信任度的正向影响都显著存在。研究结论可为制定提升自动驾驶巴士信任度的策略提供依据。
In order to explore people’s trust in autonomous buses,an analysis model of the trust in autonomous buses is built from the perspective of passengers.Firstly,the potential users of autonomous bus are taken as the research object,and the characteristics of relevant groups are extracted,and the relationship between the explicit variables and the latent variables is comprehensively used to analyze the relationship between various influencing factors and the degree of influence on trust.Secondly,the reliability of the model is tested,and the model fitness and the influence standardization coefficient of each variable are calculated.Finally,the model results are analyzed according to the clustering research path coefficient.The research shows that the two most important factors affecting the passenger trust are security and convenience,among which technology security is the main factor,including hardware infrastructure and software security engineering.In addition,the influence degree of factors selected by different groups is also different,but in different groups,the positive influence of safety on passenger trust is significant.The conclusion of the study can provide a basis for the development of strategies to enhance the trust of autonomous bus.
作者
宋臻
彭金栓
孙龄波
张磊
SONG Zhen;PENG Jinshuan;SUN Lingbo;ZHANG Lei(School of Traffic and Transportation, Chongqing Jiaotong University, Chongqing 400074, China)
出处
《合肥工业大学学报(自然科学版)》
CAS
北大核心
2021年第2期236-241,共6页
Journal of Hefei University of Technology:Natural Science
基金
国家自然科学基金资助项目(61503049)
重庆市自然科学基金资助项目(cstc2018jcyjAX0288)
重庆市研究生导师团队建设资助项目(JDDSTD2018007)
关键词
自动驾驶巴士
信任度分析
结构方程模型
群体特征分析
autonomous bus
trust analysis
structural equation model(SEM)
group characteristics analysis