Search

The demonstration, showcase, and city studies of autonomous vehicles (AVs) provide valuable opportunities for the public to interact with AV. Understanding the relationship between experiencing and intention to use AV is crucial because first-hand experience shapes an individual's initial impressions on autonomous driving. This study investigated the users' intention to use AVs based on extended theory of planned behavior, which incorporated experience satisfaction and trust. The data were collected through a field experiment from 117 respondents who had experienced a SAE Level 4 autonomous minibus in China. The proposed relationships were examined using partial least squares structural equation modelling. A satisfied experience contributes to a higher degree of trust, attitude, subjective norm (SN), and perceived behavioral control (PBC). Excluding SN, results suggest that attitude, PBC, experience satisfaction, and trust, are statistically proven to affect the intention to use AV. Moreover, an examination of individual difference reflects that the impact of experience satisfaction on PBC varies distinctively in male and female group, as well as in less educated and more educated group. Findings show the theoretical contributions and practical implications on the role of initial experience of AV acceptance., (Copyright © 2020 Elsevier Ltd. All rights reserved.)

Traffic accident management is a critical issue for advanced intelligent traffic management. The increasingly abundant crowdsourcing data and floating car data provide new support for improving traffic accident management. This paper investigates the methods to predict the complicated behavior of traffic flow evolution after traffic accidents using crowdsourcing data. Based on the available data source, the traffic condition is divided into four levels by congestion delay index: severely congested, congested, slow moving and uncongested. Four types of accidents are consequently defined based on the occurrence of each level. A hierarchical scheme is designed for identifying the most congested level and sequentially predicting duration of each level. The proposed model is validated using traffic accident data in 2017 from an anonymous source in Beijing, China by embedding three machine learning algorithms, random forest (RF), support vector machine (SVM) and neural network (NN), in the scheme. The results show NN outperforms the other two models when the assessment is conducted in absolute differences. Meanwhile, RF has a slightly better performance than SVM, especially when predicting the short-period congestion of severely congested level at the first time. By continuously updating the traffic condition information, significant improvement in accuracy can be acquired regardless of the exact model used. This study shows that emerging crowdsourcing data can be used in a real-time analysis of traffic accidents and the proposed model is effective to analyze such data., (Copyright © 2020 Elsevier Ltd. All rights reserved.)