Evaluation of autonomous vehicle driving systems for risk assessment based on three-dimensional uncertain linguistic variables

Autonomous vehicle driving systems (AVDSs) have independent decision structures from the users to manage and control the operations of the vehicles both in normal conditions and unexpected situations. Although there are some advantages, such as decreasing accidents reasoned by human errors and efficient energy usage, it is obvious that some risks are rooted in this technology usage. Therefore, it will be beneficial to realize a risk assessment application for autonomous vehicles (AVs) and/or driving systems (DSs) since whose risks are crucial to test and solve. In this paper, a multi-criteria decision making (MCDM) methodology integrating DEcision MAking Trial and Evaluation Laboratory (DEMATEL), Analytical Network Process (ANP), and VlseKriterijuska Optimizacija I Komoromisno Resenje (VIKOR) techniques under spherical fuzzy environment have been suggested to evaluate AVDS alternatives in terms of considered risk criteria. Spherical fuzzy sets (SFS), which are the extension of the ordinary fuzzy sets, have been used to consider the hesitancy of experts and decision-makers as well as uncertainty and impreciseness in the available data. In the application, six AVDS alternatives have been evaluated in terms of seven main criteria and forty sub-criteria. The factors Software Specifications'' and Reliability'' have been determined as the most important main and sub-criteria with the weights 0.193 and 0.066, respectively. Additionally, comparative and sensitivity analyses have been applied to present flexibility, validation and verification of the proposed methodology together with the sensitivity of the given decisions. Based on the application results and conducted analyses, possible implications by views of theoretical, managerial, and policy context have been discussed. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

This paper proposes a study using a multi-criteria decision-making method to evaluate alternative solutions of autonomous vehicle driving systems, taking into account risk criteria. The results of the study indicate that "Software Specifications" and "Reliability" are the most important main and sub-criteria.