Abstract

Autonomous vehicles (AVs) are supposed to make appropriate strategies to ensure driving safety and improve traffic efficiency. However, not all collisions will be avoidable. In a typical dilemma scenario of this paper, we have to make hard decisions from two evils, sparing a child with red-light running behavior or crashing into a well-equipped motorcycle driver without violation of the traffic law. Combined with the existing traffic laws and the accident liability judgment cases in China, 12 typical dilemma scenarios are established. In order to acquire data to analyze the driving decision-making factors involving ethics and legal under the moral dilemma of AVs, we conduct a series of experiments in virtual reality environments. Furthermore, key factors are extracted to characterize the driving decisions under different scenarios and quantified by the gray relation entropy analysis method. Particularly, the ethical factor is represented by the quantity and type of collision targets, the legal factor is qualified by rights of way. The results showed that priority levels of the influencing factors in each moral dilemma were considerably different. Nevertheless, when the quantity of collision targets on two sides is equal, more participants prefer to protect the ones that comply with traffic rules. The research results can provide the basis for designing moral algorithms for the AVs.

Highlights

  • Autonomous vehicles (AVs) have become a hot topic in the field of transportation

  • We identify the traffic accident liability for each scene and integrate ethics and legal into the influencing factors of decision-making

  • The gray relation entropy analysis method is used to deal with the experimental data, and the weight of each factor is calculated quantitatively

Read more

Summary

INTRODUCTION

Autonomous vehicles (AVs) have become a hot topic in the field of transportation. Apart from the above influencing factors, ethics and legal have become another two significant factors affecting decision-making in the moral dilemma [37], [38]. Lin [48] designed the corresponding scenarios to discuss the moral difficulties faced by AVs in possible accidents He discussed how AVs should choose between two evils by changing the type of collision targets, such as wild deer frequently appeared on American highways, pedestrians or motorcycles with different protective equipment, and even a large number of children with redlight running behaviors. It is significant to modify it combined with the Chinese way of thinking and the accident liability judgment system of the Chinese traffic law Derived from these findings, this paper highlights two typical driving decision-making factors in the moral dilemma, ethics and legal.

GRAY RELATION ENTROPY ANALYSIS METHOD
HOMOGENIZATION
CALCULATION OF GRAY RELATION COEFFICIENT
CALCULATION OF GRAY RELATION ENTROPY
CONCLUSION

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.