VSRQ: Quantitative Assessment Method for Safety Risk of Vehicle Intelligent Connected System

Tian Zhang, Wenshan Guan, Hao Miao, Quanlong Guan, Zhiquan Liu, Chaonan Wang, Xiujie Huang, Liangda Fang, Zhifei Duan

Abstract: The field of intelligent connectivity in modern vehicles continues to expand, with vehicle functions becoming increasingly complex over time. This expansion has led to numerous vehicle safety issues, which can easily result in safety failures, leading to injuries and deaths. Therefore, it is particularly important to identify high-risk intelligent connected systems in vehicles, as it can inform safety personnel which systems are most susceptible to safety failures, enabling them to conduct more thorough inspections and tests. In this paper, we develop a new model for vehicle intelligent connected system risk assessment by combining Interval Fuzzy Analytic Hierarchy Process (I-FAHP) with Fuzzy Cluster Analysis (FCA), called VSRQ model. We extract crucial indicators related to vehicle safety, utilizing FCA in conjunction with the I-FAHP to identify vulnerable components in the vehicle intelligent connected system. Priority testing is then conducted on these components to mitigate risks and ensure vehicle safety. We evaluate the model on OpenPilot and provide experimental evidence of the VSRQ model's effectiveness in assessing the safety of vehicle intelligent connected systems. Our experiments fully adhere to the ISO 26262 standard, and our model exhibits a higher accuracy rate compared to other models. These results provide a promising new research direction for predicting the safety risks of vehicle intelligent connected systems and provide typical application tasks for VSRQ. The experimental results show that the accuracy rate is 94.36%, and the recall rate is 73.43%, which is at least 14.63% higher than all other known methods.