Analysis on autonomous vehicle detection performance according to various road geometry settings

Abstract

This study investigates the probability of visibility limitation of autonomous driving system sensors under various road geometry conditions. This limited visibility can be a concern for the safety of the transportation system, while it is believed that the reliable autonomous driving system will improve traffic safety based on the enhanced detection and recognition capability of autonomous vehicle sensors. So, this study is conducted with the assumption that inadequate road geometry specifications can negatively affect the reliability of the sensor performance and ultimately increase autonomous vehicle crash risks. First, the study analyzes the forward detection range of an autonomous vehicle’s light detection system and radar sensors, which are affected by road curvature and slope. Second, the forward detection range of an AV is analyzed according to the actual road geometry data of expressways, national highways, and urban roads. The findings of this study emphasizes that even though autonomous vehicle manufacturers claim that their vehicles are equipped with specific automation levels allowing these vehicles to be safely driven on a particular road category, there are certain road sections that will be difficult for autonomous vehicles to traverse because of poor road geometry. Furthermore, by estimating forward detection range relative to actual road geometry data, it is demonstrated that the performance requirement level of autonomous driving systems increases when road geometries are less complex.

Keywords:

• autonomous vehicle
• detection range
• road geometry
• vehicle sensors
• visibility limitation

Acknowledgement

The following statements should be used “Conceptualization, J.S. and J.H.; methodology, J.S. and S.K.; mathematic analysis, S.K. and J.H.; validation, J.S. and S.K.; data curation, J.S. and I.Y.; writing—original draft preparation, J.S. and S.K.; writing—review and editing, J.S. and I.Y.; funding acquisition, J.S. and I.Y. All authors have read and agreed to the published version of the manuscript.” We would like to thank Editage (www.editage.co.kr) for English language editing.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by the Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure and Transport (Grant 22AMDP-C162184-02).