Safety Assessment Method for Autonomous Driving in Highway Tunnel Scenarios Based on an Improved FRES–VFS Model
Highway tunnels present a semiclosed environment with abrupt changes in illumination. Such conditions produce abnormal sensor exposure and limit the applicability of conventional safety assessment methods that rely on manual driving tests or open-road sections. This study proposed a safety assessment method for autonomous driving in highway tunnel scenarios that combines an improved fuzzy rock engineering system (IFRES) with variable fuzzy set (VFS). A fuzzy expert semiquantitative coding method was introduced to address nonlinear, highly uncertain, and coupled causal interactions among indicators. The IFRES model was developed to more robustly determine index weights under extreme conditions by optimizing the reasoning rules and the weight-determination mechanism. A safety assessment index system comprising tunnel physical information and autonomous driving perception information was established. The integration of VFS theory produced a safety assessment model that accounts for fuzziness at level boundaries. Two tunnels in Chongqing were used as empirical case studies. The proposed method identified high-risk sections at tunnel entrances and exits. Assessed risk near the portals exceeded that in middle sections. This spatial pattern aligned with the documented distributions of actual tunnel traffic accidents. Nighttime presented a higher safety risk than daytime. The IFRES-VFS model captured the uncertain causal interactions and feedback mechanisms among indicators. It also effectively distinguished transitional states across risk levels and demonstrated superior dynamic adaptability.
Authors
- Haonan Long (ORCID: https://orcid.org/0009-0009-5864-817X)
- Jia An Niu
- Shuangkai Zhu
- Rui Su
- Tao Deng
- Bo Liang
Institutions
- Chongqing Jiaotong University (CN)
Publication Details
- Journal
- Journal of Computing in Civil Engineering
- Published
- 2026-11-21
- DOI
- https://doi.org/10.1061/jccee5.cpeng-8031
- Primary Topic
- Traffic and Road Safety
- Type
- article
- Field-Weighted Citation Impact
- 0.00