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

Institutions

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
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Safety Assessment Method for Autonomous Driving in Highway Tunnel Scenarios Based on an Improved FRES–VFS Model

Haonan Long, Jia An Niu, Shuangkai Zhu, Rui Su et al.
Journal of Computing in Civil Engineering
Traffic and Road Safety
article

Safety Assessment Method for Autonomous Driving in Highway Tunnel Scenarios Based on an Improved FRES–VFS Model

Haonan Long, Jia An Niu, Shuangkai Zhu, Rui Su, Tao Deng, Bo Liang
article en

Abstract

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.

Journal of Computing in Civil EngineeringVol. 41(2)
Chongqing Jiaotong University (CN)
Traffic and Road Safety
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Safety Assessment Method for Autonomous Driving in Highway Tunnel Scenarios Based on an Improved FRES–VFS Model — Haonan Long, Jia An Niu, et al. · Journal of Computing in Civil Engineering (2026) | TGRS Research Map | TGRS