Formal Safety Guarantees for Autonomous Vehicles using Barrier Certificates

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Barhoumi, Oumaima, Zaki, Mohamed H, Tahar, Sofiène
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917204896776192
author Barhoumi, Oumaima
Zaki, Mohamed H
Tahar, Sofiène
author_facet Barhoumi, Oumaima
Zaki, Mohamed H
Tahar, Sofiène
contents Modern AI technologies enable autonomous vehicles to perceive complex scenes, predict human behavior, and make real-time driving decisions. However, these data-driven components often operate as black boxes, lacking interpretability and rigorous safety guarantees. Autonomous vehicles operate in dynamic, mixed-traffic environments where interactions with human-driven vehicles introduce uncertainty and safety challenges. This work develops a formally verified safety framework for Connected and Autonomous Vehicles (CAVs) that integrates Barrier Certificates (BCs) with interpretable traffic conflict metrics, specifically Time-to-Collision (TTC) as a spatio-temporal safety metric. Safety conditions are verified using Satisfiability Modulo Theories (SMT) solvers, and an adaptive control mechanism ensures vehicles comply with these constraints in real time. Evaluation on real-world highway datasets shows a significant reduction in unsafe interactions, with up to 40\% fewer events where TTC falls below a 3 seconds threshold, and complete elimination of conflicts in some lanes. This approach provides both interpretable and provable safety guarantees, demonstrating a practical and scalable strategy for safe autonomous driving.
format Preprint
id arxiv_https___arxiv_org_abs_2601_09740
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Formal Safety Guarantees for Autonomous Vehicles using Barrier Certificates
Barhoumi, Oumaima
Zaki, Mohamed H
Tahar, Sofiène
Robotics
Artificial Intelligence
Software Engineering
Modern AI technologies enable autonomous vehicles to perceive complex scenes, predict human behavior, and make real-time driving decisions. However, these data-driven components often operate as black boxes, lacking interpretability and rigorous safety guarantees. Autonomous vehicles operate in dynamic, mixed-traffic environments where interactions with human-driven vehicles introduce uncertainty and safety challenges. This work develops a formally verified safety framework for Connected and Autonomous Vehicles (CAVs) that integrates Barrier Certificates (BCs) with interpretable traffic conflict metrics, specifically Time-to-Collision (TTC) as a spatio-temporal safety metric. Safety conditions are verified using Satisfiability Modulo Theories (SMT) solvers, and an adaptive control mechanism ensures vehicles comply with these constraints in real time. Evaluation on real-world highway datasets shows a significant reduction in unsafe interactions, with up to 40\% fewer events where TTC falls below a 3 seconds threshold, and complete elimination of conflicts in some lanes. This approach provides both interpretable and provable safety guarantees, demonstrating a practical and scalable strategy for safe autonomous driving.
title Formal Safety Guarantees for Autonomous Vehicles using Barrier Certificates
topic Robotics
Artificial Intelligence
Software Engineering
url https://arxiv.org/abs/2601.09740