Safety

Towards Automated Air Traffic Safety Assessment Around Non-Towered Airports Using Large Language Models

Darrell, Torsten
Ghazanfari, Mahyar
Kam, Jordan
Alexandre Bayen
Tabrizian, Amin
Wei, Peng
2026

We investigate frameworks for post-flight safety analysis at non-towered airports using large language models (LLMs).

Optimal-Velocity-Based Car-Following Model With Control Lyapunov-Barrier Functions

Yeo, Yuneil
Bonsanto, Pietro
Miti, Masuma Mollika
Maria Laura Delle Monache
2026

This paper develops an optimization-based control framework for a microscopic nonlinear car-following model. The controller is obtained from a Control Lyapunov Function-Control Barrier Function-Quadratic Programming framework that enforces stability, velocity feasibility, and collision-avoidance constraints while minimizing control effort. The resulting controller mitigates the limitations of the spacing-dependent singularity-based car-following models and guarantees closed-loop safety and stability.

Extreme Heat Disproportionately Increases Severe Road Traffic Crashes in High Conflict Settings and Among Vulnerable Road Users in California

Hsu, Cheng-Kai
Quistberg, D. Alex
Pérez-Ferrer, Carolina
Daniel Rodriguez
2026

Emerging evidence suggests that extreme heat elevates road-traffic injuries, undermining international road safety efforts like Vision Zero as global warming intensifies. However, the mechanisms underlying heat-related crashes remain poorly understood, with limited research linking heat exposure to specific crash types that may be driven by heat-induced unsafe road behaviors. Here, we analyzed temperature data and police-reported crash records—including detailed crash scene information—from 177 California cities (2012–2023) using a time-stratified case-crossover design, examining...

Trends in Alcohol-involved Crashes Among Young California Drivers Before, During and After the COVID-19 Pandemic

Lotito, Ainsley
Vaca, Federico E.
Hu, Siwei
Hill, Linda
Julia Griswold
Li, Kaigang
2026

Objectives: To examine changes in alcohol-involved traffic crash rates among young drivers in California during and following the COVID-19 pandemic.
Methods: We conducted a cross-sectional study of alcohol-involved crashes among drivers aged 15–24 using data from the University of California, Berkeley Transportation Injury Mapping System (2016–2024). The primary exposure was COVID-19 policy period (pre-, during-, and post-pandemic). Annual crash rates per 100,000 population were calculated, and Quasi-Poisson regression models estimated rate ratios (RRs) comparing COVID-19 periods,...

Ambient Temperature and Homicide Mortality in 307 Latin American Cities: A Case Time Series Design

Moraes, Sara Lopes de
Daniel Rodriguez
Schinasi, Leah H.
Kephart, Josiah L.
Dronova, Iryna
Bakhtsiyarava, Maryia
Caiaffa, Waleska Teixeira
Rangel-Moreno, Karla
Rodriguez-Villamizar, Laura A.
O’Neill, Marie
de Lima Friche, Amélia Augusta
Herrera López, Astrid Berena
Alazraqui, Marcio
Magalhães, Amanda Silva
Sarmiento, Olga L.
Sanchez, Brisa N.
Gouveia, Nelson
2026

Homicide is a leading cause of death in many countries, and growing evidence suggests that short-term variations in ambient temperature, especially high temperatures, might be associated with higher risk of homicide. Latin America is the most violent region in the world, yet knowledge about the linkages between ambient temperature and homicide mortality in the region remains limited. We conducted a case time series design using conditional quasi-Poisson and distributed lag non-linear models to estimate short-term associations (0-7 lag days) between daily mean temperature and homicide...

Unsupervised Anomaly Detection in Multi-Agent Trajectory Prediction via Transformer-Based Models

Lyu, Qing
Fu, Zhe
Alexandre Bayen
2026

Identifying safety-critical scenarios is essential for autonomous driving, but the rarity of such events makes supervised labeling impractical. Traditional rule-based metrics like Time-to-Collision are too simplistic to capture complex interaction risks, and existing methods lack a systematic way to verify whether statistical anomalies truly reflect physical danger. To address this gap, we propose an unsupervised anomaly detection framework based on a multi-agent Transformer that models normal driving and measures deviations through prediction residuals. A dual evaluation scheme has been...

On the Perceptibility of Safety Systems

Grembek, Offer
Carlos Daganzo
2010

The perceptibility of a safety system is defined as the extent to which the system can be perceived by the senses or the mind. The objective here is to study which safety systems are more easily perceived by the user and to identify design attributes that affect this level of perception. A web-based, pairwise comparison survey was conducted to evaluate the perceptibility of fifteen safety systems ranging from traffic safety systems to consumer safety. The analytic hierarchy process was applied to estimate the perceptibility levels and rank the safety systems. The results show that...

Near Collision and Controllability Analysis of Nonlinear Optimal Velocity Follow-the-Leader Dynamical Model In Traffic Flow

Matin, Hossein Nick Zinat
Maria Laura Delle Monache
2023

This paper examines the optimal velocity follow-the-leader dynamics, a microscopic traffic model, and explores different aspects of the dynamical model, with particular emphasis on collision analysis. More precisely, we present a rigorous boundary-layer analysis of the model which provides a careful understanding of the behavior of the dynamics in trade-off with the singularity of the model at collision.

On the Analytical Properties of a Nonlinear Microscopic Dynamical Model for Connected and Automated Vehicles

Matin, Hossein Nick Zinat
Yeo, Yuneil
Gong, Xiaoqian
Maria Laura Delle Monache
2024

In this letter, we propose an integrated dynamical model of Connected and Automated Vehicles (CAVs) which incorporates CAV technologies and a microscopic car-following model to improve safety, efficiency, and convenience. We rigorously investigate the analytical properties such as well-posedness, maximum principle, perturbation, and stability of the proposed model in some proper functional spaces. Furthermore, we prove that the model is collision-free and derive an explicit lower bound on the distance as a safety measure.

Reinforcement Learning-Based Oscillation Dampening: Scaling Up Single-Agent Reinforcement Learning Algorithms to a 100-Autonomous-Vehicle Highway Field Operational Test

Jang, Kathy
Lichtle, Nathan
Vinitsky, Eugene
Shah, Adit
Bunting, Matthew
Nice, Matthew
Piccoli, Benedetto
Seibold, Benjamin
Work, Daniel B.
Maria Laura Delle Monache
Sprinkle, Jonathan
Lee, Jonathan W.
Alexandre Bayen
2025

In this article, we explore the technical details of the reinforcement learning (RL) algorithms that were deployed in the largest field test of automated vehicles designed to smooth traffic flow in history as of 2023, uncovering the challenges and breakthroughs that come with developing RL controllers for automated vehicles. We delve into the fundamental concepts behind RL algorithms and their application in the context of self-driving cars, discussing the developmental process from simulation to deployment in detail, from designing simulators to reward function shaping. We present the...