Safety

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...

Second-Order Time to Collision With Non-Static Acceleration

Matin, Hossein Nick Zinat
Yeo, Yuneil
Ngo, Amelie Ju-Kang
Paiva, Antonio R.
Utke, Jean
Maria Laura Delle Monache
2025

We propose a second-order time to collision (TTC) considering non-static acceleration and turning with realistic assumptions. This is equivalent to considering that the steering wheel is held at a fixed angle with constant pressure on the gas or brake pedal and matches the well-known bicycle model. Past works that use acceleration to compute TTC consider only longitudinally aligned acceleration. We additionally develop and present the Second-Order Time-to-Collision Algorithm using Region-based search (STAR) to efficiently compute the proposed second-order TTC and overcome the current...

Modeling, Monitoring, and Controlling Road Traffic Using Vehicles to Sense and Act

Maria Laura Delle Monache
McQuade, Sean T.
Matin, Hossein Nick Zinat
Gloudemans, Derek A.
Wang, Yanbing
Gunter, George L.
Alexandre Bayen
Lee, Jonathan W.
Piccoli, Benedetto
Seibold, Benjamin
Sprinkle, Jonathan M.
Work, Daniel B.
2025

This review offers a comprehensive overview of current traffic modeling, estimation, and control methods, along with resulting field experiments. It highlights key developments and future directions in leveraging technological advancements to improve traffic management and safety. The focus is on macroscopic, microscopic, and micro-macro models, as well as state-of-the-art control techniques and estimation methods for deploying vehicles in traffic field experiments.

Dynamic Risk Assessment for Autonomous Vehicles from Spatio-temporal Probabilistic Occupancy Heatmaps

Wang, Han
Yeo, Yuneil
Paiva, Antonio R.
Goodman, Jack P.
Utke, Jean
Maria Laura Delle Monache
2025

Accurately assessing collision risk in dynamic traffic scenarios is a crucial requirement for trajectory planning in autonomous vehicles (AVs) and enables a comprehensive safety evaluation of automated driving systems. To that end, this paper presents a novel probabilistic occupancy risk assessment (PORA) metric. It uses spatiotemporal heatmaps as probabilistic occupancy predictions of surrounding traffic participants and estimates the risk of a collision along an AV’s planned trajectory based on potential vehicle interactions. The use of probabilistic occupancy allows PORA to account for...

A Method for Design and Specification of Longitudinal Controllers for Vehicle Automation

Godbole, Datta N.
Raja Sengupta
1998

Within the context of advanced vehicle control systems, the authors present a general methodology for the design and evaluation of vehicle safety systems. The safety of a vehicle automation system is characterized by the operating region and capabilities of the controller, and the disturbance generating capabilities of the traffic and roadway. The authors illustrate the methodology with reference to a vehicle following scenario. Different information structures are compared by analyzing their effect on safety and system capacity

Capacity Analysis of Traffic Flow Over a Single-Lane Automated Highway System⋆

Michael, James B
Godbole, Datta N
Lygeros, John
Raja Sengupta
1998

We calculate bounds on per-lane Automated Highway System (AHS) capacity as a function of vehicle capabilities and control system information structure. We assume that the AHS lane is dedicated for use by fully automated vehicles. Capacity is constrained by the minimum inter-vehicle separation necessary for safe operation. A methodology for deriving the safe minimum inter-vehicle separation for a particular safety criterion is presented. The inter-vehicle separation, which depends on the vehicle braking capability, control loop delays and operating speed, is then used to compute site-...