A Real-Time Safety-Based Optimal Velocity Model

Awad Abdelhalim,Montasir Abbas

doi:10.1109/ojits.2022.3147744

Awad Abdelhalim, Montasir Abbas

Open Access

https://doi.org/10.1109/ojits.2022.3147744

Copy DOI

Abstract

Modeling safety-critical driver behavior at signalized intersections needs to account for the driver’s planned decision process, where a driver executes a plan to avoid collision in multiple time steps. Such a process can be embedded in the Optimal Velocity Model (OVM) that traditionally assumes that drivers base their “mental intention” on a distance gap only. We propose and evaluate a data-driven OVM based on real-time inference of roadside traffic video data. First, we extract vehicle trajectory data from roadside traffic footage through our advanced video processing algorithm (VT-Lane) for a study site in Blacksburg, VA, USA. Vehicles engaged in car-following episodes are then identified within the extracted vehicle trajectories database, and the real-time time-to-collision (TTC) is calculated for all car-following instances. Then, we analyze the driver behavior to predict the shape of the underlying TTC-based desired velocity function. A clustering approach is used to assess car-following behavior heterogeneity and understand the reasons behind outlying driving behaviors at the intersection to design our model accordingly. The results of this assessment show that the calibrated TTC-based OVM can replicate the observed driving behavior by capturing the acceleration pattern with an error 20% lower than the gap distance-based OVM.

Highlights

V EHICLE trajectory tracking is one of the major areas of research in Intelligent Transportation Systems (ITS), and is integral to other ITS applications that include driver behavior and car-following analysis, dynamic signal timing, active traffic management, advanced driver-assistance systems (ADAS), among others
The combination of trajectory tracking and driver behavior analysis is key in identifying risks and conflicts that may lead to crashes, allowing practitioners to proactively implement mitigation measures
We introduced the concept of National Electrical Manufacturers Association (NEMA) phases-based virtual traffic lanes to obtain vehicle turn movement counts and address issues of vehicle identity switching which results from occlusion

Summary

Introduction

V EHICLE trajectory tracking is one of the major areas of research in Intelligent Transportation Systems (ITS), and is integral to other ITS applications that include driver behavior and car-following analysis, dynamic signal timing, active traffic management, advanced driver-assistance systems (ADAS), among others. The combination of trajectory tracking and driver behavior analysis is key in identifying risks and conflicts that may lead to crashes, allowing practitioners to proactively implement mitigation measures. Both the tasks of accurate and efficient vehicle trajectory tracking and driving behavior modeling remain challenging. The GHR model [1] predicts a driver’s acceleration based on the current driver’s speed and the sensed difference in speed and distance from the leading vehicle These models do not account for the driver’s planned decision process, where a driver could perceive an impending danger, and plans to avoid that danger, executes that plan in multiple time steps. This is especially important when modeling safety-critical or close-to-critical situations, when an ego vehicle approaches a vehicle that slows down, forcing the driver of the ego vehicle to start a process of avoidance or adjustment in their speed trajectory

Objectives

Methods

Results

Conclusion