Horizontal Curve Safety Performance Evaluation Based on Naturalistic Vehicle Lane Position Data

Abstract

Performance-based design is a renewed approach for project decision-making to specifically address the purpose and needs of projects by providing design flexibility. Resources to evaluate roadway design based on safety performance are an important need for transportation practitioners. In this study, naturalistic driving study (NDS) data were used to estimate the safety effect of elements that influence driving behavior on rural undivided two-lane horizontal curves. Available data included 3,292 horizontal curves and 150,233 traversals, which required a significant data processing effort to conduct data cleaning and quality assessment. From the safety surrogates evaluated and methods implemented, lane position provided the most consistent and statistically significant results. Centerline and edge line encroachment events were modeled with the negative binomial using traffic volume and curve geometry as the predictor components. Encroachment estimates were associated with observed crashes from state data to convert encroachments to crashes. Predictor variables such as curve radius showed a decreasing trend in predicted crashes as curve radius increased. Similarly, as shoulder or lane width increased, predicted crashes decreased. Crash estimates derived from safety surrogates were used to develop an analytical tool aimed at practitioners for curve design considerations. Data input includes curve radius, shoulder width, lane width, curve length, traffic volume, expected service life, and construction cost. The economic assessment provides a quantitative measure for practitioners to evaluate alternative curve designs by assessing the tradeoffs between safety and costs of implementation.