Strengthening the Case for a Bayesian Approach to Car-following Model Calibration and Validation using Probabilistic Programming

Compute and memory constraints have historically prevented traffic simulation software users from fully utilizing the predictive models underlying them. When calibrating car-following models, particularly, accommodations have included 1) using sensitivity analysis to limit the number of parameters to be calibrated, and 2) identifying only one set of parameter values using data collected from multiple car-following instances across multiple drivers. Shortcuts are further motivated by insufficient data set sizes, for which a driver may have too few instances to fully account for the variation in their driving behavior. In this paper, we demonstrate that recent technological advances can enable transportation researchers and engineers to overcome these constraints and produce calibration results that 1) outperform industry standard approaches, and 2) allow for a unique set of parameters to be estimated for each driver in a data set, even given a small amount of data. We propose a novel calibration procedure for car-following models based on Bayesian machine learning and probabilistic programming, and apply it to real-world data from a naturalistic driving study. We also discuss how this combination of mathematical and software tools can offer additional benefits such as more informative model validation and the incorporation of true-to-data uncertainty into simulation traces.

Detecting Work Zones in SHRP 2 NDS Videos Using Deep Learning Based Computer Vision

Naturalistic driving studies seek to perform the observations of human driver behavior in the variety of environmental conditions necessary to analyze, understand and predict that behavior using statistical and physical models. The second Strategic Highway Research Program (SHRP 2) funds a number of transportation safety-related projects including its primary effort, the Naturalistic Driving Study (NDS), and an effort supplementary to the NDS, the Roadway Information Database (RID). This work seeks to expand the range of answerable research questions that researchers might pose to the NDS and RID databases. Specifically, we present the SHRP 2 NDS Video Analytics (SNVA) software application, which extracts information from NDS-instrumented vehicles' forward-facing camera footage and efficiently integrates that information into the RID, tying the video content to geolocations and other trip attributes. Of particular interest to researchers and other stakeholders is the integration of work zone, traffic signal state and weather information. The version of SNVA introduced in this paper focuses on work zone detection, the highest priority. The ability to automate the discovery and cataloging of this information, and to do so quickly, is especially important given the two petabyte (2PB) size of the NDS video data set.