Processing and Analyzing Real-World Driving Data: Insights on Trips, Scenarios, and Human Driving Behaviors

TL;DR

This paper presents a multi-level data processing approach for analyzing extensive real-world driving data, providing insights into trips, scenarios, and human driving behaviors to support vehicle testing and modeling.

Contribution

Developed a novel multi-level analysis method that extracts detailed insights from large-scale driving data, enabling better understanding of driving behaviors and scenarios.

Findings

Trip analysis reveals key properties of real-world trips.

Scenario analysis identifies conditions caused by road events.

Driving analysis characterizes typical human driving behaviors.

Abstract

Analyzing large volumes of real-world driving data is essential for providing meaningful and reliable insights into real-world trips, scenarios, and human driving behaviors. To this end, we developed a multi-level data processing approach that adds new information, segments data, and extracts desired parameters. Leveraging a confidential but extensive dataset (over 1 million km), this approach leads to three levels of in-depth analysis: trip, scenario, and driving. The trip-level analysis explains representative properties observed in real-world trips, while the scenario-level analysis focuses on scenario conditions resulting from road events that reduce vehicle speed. The driving-level analysis identifies the cause of driving regimes for specific situations and characterizes typical human driving behaviors. Such analyses can support the design of both trip- and scenario-based tests, the modeling of human drivers, and the establishment of guidelines for connected and automated vehicles.