Traffic and Safety Rule Compliance of Humans in Diverse Driving Situations

TL;DR

This study evaluates human driving behavior across multiple datasets to understand compliance with traffic rules and identify data quality issues, aiding the development of safer autonomous driving systems.

Contribution

It provides a comparative analysis of human rule adherence in various datasets, highlighting dataset strengths, limitations, and the need for robust data filtering techniques.

Findings

High noise levels in some datasets require filtering

Identification of undesirable driver behaviors in datasets

Insights into dataset suitability for autonomous driving research

Abstract

The increasing interest in autonomous driving systems has highlighted the need for an in-depth analysis of human driving behavior in diverse scenarios. Analyzing human data is crucial for developing autonomous systems that replicate safe driving practices and ensure seamless integration into human-dominated environments. This paper presents a comparative evaluation of human compliance with traffic and safety rules across multiple trajectory prediction datasets, including Argoverse 2, nuPlan, Lyft, and DeepUrban. By defining and leveraging existing safety and behavior-related metrics, such as time to collision, adherence to speed limits, and interactions with other traffic participants, we aim to provide a comprehensive understanding of each datasets strengths and limitations. Our analysis focuses on the distribution of data samples, identifying noise, outliers, and undesirable behaviors exhibited by human drivers in both the training and validation sets. The results underscore the need for applying robust filtering techniques to certain datasets due to high levels of noise and the presence of such undesirable behaviors.