Traffic and Safety Rule Compliance of Humans in Diverse Driving Situations

TL;DR

A comparative evaluation of human compliance with traffic and safety rules across multiple trajectory prediction datasets, including Argoverse 2, nuPlan, Lyft, and DeepUrban, aims to provide a comprehensive understanding of each datasets strengths and limitations.

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.

Figures (4)

• Figure 1: Example of an onboard sensor dataset sample from (a) Argoverse2 wilsonArgoverseNextGeneration2023a and (b) drone data DeepUrban deepurban2024.
• Figure 2: (a) TTC calculation where the red vehicle turns left and the blue vehicle follows the lane, using constant acceleration for future trajectory. (b) Visualization of all metrics except TTC in our framework.
• Figure 3: Comparison of distributions of different criteria in datasets.
• Figure 4: Examples of noisy data in Lyft dataset which have wrong heading angle.