Driving pattern interpretation based on action phases clustering

TL;DR

This paper tackles driving heterogeneity by proposing an unsupervised framework that converts Action phases into interpretable driving patterns. It introduces a Resampling and Downsampling Method ($RDM$) to standardize phase lengths and an iterative clustering calibration loop that combines Feature Selection, Clustering Analysis, Difference/Similarity Evaluation, and Action phases Re-extraction. Using real-world data from the I80 and US101 datasets, it identifies six patterns in I80 (Catch up, Keep away, Maintain distance) in both Stable and Unstable states, while US101 lacks two patterns, highlighting dataset-dependent heterogeneity. Velocity $v$ emerges as the most informative variable, unstable patterns dominate in size, and cross-dataset comparisons reveal consistent but dataset-specific patterns, supporting the potential of driving-patterns for label-scarcity reduction and enhanced trajectory prediction.

Abstract

Current approaches to identifying driving heterogeneity face challenges in comprehending fundamental patterns from the perspective of underlying driving behavior mechanisms. The concept of Action phases was proposed in our previous work, capturing the diversity of driving characteristics with physical meanings. This study presents a novel framework to further interpret driving patterns by classifying Action phases in an unsupervised manner. In this framework, a Resampling and Downsampling Method (RDM) is first applied to standardize the length of Action phases. Then the clustering calibration procedure including ''Feature Selection'', ''Clustering Analysis'', ''Difference/Similarity Evaluation'', and ''Action phases Re-extraction'' is iteratively applied until all differences among clusters and similarities within clusters reach the pre-determined criteria. Application of the framework using real-world datasets revealed six driving patterns in the I80 dataset, labeled as ''Catch up'', ''Keep away'', and ''Maintain distance'', with both ''Stable'' and ''Unstable'' states. Notably, Unstable patterns are more numerous than Stable ones. ''Maintain distance'' is the most common among Stable patterns. These observations align with the dynamic nature of driving. Two patterns ''Stable keep away'' and ''Unstable catch up'' are missing in the US101 dataset, which is in line with our expectations as this dataset was previously shown to have less heterogeneity. This demonstrates the potential of driving patterns in describing driving heterogeneity. The proposed framework promises advantages in addressing label scarcity in supervised learning and enhancing tasks such as driving behavior modeling and driving trajectory prediction.

Figures (11)

• Figure 1: General framework of driving pattern interpretation.
• Figure 2: Fix Action Phase length with Resampling and Downsampling Method (RDM).
• Figure 3: Distribution of PC1's cumulative contributions
• Figure 4: Dendrogram representations of hierarchical clustering results.
• Figure 5: Dissimilarity Index according to fastDTW - I80 dataset.