Trajectory-to-Action Pipeline (TAP): Automated Scenario Description Extraction for Autonomous Vehicle Behavior Comparison

TL;DR

This paper presents TAP, an automated pipeline that extracts structured scenario descriptions from large trajectory datasets, improving safety analysis and behavior comparison for autonomous vehicles.

Contribution

TAP introduces a rules-based, data-driven method for extracting SDL labels, enhancing scalability and generalization in AV scenario analysis.

Findings

Achieves 30% higher precision than ADE in behavior similarity detection.

Improves 24% over DTW in identifying similar trajectories.

Enables automated detection of unique driving behaviors.

Abstract

Scenario Description Languages (SDLs) provide structured, interpretable embeddings that represent traffic scenarios encountered by autonomous vehicles (AVs), supporting key tasks such as scenario similarity searches and edge case detection for safety analysis. This paper introduces the Trajectory-to-Action Pipeline (TAP), a scalable and automated method for extracting SDL labels from large trajectory datasets. TAP applies a rules-based cross-entropy optimization approach to learn parameters directly from data, enhancing generalization across diverse driving contexts. Using the Waymo Open Motion Dataset (WOMD), TAP achieves 30% greater precision than Average Displacement Error (ADE) and 24% over Dynamic Time Warping (DTW) in identifying behaviorally similar trajectories. Additionally, TAP enables automated detection of unique driving behaviors, streamlining safety evaluation processes for AV testing. This work provides a foundation for scalable scenario-based AV behavior analysis, with potential extensions for integrating multi-agent contexts.