ScenarioCharacterization: A Modular Toolkit for Characterizing Safety across Trajectory Datasets
2026-08-17 • Robotics
Robotics
AI summaryⓘ
The authors present ScenarioCharacterization, a tool that automatically analyzes driving data from different sources without needing special adjustments for each one. It works in three steps: first, it converts the data into a common format; second, it extracts important features, checks behaviors, and scores how critical the scenarios are; third, it provides visualizations and analysis tools. The design allows new datasets to be added easily without changing the core analysis parts. The authors demonstrate their tool using popular driving datasets and provide it as open-source software.
trajectory datasetsscenario representationfeature extractionbehavior probingcriticality scoringdataset adaptermodular pipelinedata visualizationopen-sourceWaymo Open Motion
Authors
Ingrid Navarro, Yutong Duan, Jonathan Francis, Jean Oh
Abstract
We introduce ScenarioCharacterization, an open-source framework for automated, dataset-agnostic profiling of driving scenarios in trajectory datasets. Our framework is packaged as a modular, configuration-driven pipeline of three layers: a dataset adapter that maps custom datasets onto an open Scenario representation, a characterizer that performs feature extraction, behavior probing, and criticality scoring at scenario and agent levels, and an analysis layer for scenario visualization and feature, score, and probe analyses. Because the layers communicate only through Pydantic-validated schemas composed via configurations, a new dataset can easily plug in without rewriting the characterization and analysis stack. This technical report describes the design and APIs, shows example outputs on Waymo Open Motion, Argoverse2, and nuPlan, and discusses downstream uses of the approach. The framework is available at https://github.com/navarrs/ScenarioCharacterization.