Causality-based Transfer of Driving Scenarios to Unseen Intersections
This work addresses the challenge of data scarcity in scenario-based testing for automated driving, offering a method to reduce reliance on extensive real-world data, though it is incremental in applying causal analysis to a specific domain.
The paper tackles the problem of generating realistic driving scenarios for automated vehicle testing when data is unavailable for certain intersections, by using Bayesian networks to analyze causal dependencies and transfer patterns, achieving successful scenario generation on unseen intersections as validated against recorded data.
Scenario-based testing of automated driving functions has become a promising method to reduce time and cost compared to real-world testing. In scenario-based testing automated functions are evaluated in a set of pre-defined scenarios. These scenarios provide information about vehicle behaviors, environmental conditions, or road characteristics using parameters. To create realistic scenarios, parameters and parameter dependencies have to be fitted utilizing real-world data. However, due to the large variety of intersections and movement constellations found in reality, data may not be available for certain scenarios. This paper proposes a methodology to systematically analyze relations between parameters of scenarios. Bayesian networks are utilized to analyze causal dependencies in order to decrease the amount of required data and to transfer causal patterns creating unseen scenarios. Thereby, infrastructural influences on movement patterns are investigated to generate realistic scenarios on unobserved intersections. For evaluation, scenarios and underlying parameters are extracted from the inD dataset. Movement patterns are estimated, transferred and checked against recorded data from those initially unseen intersections.