Towards Interactive Autonomous Vehicle Testing: Vehicle-Under-Test-Centered Traffic Simulation

TL;DR

This paper presents VCDI, a Transformer-based traffic simulation model that generates realistic, diverse, and interactive background traffic scenarios centered around the Vehicle Under Test, enhancing autonomous vehicle testing safety and effectiveness.

Contribution

Introduces VCDI, a novel Transformer-based model with a distributional cost function for realistic, diverse, and VUT-centered traffic scenario simulation in autonomous vehicle testing.

Findings

VCDI outperforms state-of-the-art trajectory prediction methods.

VCDI generates diverse, realistic traffic scenarios.

The model enables explainable scenario evolution.

Abstract

The simulation-based testing is essential for safely implementing autonomous vehicles (AV) on roads, necessitating simulated traffic environments that dynamically interact with the Vehicle Under Test (VUT). This study introduces a VUT-Centered environmental Dynamics Inference (VCDI) model for realistic, interactive, and diverse background traffic simulation. Serving the purpose of AV testing, VCDI employs Transformer-based modules in a conditional trajectory inference framework to simulate VUT-centered driving interaction events. First, the VUT future motion is taken as an augmented model input to bridge the action dependence between VUT and background objects. Second, to enrich the scenario diversity, a Gaussian-distributional cost function module is designed to capture the uncertainty of the VUT's strategy, triggering various scenario evolution. Experimental results validate VCDI's trajectory-level simulation precision which outperforms the state-of-the-art trajectory prediction work. The flexibility of the distributional cost function allows VCDI to provide diverse-yet-realistic scenarios for AV testing. We demonstrate such capability by modifying the anticipation to the VUT's cost-based strategy and thus achieve multiple testing scenarios with explainable background traffic evolution. Codes are available at https://github.com/YNYSNL/VCDI.