VP-AutoTest: A Virtual-Physical Fusion Autonomous Driving Testing Platform

TL;DR

The paper presents VP-AutoTest, a digital twin–based virtual–physical fusion platform that enables comprehensive single- and multi-vehicle autonomous driving testing by integrating diverse physical and virtual elements. It introduces adversarial and parallel-deduction single-vehicle tests, plus V2V and V2I cooperation tests, within a unified spatiotemporal framework, underpinned by credibility self-evaluation. A multidimensional algorithm intelligence evaluation, customizable metrics, and AI-driven diagnostics drive iterative improvements, while a robust credibility assessment compares fusion results with real-world data using DTW, PCA, and multiple metrics. The work demonstrates high-fidelity testing, practical applicability through real-world deployments like OnSite, and directions toward broader scenario coverage, regulatory alignment, and end-to-end validation.

Abstract

The rapid development of autonomous vehicles has led to a surge in testing demand. Traditional testing methods, such as virtual simulation, closed-course, and public road testing, face several challenges, including unrealistic vehicle states, limited testing capabilities, and high costs. These issues have prompted increasing interest in virtual-physical fusion testing. However, despite its potential, virtual-physical fusion testing still faces challenges, such as limited element types, narrow testing scope, and fixed evaluation metrics. To address these challenges, we propose the Virtual-Physical Testing Platform for Autonomous Vehicles (VP-AutoTest), which integrates over ten types of virtual and physical elements, including vehicles, pedestrians, and roadside infrastructure, to replicate the diversity of real-world traffic participants. The platform also supports both single-vehicle interaction and multi-vehicle cooperation testing, employing adversarial testing and parallel deduction to accelerate fault detection and explore algorithmic limits, while OBU and Redis communication enable seamless vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) cooperation across all levels of cooperative automation. Furthermore, VP-AutoTest incorporates a multidimensional evaluation framework and AI-driven expert systems to conduct comprehensive performance assessment and defect diagnosis. Finally, by comparing virtual-physical fusion test results with real-world experiments, the platform performs credibility self-evaluation to ensure both the fidelity and efficiency of autonomous driving testing. Please refer to the website for the full testing functionalities on the autonomous driving public service platform OnSite:https://www.onsite.com.cn.

Figures (14)

• Figure 1: Framework of the virtual-physical fusion testing platform VP-AutoTest.
• Figure 2: Data transmission pipeline of the VP-AutoTest.
• Figure 3: Overview of the connected and automated vehicle setup.
• Figure 4: The implementation schematic diagram of adversarial testing.
• Figure 5: Typical testing cases of adversarial testing.