A Vehicle-in-the-Loop Simulator with AI-Powered Digital Twins for Testing Automated Driving Controllers

2025-07-03

AI Summary

Traditional vehicle-in-the-loop (ViL) testing suffers from excessive physical space requirements, high costs, and significant fidelity gaps between physics-based digital twins and real-world dynamics. To address these limitations, this work proposes a novel ViL paradigm integrating scaled-down physical vehicles with AI-driven digital twins. Methodologically, we replace conventional first-principles modeling with a deep learning–enhanced digital twin, tightly coupled with a 1:5-scale physical testbed and a high-fidelity simulation architecture supporting both filtering-based control benchmarks and formal safety verification. Experimental results demonstrate that the proposed system substantially reduces spatial footprint and operational cost while markedly improving simulation realism and closed-loop test fidelity. It successfully enables rigorous safety validation of autonomous driving controllers. This work establishes an efficient, trustworthy, and scalable testing infrastructure for connected and automated vehicle development.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements

Abstract

Simulators are useful tools for testing automated driving controllers. Vehicle-in-the-loop (ViL) tests and digital twins (DTs) are widely used simulation technologies to facilitate the smooth deployment of controllers to physical vehicles. However, conventional ViL tests rely on full-size vehicles, requiring large space and high expenses. Also, physical-model-based DT suffers from the reality gap caused by modeling imprecision. This paper develops a comprehensive and practical simulator for testing automated driving controllers enhanced by scaled physical cars and AI-powered DT models. The scaled cars allow for saving space and expenses of simulation tests. The AI-powered DT models ensure superior simulation fidelity. Moreover, the simulator integrates well with off-the-shelf software and control algorithms, making it easy to extend. We use a filtered control benchmark with formal safety guarantees to showcase the capability of the simulator in validating automated driving controllers. Experimental studies are performed to showcase the efficacy of the simulator, implying its great potential in validating control solutions for autonomous vehicles and intelligent traffic.

Problem

• Testing automated driving controllers with limited space and cost
• Reducing reality gap in digital twin simulations
• Integrating simulator with existing software and algorithms

Innovation

• AI-powered digital twins enhance simulation fidelity
• Scaled physical cars reduce space and expenses
• Integration with off-the-shelf software ensures extensibility