From Optimizable to Interactable: Mixed Digital Twin-Empowered Testing of Vehicle-Infrastructure Cooperation Systems

2026-03-18

AI Summary

This work addresses the limitation of existing Vehicle-Infrastructure Cooperative Systems (VICS) in extreme scenario testing, which predominantly relies on simulation and fails to authentically capture the high uncertainty of complex human behaviors. To overcome this, the paper proposes IMPACT, a Level-5 “interactive” digital twin framework that redefines the conventional Level-4 “optimizable” paradigm by integrating hybrid digital twins with physical-virtual action interaction. This framework establishes a human-in-the-loop closed-loop testing environment where natural human behaviors actively drive the generation of realistic, fused physical-virtual extreme scenarios. Experimental validation on the authors’ self-developed I-VIT interactive VICS testing platform demonstrates that IMPACT efficiently produces high-quality edge cases, enabling safe, controllable, and realistically grounded closed-loop evaluation.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Computer Vision: Low Level & Physics-based Vision

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
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Sufficient testing under corner cases is critical for the long-term operation of vehicle-infrastructure cooperation systems (VICS). However, existing corner-case generation methods are primarily AI-driven, and VICS testing under corner cases is typically limited to simulation. In this paper, we introduce an L5 ''Interactable'' level to the VICS digital twin (VICS-DT) taxonomy, extending beyond the conventional L4 ''Optimizable'' level. We further propose an L5-level VICS testing framework, IMPACT (Interactive Mixed-digital-twin Paradigm for Advanced Cooperative vehicle-infrastructure Testing). By enabling direct human interactions with VICS entities, IMPACT incorporates highly uncertain and unpredictable human behaviors into the testing loop, naturally generating high-quality corner cases that complement AI-based methods. Furthermore, the mixedDT-enabled ''Physical-Virtual Action Interaction'' facilitates safe VICS testing under corner cases, incorporating real-world environments and entities rather than purely in simulation. Finally, we implement IMPACT on the I-VIT (Interactive Vehicle-Infrastructure Testbed), and experiments demonstrate its effectiveness. The experimental videos are available at our project website: https://dongjh20.github.io/IMPACT.

Problem

• corner cases
• vehicle-infrastructure cooperation systems
• digital twin
• human interaction
• testing

Innovation

• Digital Twin
• Vehicle-Infrastructure Cooperation
• Corner Case Generation
• Human-in-the-loop Testing
• Mixed Reality Simulation