Virtual Roads, Smarter Safety: A Digital Twin Framework for Mixed Autonomous Traffic Safety Analysis

2025-04-24

AI Summary

Active safety analysis in mixed-traffic environments—where autonomous and conventional vehicles coexist—faces significant challenges due to the complexity and heterogeneity of dynamic interactions. Method: This paper proposes a digital twin platform tailored for mixed traffic, featuring an aerial-ground-vehicle collaborative modeling framework. It integrates UAV-mounted LiDAR, OpenStreetMap, and heterogeneous in-vehicle sensor data, enabling high-fidelity 3D road reconstruction via AI-driven semantic segmentation and georeferenced registration. The platform tightly couples CARLA (for microscopic perception simulation), SUMO (for macroscopic traffic flow modeling), and NVIDIA PhysX (for high-fidelity vehicle dynamics). Contribution/Results: The approach significantly improves the fidelity of vehicle dynamic behavior replication in complex mixed-traffic scenarios. It enhances the interpretability and evaluation reliability of active safety strategies under dynamic, heterogeneous conditions, establishing a novel paradigm for active safety validation in mixed-traffic environments.

Technology Category

• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

This paper presents a digital-twin platform for active safety analysis in mixed traffic environments. The platform is built using a multi-modal data-enabled traffic environment constructed from drone-based aerial LiDAR, OpenStreetMap, and vehicle sensor data (e.g., GPS and inclinometer readings). High-resolution 3D road geometries are generated through AI-powered semantic segmentation and georeferencing of aerial LiDAR data. To simulate real-world driving scenarios, the platform integrates the CAR Learning to Act (CARLA) simulator, Simulation of Urban MObility (SUMO) traffic model, and NVIDIA PhysX vehicle dynamics engine. CARLA provides detailed micro-level sensor and perception data, while SUMO manages macro-level traffic flow. NVIDIA PhysX enables accurate modeling of vehicle behaviors under diverse conditions, accounting for mass distribution, tire friction, and center of mass. This integrated system supports high-fidelity simulations that capture the complex interactions between autonomous and conventional vehicles. Experimental results demonstrate the platform's ability to reproduce realistic vehicle dynamics and traffic scenarios, enhancing the analysis of active safety measures. Overall, the proposed framework advances traffic safety research by enabling in-depth, physics-informed evaluation of vehicle behavior in dynamic and heterogeneous traffic environments.

Problem

• Analyzes active safety in mixed autonomous traffic environments
• Integrates multi-modal data for high-fidelity traffic simulations
• Evaluates vehicle behavior in dynamic, heterogeneous traffic conditions

Innovation

• Digital twin platform with multi-modal drone and sensor data
• AI-powered 3D road mapping from aerial LiDAR
• Integrated CARLA-SUMO-PhysX simulation for vehicle dynamics