[Paper Review] Towards Next Generation of Pedestrian and Connected Vehicle In-the-loop Research: A Digital Twin Co-Simulation Framework

Zijin Wang, Ou Zheng+4 more|arXiv (Cornell University)|Dec 8, 2022

Traffic control and management4 citations

TL;DR

This paper proposes a Digital Twin co-simulation framework integrating connected vehicles (CVs) and pedestrians in a physical-digital loop using Carla-SUMO co-simulation and CAVE for immersive testing. It enables real-time, bidirectional data exchange between physical and digital twins, validated through a V2P warning system case study, demonstrating enhanced realism and scalability for next-generation ITS research.

ABSTRACT

Digital Twin is an emerging technology that replicates real-world entities into a digital space. It has attracted increasing attention in the transportation field and many researchers are exploring its future applications in the development of Intelligent Transportation System (ITS) technologies. Connected vehicles (CVs) and pedestrians are among the major traffic participants in ITS. However, the usage of Digital Twin in research involving both CV and pedestrian remains largely unexplored. In this study, a Digital Twin framework for CV and pedestrian in-the-loop simulation is proposed. The proposed framework consists of the physical world, the digital world, and data transmission in between. The features for the entities (CV and pedestrian) that need digital twining are divided into external state and internal state, and the attributes in each state are described. We also demonstrate a sample architecture under the proposed Digital Twin framework, which is based on Carla-Sumo Co-simulation and Cave automatic virtual environment (CAVE). A case study that investigates Vehicle-Pedestrian (V2P) warning system is conducted to validate the effectiveness of the presented architecture. The proposed framework is expected to provide guidance to the future Digital Twin research, and the architecture we build can serve as the testbed for further research and development of ITS applications on CV and pedestrians.

Motivation & Objective

• To address the lack of integrated Digital Twin frameworks for both connected vehicles and pedestrians in intelligent transportation systems.
• To develop a bidirectional data transmission system between physical and digital twins for real-time simulation.
• To create a scalable, immersive testbed for evaluating V2X applications involving pedestrians and connected vehicles.
• To validate the framework through a case study on Vehicle-Pedestrian (V2P) warning systems.
• To provide a foundational architecture for future ITS research involving human-vehicle interactions in digital twin environments.

Proposed method

• The framework establishes a closed-loop system with three components: the physical world, the digital world, and bidirectional data transmission.
• Entities (CVs and pedestrians) are modeled with external states (e.g., position, speed) and internal states (e.g., decision-making logic, behavioral intent).
• The digital twin architecture is implemented using the Carla-SUMO co-simulation platform for traffic and vehicle dynamics simulation.
• Immersive human-in-the-loop testing is enabled via the CAVE (Cave Automatic Virtual Environment) for realistic pedestrian behavior simulation.
• Data synchronization ensures real-time consistency between physical and digital representations during simulation.
• The framework supports dynamic scenario generation and real-time feedback for V2P warning system evaluation.

Experimental results

Research questions

• RQ1 How can a Digital Twin co-simulation framework be designed to simultaneously model connected vehicles and pedestrians in a bidirectional, real-time loop?
• RQ2 What architectural components are necessary to ensure accurate and low-latency data exchange between physical and digital twins of CVs and pedestrians?
• RQ3 How does the integration of CAVE-based immersive environments improve the fidelity of pedestrian behavior modeling in ITS simulations?
• RQ4 To what extent can the proposed framework support the development and validation of V2P warning systems?
• RQ5 What are the key performance and scalability characteristics of the framework in complex, dynamic traffic scenarios?

Key findings

• The proposed Digital Twin framework successfully enables real-time, bidirectional interaction between physical and digital representations of connected vehicles and pedestrians.
• The integration of Carla-SUMO co-simulation with CAVE provides a high-fidelity, immersive environment for human-in-the-loop testing of pedestrian behavior.
• The case study demonstrates that the framework can effectively simulate and evaluate V2P warning systems under realistic traffic conditions.
• The framework supports dynamic scenario generation and real-time data synchronization, enhancing simulation accuracy and responsiveness.
• The architecture is extensible and serves as a viable testbed for future ITS applications involving pedestrians and connected vehicles.