Digital Twin Logistics

Aims & Scope

The escalating demand for operational efficiency and cost optimization in logistics systems has elevated the necessity for intelligent system upgrades to unprecedented levels. Contemporary logistics ecosystems are witnessing accelerated integration of automated machinery and robotics across core operational nodes including warehousing, sorting, packaging, and transportation. This convergence of human expertise, mechanical automation, and robotic intelligence has given rise to next-generation intelligent logistics systems that prioritize collective system performance over individual component capabilities.

 

Accurate prediction of systemic performance metrics has emerged as a critical prerequisite for optimal system design and operational control. Conventional analytical methodologies demonstrate inherent limitations in addressing the dynamic complexity of these cyber-physical systems. Digital Twin (DT) technology presents a paradigm-shifting solution, enabling bidirectional synchronization between physical logistics infrastructure and their virtual counterparts through real-time data integration and simulation modeling.

 

As an innovative technological framework, digital twins facilitate unprecedented fidelity in virtual system representation, proving particularly valuable throughout the lifecycle of logistics systems - from initial design prototyping and system debugging to continuous operational optimization. Recent years have witnessed exponential growth in Logistics Digital Twin (LDT) research and industrial applications, establishing this domain as a focal point in global technological innovation.

 

This dedicated session aims to present cutting-edge advancements in LDT theory and practice, featuring interdisciplinary research that bridges academic innovation with industrial implementation. Contributions will explore novel methodologies for digital twin development, implementation challenges, and transformative applications in modern logistics ecosystems.

 

The session will focus on the following aspects:

▪ Methodologies of combing logistics system and digital twin.

▪ AI for LDT.

▪ Innovative researches of RDT

▪Advanced application researches of LDT

▪ Performance prediction of logistics system via LDT


------

For session presentation applications, please contact the session chairs below:

Ning Zhao

Email: nickzhao#me.ustb.edu.cn (replace # with @)



Session Chairs

Presentations

  • Professor (Dr.-Ing.)
    Tongji University (China)
    Trusted Data Space for Digitalized Logistics and Supply Chain
    Abstract As global supply chain networks grow increasingly complex and face rising uncertainties, the digital transformation of logistics and supply chains has become a key driver for enhancing enterprise resilience and sustainable competitiveness. At the same time, ensuring data sovereignty, security, and trust in cross-enterprise and cross-regional data collaboration has emerged as a critical challenge for the industry. Trusted Data Spaces (TDS), built upon the International Data Spaces (IDS) reference architecture, are rapidly evolving into essential infrastructure for enabling secure, sovereign, and interoperable data sharing and collaborative innovation.

    This presentation will provide a systematic overview of the application of the Trusted Data Spaces for the Digitalized Logistics and Supply Chain. Drawing on an example of Trusted Data Space for the automotive industry Catena-X, the presentation will highlight how Trusted Data Spaces empowers key use cases such as end-to-end supply chain visibility, multi-party collaborative optimization, green logistics traceability and carbon management, and data-driven intelligent decision-making. Furthermore, the talk will explore in depth how Trusted Data Spaces seamlessly integrate with Digital Twin technologies, enabling the creation of real-time, trusted, and dynamic digital twin models for logistics nodes, logistics processes, and product lifecycle management, thereby driving the evolution of intelligent logistics systems. Last but not least the important results of the national key research project “Transnational Interoperability Rules and Solution Patterns in Collaborative Production Networks based on IDS and GAIA-X” will be presented, which will showcase cutting-edge progress and future trends in the application of Trusted Data Spaces within the global supply chain ecosystem.
  • Assistant Professor
    University of Birmingham (UK)
    Digital Twin-Enabled Forward Environmental Perception System for Enhancing Rail Safety and Operational Capacity
    Abstract Enhancing railway safety and operational efficiency requires an intelligent, real-time monitoring and predictive system. This research presents a Digital Twin-enabled Forward Environmental Perception System, integrating LiDAR, structured light laser, and cameras with Simultaneous Localisation and Mapping to create a dynamic digital representation of the railway environment. By applying deep-learning models and AI-based predictive analytics, the system assesses track intrusion probabilities, enabling proactive risk mitigation. The digital twin framework not only facilitates real-time object detection but also continuously refines railway situational awareness through historical and real-time data fusion. The system has been successfully deployed and tested at BCIMO and a local tram, demonstrating effective predictive safety enhancements and operational optimisation. 
  • Associate Professor
    Southwest Jiaotong University (China)
    Scalable Multi-AMR Material Handling System with Configurable Task Orchestration: From Development to Real-World Testing
    Abstract In this talk, we introduced a scalable multi-AMR collaborative system for heterogeneous material handling, adaptable to diverse operational scenarios. Through integrated technical investigations encompassing systemic functional design, facility planning, process optimization analytics, and intelligent scheduling algorithms, we established a unified framework for system integration and optimization. A prototype demonstration system validates the approach with configurable task templates that decompose workflows into device-level operations, dynamically assign tasks to AMRs and workstations based on real-time spatial constraints (equipment availability, safety distances), generate optimized execution plans, and dispatch sequential commands according to predefined temporal logic. This template-driven architecture enables synchronized multi-equipment coordination, demonstrating a significant efficiency gains over conventional systems in validation trials.
  • Associate Professor
    Wuhan University of Technology (China)
    Mirror the Mind of Crew: Simulation-Based Ship Driving Risk Analysis with Crew's Cognitive Processes in a Human Digital Twin
    Abstract Human Digital Twin (HDT) are digital representations of individuals that seek to revolutionize the practice of human-system integration by directly incorporating human characteristics into system design and performance. It is expected to be adopted in maritime fields and enhance system reliability. However, to date, the exploration of HDT development has paid limited efforts to human cognitive processes. The cognitive process plays a pivotal role in ensuring the safety of shipping operations, as it is closely tied to the decision-making and reliability of the crew on duty. Hence, this study proposes the Cognitive Processes in Human Digital Twin (CogP-HDT) via a model-based approach to fill this research gap. A framework for establishing model-based CogP-HDT in the maritime field is developed. To explicitly capture the dynamic patterns of human cognitive process, we combine the Information, Decision, Action of Crew (IDAC) model and Discrete Dynamic Event Tree (DDET). The human cognitive process is revealed by the events and their associated probabilities at each discrete time step as depicted in a DDET. In addition, a descriptive mapping method is developed to reveal the relations between personnel postural behavior and human performance influencing factors (PIFs). A case study is conducted to illustrate and verify the proposed method using a ship hydrodynamic simulator and crew model under preset scenarios. The results show that the proposed model-based CogP-HDT can quantitatively and dynamically characterize various crew state changes and their response mechanisms.
  • Professor
    University of Science and Technology Beijing (China)
    Modular based flexible digital twin for distribution center
    Abstract Distribution centers are critical nodes connecting logistics networks. Modern distribution centers are hubs where various material handling equipment operates intensively, performing daily operations such as goods receiving, storage, sorting, order consolidation, and shipping. The design and operation of distribution centers still largely rely on human experience. Digital twin technology significantly enhances the ability to reduce this dependence on experience and develop scientific design and operational methodologies. Modular digital twin models have been constructed for equipment such as automated storage and retrieval systems (AS/RS), multi-tier shuttles, sorters, autonomous mobile robots (AMRs), and overhead cranes. This enables the rapid construction of digital twin instances tailored to different distribution centers. Through rapid multi-scenario simulation, understanding of the operational principles of different equipment is enhanced. When business volume increases or decreases, simulation and optimization using future data generate optimized staffing configurations and equipment operation plans.
  • Factory planning & simulation consultant
    Siemens Ltd. China
    Siemens Digital Twin Smart Manufacturing Practice and Insights
    Abstract In the context of rapidly evolving global manufacturing, enterprises are under increasing pressure to enhance flexibility, efficiency, and innovation through digital transformation. Digital twin technology, affirmed as a strategic driver of intelligent manufacturing, has emerged as a key enabler, bridging the physical and digital worlds to optimize decision-making and operational excellence.As a leading advocate of digital twin technology, Siemens has committed to advancing its application and ecosystem in China. This article, based on Siemens' practical cases, thoroughly explores the implementation paths and application effectiveness of digital twin technology in manufacturing enterprises of different scales.

    The report highlights two typical cases: SEWC factory digital talent cultivation and innovation practices as a large-scale manufacturing enterprise, and SMCM new factory's digital transformation practice during relocation as a small and medium-sized enterprise. Through comparative analysis of these two enterprises of different scales, the article elaborates on the flexible adaptability of digital twin technology, demonstrating that digital twin solutions can be reasonably configured according to actual factory needs. The key lies in selecting appropriate application scenarios and focusing on model-driven decision-making. These practical cases showcase how Siemens, as an advocate and practitioner of digital twin technology, advances digital transformation in local Chinese industrial scenarios in a context-specific manner, providing implementable paths and experiential references for manufacturing enterprises.