Multi-Agent Digital Twinning for Collaborative Logistics: Framework and Implementation

TL;DR

This work addresses information-sharing barriers and trust issues in collaborative logistics by proposing a decentralised platform that fuses multi-agent systems with digital twins. It introduces the MACL framework to model stakeholders as BDI agents and demonstrates an integrated testbed consisting of a physical map with robocars and a digital twin dashboard for real-time visibility. The implementation shows a 29.4% reduction in total travel distance through carrier collaboration in a three-carrier scenario, illustrating tangible environmental and efficiency benefits and the platform’s potential to motivate participation. The approach advances digital-twin-based, agent-driven coordination in logistics and lays groundwork for scalable, privacy-preserving collaboration aligned with the Physical Internet concept.

Abstract

Collaborative logistics has been widely recognised as an effective avenue to reduce carbon emissions by enhanced truck utilisation and reduced travel distance. However, stakeholders' participation in collaborations is hindered by information-sharing barriers and the absence of integrated systems. We, thus, in this paper addresses these barriers by investigating an integrated platform that foster collaboration through the integration of agents with digital twins. Specifically, we employ a multi-agent system approach to integrate stakeholders and physical mobile assets in collaborative logistics, representing them as agents. We introduce a loosely-coupled system architecture that facilitates the connection between physical and digital systems, enabling the integration of agents with digital twins. Using this architecture, we implement the platform (or testbed). The resulting testbed, comprising a physical environment and a digital replica, is a digital twin that integrates distributed entities involved in collaborative logistics. The effectiveness of the testbed is demonstrated through a carrier collaboration scenario. This paper is among the earliest few efforts to investigate the integration of agents and digital twin concepts and goes beyond the conceptual discussion of existing studies to the technical implementation of such integration.

Figures (15)

• Figure 1: Illustration of a horizontal collaboration scenario.
• Figure 2: An agent framework for carrier collaboration.
• Figure 3: Agent interaction sequence of the MACL.
• Figure 4: Main conceptual components of the testbed.
• Figure 5: Context diagram of the testbed.