Digital Twin-Enabled Adaptive Fleet Management

Developing a human-centred, resilient Digital Twin framework that enables real-time incident-aware scheduling, operator-guided decision making, and robust Autonomous Mobile Robot fleet coordination in smart manufacturing environments.

SAR Setup Overview

Overview

This project introduces a human-centred Digital Twin framework that integrates multi-fidelity models, surrogate optimisation, and high-fidelity simulation to support resilient AMR fleet management in dynamic smart factories. It detects operational disruptions such as robot failures or machine breakdowns and rapidly generates incident-aware schedules while preserving throughput and energy efficiency. A human-in-the-loop decision layer allows operators to review trade-offs, request re-simulation and apply policy-bound overrides, ensuring transparency, governance and Industry 5.0–ready coordination.

Motivation
This project addresses limitations of conventional assembly instructions that rely on static manuals or wearable devices. By projecting guidance directly onto the workspace, SAR reduces cognitive load and improves task flow.
System Architecture
The system integrates computer vision, gesture recognition, and spatial projection to deliver adaptive assembly instructions in real time.
Key Components
Evaluation
User studies compared SAR guidance with conventional instructions. Participants showed reduced completion time and fewer errors.
Key Findings
  • Faster task completion
  • Lower error rate
  • Reduced perceived workload

Related Publications

Louie Webb

Louie Webb

PhD Student

My research interests include distributed robotics, mobile computing and programmable matter.

Bugra Alkan

Bugra Alkan

Senior Lecturer in AI and Robotics

My research interests include distributed robotics, mobile computing and programmable matter.