This research focuses on the design of an intelligent roaming display system based on Mixed Reality (MR). Against the backdrop of the vigorous development of MR technology and the surging demand for innovative display systems across various industries, this study delves deep into the principles and characteristics of MR technology and innovatively constructs the architecture of the intelligent roaming display system. The system encompasses the hardware layer, software layer, and data layer. Through key technologies such as 3D modeling, real-time positioning and tracking, and multi-modal interaction, it realizes core functions including scene roaming, information display, and interactive control. The research indicates that in the future, MR technology will be deeply integrated with artificial intelligence and the Internet of Things, expanding its application fields. However, currently, it still faces challenges such as technical bottlenecks, high costs, and user acceptance. This research provides theoretical and practical support for the development of MR intelligent roaming display systems and is of great significance for promoting technological progress and industrial applications in this field.

Enhan Chen, Qi Zhang, Ning Mao, Jinxiu Li, Guwei Li. Design of an MR-based Intelligent Roaming Display System. Intemational Journal of Frontiers in Engineering Technology(2025), Vol. 7, Issue 2: 56-61. https://doi.org/10.25236/IJFET.2025.070208.

[1] Meta Reality Labs. “Varifocal Display Latency Optimization.” SID Symposium Digest, 54(1), 112-115,2023.

[2] DeepMind. “Reinforcement Learning for Adaptive Fire Scenarios.” Nature Machine Intelligence, 6(7), 732-744,2022.

[3] Chen, T., et al. “EEG-Based Fatigue Detection in Prolonged VR Drills.” IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31, 2304-2313,2023.

[4] Li, H., et al. “Federated Learning Across Fire Departments: Privacy-Preserving Model Sharing.” ACM Transactions on Internet Technology, 24(2), 1-24, 2024.

[5] Floridi, L., et al. “Ethical AI in Emergency Training Simulations.” Science and Engineering Ethics, 29(4), 32,2023.

[6] IBM Quantum. “Quantum Annealing for Fire Evacuation Path Optimization.” npj Quantum Information, 10(1), 88,2024.

[7] Kolb, D.A., et al. “Experiential Learning in VR Firefighting: An Updated Cycle.” Simulation & Gaming, 55(1), 78-102, 20214.

[8] Fernández-Caballero, A., et al. “Thermal Feedback Systems for VR Fire Training.” IEEE Access, 10, 9876-9892,2022.

[9] Tokyo Fire Department. “VR vs Live Fire Training: 3-Year Injury Rate Analysis.” Prehospital Emergency Care, 29(2), 210-219, 20225.

[10] G. Vigueras and J. M. Orduña, “On the use of GPU for accelerating communication-aware mapping techniques,” The Computer Journal, vol. 59, no. 6, pp. 838–847, 2016.