From Data Mirror to Smart Copilot: A Survey on NextG Semantic Communication for Propelling Digital Twin World into Cognitive Stage
Zhu, Fang Chen, Jiayuan Wen, Junjie Yang, Yuye Yi, Changyan Tie, Yun Zhang, Peng Cai, Jun Niyato, Dusit Guizani, Mohsen
Zhu, Fang
Chen, Jiayuan
Wen, Junjie
Yang, Yuye
Yi, Changyan
Tie, Yun
Zhang, Peng
Cai, Jun
Niyato, Dusit
Guizani, Mohsen
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
The revolution of information technologies is blur-ring the boundary between physical and virtual worlds, with digital twin (DT) at the forefront of this transformation. Mean-while, DT is evolving from offering simple data mirrors to smart copilots, capable of understanding user’s intents and proactively providing profound insights. This ushers in the pivotal cognitive stage of the DT, where humans or embodied artificial intelligence agents (EAIs) can obtain cognitive perceptions within the DT world. Among various issues, in the cognitive stage, establishing strong interactions between the physical and DT worlds is critical. This paper thus explores the Next-Generation Semantic Communication (NextG-SemCom), well-suited for this issue, to fully enable the DT world with human-like cognitive capabilities. NextG-SemCom is envisioned as a cognitive-native paradigm that leverages Large AI Models (LAMs) as its core engine to perform intent understanding, contextual planning, and intent-oriented generative extraction. NextG-SemCom establishes a closed cognitive loop that shifts communication from data-driven to cognitive-driven, thereby not only reducing the traffic overhead, but also achieving cognitive comprehension of the transmitted information. This paper provides the first survey of the NextG-SemCom driven DT world, focusing on the advancement, trend and vision. We start by tracing the evolution of the DT from the initial virtual mapping stage to the current cognitive stage, and detail the distinguishing features of NextG-SemCom. We then present a holistic framework of cognitive interactions in the DT world, analyzing its core components, including the NextG-SemCom codec and network management, along with its design requirements and challenges. Furthermore, we discuss potential applications across a spectrum of human-human, human-EAI, and EAI-EAI interactive scenarios. Finally, we outline future research directions to provide a roadmap and inspire further studies in this promising field.
Citation
F. Zhu, J. Chen, J. Wen, Y. Yang, C. Yi, Y. Tie , et al., "From Data Mirror to Smart Copilot: A Survey on NextG Semantic Communication for Propelling Digital Twin World into Cognitive Stage," IEEE Communications Surveys & Tutorials, vol. 28, no. 99, pp. 1-1, https://doi.org/10.1109/comst.2026.3665395.
Source
IEEE Communications Surveys & Tutorials
Conference
Keywords
46 Information and Computing Sciences, 4606 Distributed Computing and Systems Software, 9 Industry, Innovation and Infrastructure
Subjects
Source
Publisher
IEEE