Goal-oriented and semantic communication in 6G AI-native networks: The 6G-GOALS approach

Calvanese Strinati, Emilio; Di Lorenzo, Paolo; Sciancalepore, Vincenzo; Aijaz, Adnan; Kountouris, Marios; Gündüz, Deniz; Popovski, Petar; Sana, Mohamed; Stavrou, Photios A. ; et al.
EuCNC & 6G Summit 2024, European Conference on Networks and Communications (EuCNC) and the 6G Summit, 3-6 June 2024, Antwerp, Belgium

Recent advances in AI technologies have notably expanded device intelligence, fostering federation and cooperation among distributed AI agents. These advancements impose new requirements on future 6G mobile network architectures. To meet these demands, it is essential to transcend classical boundaries and integrate communication, computation, control, and intelligence. This paper presents the 6G-GOALS approach
to goal-oriented and semantic communications for AI-Native 6G Networks. The proposed approach incorporates semantic, pragmatic, and goal-oriented communication into AI-native technologies, aiming to facilitate information exchange between intelligent agents in a more relevant, effective, and timely manner, thereby optimizing bandwidth, latency, energy, and electromagnetic field (EMF) radiation. The focus is on distilling data to its most relevant form and terse representation, aligning with the source’s intent or the destination’s objectives and context, or serving a specific goal. 6G-GOALS builds on three fundamental pillars: i) AI-enhanced semantic data representation, sensing, compression, and communication, ii) foundational AI reasoning and causal semantic data representation, contextual relevance, and value for goal-oriented effectiveness, and iii) sustainability enabled by more efficient wireless services. Finally, we illustrate two proof-of-concepts implementing semantic, goal-oriented, and pragmatic communication principles in near-future use cases. Our study covers the project’s vision, methodologies, and potential impact.

DOI
Type:
Conference
City:
Antwerp
Date:
2024-06-03
Department:
Communication systems
Eurecom Ref:
7604
Copyright:
© 2024 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PERMALINK : https://www.eurecom.fr/publication/7604