Proceeding of the Faculty of technical Sciences, Novi Sad

Selected Research Articles

Vol. 41 No. 10 (2026): Proceedings of the Faculty of Technical Sciences

6G Evolution Towards Connected Intelligent Machines

  • Dejan Vukobratović
DOI:
https://doi.org/10.24867/36WS042610
Submitted
October 15, 2026
Published
2026-10-16

Abstract

The evolution towards 6G raises a fundamental question: will future mobile networks connect machines more efficiently, or will they become an integral part of intelligent systems? This overview paper explores this question through the concept of task-oriented communications, which shifts the focus from faithfully transmitting data towards delivering the information needed to accomplish a task. We illustrate these ideas through two connected-robotics scenarios investigated in our research: semantic communication of 3D point clouds for industrial object recognition, and edge-based robotic localisation and mapping supported by 5G/6G connectivity. These examples highlight how communication, computation and sensing can be designed together to support potentially the fundamental role of 6G technology, that is to connect intelligent machines.

References

  1. [1] M. Ghassemian, A. M. Valenzuela, A. G. Armada, D. Vukobratovic, P. Chatzimisios, K. Althofer, P. R. Venkatesh: "6G Empowering Future Robotics: A Vision for Next-Generation Autonomous Systems," to appear, IEEE Communication Magazine, 2026.
  2. [2] G. Singh, S. Amatare, E. Natalizio, D. Roy: "Realizing the 6G-Enabled Industrial Internet of Robotic Things: Targets, Enablers, and a Case Study," to appear, IEEE Internet of Things Magazine, 2026.
  3. [3] D. Gündüz, Z. Qin, I.E. Aguerri, H.S. Dhillon, Z. Yang, A. Yener, K.K. Wong, C.B. Chae, "Beyond transmitting bits: Context, semantics, and task-oriented communications," IEEE Journal on Selected Areas in Communications, Vol. 41, No. 1, pp. 5-41, 2022.
  4. [4] L. Bariah, M. Debbah: "AI embodiment through 6G: Shaping the future of AGI," IEEE Wireless Communications, Vol. 31, No. 5, pp.174-181, 2024.
  5. [5] A. Antonopoulos, E. Kartsakli, N. Bartzoudis, D. Brodimas, D. Vukobratovic, D. Tsolkas, F. Diego, G. Roumelas, L. Tomaszewski: "AGILE-6G: Agentic AI for autonomous management of 6G network/application services," to appear, IEEE Network, 2026.
  6. [6] https://www.itu.int/en/ITU-R/study-groups/rsg5/rwp5d/imt-2030/pages/default.aspx (Accessed: 30.09.2026)
  7. [7] X. Lin: "An overview of the 3GPP study on artificial intelligence for 5G new radio," arXiv preprint arXiv:2308.05315, 2023.
  8. [8] P. Taksande, S. Kiran, P. Jha, P. Chaporkar: "AI/ML in 3GPP 5G Advanced: Services and Architecture," arXiv:2512.03728, 2026.
  9. [9] C.E. Shannon: "A mathematical theory of communication," The Bell system technical journal, Vol. 27, No. 3, pp.379-423, 1948.
  10. [10] Y. Shi, Y. Zhou, D. Wen, Y. Wu, C. Jiang, K.B. Letaief: "Task-oriented communications for 6G: Vision, principles, and technologies," IEEE Wireless Communications, Vol. 30, No. 3, pp.78-85, 2023.
  11. [11] E. Bourtsoulatze, D.B. Kurka, D. Gündüz: "Deep joint source-channel coding for wireless image transmission," IEEE Transactions on Cognitive Communications and Networking, Vol. 5, No. 3, pp. 567-579, 2023.
  12. [12] V. Ninkovic, D. Vukobratovic, D. Miskovic, M. Zennaro: "COMMSPLIT: A Communication-Aware Split Learning Design for Heterogeneous IoT Platforms," IEEE Internet of Things Journal, Vol. 12, No. 5, pp. 5305-5319, March 2025.
  13. [13] V. Ninkovic, D. Vukobratovic, D. Miskovic, C. Wang: "Adaptive Unequal Error Protection for Semantic Split Learning over Wireless Channels," to appear, IEEE Communication Letters, 2026.
  14. [14] V. Ninkovic, T. Sobot, V. Vincan, G. Gojic, D. Miskovic, D. Vukobratovic: "Task-Oriented Wireless Transmission of 3D Point Clouds: Geometric Versus Semantic Robustness," In 2026 Global 6G Conference (Global 6G), pp. 1-6, Nanjing, China, April 2026.
  15. [15] B. Radovanovic, V. Ninkovic, K. Vidojevic, B. Bajic Papuga, D. Vukobratovic: "A Semantic Communication Approach to Fiducial Marker Processing in 5G-Enabled Edge SLAM," In IEEE CSCN 2026, London, UK, September 2026, arXiv preprint arXiv:2608.09620.