
RECONNECTION – futuRE COmmunication Networks aNd tEChnologies for Tactile Internet applicatiONs
Main Goal
The project focuses on addressing the unique challenges of enabling ultra-low latency communication for emerging data-intensive applications such as Extended Reality (XR), highly dependable machine-to-machine (M2M), and human-to-machine interaction. These technologies demand near-instantaneous data processing and transmission for the development of real-time interactive systems, capable of delivering remote tactile experiences and merging physical and virtual worlds through AI, Machine Learning, and intelligent networking.
Our objectives include the advancement of use cases in gaming, entertainment, work collaboration, social media, virtual worlds, education, and fitness. Additionally, we aim to bring industry-specific benefits to healthcare, real estate, manufacturing, and critical mission communications.
Scientific goals
-
Facilitate the utilization of 3D data acquisition and analysis techniques, improve performance, reduce technology costs, and provide a better understanding of real-world environments to meet the needs of Time-Insensitive (TI) systems.
-
Enhance existing appearance models of 3D real-world objects to meet the requirements of low computational resources, data compression, object animation through rigging, relighting, and rendering for XR.
-
Develop algorithms for intelligent network state prediction, volumetric spectrum utilization, and transceiver architectures, and demonstrate their practical application.
-
Design and test real-time algorithms for user interactions co-located in both physical and virtual environments.
Posts related to this project
TeliLab members related to this project
Agata Manolova
Antoni Ivanov
Ivaylo Bozhilov
Krasimir Tonchev
Nicole Christoff
Publications related to this project
Outlier Detection in Streaming Data for Telecommunications and Industrial Applications: A Survey
Electronics
On the Way to Holographic-Type Communications: Perspectives and Enabling Technologies
IEEE Access
Deep Learning for Reduced Sampling Spatial 3-D REM Reconstruction
IEEE Open Journal of the Communications Society





