centric-open-source-repositories-for-ml-community

CENTRIC Open-Source Repositories

The CENTRIC project provides open datasets and training environments to support researchers and developers exploring emerging ML techniques in wireless communications.

Aiming to enable sustainable user-centric 6G networks with an AI-native Air Interface, the project adopts a modular, AI-driven approach to wireless connectivity. By prioritizing users’ communication needs and environmental constraints, CENTRIC advances ML applications across physical and MAC networking layers. This effort has resulted in several open-source repositories and datasets, enabling the research community to utilize CENTRIC’s findings and validate new solutions.

CENTRIC in key numbers

What is CENTRIC?

CENTRIC is a co-funded R&D&I European project that proposes leveraging AI techniques through a top-down, modular approach to wireless connectivity that puts the users’ communication needs and environmental constraints at the centre of the network stack design. AI techniques will be used to create and customize tailor-made waveforms, transceivers, signalling, protocols and RRM procedures to support these requirements. This is the user-centric AI Air Interface (AI-AI) that CENTRIC will enable.

The results of CENTRIC will be validated and demonstrated in laboratory prototypes. Its breakthroughs will enable future 6G use cases, such as self-driving vehicles, the internet of nano bio-things, or multi-sensory holographic communications.

centric-flyer-featured-image-post-news
CENTRIC flyer

Latest News

NOKIA Separate Training Framework for AIML-based CSI Compression

NOKIA Separate Training Framework for AIML-based CSI Compression Channel State Information (CSI) acquisition at the Base Station (BS) received from each User Equipment (UE) is critical to sweep its beam towards the corresponding UE accurately. However, transmitting uncompressed CSI in limited-rate feedback channels is impossible due to the significant signalling...
Read More

Safe Model Predictive Control via Reliable Time-Series Forecasting

The control of dynamical systems is the backbone of modern technologies, ranging from industrial processes to autonomous vehicles. In many of these scenarios, systems must be controlled while satisfying a set of safety and reliability constraints concerning the unknown evolution of a target process. In our recent work, we proposed...
Read More

Adaptive Non-Uniform Quantization for CSI Compression

AIML-based Channel State Information (CSI) compression that uses autoencoders to lower the overhead of feedback on the MIMO channel information from the UE to the NW has been an active study in 3GPP RAN1 Release-18. One of the discussion topics for the CSI compression is on the quantization of the...
Read More

CENTRIC participated at the FUSECO Forum 2023 in Berlin

Our progressAnastasius Gavras from Eurescom and member of the CENTRIC management team, participated at the FUSECO Forum on 14-15 September 2023 in Berlin. In the session “Beyond 5G and 6G Network Technologies and Enablers: RAN, Core Network, Edge Computing, Network Management and AI”, he presented a brief overview of the...
Read More

LinkedIn Feed

centric-newsletter-banner-hp-format

Subscribe to our newsletter

The CENTRIC project will use the information you provide on this form to send you regular emails about our results, relevant news and activities. You can change your mind at any time by clicking the “unsubscribe” link, available in the footer of any email you receive from us, or by contacting us at contact@centric-sns.eu. We will always treat your information with respect.