We Connect intelligences
The future of wireless communications will go beyond connecting people or things to connecting smart robots or unmanned vehicles without human intervention. HERMES proposes the fusion of Artificial Intelligence (AI) and deep sub-micron CMOS technology to open a new generation of wireless transceivers. For the first time, HERMES will deliver to the telecommunications industry a disruptive way of designing transceivers, with impact on production of billions of units that can be implemented in any autonomous system to communicate. This new wireless link will be a springboard for an innovation leap in the robotics and the security industry.
|
|
HERMES Consortium
Driving excellence for tomorrow's world
Commissariat à l'énergie atomique et aux énergies (CEA)
Work package leader
|
Université de Bordeaux (UBx)
Lead coordinator - Work package leader
|
Baltijos pažangių technologijų institutas (BPTI)
Work package leader
|
Silicon Austria Labs (SAL)
Work package leader
|
Katholieke Universiteit Leuven (KUL)
Work package leader
|
Intracom Defense S.A. (IDE)
Task leader
|
HERMES overview
HERMES workplan
Collaboration and innovation
WP1: AI for Cognitive Radio and Walsh signal processing for RF signal conditioningLead: KATHOLIEKE UNIVERSITEIT LEUVEN (KUL)
WP1 will achieve nonlinearity compensation for the newly proposed transceiver design, End-to-end wireless communication models for high speed communication and Improve network throughput through interference management and spectrum usage prediction.
End-to-end deep learning communication models. SoA systems are adapted for high bandwidth THz scenarios. Detailed performance profiling is performed. These models are further enhanced assuming imperfect channel knowledge. SoA auto-encoder models are adapted to achieve higher constellations and even multicarrier communication to address the challenges posed by the high bandwidth frequency selective channel. |
|
WP2: Wide band signal converterLead: COMMISSARIAT À L'ÉNERGIE ATOMIQUE ET AUX ÉNERGIES (CEA)
Perform a high-level simulation of the wide band signal converter for sub-10GHz signals with defined specifications (SNR, BER, EVM).
Design the Walsh Sequences building block. Design the VGAs for both Tx and Rx. Design the Walsh Signal Generator. Design the receiver with the N-Path filter and the Walsh Mask Generator. |
|
WP3: Radio-Frequency Front-EndLead: BALTIJOS PAŽANGIŲ TECHNOLOGIJŲ INSTITUTAS (BPTI)
Design the frequency synthesizer to generate the LO signals for the I/Q up-/down conversion for transmitter and receiver covering 141GHz to 164GHz range.
Perform a feasibility study and design up-conversion mixer and down-conversion I/Q mixer components for Tx and Rx stages covering frequencies from 141GHz to 164GHz. Design a wide-band Power stage able to operate from 141GHz to 164GHz. Design an LNA covering the 141GHz to 164GHz range. |
|
WP4: Tx-Rx specifications, co-integration and measurementsLead: SILICON AUSTRIA LABS (SAL)
Specify technical requirements of each building block and their interaction based on the KPI and the achievable performances with the actual technology.
Measurements techniques for THz frequencies. Fabrication followup. Co-integration of heterogeneous devices, ASIC, RFIC, measurements bench management, methodologies and results. |
|
WP5: Dissemination and exploitationLead: BALTIJOS PAŽANGIŲ TECHNOLOGIJŲ INSTITUTAS (BPTI)
Coordinate project dissemination to target audiences with the right timing, format and message.
Plan project sustainability via an exploitation plan and IP strategy. Coordinate project communication. |
|
WP6: Management and advisoryLead: UNIVERSITY OF BORDEAUX (UBX)
Monitor project implementation in line with the Grant Agreement and Consortium Agreement to ensure efficient communication between the partners, the EC, and external experts.
|
|
Project Partners
FVLLMONTI
In the context of the fourth industrial revolution along with unprecedented growing global interdependencies, an innovative, inclusive and sustainable society is a sound European priority. For many people, the way towards inclusive and sustainable daily life goes through a lightweight in-ear device allowing speech-to-speech translation. Today, such IoT devices require internet connectivity which is proven to be energy inefficient.
While machine translation has greatly improved, an embedded lightweight energy-efficient hardware remains elusive because existing solutions based on artificial neural networks (NNs) are computation-intensive and energy-hungry requiring server-based implementations, which also raises data protection and privacy concerns. Today, 2D electronic architectures suffer from "unscalable" interconnects, making it difficult for them to compete with biological neural systems in terms of real-time information-processing capabilities with comparable energy consumption.
See more at: https://fvllmonti.eu/
In the context of the fourth industrial revolution along with unprecedented growing global interdependencies, an innovative, inclusive and sustainable society is a sound European priority. For many people, the way towards inclusive and sustainable daily life goes through a lightweight in-ear device allowing speech-to-speech translation. Today, such IoT devices require internet connectivity which is proven to be energy inefficient.
While machine translation has greatly improved, an embedded lightweight energy-efficient hardware remains elusive because existing solutions based on artificial neural networks (NNs) are computation-intensive and energy-hungry requiring server-based implementations, which also raises data protection and privacy concerns. Today, 2D electronic architectures suffer from "unscalable" interconnects, making it difficult for them to compete with biological neural systems in terms of real-time information-processing capabilities with comparable energy consumption.
See more at: https://fvllmonti.eu/
RADIOSPIN
The goal of RadioSpin is to build a hardware neural network that computes using neural dynamics as in the brain, has a deep layered architecture as in the neocortex, but runs and learns faster, by seven orders of magnitude. For this purpose, we will use ultrafast radio-frequency (RF) oscillators to imitate the rich, reconfigurable dynamics of biological neurons. Within the RadioSpin project, we will develop a new breed of nanosynapses, based on spintronics technology, that directly process the RF signals sent by neurons and interconnects them layer-wise.
See more at: https://www.radiospin.eu
The goal of RadioSpin is to build a hardware neural network that computes using neural dynamics as in the brain, has a deep layered architecture as in the neocortex, but runs and learns faster, by seven orders of magnitude. For this purpose, we will use ultrafast radio-frequency (RF) oscillators to imitate the rich, reconfigurable dynamics of biological neurons. Within the RadioSpin project, we will develop a new breed of nanosynapses, based on spintronics technology, that directly process the RF signals sent by neurons and interconnects them layer-wise.
See more at: https://www.radiospin.eu
WiPLASH
The WiPLASH project aims to pioneer an on-chip wireless communication plane able to provide architectural plasticity, reconfigurability and adaptation to the application requirements with near-ASIC efficiency but without loss of generality. The WiPLASH consortium will provide solid experimental foundations of the key enablers of on-chip wireless communication at the functional unit level as well as their technological and architectural integration.
See more at: https://www.wiplash.eu/
The WiPLASH project aims to pioneer an on-chip wireless communication plane able to provide architectural plasticity, reconfigurability and adaptation to the application requirements with near-ASIC efficiency but without loss of generality. The WiPLASH consortium will provide solid experimental foundations of the key enablers of on-chip wireless communication at the functional unit level as well as their technological and architectural integration.
See more at: https://www.wiplash.eu/
