Periodic Reporting for period 1 - HERMES (High Efficiency wiReless CMOS transceiver boosted by artificial intelligencE for 6G bandS and beyond)
Reporting period: 2021-09-01 to 2022-08-31
The future of wireless communications will go beyond connecting people or things to connecting smart robots or unmanned vehicles without human intervention. Only sub-THz frequencies can offer the spectrum to achieve unprecedented communication throughput. Yet current technologies suffer from barriers that prevent mass-market operations, such as high cost, limited bandwidth or a power-hungry hardware not compatible with autonomous systems. HERMES proposes the fusion of Artificial Intelligence (AI) and deep sub-micron CMOS technology to open a new generation of wireless transceivers. The HERMES project focuses on sub-THz frequencies between 140 and 160GHz, and will break new ground in the conversion of information from digital to THz using European CMOS technology to develop a highly integrated transceiver. 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. Our ambitious and risky approach goes significantly beyond the SoA: we will demonstrate that the power of AI developed by computer sciences research and associated with an original electronics signal processing technique can push CMOS technology to release outstanding performances. The project will produce a chipset of a low-cost radio that exchanges tens of Gbps and will test it in use cases of unmanned vehicles.
WP1 focuses on adding intelligence to joint wireless communication and spectrum sensing, with a combination on learning algorithms to Walsh signal processing techniques and dealing with system non-idealities. Specifically, an end-to-end deep learning communication model, a.k.a. autoencoder, was proposed to predict the symbols and the Walsh coefficients by taking into account the transmitter, channel and receiver altogether. Its classical counterparts, the signal processing pre-distortion techniques, as well as the learning-based optimization of parts of a communication link are investigated and compared with the end-to-end approach.
WP2 leads the activities around the system study of the transceiver architecture based on Walsh signal processing in the context of Carrier Aggregation Communications. The general framework of the Walsh transform was studied as well as the generic scenarios of interest (D band and sub 15GHz). Then, the approach to apply such an analog signal processing was investigated together with the benefits of doing so, introducing KPI and FoM to quantify those benefits. The Walsh transmitter and receiver are described, modeled, and extensively simulated on the considered scenarios. Finally, different paths for implementation are given with a design perspective.
WP3 designed radiofrequency front-end components (mixer, frequency synthesis, power amplifier, low noise amplifier) at the schematic level. It includes the chosen topologies, schematics and simulation results.
WP4 specified the system defining 3 scenarii and all the requirements for each building blocks. It also drafted the measurements methodlogies and facilities, and the co-integration roadmap of the building blocks.
WP2 leads the activities around the system study of the transceiver architecture based on Walsh signal processing in the context of Carrier Aggregation Communications. The general framework of the Walsh transform was studied as well as the generic scenarios of interest (D band and sub 15GHz). Then, the approach to apply such an analog signal processing was investigated together with the benefits of doing so, introducing KPI and FoM to quantify those benefits. The Walsh transmitter and receiver are described, modeled, and extensively simulated on the considered scenarios. Finally, different paths for implementation are given with a design perspective.
WP3 designed radiofrequency front-end components (mixer, frequency synthesis, power amplifier, low noise amplifier) at the schematic level. It includes the chosen topologies, schematics and simulation results.
WP4 specified the system defining 3 scenarii and all the requirements for each building blocks. It also drafted the measurements methodlogies and facilities, and the co-integration roadmap of the building blocks.
TELECOMMUNICATIONS INDUSTRY: HERMES’s first outcome will be chipsets for the telecommunication industry. The project follows the NEREID roadmap by responding to the needs for new applications from beyond 5G (2025) to 6G evolutions (2030). HERMES goes far beyond 5G technologies, as our solution will be low cost, increase the energy efficiency by tenfold and give access to 10 times larger bandwidths instantaneously. It will evaluate a new frequency band with a focus on >100 GHz, and provide strong technology and engineering support foundations for the low-cost integration of very large, complex and evolvable System of Systems (SoS). Our connectivity will enable the creation of autonomous systems using heterogeneous protocols over heterogeneous hardware capable of sensing, diagnosing, deciding, and actuating in a communicative, collaborative way. We will provide this connectivity from device to backend systems, such as the UxVs sector for video and data backhauling with secured and reliable short-range communication features. Our ambition is to capture the emerging SoS market and benefit from its high growth rate.
ROBOTICS INDUSTRY: The chipset we will create has a direct impact in the robotics industry. Smart robots are designed to carry out various operations without human interference, to learn from their environment and experience, collaborate, and learn from the behavior of humans. HERMES is the essential building block to help smart robots exchange the tens of Gbps of data rate to collaborate. Our target impact is to deliver the connectivity solution for smart robots so the robotics industry can take a leap in R&D capabilities. We target billions of robots’ market.
SECURITY INDUSTRY: HERMES’s hardware achievement will foster new research actions in cognitive radio, broadband communications, signal intelligence, dynamic filtering, spectrum sensing with enhanced detection capabilities in the civilian security, and the safety industry. We expect that large industrial companies will gain interest in extending their research activities to more sophisticated solutions. We predict that HERMES will radically cut costs of the border surveillance missions and search-and-rescue operations with UxVs.
ROBOTICS INDUSTRY: The chipset we will create has a direct impact in the robotics industry. Smart robots are designed to carry out various operations without human interference, to learn from their environment and experience, collaborate, and learn from the behavior of humans. HERMES is the essential building block to help smart robots exchange the tens of Gbps of data rate to collaborate. Our target impact is to deliver the connectivity solution for smart robots so the robotics industry can take a leap in R&D capabilities. We target billions of robots’ market.
SECURITY INDUSTRY: HERMES’s hardware achievement will foster new research actions in cognitive radio, broadband communications, signal intelligence, dynamic filtering, spectrum sensing with enhanced detection capabilities in the civilian security, and the safety industry. We expect that large industrial companies will gain interest in extending their research activities to more sophisticated solutions. We predict that HERMES will radically cut costs of the border surveillance missions and search-and-rescue operations with UxVs.