CITI is hiring two PhD Students

PhD Student – Powering neural network based wake-up radio with radio-frequency energy harvesting

Supervision: Matthieu Gautier and Olivier Berder (IRISA), Guillaume Villemaud and Florin Hutu (CITI)
Keywords: Internet of things, Wake-up radio, Energy harvesting
Location: Shared between Lannion and Lyon (to be discussed)
Candidate skills: Signal processing and electronics are mandatory; backgrounds in digital communication, IoT, microcontroller programming are welcome.
Application: Send CV, marks, and motivation letter to matthieu.gautier@irisa.fr and guillaume.villemaud@insa-lyon.fr

Context:
Internet of Things (IoT) is becoming a reality, impacting daily lives (city, housing, transportation, health, environment) and economic sectors (agriculture, industry). Unlicensed bands (868 MHz, 2.4 GHz) play an important role in this evolution with technologies like LoRa, SigFox, or IEEE 802.15.4. However, energy consumption remains a major bottleneck, with many applications requiring the lifespan of objects to reach several years, even decades, without changing batteries. Many efforts have been deployed to push the boundaries of energy autonomy, but without full success.

The radio transceiver is often the most energy-consuming part of a wireless node, due to both transmitting and receiving phases. Initiating communication requires that both source and destination are awake simultaneously, which can be difficult to plan and often requires penalizing signaling protocols. In short-range multi-hop networks, energy-consuming MAC strategies are implemented to synchronize the source and destination. Low Power Wide Area Networks have solved this issue by using always-on base stations with single-hop communications and a simple ALOHA protocol, but this only works for the uplink. Wake-up receivers are an emerging technology that allows continuous channel monitoring while consuming significantly less power than traditional receivers. These receivers wake up a main transceiver using interrupts only when a specific signal is detected, allowing fully asynchronous communication and a substantial decrease in energy waste. However, most wake-up receivers still rely on low-power microcontrollers that perform signal recognition but consume peak powers higher than 200 μW, preventing IoT nodes from achieving ultimate energy efficiency.

The ANR U-Wake project aims to achieve a breakthrough in the field of IoT by developing a disruptive wake-up receiver solution based on (1) a bioinspired architecture achieved with industrial CMOS technology (with transistors operating in deep sub-threshold regime) and (2) Electro Magnetic energy harvesting. The originality lies in the combination of a Radio Frequency (RF) demodulator with a neuro-inspired detector and data processing through a spiking neural network (SNN), resulting in a complete ultra-low power wake-up radio supplied with a voltage of a few hundred mV.

Objective of the PhD:
The proposed receiver will be activated upon detecting a dedicated off-line learned sequence and implemented in hardware using an ultra-low power SNN. The main advantage of such a design is that it requires a few mW or less for the entire wake-up receiver. Furthermore, it can operate in the 868 MHz or 2.4 GHz bands and recognize various signal types (on-off keying, BPSK, or chirp spread spectrum modulation). Such low consumption opens up the possibility to be powered using RF energy harvesting or Wireless Power Transfer, facilitating a wide range of applications.

This PhD will focus on the energy efficiency of the proposed solution at both hardware and software levels. It will address the global node design, including the RF energy harvesting unit, the integration of neuro-inspired circuits and related wake-up mechanisms, and propose adequate power management policies.