Valentin Poirot

IoT and Embedded AI/ML Research Scientist - Doctoral Candidate

Kiel University, Germany & Chalmers University of Technology, Sweden

portrait

Summary

Systems Researcher with 5+ years of experience in IoT, low-power wireless communication, and embedded machine learning. I like to design embedded AI/ML and TinyML solutions for constrained platforms using Tensorflow Lite for Microcontrollers and CMSIS-NN. I also build distributed algorithms and network protocols for IEEE 802.15.4, Bluetooth Low Energy and Mesh.
Proficient in Python, C, Tensorflow, and embedded operating systems (Zephyr RTOS, Contiki-NG).
Team-oriented, I supervised 10+ theses and projects during my PhD. Erasmus alumnus, I studied and worked in four countries.
I will defend my PhD in September 2022, looking for my next challenges in embedded AI/ML, IoT, or edge computing.

Projects

Adaptive TinyML: Controlling latency and accuracy trade-offs on the smallest devices

How can we adaptively control the latency-accuracy trade-off on embedded devices with < 100 MHz CPU and < 500 KB RAM?

BlueSeer: AI-Driven Environment Detection via BLE Scans

Environment detection and classification on embedded devices solely from Bluetooth Low Energy advertisement packets.
Paper accepted at DAC 2022.

eAFH: Improved Frequency Hopping for Bluetooth Low Energy

Adaptive channel management for Bluetooth Low Energy and Zephyr OS
Paper under submission

Dimmer: RL-based Adaptive Wireless Communication

Embedded reinforcement learning and self-learned transmission policies to avoid interference in low-power IoT
Published at IEEE ICDCS 2021
[Code], [Paper], [Video]

STARC: Decentralized Coordination at Intersections

Decentralized coordination for connected cars at intersections
Published at the ITCVT Workshop at NOMS 2020
[Code], [Paper]

Wireless Paxos: Low-power Wireless Consensus

Fault-tolerant, network-wide consensus protocol for low-power IoT
Published at EWSN 2019, Best paper runner-up
[Code], [Paper], [Slides]