Valentin Poirot

IoT and Embedded ML Researcher - Doctoral Candidate

Kiel University, Germany & Chalmers University of Technology, Sweden

GitHub | Scholar | LinkedIn | CV

portrait

Summary

Systems Researcher with 4+ years of experience in low-power wireless communication for IoT (Bluetooth Low Energy and Mesh, IEEE 802.15.4).
I also design Machine Learning solutions for constrained platforms (Tensorflow Lite for Microcontrollers, CMSIS NN, Tiny ML). Proficient in C, Python, Tensorflow, and embedded operating systems (Zephyr RTOS, Contiki-NG).
Team-oriented, I led 10+ B.Sc/M.Sc theses and projects during my PhD.
Erasmus Mundus alumnus, I studied and worked in four countries.
Final year PhD Candidate, defense target is September 2022.

Projects

Pushing Embedded Deep Learning to its Limits

How can we enable Deep Machine Learning on devices with < 100 MHz CPU and < 200 kB RAM?

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 ‘21
[GitHub] , [Paper]

STARC: Decentralized Coordination at Intersections

Decentralized coordination for connected cars at intersections
Published at IEEE/IFIP NOMS - ITCVT Workshop ‘20
[GitHub] , [Paper]

Wireless Paxos: Low-power Wireless Consensus

Fault-tolerant, network-wide consensus protocol for low-power IoT
Published at EWSN ‘19, Best paper runner-up
[GitHub] , [Paper]

Selected Publications

Dimmer: Self-Adaptive Network-Wide Flooding with Reinforcement Learning, Valentin Poirot, Olaf Landsiedel, In the Proceedings of the IEEE International Conference on Distributed Computing Systems (ICDCS), Jul. 2021, [PDF]
Coordination and Self-Adaptive Communication Primitives for Low-Power Wireless Networks, Valentin Poirot, Licentiate Thesis, Sep. 2020 [PDF]
STARC: Low-power Decentralized Coordination Primitive for Vehicular Ad-hoc Networks, Patrick Rathje, Valentin Poirot, Olaf Landsiedel, In the proceedings of the 2020 IEEE/IFIP Network Operations and Management Symposium (NOMS), Apr. 2020 [PDF]
Energy efficient multi-connectivity algorithms for ultra-dense 5G networks, Valentin Poirot, Mårten Ericson, Mats Nordberg, Karl Andersson, In Wireless networks, Springer, 2020 [PDF]
Paxos Made Wireless: Consensus in the Air, Valentin Poirot, Beshr Al Nahas, Olaf Landsiedel, In the Proceedings of the International Conference on Embedded Wireless Systems and Networks (EWSN), Feb. 2019, (Best Paper Runner-Up) [PDF]