Hey, I'm 👋
Mohamed Souab
Robotics & embedded AI · M2 Autonomous Mobile Systems @ Paris-Saclay · Paris, France
I build robots that figure things out on their own. Drones that fly without GPS, ground robots that map and find their way, and the embedded software and AI that runs on them. I'm a Master's student in autonomous systems, and this is where I keep the things I'm working on.
I've worked my way up from electronics to autonomous systems: a DUT in industrial computing and automated systems in Kénitra, a Licence in electronics and automatic control in the Paris area, and now a Master's at Paris-Saclay in autonomous mobile systems. That last one is all about how drones, ground robots, and other vehicles sense their surroundings, decide what to do, and act on it without a human in the loop.
That's the direction I want to keep going: robotics, autonomous vehicles, and drones, with applied AI and embedded systems doing the real work. An automation internship at Groupe Bel gave me my first taste of building things that have to run in the real world. The projects below are what I build when I get to pick the problem myself.
This is what I reach for most days:
- ROS 2
- PX4 / MAVLink
- Gazebo
- Python
- C/C++
- PyTorch
- OpenCV
- STM32 / Arduino
- Raspberry Pi
- FPGA / VHDL
- MATLAB / Simulink
- Docker
- Linux
- TIA Portal / WinCC
- 2025 — 2027Master's in EEA — Autonomous Mobile Systems (M2 SAM)Université Paris-Saclay
Control, fault diagnosis, signal and image processing, and embedded computing for autonomous ground and aerial vehicles.
- apr — jun 2024Automation engineering internGroupe Bel
Migrated Siemens S7-300 PLCs to S7-1500 with minimal production downtime, built a real-time maintenance-KPI tracker (OEE, MTBF, MTTR…), and web-based HMIs on Siemens Unified Panels.
- 2024 — 2025Licence in electronics, automation & signal processingUniversité d'Évry Paris-Saclay
- 2022 — 2024DUT in industrial computing & automated systemsEST Kénitra, Université Ibn Tofail
Where I got started with electronics and embedded systems.
A few projects I keep coming back to. Click one for the full write-up.
Autonomous PX4 Drone
A quadrotor that flies missions, navigates without GPS using visual SLAM, and lands itself on a marker. Built on ROS 2, PX4, and a Raspberry Pi mounted on a Holybro X500.
ROS 2 Mobile Robot
A wheeled robot that maps a room in Gazebo as it drives, then navigates to goals on its own. ROS 2 Jazzy with slam_toolbox and Nav2, kept deliberately small.
ML Digital Twin of a Drone
Teaching machine learning models to imitate a quadrotor's flight dynamics. LSTM vs Neural ODE vs XGBoost, trained on flight data collected in simulation through ROS 2.
EdgeSense
Predictive maintenance that runs entirely on the machine it's watching. Unsupervised anomaly detection, a 0–100 health score, and remaining-useful-life estimation, with no cloud and no labeled failures required.
- hello, world — why this site exists 2026-06-12
Want to talk robots and drones, or have a project in mind? Send me a message and I'll get back to you.
say_hello()