Bridging Generative AI and Robust Control for Autonomous Systems

I am a soon-to-be Master's graduate in Control Systems and Computer Vision from Télécom Physique Strasbourg. My core interest lies in designing predictive architectures that tightly couple visual perception (deep learning) with physical decision-making and robust state estimation.

• Education: Master of Science (MSc) in Engineering, specializing in Control Systems & Computer Vision.
• Current Work: R&D Engineering Intern in Computer Vision & AI. I develop synthetic image generators (Blender/BlenderProc) and implement active learning pipelines (hard example mining) to train state-of-the-art object detection models (YOLO, RF-DETR).
• PhD Objective: Actively seeking a PhD position to research visual generative modeling / latent world models and real-time anomaly detection for autonomous systems or spatial robotics.

• AI & Vision: PyTorch, TensorFlow, Synthetic Data Generation (BlenderProc), Active Learning, YOLO, RF-DETR.
• Control & Robotics: Robust estimators (Kalman Filters), MPC, LQR, Kinematic/Dynamic Modeling, Industrial Robotics (KUKA, FANUC).
• Languages & Tools: Python, C/C++, MATLAB, LabVIEW, Git, LaTeX.

My most recent, advanced computer vision and deep learning projects have been developed within industrial environments (FN Herstal) and are currently under Non-Disclosure Agreements (NDA).

However, you can explore the methodology and results of my work on synthetic data optimization through this validated public study:

• Synthetic Data & Ablation Study Project (featuring my Ablation Study Presentation)

Below, you will find select academic and engineering projects (such as advanced control systems and hardware-in-the-loop interfaces) demonstrating my coding practices, mathematical modeling, and system architecture skills.

Let's connect! Reach me on LinkedIn or via email: [email protected]