France
With a strong background in robotics and artificial intelligence, I have developed my expertise through a wide range of projects during my master's program in intelligent systems engineering. Key Areas of Expertise: - Autonomous Navigation: Designed algorithms to enhance mobile robot capabilities (Turtlebot). - Path Planning: Implemented Dijkstra and A* algorithms for efficient route optimization. - Computer Vision: Developed advanced models (U-Net, R-CNN) for high-performance image segmentation and object detection. - Machine Learning: Extensive experience with TensorFlow and PyTorch in deep learning applications. Technical Skills: Programming Languages: Python, C++, HTML, CSS, SQL Frameworks & Tools: TensorFlow, PyTorch, ROS (Robot Operating System), Git Focus Areas: Artificial Intelligence, Computer Vision, Autonomous Systems Career Objective: Seeking a challenging role as a Machine Learning Engineer in robotics or related fields, where I can leverage my expertise in AI and autonomous systems to drive innovation and solve complex problems. French Version : Avec une solide formation en robotique et en intelligence artificielle, j’ai développé mon expertise à travers divers projets réalisés durant mon master en ingénierie des systèmes intelligents. Domaines de Compétence : - Navigation autonome : Conception d’algorithmes optimisant les capacités des robots mobiles (Turtlebot). - Planification de trajectoire : Implémentation des algorithmes de Dijkstra et A* pour un routage efficace. - Vision par ordinateur : Développement de modèles avancés (U-Net, R-CNN) pour la détection et la segmentation d’images, avec des performances optimisées. - Apprentissage automatique : Expérience approfondie avec TensorFlow et PyTorch pour la mise en œuvre de modèles de deep learning. Compétences Techniques : Langages de programmation : Python, C++, HTML, CSS, SQL Frameworks & Outils : TensorFlow, PyTorch, ROS (Robot Operating System), Git, Ollama, Docker Domaines d'expertise : Intelligence artificielle, Vision par ordinateur, Systèmes autonomes Objectif Professionnel : Je recherche un poste de Machine Learning Engineer en robotique ou dans un domaine connexe, où je pourrai exploiter mon expertise en intelligence artificielle et en systèmes autonomes pour innover et relever des défis complexes.
- In-depth state of the art on different deep learning crack detection methods. - Design and implementation of initial models based on R-CNN, as well as models based on U-Net, optimizing both performance and efficiency. - Training and performance evaluation of the models, applying advanced image processing techniques to extract crucial data such as crack length and severity. - Design of a robust software solution via PyQt, integrating the models developed into a streamlined pipeline for rapid degradation analysis. - Implementation of multithreading to significantly improve software performance, particularly in data extraction and processing tasks. - Performance optimization: 96% F1-score for R-CNN (+16%), 96% in binary segmentation and 72% in multi-class for U-Net, with minimal number of parameters.
- Studied the prototype of a state-of-the-art, flexible tactile sensor based on liquid spectroscopy. - Developed some convolutional neural networks(CNN) for the classification of touch sensor data and utilized transfer learning with models such as VGG16, ResNet50, and Inception V3, including fine tuning of the models. - Carried out a comparative study of the performance of the different convolutional neural network models and pre-trained models used, analyzing precision, recall and f1-score rates for each model in terms of classification. - Achieved a classification of over 92%, with an f1-score for each model of over 0.90, as well as for the pre-trained models.