Guillem Ribes Espurz

I am a Robotics Master’s student at the Technical University of Delft with a deep interest in machine learning, computer vision, and autonomous navigation. My recent work has focused on the intersection of language and robotics, specifically exploring how Visual-Language-Action (VLA) models can be enhanced with Large Language Models (LLMs) to solve complex, long-horizon manipulation tasks. I am passionate about leveraging deep learning frameworks like PyTorch to develop intelligent systems that can perceive, understand, and interact with the world.

Through my internships, I have gained hands-on experience in both high-level AI-driven robotics and low-level navigation. I have systematically benchmarked and validated state-of-the-art 3D SLAM and coverage planning algorithms for autonomous robots in challenging real-world environments. My experience extends from implementing robust navigation stacks in ROS2 to conducting research on cutting-edge VLA models like NVIDIA’s GR00T. I am a highly motivated and collaborative engineer, eager to contribute to innovative and transformative projects in the field of robotics.