I’m Fidel Echevarría. I bridge the physics of flight and sensor fusion with modern computer vision and AI.

For over a decade, my work has revolved around a fundamental engineering question: how can an autonomous vehicle reliably perceive its environment, estimate its state in 3D space, and make safe decisions under real-world uncertainty?

I started my career at UAV Navigation developing sensor fusion algorithms (Kalman filtering, attitude & heading estimation), high-fidelity 6-DOF flight simulators, and vision-based navigation solutions for unmanned aerial vehicles operating in GNSS-denied environments. Along the way, I earned my B.Sc. in Aerospace Engineering at Universidad Politécnica de Madrid (UPM), completed Udacity’s Self-Driving Car Engineering Nanodegree, and obtained an M.Sc. in Artificial Intelligence from UNED, researching machine learning methods for aerodynamic coefficient identification from flight data.

At Airbus Defence and Space, I have worked on navigation & sensor architectures for military transport aircraft, R&T projects for GPS-denied visual navigation and inertial sensor error characterization (leading to a 2024 patent on vision-based relative 3D positioning), and end-to-end development of safety-critical Aerial Refueling Boom Systems (ARBS), applying AI/ML to telemetry anomaly detection, photorealistic 3D simulation, and precision relative positioning.

Beyond aerospace, I am a passionate software maker. Over the past few years I have designed and shipped full-stack AI applications, real-time 3D conversational avatars (Three.js, Google Filament, blendshapes), and computer vision accessibility tools. Today, I channel my spare time into open-source engineering like PadelKit — an open-source computer vision framework for sports court calibration, player tracking, and motion analysis — as well as exploring Visual-Inertial Odometry (VIO), SLAM, and Spatial AI.