Generalizable Autonomy
Methods that help intelligent and autonomous systems perceive, reason, and adapt when conditions differ from those seen during training.
About
I’m a Principal Researcher in Artificial Intelligence at ARQUIMEA Research Center, where I lead research on Generalizable Autonomy for intelligent and autonomous systems.
My work focuses on world models, embodied AI, adaptive agents, planning, memory and robot learning, with the goal of building systems that can perceive, reason and adapt beyond their training conditions.
I have around a decade of experience in AI, spanning computer vision, deep learning, robotics and UAVs, and I’m particularly interested in bridging fundamental AI research with real autonomous systems.
Interests
- Generalizable Autonomy
- Embodied AI
- World Models
- Robot Learning
Education
PhD in Artificial Intelligence, 2024
Universidad Politécnica de Madrid
MSc in Artificial Intelligence, 2017
Universidad Politécnica de Madrid
MEng in Research in Systems Engineering and Computer Science, 2016
Universidad de Cádiz
BSc in Computer Science, 2015
Universidad de Cádiz
Research Focus
Building intelligent systems that operate beyond their training conditions.
Embodied & Adaptive AI
World models, adaptive agents, planning, memory, and robot learning for agents that interact with complex environments.
Perception for Autonomous Systems
Computer vision and deep learning for robotics, UAVs, industrial inspection, material understanding, and real-world deployment.
Selected Work
Research directions and applied systems across autonomy, perception, and learning.
Generalizable Autonomy
Leading research on intelligent and autonomous systems that combine world models, planning, memory, adaptation, and robot learning.
World modelsPlanningMemoryRobot learning
ARQUIMEA Research Center Adaptive Learning for Robotic Perception
Weak supervision and adaptive learning methods aimed at reducing data requirements and improving deep-learning systems for real-world robotic perception.
Weak supervisionDomain adaptationRobotic perception
View doctoral thesis Autonomous Aerial Robotics
Perception and autonomous-system development for UAV inspection, navigation, trajectory generation, and high-speed search and interception.
Computer visionUAVsMotion planningEmbedded AI
Explore MBZIRC project Visual Material Understanding
Learning-based methods for single-image fabric digitization and material appearance modelling, including reflectance, opacity, and transmittance estimation.
Material captureGenerative modelsSVBSDF
View publication Selected Publications
Peer-reviewed work spanning autonomy, robotic perception, computer vision, and applied machine learning.
Experience
A career connecting fundamental AI research with autonomous and industrial systems.
2024 — Present
ARQUIMEA Research Center
Principal Researcher
Leading the Generalizable Autonomy research line. Previously Project Leader & Postdoctoral Researcher and Postdoctoral Researcher.
Postdoctoral Researcher · May 2024Project Leader · Jun 2025Principal Researcher · Jan 2026
2023 — 2024
SEDDI
Research Scientist
Research on learning-based fabric digitization, generative material modelling, and continuous improvement of the neural-network model behind textura.ai.
2017 — 2023
Computer Vision and Aerial Robotics Group · UPM
Research Scientist
Learning-based computer vision for aerial robotic perception, applied research, industry collaboration, and doctoral work on adaptive learning with weak supervision.
2014 — 2020
Earlier research and engineering roles
Research Assistant at UPM GFMC and Universidad de Cádiz, and Consulting Intern at Altran, working across electron microscopy, GPU computing, multiview vision, and immersive manufacturing systems.
Let’s Connect
Professional conversations about AI research, autonomous systems, and research collaboration.
Connect with me through LinkedIn, or explore my complete research record on Google Scholar and ORCID.