Kerox Technology is a spin-off of the Technical University of Madrid focused on AI research.- Partnering with Airbus Defence & Space and Airbus Operations to explore cutting-edge AI applications in the aerospace sector. Expertise includes Reinforcement Learning, Computer Vision, Time Series Modeling, and Surrogate Modeling.- Building innovative LLM-based solutions for diverse use cases over different industries and clients.

Working on Reinforcement Learning for Autonomous Navigation, Motion Planning and Control

- Developed and implemented machine learning algorithms for time-series forecasting to predict future trends and patterns.- Conducted unsupervised learning techniques to identify anomalies in traffic behavior and recommend strategies for improvement.- Utilized optimization and stochastic optimization algorithms to optimize various systems and improve performance.- Collaborated with a team to design and develop a revenue management optimization system, leveraging various algorithms and techniques to maximize profitability.

As a student researcher at the Department of Applied Mathematics for Aerospace Engineering (UPM), I had the opportunity to work on a fascinating project in the field of artificial intelligence, specifically in deep reinforcement learning (DRL). My project focused on designing a DRL-based system to optimize the revenues of an airline company. This involved developing a simulation environment that could simulate stochastic events and scenarios, and then using DRL algorithms such as Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO) to enable the system to make decisions that maximize the airline's profits.Deep reinforcement learning is a subset of machine learning that uses a trial-and-error approach to train agents to make decisions that maximize a reward function. The deep neural networks used in DRL can learn to recognize patterns and make decisions based on complex input data, making it a powerful tool for solving complex optimization problems.During my time as a student researcher, I was responsible for designing the architecture of the DRL system, implementing and testing different DRL algorithms, and analyzing the results of the simulations. This work required a deep understanding of machine learning concepts and techniques, as well as strong programming skills in Python and familiarity with popular machine learning frameworks like TensorFlow and PyTorch.Overall, my experience as a student researcher at UPM has been invaluable in helping me develop my skills and knowledge in the exciting field of artificial intelligence and DRL.

• Participation in the Free-Route implementation project in the Spanish Airspace (HISPAFRA), providing support inData Science and Data Analysis activities through the use of the Python.• Supporting the design, development and improvement of a graphical simulator of an Air Traffic Control (ATC)position implemented using the Python language.• Providing support in the improvement and application of methods of analysis and optimization of ATCsectorization in en-route and TMA airspace.• Acquiring knowledge of the methods used in traffic demand analysis.