Research

Research Areas of Interest:

Reinforcement Learning, Machine Learning, Deep Learning, System modelling and identification, Linear and Nonlinear Control, Robotics

Vision and Expertise

My expertise is in human-behaviour learning, comprised of: machine learning, reinforcement learning, control systems, neural networks, and system modeling and identification. In particular, I design future complementary learning architectures inspired in humans' brain activity and their expertise for complex-decision making. The application areas include:

Reinforcement Learning for Optimal Decision Making
Complementary Learning for Experience Transference/Inference
Encoding Temporal Difference Error
Complementary Learning based on Semi-Supervised Learning Architectures.

I am particularly interested in designing novel drone intention prediction algorithms that combines the merits of data-driven methods and physics informed models to enhance prediction capabilities. The applications areas include:

Trajectory Inference algorithms based on non-cooperative sensors.
Physics informed models.
Recurrent Neural Networks and Reservoir Computing.
Objective function extraction of control policies.
Complementary Learning: Data-driven methods and physics informed models.