Although I'm interested in various aspects of artificial intelligence and robotics in general my research is focused on active perception, human-robot interaction and software engineering for robotics. During the last years, I have been one of the core developers of the RoboComp robotics framework. I have also developed AGM/AGGL, a cognitive architecture with a special focus in enabling robots to reason about perceptive actions. During the last months, I have been working on SNGNN (GitHub repository), a Graph Neural Network to model adherence to social-navigation conventions for robots.
SNGNN (GitHub repository), a Graph Neural Network to model adherence to social-navigation conventions for robots. Given a particular scenario composed of a room with any number of walls, objects and people (who can be interacting with each other) the network provides a social adherence ratio from 0 to 1. This information can be used to plan paths for human-aware navigation.
RoboComp is an open-source modern robotics framework. It makes extensive use of technologies such as component-oriented programming and domain-specific languages.
AGM/AGGL is an open-source robotics cognitive architecture. Its key features are its ability to reason about perceptive tasks (e.g., how to find an object), its modularity and reusability.