Research
Current Research Focus
Deep Learning-Based Architectures for Semantics Discovery of Entities and Events
My research focuses on developing deep learning architectures that address the challenge of processing and understanding multimedia data—images, videos, texts, and audio. The project aims to bridge the gap between multimedia representation and machine perception of entities, their semantic meanings, and interconnected events.
Key Objectives
- Developing architectures that link visual entities in images and textual descriptions to knowledge databases
- Enabling semantic descriptions through ontology
- Enhancing a robot's ability to interpret and communicate its understanding of the environment
- Improving multimedia data processing and semantic understanding for better human-robot interactions
Funding & Collaboration
This research is funded by HORIZON-MSCA-2021-DN-01-01, project n. 101072488, as part of the TRAIL Doctoral Network , fostering collaboration across European institutions in the field of AI and robotics.
Past Research Projects
Mobile Robot Obstacle Detection and Avoidance with NAV-YOLO
Developed an optimized obstacle avoidance system using a hybrid navigation framework with YOLOv7. This research contributed to improved autonomous navigation capabilities for mobile robots in dynamic environments, combining computer vision with real-time decision-making algorithms.