PhD Student —
Riccardo Izzo is a PhD student in Information Technology at Politecnico di Milano under the supervision of Prof. Matteo Matteucci. He received a B.Sc. (2022) and a M.Sc. (2024) in Computer Science and Engineering at Politecnico di Milano. With his master thesis “BTGenBot: Behavior Tree Generation for Robotic Tasks with Lightweight LLMs”, he developed a system that employs lightweight LLMs to convert natural language task descriptions into behavior trees directly executable on robots. His research line sits at the intersection of language, vision and action focusing on the integration of Large Language Models (LLMs) and Vision-Language Models (VLMs) in the robotic domain, with a particular emphasis on high-level task planning and complex reasoning. This includes developing systems that bridge natural language description and multimodal sensory inputs to enhance the capabilities of robots in both navigation and manipulation tasks. His current projects explore agentic AI architectures built around compact Multimodal LLMs and emerging Vision-Language-Action (VLA) models, enabling robots to plan, navigate, and manipulate with minimal user prompting and no reliance on external servers. The end goal of his PhD is to equip robots with powerful foundational models that operate efficiently and intuitively, minimizing both computational load and user intervention, paving the way for truly autonomous service robots in homes, factories, and beyond.
Links
Google Scholar: https://scholar.google.com/citations?user=7EMSspUAAAAJ&hl=en
LinkedIn: https://www.linkedin.com/in/riccardo-andrea-izzo-6755b8200/
Email: riccardo.izzo@polimi.it