Daniele Zambuto

Papers

Total Citations

H-Index

About

Daniele Zambuto is a researcher whose work lies at the intersection of robotics, cognitive science, and computational linguistics, with a primary focus on grounded human-robot interaction. His key research area involves developing computational models that allow robots to acquire language not through pre-programmed rules, but by grounding words and meanings in their own sensory-motor experiences—much like human infants learn. Zambuto’s major contribution is a probabilistic, trainable framework that enables robots to learn visually grounded language models from examples, requiring minimal user intervention. This approach allows artificial agents to resolve ambiguities in spatial and descriptive terms (such as adjectives and nouns) and to engage in cooperative tasks with humans. His most-cited work, “A probabilistic approach to learning a visually grounded language model through human-robot interaction” (29 citations), demonstrates how a humanoid robot can develop rudimentary language skills by integrating perception, cognition, and motor control. Through his innovative systems for advanced verbal interaction, Zambuto has advanced the goal of creating robots that can learn and communicate in a human-like, context-aware manner—a significant step toward more intuitive and effective human-robot collaboration.