Raquel Torres Peralta

Papers

Total Citations

H-Index

About

Raquel Torres Peralta is a pioneering researcher in Human-Robot Interaction, focusing on how non-experts can naturally teach complex behaviors to autonomous agents. Her work bridges the gap between human teaching methods and machine learning, aiming to make robots instructable through intuitive, multi-modal communication rather than programming. Her most-cited paper, "Towards Understanding How Humans Teach Robots" (2011, 21 citations), lays the groundwork for developing interfaces that accommodate natural teaching styles, while its 2013 follow-up (17 citations) explores a prototype system for teaching simulated robots through demonstration and feedback. In "Challenges to decoding the intention behind natural instruction" (2011, 9 citations), she identifies key obstacles in interpreting human intent during teaching interactions. Her research is notable for integrating multiple instruction modes—such as demonstration, feedback, and natural language—into a single, fluid teaching experience. With a total of 49 citations across her top works, Torres Peralta’s contributions are foundational for creating robots that learn as easily as human students, advancing the vision of accessible, user-friendly artificial intelligence.