Yuko Ozasa

Papers

Total Citations

H-Index

About

Yuko Ozasa’s research lies at the intersection of robotics, human-robot interaction, and multimodal perception, with a particular focus on enabling robots to understand and act upon spoken human requests. Her most significant contribution is in the domain of disambiguation for unknown object detection, where she pioneered methods that integrate speech and image recognition confidences to improve a robot’s ability to identify objects requested by voice. This work, detailed in her 2013 paper (7 citations), directly addresses the challenge of robots operating in unstructured environments with ambiguous verbal commands. She further advanced this line of inquiry by proposing object recognition techniques that fuse speech and image data using web images as a reference (3 citations), allowing robots to leverage external knowledge for more robust identification. Ozasa also contributed to educational robotics through her work on the PRINTEPS platform, developing a quiz module for teacher-robot collaboration (3 citations). While her citation counts reflect a focused, early-career impact, her research is foundational for anyone interested in practical, real-world robot perception and the seamless integration of linguistic and visual cues for autonomous task execution.