Yu Ishihara

Papers

Total Citations

H-Index

About

Yu Ishihara is a robotics researcher whose work lies at the intersection of computer vision, robot navigation, and human-robot interaction. His primary research focuses on enabling robots to understand and act within their environments through predictive modeling and natural language instructions. Ishihara’s most cited work, “Empirical study of future image prediction for image-based mobile robot navigation” (2022, 10 citations), explores how robots can anticipate future visual states to improve autonomous navigation—a key challenge in dynamic environments. He further advances this line of inquiry in “Image-based Action Generation Method using State Prediction and Cost Estimation Learning” (2021, 2 citations), where he integrates cost estimation with state prediction to generate more efficient robot actions. Notably, his 2023 paper “Naming Objects for Vision-and-Language Manipulation” (2 citations) addresses a critical bottleneck in human-robot collaboration: the ambiguity of natural language instructions. By developing methods for robots to name objects in a way that aligns with human referents, Ishihara tackles the fundamental problem of shared understanding—ensuring that when a human says “the red cup,” the robot knows exactly which object is intended. Though early in his career, Ishihara’s work on bridging perception, prediction, and language is laying essential groundwork for more intuitive and capable robotic systems.