Hitoe Ochi
Papers
1
Total Citations
19
H-Index
1
About
Hitoe Ochi is a robotics researcher whose work bridges the gap between human dexterity and machine learning, with a primary focus on bilateral teleoperation and deep learning for robotic manipulation. Her most-cited paper, "Deep Learning Scooping Motion Using Bilateral Teleoperations" (2018, 19 citations), introduces a pioneering system that combines a bilateral teleoperation platform with deep learning software to capture and replicate human demonstration. This work is notable for its practical approach to task learning, where visual images collected during human-guided teleoperation are used to generate autonomous robot motions—a critical step toward more intuitive and adaptable robotic systems. Ochi’s contributions are particularly impactful in the field of assistive and industrial robotics, where precise, learned motions can reduce programming complexity. By demonstrating that complex tasks like scooping can be taught through direct human-robot interaction, her research has opened new pathways for skill transfer in robotics. With a citation count reflecting growing interest in her methodology, Ochi is recognized for advancing the synergy between human demonstration and deep learning, making her a key figure in the evolution of intelligent robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Deep Learning Scooping Motion Using Bilateral Teleoperations19 citations · 2018