Fumiya Kitano
Papers
2
Total Citations
16
H-Index
2
About
Fumiya Kitano is a rising researcher at the intersection of robotics, control systems, and artificial intelligence, with a primary focus on applying deep reinforcement learning (DRL) to real-world robotic manipulation. His work addresses a critical bottleneck in robotics: the sim-to-real gap. In his highly cited 2022 paper (10 citations), Kitano developed a novel sim-real mapping framework for image-based robot arm control, enabling policies trained entirely in simulation to transfer effectively to physical hardware without extensive real-world data collection. This contribution is foundational for deploying DRL in industrial settings where data gathering is costly. Expanding on this, his 2023 work (6 citations) tackles the challenging domain of flexible link manipulators—lightweight, energy-efficient arms prone to vibration. Kitano pioneered a reinforcement learning approach for simultaneous vibration suppression and position control, a breakthrough for high-speed, cost-effective automation. Though early in his career, his work is already shaping next-generation robotic systems that are both agile and precise. Kitano’s research promises to make flexible, adaptive robots a practical reality in manufacturing and beyond.
Research Focus
Key Achievements
Top Papers
- 1
- 2