Daichi Furuta
Papers
2
Total Citations
11
H-Index
2
About
Daichi Furuta’s research lies at the intersection of robotics, machine learning, and autonomous manipulation, with a focus on enabling robots to learn and execute complex tasks in dynamic, human-centered environments. His major contributions include pioneering a Learning from Demonstration framework that integrates a success judgment model, allowing robots to adaptively reuse taught actions across varying situational constraints—a critical step toward practical, generalizable robot learning. Furuta also advanced dynamic manipulation by developing a model predictive control-based deep neural network for trajectory planning, where target positions and model parameters are incorporated as network inputs, enabling more flexible and robust motion generation. Though his citation counts (9 and 2 for his most-cited works) reflect an early-stage career, the conceptual novelty of his work—particularly in bridging demonstration learning with predictive control—positions him as an emerging voice in robotic skill acquisition. His research directly addresses the challenge of transferring learned behaviors between different physical contexts, a key bottleneck in deploying assistive robots in unstructured human spaces. Furuta’s work is especially notable for its practical orientation: it seeks not just to teach robots, but to teach them how to generalize.
Research Focus
Key Achievements
Top Papers
- 1
- 2