Keisuke Umezawa
Papers
1
Total Citations
68
H-Index
1
About
Keisuke Umezawa is a leading researcher in robot learning and human-robot interaction, with a focus on enabling machines to acquire complex skills from human demonstrations. His most influential work, "Task Parameterization Using Continuous Constraints Extracted From Human Demonstrations" (2015, 68 citations), introduces a novel framework for automatically learning task specifications by observing human actions. This approach allows robots to decompose high-level goals into continuous constraints, enabling them to generalize and combine individual actions across varied scenarios. Umezawa’s contributions bridge the gap between demonstration-based learning and autonomous task execution, significantly advancing the field of programming by demonstration. His work has been widely cited for its practical impact on robotic manipulation and adaptive control, inspiring subsequent research in constraint-based task representation. Beyond this seminal paper, Umezawa continues to explore how robots can infer underlying human intent from sparse demonstrations, pushing the boundaries of intuitive human-robot collaboration. His research is essential reading for students and engineers interested in making robots more flexible, teachable, and capable of operating in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1