K. Sakamoto
Papers
3
Total Citations
51
H-Index
2
About
K. Sakamoto is a versatile robotics and sensing researcher whose work spans mobile robot localization, soft tactile sensing, and intelligent control systems. Perhaps most notably, Sakamoto's 2005 paper introducing the **expansion resetting method** for Monte Carlo localization addressed a critical vulnerability in probabilistic robot navigation — the challenge of recovering from catastrophic localization failures. By blending expansion resetting with sensor resetting approaches, this contribution earned 42 citations and remains a meaningful reference in the autonomous mobile robotics community. Sakamoto's earlier work in 2003 explored the generation of high-quality training data for extracting interpretable decision trees from evolved neural network robot controllers, bridging the gap between opaque learned behaviors and transparent, explainable systems — a concern that has only grown more relevant with modern AI. More recently, Sakamoto has turned attention to soft robotics and human-machine interfaces, contributing to the design of high-performance tomographic tactile sensors through manipulation of detector conductivity, a promising direction for wearable electronics and next-generation robotic touch sensing. Across these diverse domains, Sakamoto's research reflects a consistent commitment to improving robot perception, adaptability, and interpretability — qualities fundamental to the future of intelligent autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3