Papers
3
Total Citations
7
H-Index
2
About
Soya Shimizu is a researcher in humanoid robotics, specializing in motion synthesis and optimal control. Their work focuses on generating complex, physically consistent whole-body motions for humanoid robots using low-dimensional representations. Shimizu’s major contribution is the application of Functional Principal Component Analysis (FPCA) to motion synthesis, enabling the expression of high-dimensional joint trajectories in a compact feature space while preserving physical constraints like balance and torque limits. This approach is demonstrated in their 2018 paper on whole-body motion blending, which has garnered 2 citations. Building on this, Shimizu introduced pseudo direct and inverse optimal control methods in 2021 (2 citations), allowing for efficient estimation of cost function weights and motion time-series without the computational burden of traditional optimal control. Their 2020 work on motion synthesis in low-dimensional feature spaces (3 citations) further advances inverse optimal control for robotics. By bridging dimensionality reduction and control theory, Shimizu’s research offers practical tools for designing agile, human-like robot behaviors, with potential applications in assistive robotics and animation. Their work stands out for its elegant integration of statistical methods with physical modeling.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3