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

2
H-Index
3
Papers
7
Total Citations
2
Avg Citations/Paper
🏆 Most Cited Paper
Motion Synthesis Using Low-Dimensional Feature Space and Its Application to Inverse Optimal Control
3 citations · 2020
📈 Most Prolific Year: 2020 (1 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: National Institute of Advanced Industrial Science and Technology, Tokyo University of Agriculture and Technology

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago