Yuichi Ohsita
Papers
3
Total Citations
8
H-Index
2
About
Yuichi Ohsita’s research lies at the intersection of robotics, cyber-physical systems, and environmental intelligence, with a focus on enabling autonomous systems to operate reliably in dynamic, real-world settings. His major contributions include developing a robot path-planning method that uses Gaussian Process Regression to minimize predictive uncertainty, allowing robots to adaptively monitor environments where factors like temperature shift over time—a critical advance over static spatial sampling. He has also pioneered probabilistic representations for digital twins of spatio-temporal real-world scenes, moving beyond simple digital copies to model complex interactions among objects and humans in spaces like buildings and cities, thereby enhancing trustable cyber-physical interactions. Additionally, Ohsita has addressed communication challenges in remote robot control by sending multiple predicted commands to maintain operation under unstable network conditions. While his most-cited works currently hold modest citation counts (2–3), their forward-looking themes—predictive uncertainty, digital twin fidelity, and robust teleoperation—signal growing relevance as autonomous systems become more prevalent. His work is particularly notable for bridging theoretical probabilistic models with practical robotic deployment, offering a foundation for next-generation environmental monitoring and smart infrastructure.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3