Ryo Kabutan
Papers
3
Total Citations
24
H-Index
2
About
Ryo Kabutan’s research lies at the intersection of robot motion planning and machine learning, with a focus on enabling articulated manipulators to navigate complex environments more intelligently. His most influential work introduces the T-RRT (Transition-based Rapidly-exploring Random Tree) enhanced with a potential function, a method that significantly improves path planning efficiency for vertical articulated robots. By guiding random sampling toward promising regions, this approach reduces computational overhead while maintaining robust obstacle avoidance—a contribution that has earned his 2018 paper 15 citations and recognition as a practical tool for industrial automation. Kabutan further advanced the field with the Gaussian Mixture Spline Trajectory (GMST) algorithm, which learns from prior motion datasets to generate smooth, collision-free trajectories for new problems without requiring explicit replanning from scratch. This work bridges the gap between data-driven learning and traditional optimization, offering a scalable solution for repetitive tasks in manufacturing. With a total of 24 citations across his core publications, Kabutan’s research demonstrates a clear trajectory from foundational path planning to adaptive, experience-based motion generation—a promising direction for next-generation robotic systems that must operate safely and efficiently alongside humans.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3