Kohei Omoto

Papers

Total Citations

H-Index

About

Kohei Omoto is a robotics researcher whose work centers on the real-time motion generation and control of humanoid robots, with a particular focus on complex, non-gaited locomotion. His most notable contribution is the integrated optimization of climbing locomotion, where he applies nonlinear model predictive control (NMPC) to simultaneously plan a humanoid robot’s path and limb movements while scaling a wall. This approach addresses the critical challenge of determining which handholds to grasp at each step while respecting strict kinematic constraints, enabling dynamic and adaptive climbing behavior. Though his most-cited paper has garnered 5 citations, the work represents a foundational step in merging high-level task planning with low-level control for humanoid robots operating in unstructured environments. Omoto’s research is significant for advancing the autonomy of legged robots in tasks that require precise coordination and real-time optimization, such as disaster response or industrial inspection. His contributions highlight a growing trend toward holistic motion planning, where robots must reason about both where to go and how to move in a single, computationally efficient framework.