Papers
1
Total Citations
5
H-Index
1
About
Akihiro Kubo is a researcher at the forefront of bio-inspired robotics and machine learning, with a primary focus on enabling agile and adaptive locomotion in legged robots. His major contribution lies in the development of a novel data-driven deep reinforcement learning (DRL) method that integrates hierarchical control with biological central pattern generators (CPGs). This approach, detailed in his most-cited work, "Hierarchical reinforcement learning with central pattern generator for enabling a quadruped robot simulator to walk on a variety of terrains," has garnered 5 citations since its 2025 publication. By combining the rhythmic, low-level motor control of CPGs with high-level DRL policy optimization, Kubo’s framework allows quadruped robots to autonomously adapt their gait to complex and uneven surfaces—a critical challenge in field robotics. This work not only demonstrates a significant step toward more robust and versatile robotic systems but also bridges computational neuroscience and practical engineering. Kubo’s research is particularly notable for its potential applications in search-and-rescue, exploration, and assistive robotics, where reliable locomotion across unpredictable terrain is essential.
Research Focus
Key Achievements
Top Papers
- 1