Max Robotics — Global Service Robot Directory + US Certification

About

Takeshi Mori is a pioneering researcher in the intersection of reinforcement learning and bio-inspired robotics, with a particular focus on bipedal locomotion. His work centers on developing autonomous learning frameworks that enable robots to walk and move with human-like efficiency, drawing inspiration from biological central pattern generators (CPGs). Mori's most significant contribution is the CPG-actor-critic method (2007, 118 citations), a novel reinforcement learning architecture that allows biped robots to autonomously learn and adapt their walking gaits. This foundational work has been widely cited and built upon by researchers in legged robotics. He further advanced the field by introducing natural policy gradient methods for CPG control (2004, 15 citations), improving learning stability and convergence. Notably, Mori also explored model-free apprenticeship learning (2011, 18 citations), developing techniques to transfer human impedance behavior to robots without requiring accurate dynamical models—a practical breakthrough for real-world applications. His research elegantly bridges computational neuroscience and robotics, demonstrating how biological motor control principles can be effectively implemented in autonomous systems. Through his work, Mori has established himself as a key contributor to the development of more adaptive, efficient, and human-like robotic locomotion systems.