I am a 3rd year Ph.D student in Assured Reliable Interactive Autonomous (ARIA) Systems Group at the University of Colorado Boulder.

Current Work

My ultimate goal is to easily tell a robot what a task is (or make the robot infer what the task is) and make the robot autonomously perform the task. Especially, my work focuses on Learning from Demonstrations (LfD), i.e., the robot learns the specifications of a task through demonstrations. I am interested in learning a high-level abstract task as a formal language so that robot can utilize the learned specifications to adapt to similar environments. For example, I am desired to make a robot that can be trained in a lab but can adapt to any restaurants or factories.


My research is on motion learning and task learning for robots. Especially, I am interested in the intersection between Formal Method, Control Theory and Reinforcement Learning. In other words, intersection between classic model-based control and computer science approach.


I completed my Bachelor and Master at Keio University in Japan, under the supervision of Masaki Takahashi. I also studied at the University of Illinois at Urbana-Champain for a year. Majored in Aerospace Engineering and Computer Science.