Naoya Takeishi is a postdoctoral researcher of Structured Learning Team, RIKEN Center for Advanced Intelligence Project (AIP), Japan. He is also a visiting scholar at School of Engineering, The Unviersity of Tokyo. He received his B.Eng., M.Eng., and Ph.D. in Engineering from the Department of Aeronautics and Astronautics, The University of Tokyo, Japan in 2013, 2015, and 2018, respectively. His research interest includes numerical analysis of dynamical systems, machine learning with knowledge, and space robotics.
Dynamical Systems, Time-Series Data
Analysis of dynamical systems and time-series data based on the operator-theoretic view and its data-driven method, dynamic mode decomposition (DMD).
Fault detection using machine learning techniques, so far applied to artificial satellites, vehicles, power plants, oil refinery, etc.
Visual SLAM in Space
Simultaneous estimation of the relative position of a spacecraft and the shape and motion parameters of the target asteroid using images of the asteroid.
Utilization of Knowledge for ML
Incorporation of structured or unstructured knowledge, often given distantly, in procedures of statistical machine learning.