I am a PhD student in the JSK Lab at the University of Tokyo, Japan. My research focuses on the intersection of planning and learning in robotics. Specifically, I believe that learning the feasibility (capability) of an action is crucial for robot motion generation. In light of this belief, a recently posted preprint addresses the plannability-speed trade-off in motion planning, leveraging learned feasibility via classifiers. Another RA-L article defines a robot’s feasible “error” region and optimizes the motion parameter to maximize this region through the robot’s trial-and-error. The motion with the learned parameter is thus robust to the recognition error of the robot’s environment.

Before starting my PhD, I studied aerospace engineering for my B.Eng and M.Eng. Some of my works from that time are included in my google scholar profile.

Contact

• email: h-ishida.i.u-tokyo.ac.jp
• github: HiroIshida
• linkedin: Hirokazu Ishida

Education

• 2019.4 - Present: Ph.D. student in Mechano-Informatics, The University of Tokyo
• 2016.4 - 2018.3: M.Eng. in Aerospace Engineering, The University of Tokyo
• 2012.4 - 2016.3: M.Eng. in Aerospace Engineering, Osaka Prefecture University

Publications

• H. Ishida, N. Hiraoka, K. Okada and M. Inaba CoverLib: Classifiers-equipped Experience Library by Iterative Problem Distribution Coverage Maximization for Domain-tuned Motion Planning, submitted to IEEE Transactions on Robotics, arXiv link (version 2024/05/05).

• N. Hiraoka, H. Ishida, T. Hiraoka, K. Kojima, K. Okada, M. Inaba: Sampling-based Global Path Planning using Convex Polytope Approximation for Narrow Collision-free Space of Humanoid. International Journal of Humanoid Robotics (2024), Paper link.

• H. Ishida, K. Okada and M. Inaba, Classifier-Aided Maximization of Feasible-Error-Region for Robust Manipulation Learning, IEEE Robotics and Automation Letters (2021), Paper link.

• See more in Google Scholar