photo

I am a PhD student in the JSK Lab at the University of Tokyo. My research focuses on developing learning methods for robotic skills (motion planning and manipulation) which explicitly take advantage of feasibility and capability assessment. To highlight this motivation, our recent IEEE T-RO article introduces a method to construct/reuse a database of reusable experiences (analogous to initial solutions in numerical optimization), specifically designed to accelerate online planning across problems in a user-specified domain. The construction process employs deep-NN classifiers to efficiently cover the problem space. The IEEE RA-L article defines a robot’s feasible error region and develops a policy searching method that identifies optimal policy parameters to maximize the region volume.

Alongside research activities, I am interested in writing fast and well modularized software. A notable work includes plainmp: a highly tuned motion planning library for articulated robots written in C++ with Python bindings. It solves moderately complex planning problems (e.g., 8DOF Fetch in front of table) in less than 1ms on a laptop, which is, to my knowledge, significantly faster compared to standard implementations.

My industrial experience includes part-time jobs at two companies: Tier IV (2021.4 - 2022.6), where I worked on autonomous driving software and gained experience developing high-quality software in a team with large codebases (Some PRs are publicly available here). At Integral AI (2024.4 - 2024.11), a startup company, I gained valuable experience working on projects in the very initial phases.

Contact

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

Selected 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, IEEE Transactions on Robotics (T-RO), 2025, arXiv link, IEEE link.

  • 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 (RA-L), 2021, Paper link.

  • T. Chujo, H. Ishida, O. Mori, J. Kawaguchi: Liquid crystal device with reflective microstructure for attitude control, Journal of Spacecraft and Rockets, 2018, Paper link.

  • H. Ishida, Y. Tsuda, Robust terrain-aided localization of spacecraft using low-fidelity asteroid shape model, SICE International Symposium on Control System, 2018, Paper link.

  • H. Ishida, T. Chujo, O. Mori, J. Kawaguchi: Evaluation of Optical Properties of Advanced Reflectivity Control Device for Solar Sails by Numerical Simulation, 68th International Astronautical Congress (IAC), 2017, Paper link.

  • H. Ishida, T. Chujo, O. Mori, J. Kawaguchi: Optimal design of advanced reflectivity control device for solar sails considering polarization properties of liquid crystal, Proceedings of the 26th International Symposium on Space Flight Dynamics (ISSFD), 2017, Paper link.

Grant-in-Aid

  • JSPS Postdoctoral Research Fellow (学振特別研究員PD), 2024 (withdrawn due to postponement of graduation)