Hirokazu Ishida (石田寛和)

I am a Researcher (July 2025 ~) and Robotics Team Lead (Dec 2025 ~) at SB Intuitions, specializing in large-scale robot learning. My primary focus is on architecting highly optimized data/software pipelines and the algorithmic side of robot learning. Yet, I am a roboticist at heart. I never hesitate to get my hands dirty in the team whenever necessary; whether it’s assembling fleet of robots, soldering, or spending days debugging complex hardware issues.

I am also 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. Research range includes data-driven motion planning (IEEE T-RO 2025) and policy search for manipulation (IEEE RA-L 2021).

Alongside research activities, I like 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.