Takeshi Ohkawa

About

Takeshi Ohkawa is a prominent researcher specializing in FPGA-based acceleration for robotic systems, with a particular focus on integrating reconfigurable hardware with the Robot Operating System (ROS). His work addresses one of robotics' most pressing challenges: enabling computationally demanding tasks such as SLAM, deep neural network inference, and reinforcement learning on power-constrained platforms without sacrificing performance. Ohkawa's most significant contributions center on bridging the gap between FPGA hardware design and robot software frameworks. His development of cReComp, an automated design tool for ROS-compliant FPGA components (27 citations), and subsequent work on publish/subscribe messaging acceleration (31 citations) have substantially lowered the barrier to FPGA adoption in robotics. His research trajectory evolved naturally into ROS2 integration, culminating in tools like Forest, which automates high-level synthesis module generation for modern robot systems (15 citations). With a body of work spanning over a decade — from data acquisition middleware in 2007 to FPGA-accelerated reinforcement learning agents in 2020 — Ohkawa has consistently pursued energy-efficient, high-performance robot architectures. Collectively accumulating over 170 citations, his research has meaningfully shaped how the robotics community approaches hardware-software co-design for intelligent autonomous systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Acceleration of Publish/Subscribe Messaging in ROS-compliant FPGA Component

   31 citations · 2017
2. 2
   cReComp: Automated Design Tool for ROS-Compliant FPGA Component

   27 citations · 2016
3. 3
   High Level Synthesis of ROS Protocol Interpretation and Communication Circuit for FPGA

   21 citations · 2019
4. 4
   FPGA Components for Integrating FPGAs into Robot Systems

   19 citations · 2018
5. 5
   A Data Acquisition Middleware

   16 citations · 2007
6. 6
   Automated Integration of High-Level Synthesis FPGA Modules with ROS2 Systems

   15 citations · 2020
7. 7
   Proposal of ROS-compliant FPGA Component for Low-Power Robotic Systems

   14 citations · 2015
8. 8
   Architecture exploration of intelligent robot system using ROS-compliant FPGA component

   13 citations · 2016
9. 9
   FPGA Acceleration of ROS2-Based Reinforcement Learning Agents

   11 citations · 2020
10. 10
    Development of a Robot Car by Single Line Search Method for White Line Detection with FPGA

    6 citations · 2018

Key Collaborators

Contact & Links