Hideharu Amano
Papers
7
Total Citations
42
H-Index
4
About
Hideharu Amano is a leading researcher at the intersection of reconfigurable computing, FPGA acceleration, and robotics, with a career spanning from foundational reconfigurable systems to cutting-edge edge-AI for socially assistive robots. His major contributions focus on bridging the gap between high-level FPGA design and real-time robotic applications, notably through the development of **Forest**, an open-source tool that automates the integration of high-level synthesis FPGA modules with ROS2 systems (15 citations). Amano has pioneered the use of FPGAs for low-power acceleration of robot audition, particularly for sound source localization and source separation using the HARK framework, achieving significant speedups while maintaining energy efficiency—critical for edge computing in assistive robotics. His work on FPGA-accelerated reinforcement learning agents for robot control (11 citations) demonstrates how reconfigurable hardware can meet strict latency and power constraints. With a career that began with foundational work on reconfigurable sensor-data processing for personal robots in 1997, Amano’s sustained impact is evident in his consistent output of practical, open-source solutions that enable autonomous, power-efficient robotic systems for real-world applications like elderly care.
Research Focus
Key Achievements
Top Papers
- 1Automated Integration of High-Level Synthesis FPGA Modules with ROS2 Systems15 citations · 2020
- 2FPGA Acceleration of ROS2-Based Reinforcement Learning Agents11 citations · 2020
- 3
- 4FPGA-based Low Power Acceleration of HARK Sound Source Localization4 citations · 2024
- 5
- 6An FPGA off-loading of HARK sound source localization3 citations · 2022
- 7A reconfigurable sensor-data processing system for personal robots2 citations · 1997