| Project/Area Number |
26330279
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Soft computing
|
|---|
| Research Institution | Kyushu Institute of Technology |
|---|
Principal Investigator |
TAMUKOH Hakaru 九州工業大学, 大学院生命体工学研究科, 准教授 (90432955)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
森江 隆 九州工業大学, 大学院生命体工学研究科, 教授 (20294530)
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2015: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2014: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 脳型計算機 / Deep Learning / FPGA / ディジタルハードウェア / 論理回路 / Robot Operating System / RoboCup / ホームロボット / 自己組織化マップ |
|---|
| Outline of Final Research Achievements |
In this research, we aim to realize a brain-like computer that can be applied to autonomous robots. In the theory and circuit team, we proposed hardware oriented algorithms for Restricted Boltzmann Machines and AutoEncoders. In the application team, we proposed a ROS-FPGA system that can easily be accessed from Robot Operating System (ROS) to virtual hardware circuits inside a reconfigurable semiconductor, FPGA. In addition, we proposed an image recognition system for robots by deep convolutional neural networks and knowledge transfer learning. We integrated these achievements into a home robot and showed its effectiveness through robot competitions.
|
