2022 Fiscal Year Final Research Report
Pneumatic reservoir computing and its application to robot control
| Project/Area Number |
20K04375
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 20020:Robotics and intelligent system-related
|
|---|
| Research Institution | Tokyo Denki University (2022)
Tokyo Medical and Dental University (2020-2021) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2020-04-01 – 2023-03-31
|
| Keywords | リザバーコンピューティング / 空気圧 / 人工筋 / ソフトロボット / 形態学的計算 |
|---|
| Outline of Final Research Achievements |
As a new principle for soft robots to utilize their own bodies for computation, we proposed physical reservoir computing using air in tubes, called as pneumatic reservoir computing, and developed a soft robot that can actually be controlled using this principle. In addition to verifying the computational capability and analyzing the characteristics of pneumatic reservoir computing, we applied it to the control of a pneumatic rubber artificial muscle assist suit and verified a system for learning and generating periodic waveform used in walking assist systems, etc. The results showed that pneumatic reservoir computing can be applied to robot control and that it has potential for further development.
|
| Free Research Field |
生体医工学, ロボティクス
|
| Academic Significance and Societal Importance of the Research Achievements |
空気圧人工筋を使用したアシストスーツなどのソフトロボットに必要となる計算の一部を、これまでの電子的なコンピュータによる計算から、空気のダイナミクスを利用した計算に置き換えることにより、ロボットに搭載する電子機器をより簡素なものにすることができる。これにより、ロボットの軽量化・耐久性の向上・省電力化が促進され、アシストスーツ使用者の負担軽減、ソフトロボットの水中など幅広い環境への適用につながる。
|
