Skill inheritance control by human and robots based on multi-modal machine learning
| Project/Area Number |
18K13780
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 21040:Control and system engineering-related
|
|---|
| Research Institution | Chuo University |
|---|
Principal Investigator |
Nagatsu Yuki 中央大学, 理工学部, 助教 (60804987)
|
|---|
| Project Period (FY) |
2018-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2020: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2019: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2018: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
|
|---|
| Keywords | 制御工学 / 力制御 / 知能ロボティックス / 知能機械 / 機械学習 |
|---|
| Outline of Final Research Achievements |
In this research, we carried out research toward the realization of skill inheritance control by humans and robots. We have developed a Wide-band force measurement and control method based on multi-sensor information, which is important and indispensable for skill inheritance control. We also analyzed the performance and stability of disturbance cancellation control based on the acceleration dimension for the position/force hybrid control system required for extending skill inheritance control to a system with redundant degrees of freedom. We also devised a method for saving and reproducing the human motion by bilateral control based on the transmission of only force information between the master and slave systems. As a result, it is not necessary to save the trajectory in the realization of skill inheritance control, and it can be expected that the amount of information to be acquired and analyzed can be reduced.
|
| Academic Significance and Societal Importance of the Research Achievements |
ロボットによる人間の代替技術が求められており、熟練技術者のもつ技能の継承は重要な課題である。本研究の過程で得られた成果は、ロボットによる人間の代替を行う上で重要な力覚情報の計測・制御の広帯域化・高精度化に貢献する。さらに、これまでにロボットを介した人間動作の抽出と再現には位置と力の計測と制御が必要と考えられてきたが、本研究で考案した力情報のみの伝送によるバイラテラル制御に基づく動作の抽出と再現手法により、位置情報が冗長な情報であるということを示唆する結果を得た。これにより、力情報を基盤としたロボットによる動作の抽出、再現および継承のための新たなフレームワークが構築されることが期待できる。
|
Report
(4 results)
Research Products
(13 results)
