| Project/Area Number |
17360105
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Dynamics/Control
|
|---|
| Research Institution | The University of Electro-Communications |
|---|
Principal Investigator |
MATSUNO Fumitoshi The University of Electro-Communications, Faculty of Electro-Communications, Professor (00190489)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
FUKUSHIMA Hiroaki The University of Electro-Communications, Faculty of Electro-Communications, Assistant Professor (40377015)
|
|---|
| Project Period (FY) |
2005 – 2007
|
| Project Status |
Completed (Fiscal Year 2007)
|
| Budget Amount *help |
¥15,220,000 (Direct Cost: ¥14,200,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2007: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2006: ¥3,400,000 (Direct Cost: ¥3,400,000)
Fiscal Year 2005: ¥7,400,000 (Direct Cost: ¥7,400,000)
|
|---|
| Keywords | Hyper-redundant Systems / Flexible Mechanical Systems / Dynamic based Control / Dynamics based Intelligence / Nonholonomic Constraint / Infinite dimensional systems / Learning Algorithm / Snake-like Robot / ダイナミクスペースト制御 / ダイナミクスペースト・インテリジェンス / 可変拘束システム / ねじ推進機構 / 強化学習 |
|---|
| Research Abstract |
We have extended the concept of "Dynamic based Control" of the nonlinear system to the nonholonomic hyperredundant systems. We have proposed the reinforcement learning algorithm for the hyperredundant systems based on the dynamics based control.
The results obtained in the research are as follows:
1. Derivation of dynamic model of hyperredundant systems with nonholonomic constraints
2. Construction of model based control law for hyperredundant systems with nonholonomic constraints and experimental demonstration of effectiveness of the proposed control law
3. Construction of dynamics based control law for infinite dimensional systems and experimental demonstration of effectiveness of the proposed control law for flexible mechanical systems
4. Design of the reinforcement learning algorithm for the hyperredundant systems based on the dynamics based control
5. Experimental demonstration of effectiveness of the proposed reinforcement learning method by using a redundant snake-like robot
|
