Abstract
Current research for Learning From Demonstra-
tion (LfD) seems to concentrate on the learning kernel. This
paper outlines the need for a more useful variable selection
technique using the training dataset. The paper presents a
new training dataset selection method, called Information Ex-
traction (IE). The application area is a complex task involving
robot mining tunnel inspection, and IE is applied to the robot
for this task. The Gaussian Mixture Model (GMM) is adopted
to generate a learning curve utilized by a robot. The Gaussian
Mixture Regression (GMR) is used to infer actions based on
given states. After human demonstration, the robot can finish
a pre-defined task independently.
tion (LfD) seems to concentrate on the learning kernel. This
paper outlines the need for a more useful variable selection
technique using the training dataset. The paper presents a
new training dataset selection method, called Information Ex-
traction (IE). The application area is a complex task involving
robot mining tunnel inspection, and IE is applied to the robot
for this task. The Gaussian Mixture Model (GMM) is adopted
to generate a learning curve utilized by a robot. The Gaussian
Mixture Regression (GMR) is used to infer actions based on
given states. After human demonstration, the robot can finish
a pre-defined task independently.
| Original language | English |
|---|---|
| Title of host publication | IEEE International Conference on Robot, Vision and Signal Processing (RSVP) |
| Place of Publication | Taiwan |
| Publisher | IEEE |
| Pages | 32-35 |
| Number of pages | 4 |
| ISBN (Electronic) | 9780769545813 |
| DOIs | |
| Publication status | Published - 2011 |
| Event | RSVP: First International Conference on robot, vision and signal processing - Kaohsiung, Taiwan, China Duration: 21 Nov 2011 → 23 Nov 2011 |
Conference
| Conference | RSVP |
|---|---|
| Country/Territory | China |
| Period | 21/11/11 → 23/11/11 |