| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2016: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2015: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2014: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2013: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
|
|---|
| Outline of Final Research Achievements |
I propose an estimation method of coefficient of static friction of a floor surface by the photo image of the floor tile. The image feature used to presume are local image features that are generated by machine learning. And the estimation is performed by classification according to the magnitude of the friction coefficient. Although detailed texture features can not be obtained from the image of the front floor surface, estimation is performed using the floor image under the robot, and determine whether the under floor image of robot and the front floor are the same type. As a result, it was shown that the friction coefficient can be estimated with non-contact, an accuracy of the coefficient is enough to control the robot, and it is useful for robot object grasping and walking control.
|
