Back to Search
Start Over
Material identification based on electrostatic sensing technology.
- Source :
-
AIP Conference Proceedings . 2018, Vol. 1955 Issue 1, pN.PAG-N.PAG. 9p. 3 Color Photographs, 2 Diagrams, 3 Graphs. - Publication Year :
- 2018
-
Abstract
- When the robot travels on the surface of different media, the uncertainty of the medium will seriously affect the autonomous action of the robot. In this paper, the distribution characteristics of multiple electrostatic charges on the surface of materials are detected, so as to improve the accuracy of the existing electrostatic signal material identification methods, which is of great significance to help the robot optimize the control algorithm. In this paper, based on the electrostatic signal material identification method proposed by predecessors, the multi-channel detection circuit is used to obtain the electrostatic charge distribution at different positions of the material surface, the weights are introduced into the eigenvalue matrix, and the weight distribution is optimized by the evolutionary algorithm, which makes the eigenvalue matrix more accurately reflect the surface charge distribution characteristics of the material. The matrix is used as the input of the k-Nearest Neighbor (kNN)classification algorithm to classify the dielectric materials. The experimental results show that the proposed method can significantly improve the recognition rate of the existing electrostatic signal material recognition methods. [ABSTRACT FROM AUTHOR]
- Subjects :
- *ROBOTS
*EVOLUTIONARY algorithms
*EIGENVALUES
*ELECTROSTATICS
*DIELECTRIC materials
Subjects
Details
- Language :
- English
- ISSN :
- 0094243X
- Volume :
- 1955
- Issue :
- 1
- Database :
- Academic Search Index
- Journal :
- AIP Conference Proceedings
- Publication Type :
- Conference
- Accession number :
- 129246607
- Full Text :
- https://doi.org/10.1063/1.5033585