Robot Grasp Pattern Recognition Based on Wavlet and BP Neural Network

Jin Jun Chen; Ting Xiang

doi:10.4028/www.scientific.net/AMM.331.290

Paper Titles

Optimal Scheduling of Compressors Considering Linepack Storage in a Pipeline Network
p.271

Fuzzy Controller of Voltage Regulator System BP Neural Network Model Design and Simulation
p.277

Research and Application of Compound CNC Five Axis Five Linkage Milling-Grinding-All-in-One Machine
p.281

The Correction Methods of Morphology on Uneven Lighting Pavement Image
p.286

Robot Grasp Pattern Recognition Based on Wavlet and BP Neural Network
p.290

A New Stabilizing Controller Design Based on the Wireless Networked Control System
p.294

A Novel Dual-Galvanometers Control Card
p.299

Theoretical Analysis of a New Intrinsic Fabry-Perot Interferometric Fiber Pressure Sensor Structure
p.303

Nonlinear Control of SVG Based on Hamiltonian Energy Theory
p.307

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 331Robot Grasp Pattern Recognition Based on Wavlet...

Robot Grasp Pattern Recognition Based on Wavlet and BP Neural Network

Abstract:

Tactile sensation is one of essential perceptions for a functional robot hand to monitor slip states, grasp objects with proper force, and distinguish different properties of objects etc. A practical tactile sensor based on acoustic-electric converting principle is introduced. The grasp signals of objects of three sort materials are collected by the tactile sensor. The power spectrum feature vectors of them are taken as learning sample book set. Transfer function of neurons in hidden layer is tangent function and that in output layer is logarithmic function. L-M algorithm is selected and convergence precision set is as 0.0001. The hidden layer nodes are taken by experiments as 13. When neural network structure is 8-13-4, BP neural network has the fastest convergence rate and short running time of milliseconds.

You might also be interested in these eBooks

2013 International Conference on Process Equipment, Mechatronics Engineering and Material Science

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 331)

Pages:

290-293

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.331.290

Citation:

Cite this paper

Online since:

July 2013

Authors:

Jin Jun Chen, Ting Xiang

Keywords:

Acoustic-Electric, Pattern Recognition, Spectrum, Tactile Sensor, Wavelet Packet

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Liu shao-qiang ,Huang Wei-yi, Wang Ai-min, et al. Overview and prospect of research and development on robot tactile sensory technology. Robot. 2002 24(4):362-367.

Google Scholar

[2] Pan Ying-jun. Research and development of tactile sensing technology in intelligent robots. China Optical Conference.(2004)

Google Scholar

[3] Wang Ying, Chen Jin-jun. Research of touch-slide sensor based on theory of acoustic. Chinese journal of sensor and actuators.2009 22(12):1701-1703.

Google Scholar

[4] Hua Zi-xing. Current situation and development of microphone. Industry Perspective. 2007 4-8.

Google Scholar

[5] Zhang Ming-yuan, Yu Ming. Wavelet packet decomposition-based feature extraction of under water detector targets. Forestry machinery and woodworking equipment.2009 37(3):24-27.

Google Scholar

[6] Xue Hui, Wang Ren-gang. Frequency division character of wavelet packet transform. Proceedings of the EPSA.2003 15(2) 5-8.

Google Scholar

[7] Zhong You-ming. Wavelet time-frequency analysis and characterization. Journal of vibration, measurement and diagnosis.2009 29(1) 51-54.

Google Scholar