Radical basis function neural network for a novel tactile sensor design

In this paper, a decoupling algorithm based on the RBF (radical basis function) network is proposed. Compared to the Levenberg-Marquardt (L-M) algorithm and CMA-ES algorithm, numerical experiments show that the decoupling algorithm based on the radial basis function network is of higher performance on both accuracy and time complexity, which makes the real-time property of the tactile sensor possible. In the further research, the mapping between the force and the deformation of the tactile sensor surface can be revealed by the ANSYS simulation, and the RBF network plays a key role in the digital model of the tactile sensor.

[1]  Ge Yunjian.  Research of A Novel Three-Dimensional Force Flexible Tactile Sensor , 2009 .

[2]  John E. Dennis,et al.  Numerical methods for unconstrained optimization and nonlinear equations , 1983, Prentice Hall series in computational mathematics.

[3]  Tao Liu,et al.  Design of low-cost tactile force sensor for 3D force scan , 2008, 2008 IEEE Sensors.

[4]  Hyung-Kew Lee,et al.  A Flexible Polymer Tactile Sensor: Fabrication and Modular Expandability for Large Area Deployment , 2006, Journal of Microelectromechanical Systems.

[5]  Nikolaus Hansen,et al.  Completely Derandomized Self-Adaptation in Evolution Strategies , 2001, Evolutionary Computation.

[6]  Hiroyuki Shinoda,et al.  Passive wireless sensing element for sensitive skin , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[7]  Á. Tar,et al.  Development of a low cost 3D optical compliant tactile force sensor , 2011, 2011 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM).

[8]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[9]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[10]  Benjamin C. K. Tee,et al.  Highly sensitive flexible pressure sensors with microstructured rubber dielectric layers. , 2010, Nature materials.

[11]  Feng Shuang,et al.  Design of a Large-scale Three-dimensional Flexible Arrayed Tactile Sensor , 2009 .

[12]  S. Büttgenbach,et al.  Development, fabrication and characterization of a 3D tactile sensor , 2009 .

[13]  Petros Koumoutsakos,et al.  Reducing the Time Complexity of the Derandomized Evolution Strategy with Covariance Matrix Adaptation (CMA-ES) , 2003, Evolutionary Computation.

[14]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[15]  O. Paul,et al.  Novel 3D piezoresistive silicon force sensor for dimensional metrology of micro components , 2005, IEEE Sensors, 2005..

[16]  Yu Ge,et al.  Design and fabrication of an integrated three-dimensional tactile sensor for space robotic applications , 1999, Technical Digest. IEEE International MEMS 99 Conference. Twelfth IEEE International Conference on Micro Electro Mechanical Systems (Cat. No.99CH36291).

[17]  Chang Liu,et al.  Super flexible sensor skin using liquid metal as interconnect , 2007, 2007 IEEE Sensors.

[18]  Z. Vizvary,et al.  Characterization of an Integrable Single-Crystalline 3-D Tactile Sensor , 2006, IEEE Sensors Journal.