Method for estimating intention using unsupervised learning

A method of operating a robot hand system, the method comprising:

• obtaining a biometric signal;
• estimating a motion intention by applying a kernel principal component analysis to which at least one kernel function is applied to the biometric signal;
• calculating a first kernel matrix for a recorded biometric signal based on the at least one kernel function;
• centering the first kernel matrix;
• calculating an eigenvector for the first kernel matrix;
• learning a mapping function based on the eigenvector:
• calculating a second kernel matrix for the biometric signal based on the at least one kernel function;
• centering the second kernel matrix;
• estimating the motion intention based on the learned mapping function and the centered second kernel matrix;
• and
• operating a robot hand in response to the estimated motion intention.

A non-transitory computer-readable storage medium on which a program is stored, the program comprising instructions for performing steps of:

• obtaining a biometric signal;
• estimating a motion intention by applying a kernel principal component analysis to which at least one kernel function is applied to the biometric signal;
• calculating a first kernel matrix for a recorded biometric signal based on the at least one kernel function;
• centering the first kernel matrix;
• calculating an eigenvector for the first kernel matrix;
• and
• learning a mapping function based on the eigenvector;
• calculating a second kernel matrix for the biometric signal based on the at least one kernel function;
• centering the second kernel matrix;
• and
• estimating the motion intention based on the learned mapping function and the centered second kernel matrix;
• and
• operating a robot hand in response to the estimated motion intention.