US 12,296,482 B2
System for controlling robot finger and method for the same
Muhammad Zahak Jamal, Yongin-si (KR); Dong Jin Hyun, Suwon-si (KR); and Dong Hyun Lee, Uiwang-si (KR)
Assigned to HYUNDAI MOTOR COMPANY, Seoul (KR); and KIA CORPORATION, Seoul (KR)
Filed by HYUNDAI MOTOR COMPANY, Seoul (KR); and Kia Corporation, Seoul (KR)
Filed on Sep. 15, 2021, as Appl. No. 17/475,771.
Claims priority of application No. 10-2020-0121746 (KR), filed on Sep. 21, 2020.
Prior Publication US 2022/0088777 A1, Mar. 24, 2022
Int. Cl. B25J 9/16 (2006.01); B25J 15/10 (2006.01)
CPC B25J 9/163 (2013.01) [B25J 9/1607 (2013.01); B25J 9/1612 (2013.01); B25J 15/10 (2013.01); B25J 9/161 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A system for controlling a robot finger, the system comprising:
a processor configured to determine a mapping function using a kernel matrix by a multichannel electromyographic (EMG) signal to train a learning algorithm through at least one EMG signal training sample; and
a storage configured to store data and an algorithm driven by the processor,
wherein the processor is configured to:
determine the kernel matrix by applying a polynomial function to the at least one EMG signal training sample;
perform an operation for the kernel matrix and the mapping function to output a signal and control the robot finger using the signal;
evaluate the kernel matrix by determining individual terms of a second order polynomial function using the multichannel EMG signal; and
determine a covariance matrix of kernel matrix value, and
wherein the processor is further configured to:
calculate the kernel matrix value by calculating a sum of the at least one EMG signal and calculating a square of the sum.