# US 2023/0021447 A1 · Method for Estimating Intention Using Unsupervised Learning

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0021447 A1
- Document ID: US20230021447A1
- Status: Published application
- Kind: A1
- Application number: 17/844,361
- Filed: 2022-06-20
- Published: 2023-01-26
- Earliest claimed: 2021-07-26
- Assignees: Hyundai Motor Company; Kia Corporation
- Applicants: Hyundai Motor Company; Kia Corporation
- Inventors: Muhammad Zahak Jamal; Ju Young Yoon; Dong Hyun Lee
- Web page: https://patentgrep.com/patent/US20230021447A1

## CPC

- B25J 15/0009: {comprising multi-articulated fingers, e.g. resembling a human hand}
- G05B 19/4155: characterised by program execution, i.e. part program or machine function execution, e.g. selection of a program
- B25J 9/1612: {characterised by the hand, wrist, grip control}
- B25J 9/1694: {characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion}
- B25J 13/00: Controls for manipulators (program controls B25J9/16)
- B25J 13/02: Hand grip control means {(handles or pedals for crane control B66C13/56; for measuring the force applied to control members G01L5/22; hand-held casings for switching devices, e.g. joy-sticks H01H9/0214)}
- G06F 3/014: {Hand-worn input/output arrangements, e.g. data gloves}
- G06F 3/015: {Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection}
- G06F 3/016: {Input arrangements with force or tactile feedback as computer generated output to the user}
- G06F 3/14: Digital output to display device {; Cooperation and interconnection of the display device with other functional units}
- G05B 2219/36435: Electromyographical, myoelectric control signal
- G05B 2219/40264: Human like, type robot arm
- B25J: MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES ({manipulators specially adapted for use in surgery A61B34/70; manipulators used in cleaning hollow articles B08B9/04}; manipulators associated with rolling mills B21B39/20; manipulators associated with forging machines B21J13/10; {manipulators associated with picking-up and placing mechanisms B23P19/007}; means for holding wheels or parts thereof B60B30/00; {vehicles with ground-engaging propulsion means, e.g. walking members B62D57/02, B62D57/032; devices for picking-up and depositing articles or materials between conveyors B65G47/90, B65G47/91; manipulators with gripping or holding means for transferring packages B65H67/065}; cranes B66C; {manipulators used in the protection or supervision of pipe-line installations F17D5/00; walking equipment adapted for nuclear steam-generators F22B37/006}; manipulators specially adapted for, or associated with, nuclear reactors G21C; {apparatus used for handling wafers during manufacture or treatment of semiconductor H10P72/50})
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

This patent proposal document provides a complete robot hand control scheme using myoelectric intention estimation of the human being using the kernel Principal Component Analysis Algorithm (kPCA). The robot hand system includes a biometric EMG sensor system, a robot hand including with multiple fingers, a controller connected with the biometric EMG sensor system, and a robot hand. The controller acquires the biometric EMG signal by means of a biometric sensor system, estimates myoelectric motion intention by applying the kernel principal component analysis (kPCA) algorithm using a kernel function, and delivers a control command corresponding to the estimated motion intention of the user to the robot hand.

## Claims

### Claim 1

A robot hand system, the system comprising:
a biometric sensor system;
a robot hand including a plurality of fingers; and
a controller connected with the biometric sensor system and the robot hand, wherein the controller is configured to:
obtain a biometric signal using the biometric sensor system;
estimate a motion intention by applying a kernel principal component analysis to which at least one kernel function is applied to the biometric signal; and
deliver a control command corresponding to the estimated motion intention to the robot hand.

### Claim 2 (depends on 1)

The system of claim 1, further comprising an output device, wherein the controller is configured to output a graphic user interface indicating the estimated motion intention through the output device.

### Claim 3 (depends on 1)

The system of claim 1, wherein the controller is configured to:
calculate a first kernel matrix for a recorded biometric signal using the at least one kernel function;
center the first kernel matrix;
calculate an eigenvector for the first kernel matrix; and
learn a mapping function based on the eigenvector.

### Claim 4 (depends on 3)

The system of claim 3, wherein the controller is configured to:
calculate a second kernel matrix for the biometric signal using the at least one kernel function;
center the second kernel matrix; and
estimate the motion intention based on the learned mapping function and the centered second kernel matrix.

### Claim 5 (depends on 1)

The system of claim 1, wherein the biometric sensor system comprises:
a plurality of electrodes configured to receive a signal;
an instrumentation amplifier configured to measure and amplify the received signal;
a filter configured to filter the amplified signal at a specified frequency band;
a gain controller configured to adjust a gain of the filtered signal to a specified value; and
a data collection device configured to collect data for the biometric signal from the signal, the gain of which is adjusted.

### Claim 6 (depends on 1)

The system of claim 1, wherein the controller is configured to generate the control command by applying a moving average filter to the estimated motion intention.

### Claim 7

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; and
operating a robot hand in response to the estimated motion intention.

### Claim 8 (depends on 7)

The method of claim 7, further comprising outputting a graphic user interface indicating the estimated motion intention.

### Claim 9 (depends on 7)

The method of claim 7, further comprising:
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.

### Claim 10 (depends on 9)

The method of claim 9, further comprising:
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.

### Claim 11 (depends on 7)

The method of claim 7, wherein the robot hand includes a plurality of fingers.

### Claim 12 (depends on 7)

The method of claim 7, further comprising:
receiving a signal;
measuring and amplifying the received signal;
filtering the amplified signal at a specified frequency band;
adjusting a gain of the filtered signal to a specified value; and
collecting data for the biometric signal from the signal, the gain of which is adjusted.

### Claim 13 (depends on 7)

The method of claim 7, further comprising generating a control command by applying a moving average filter to the estimated motion intention.

### Claim 14

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; and
operating a robot hand in response to the estimated motion intention.

### Claim 15 (depends on 14)

The non-transitory computer-readable storage medium of claim 14, wherein the program further comprises instructions for outputting a graphic user interface indicating the estimated motion intention.

### Claim 16 (depends on 14)

The non-transitory computer-readable storage medium of claim 14, wherein the program further comprises instructions for:
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.

### Claim 17 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein the program further comprises instructions for:
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.

### Claim 18 (depends on 14)

The non-transitory computer-readable storage medium of claim 14, wherein the program further comprises instructions for:
receiving a signal;
measuring and amplifying the received signal;
filtering the amplified signal at a specified frequency band;
adjusting a gain of the filtered signal to a specified value; and
collecting data for the biometric signal from the signal, the gain of which is adjusted.

### Claim 19 (depends on 14)

The non-transitory computer-readable storage medium of claim 14, wherein the program further comprises instructions for generating a control command by applying a moving average filter to the estimated motion intention.
