Application US20200057498

SYSTEMS AND METHODS FOR A HYBRID BRAIN INTERFACE FOR ROBOTIC SWARMS USING EEG SIGNALS AND AN INPUT DEVICE
[+] Show Details

US20200057498

1. A method, comprising: (5) (7)

utilizing a processor in communication with a tangible storage medium storing instructions that are executed by the processor to perform operations comprising: accessing data associated with a plurality of test Electroencephalographic (EEG) signals, and

training a machine learning model to identify a brain state associated with a predetermined signal of the plurality of test EEG signals using the data;

providing an interface in communication with the processor, the interface configured to access a plurality of control EEG signals;

providing an input device in communication with the processor for generating input data associated with a desired position, the desired position associated with a plurality of robotic devices;

translating the input data to a first command configured to move the plurality of robotic devices collectively to the desired position;

translating a control signal of the plurality of control EEG signals to control data;

applying the control data to the machine learning model to identify the brain state; and

generating a second command configured to adjust a density associated with the plurality of robotic devices based on the brain state.

2. The method of claim 1, further comprising: (0) (2)

3. The method of claim 1, further comprising: (0) (2)

4. The method of claim 1, further comprising: (0) (1)

5. The method of claim 1, wherein the data associated with the plurality of test EEG signals is derived from a plurality of channels of interest arranged along a sensorimotor cortex. (0)

6. The method of claim 1, further comprising extracting a set of features from the data associated with the plurality of test EEG signals. (1) (0)

7. The method of claim 6, further comprising extracting the set of features by: (1) (2)

applying a Hanning window to the data; and

applying a Fast Fourier Transform (FFT) to the data to generate a set of spectral features.

8. The method of claim 7, further comprising: (1) (1)

applying Principal Component Analysis (PCA) to the set of spectral features.

9. The method of claim 8, further comprising: (1) (1)

11. A device, comprising: (4) (3)

a control interface, the control interface defining a plurality of electrodes configured for accessing a plurality of brain signals associated with a plurality of channels located over a sensorimotor cortex;

a processor in operative communication with the control interface, the processor configured to: train a machine learning model to associate a brain state with data defining a brain signal,

decode a control signal of the plurality of brain signals to generate control data,

apply the control data to the machine learning model to identify the brain state, and

transmit instructions to a plurality of robotic devices to modify a density of the plurality of robotic devices based on the brain state; and

an input device in operable communication with the processor for generating input data, the input data utilized by the processor to modify a position of the plurality of robotic devices.

12. The device of claim 11, wherein the processor is configured to detect a frequency where (ERD/ERS) phenomena exceeds a predefined threshold value. (0)

13. The device of claim 11, wherein the plurality of channels includes C3, Cz, C4, FC3, CP3, C1, FCz, CPz, C2, FC4, and CP4. (0)

14. The device of claim 11, wherein a thresholding procedure is applied by the processor to reduce a probability of misclassification during a control phase. (0)

15. The device of claim 11, wherein the plurality of robotic devices each comprise rotorcraft and the processor translates data associated with brain states and the input data to desired changes in positions of the rotorcraft. (0)

16. A device, comprising: (4) (3)

an interface configured for accessing a brain signal;

a processor in communication with the interface, the processor configured to decode the brain signal to control data defining a known brain state, the processor further configured to control a first movement associated with a plurality of robotic devices using the control data associated with the known brain state; and

an input device in operable communication with the processor for generating input data interpretable by the processor to control a second movement associated with the plurality of robotic devices.

17. The device of claim 16, wherein the first movement comprises a movement of one or more of the plurality of robotic devices to adjust a density associated with the plurality of robotic devices. (0)

18. The device of claim 16, wherein the second movement comprises a shift in position of the plurality of robotic devices collectively. (0)

19. The device of claim 16, wherein the processor is configured to train a machine learning model to classify brain states from the control data using Hidden Markov Models and Principal Component Analysis, the brain states associated with intended movement of one or more of the plurality of robotic devices. (0)

20. The device of claim 16, wherein the processor combines the control data with the input data to control the plurality of robotic devices in real-time and increase an amount of degrees of freedom associated with a user. (0)

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Application US20200057498

SYSTEMS AND METHODS FOR A HYBRID BRAIN INTERFACE FOR ROBOTIC SWARMS USING EEG SIGNALS AND AN INPUT DEVICE

Patent Matrix® Search