# US 2025/0147590 A1 · Method and Device for Carrying Out Eye Tracking > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0147590 A1 - Document ID: US20250147590A1 - Status: Published application - Kind: A1 - Application number: 18/835,729 - Filed: 2023-01-19 - Published: 2025-05-08 - Earliest claimed: 2022-02-09 - Assignees: Robert Bosch GmbH - Applicants: Robert Bosch GmbH - Inventors: Christoph Wieland; Daniela Zoeller-Borst; Victor Pankratius - Web page: https://patentgrep.com/patent/US20250147590A1 ## CPC - G06F 3/013: {Eye tracking input arrangements (G06F3/015 takes precedence)} - G06F 3/015: {Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection} - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/08: Learning methods - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method is disclosed for determining an eye position and/or eye gesture, in particular for use in controlling a function of an application system, in particular a wearable. The method includes (i) recording a profile of at least one EEG signal over time by way of a contact electrode in order to obtain a signal time series of the at least one EEG signal, (ii) providing input data sets from a signal block which arises from the signal time series, for successive time windows, and (iii) evaluating the input data sets in a data-based eye movement model in order to obtain the eye position or eye gesture, the eye movement model being formed using a neural network with one or more recurrent layers, in particular a respective LSTM layer or GRU layer or a transformer layer, and one or more neuron layers. ## Claims ### Claim 1 A method for determining an eye position and/or eye gesture for use in controlling a function of a wearable, comprising: acquiring a profile of at least one EEG signal over time by way of a contact electrode in order to obtain a signal time series of the at least one EEG signal; providing input data sets from a signal block resulting from the signal time series for successive time windows; and evaluating the input data sets in a data-based eye movement model in order to obtain the eye position or eye gesture, the eye movement model being formed using a neural network with one or more recurrent layers and one or more neuron layers. ### Claim 2 (depends on 1) The method according to claim 1, wherein; the signal time series is processed to remove interference, the interference includes a jitter, a potential trend, and/or a noise component and is removed or reduced by way of conventional digital signal processing techniques, and the input data sets are provided from the signal block which results from or with the processed signal time series. ### Claim 3 (depends on 1) The method according to claim 1, wherein: the eye position is provided in a two-dimensional eye coordinate system, and an x-value indicates a horizontal eye position and a y-value indicates a vertical eye position. ### Claim 4 (depends on 1) The method according to claim 1, wherein: one or more signal characteristics are extracted from the signal time series(S) or the processed signal time series, and the one or more signal characteristics are added to the relevant input data set for the respective time window. ### Claim 5 A method for training a data-based eye movement model, wherein the eye movement model is a neural network comprising one or more recurrent layers and one or more neuron layers, comprising: creating training data sets, wherein the training data sets are respectively created by acquiring a profile of at least one EEG signal over time by way of at least one contact electrode in order to obtain a signal time series of the at least one EEG signal; determining a signal block depending on the signal time series for one of successive time windows, determining an eye position and/or eye gesture during the respective time window, providing an input data set from the respective signal block and the associated eye position and/or an associated eye gesture as a training data set; and training the eye movement model with the training data sets. ### Claim 6 (depends on 5) The method according to claim 5, wherein: at least one signal characteristic is respectively added to the input data set, and the at least one signal characteristic is extracted from the signal time series or a processed signal time series. ### Claim 7 (depends on 1) A device for carrying out the method according to claim 1. ### Claim 8 (depends on 7) An application system, comprising: one or more attached contact electrodes configured to acquire a respective EEG signal; and the device according to claim 7. ### Claim 9 (canceled) ### Claim 10 (depends on 1) The method according to claim 1, wherein the one or more recurrent layers includes a respective LSTM layer or GRU layer or a transformer layer. ### Claim 11 (depends on 1) The method according to claim 1, wherein the conventional digital signal processing techniques include at least one of linear regression, trend elimination, and noise elimination. ### Claim 12 (depends on 5) The method according to claim 5, wherein the one or more recurrent layers includes a respective LSTM layer or GRU layer or a transformer layer. ### Claim 13 (depends on 8) The application system according to claim 8, wherein the application system includes a head-mounted device. ### Claim 14 (depends on 13) The application system according to claim 13, wherein: the head-mounted device includes smart glasses, the smart glasses include (i) one or more contact electrodes, and (ii) a side piece and/or a nose pad, and the one or more contact electrodes are disposed on the side piece and/or on the nose pad.