公开(公告)号：US11620021B1

公开(公告)日：2023-04-04

申请号：US17020749

申请日：2020-09-14

Applicant: Apple Inc.

Inventor： Sai Zhang ,  Behrooz Shahsavari ,  Ari Y. Benbasat ,  Nima Ferdosi

IPC: G06F3/041 ,  G06F3/044

Abstract: Cross-coupling correction techniques on a touch sensor panel can be improved using machine learning models (particularly for touch sensor panels with relatively low signal-to-noise ratio). In some examples, the machine learning model can be implemented using a neural network. The neural network can receive a touch image and perform cross-coupling correction to mitigate cross-talk due to routing traces of the touch sensor panel. Mitigating cross-talk can improve touch sensing accuracy, reduce jitter, and/or reduce false positive touch detection.

公开(公告)号：US11449802B2

公开(公告)日：2022-09-20

申请号：US16937481

申请日：2020-07-23

Applicant: Apple Inc.

Inventor： Charles Maalouf ,  Shawn R. Scully ,  Christopher B. Fleizach ,  Tu K. Nguyen ,  Lilian H. Liang ,  Warren J. Seto ,  Julian Quintana ,  Michael J. Beyhs ,  Hojjat Seyed Mousavi ,  Behrooz Shahsavari

IPC: G06V10/00 ,  G06N20/00 ,  G06F3/01 ,  G06F3/04883 ,  G06K9/62 ,  G06N3/08

Abstract: A device implementing a system for machine-learning based gesture recognition includes at least one processor configured to, receive, from a first sensor of the device, first sensor output of a first type, and receive, from a second sensor of the device, second sensor output of a second type that differs from the first type. The at least one processor is further configured to provide the first sensor output and the second sensor output as inputs to a machine learning model, the machine learning model having been trained to output a predicted gesture based on sensor output of the first type and sensor output of the second type. The at least one processor is further configured to determine the predicted gesture based on an output from the machine learning model, and to perform, in response to determining the predicted gesture, a predetermined action on the device.

公开(公告)号：US11287926B1

公开(公告)日：2022-03-29

申请号：US17161499

申请日：2021-01-28

Applicant: Apple Inc.

Inventor： Behrooz Shahsavari ,  Bongsoo Suh ,  Utkarsh Gaur ,  Nima Ferdosi ,  Baboo V. Gowreesunker

IPC: G06F3/041 ,  G06F3/0354 ,  G06F3/044 ,  G06K9/62 ,  G06N3/04

Abstract: In some examples, an electronic device can use machine learning techniques, such as convolutional neural networks, to estimate the distance between a stylus tip and a touch sensitive surface (e.g., stylus z-height). A subset of stylus data sensed at electrodes closest to the location of the stylus at the touch sensitive surface including data having multiple phases and frequencies can be provided to the machine learning algorithm. The estimated stylus z-height can be compared to one or more thresholds to determine whether or not the stylus is in contact with the touch sensitive surface.

公开(公告)号：US11025098B2

公开(公告)日：2021-06-01

申请号：US15875287

申请日：2018-01-19

Applicant: Apple Inc.

Inventor： Behrooz Shahsavari ,  Sneha Kadetotad ,  Weiyu Huang ,  Baboo V. Gowreesunker

IPC: H02J50/60 ,  H02J7/02 ,  H02J50/12 ,  G08B21/18 ,  G06K9/62 ,  G01R27/26 ,  H01F38/14 ,  H04B5/00 ,  G08B3/10 ,  G08B5/22

Abstract: A wireless power transmission system has a wireless power receiving device with a wireless power receiving coil that is located on a charging surface of a wireless power transmitting device with a wireless power transmitting coil array. Control circuitry in the wireless power transmitting device may use inverter circuitry to supply alternating-current signals to coils in the coil array, thereby transmitting wireless power signals. The control circuitry may also be used to detect foreign objects on the coil array such as metallic objects without wireless power receiving coils. For example, control circuitry may use inductance measurements from the coils in the coil array to determine a probability value indicative of whether a foreign object is present on the charging surface. The control circuitry may compare the probability value to a threshold and take suitable action in response to the comparison.

公开(公告)号：US10236725B1

公开(公告)日：2019-03-19

申请号：US15875418

申请日：2018-01-19

Applicant: Apple Inc.

Inventor： Behrooz Shahsavari ,  Weiyu Huang ,  Sneha Kadetotad ,  Baboo V. Gowreesunker

IPC: H01M10/46 ,  H02J50/12 ,  H02J50/60 ,  H02J50/40 ,  H02J7/02 ,  H02J7/00 ,  H02J7/04 ,  H02J50/80

Abstract: A wireless power transmission system has a wireless power receiving device with a wireless power receiving coil that is located on a charging surface of a wireless power transmitting device with a wireless power transmitting coil array. Control circuitry in the wireless power transmitting device may use inverter circuitry to supply alternating-current signals to coils in the coil array, thereby transmitting wireless power signals. The control circuitry may also be used to detect foreign objects on the coil array such as metallic objects without wireless power receiving coils. For example, control circuitry may use inductance measurements from the coils in the coil array to identify segments of the coil array that correspond to potential wireless power receiving devices. The control circuitry may control wireless power transmission based on a comparison between the number of identified segments corresponding to potential wireless power receiving devices and a number of received device-identifiers.

公开(公告)号：US11954288B1

公开(公告)日：2024-04-09

申请号：US17406990

申请日：2021-08-19

Applicant: Apple Inc.

Inventor： Lichen Wang ,  Behrooz Shahsavari ,  Hojjat Seyed Mousavi ,  Nima Ferdosi ,  Baboo V. Gowreesunker

IPC: G06F3/041 ,  G06F3/044 ,  G06N3/044 ,  G06N3/08

CPC classification number: G06F3/04182 ,  G06F3/044 ,  G06N3/044 ,  G06N3/08 ,  G06F2203/04104

Abstract: In some examples, touch data can include noise. Machine learning techniques, such as gated recurrent units and convolutional neural networks can be used to mitigate noise present in touch data. In some examples, a gated recurrent unit stage and a convolutional neural network stage can be arranged in series, such as by providing the output of the gated recurrent unit as input to the convolutional neural network. The gated recurrent unit can remove noise caused by a first component of the electronic device and the convolutional neural network can remove noise caused by a second component of the electronic device, for example. Thus, together, the gated recurrent unit and the convolutional neural network can remove or substantially reduce the noise in the touch data.

公开(公告)号：US11899881B2

公开(公告)日：2024-02-13

申请号：US17123015

申请日：2020-12-15

Applicant: Apple Inc.

Inventor： Hojjat Seyed Mousavi ,  Nima Ferdosi ,  Baboo V. Gowreesunker ,  Behrooz Shahsavari

IPC: G06F3/041 ,  G06N3/08 ,  G06F18/25

CPC classification number: G06F3/0418 ,  G06F18/251 ,  G06N3/08

Abstract: In some examples, touch data can include noise. The noise can be generated by a component of an electronic device that includes a touch screen. For example, one or more signals transmitted to the display circuitry of an electronic device can become capacitively coupled to the touch circuitry of the device and cause noise in the touch data. Machine learning techniques, such as gated recurrent units and/or convolutional neural networks can estimate and reduce or remove noise from touch data when provided data or information about the displayed image as input. In some examples, the algorithm includes one or more of a gated recurrent unit stage and a convolutional neural network stage. In some examples, a gated recurrent unit stage and a convolutional neural network stage can be arranged in series, such as by providing the output of the gated recurrent unit as input to the convolutional neural network.

公开(公告)号：US11699104B2

公开(公告)日：2023-07-11

申请号：US17869740

申请日：2022-07-20

Applicant: Apple Inc.

Inventor： Charles Maalouf ,  Shawn R. Scully ,  Christopher B. Fleizach ,  Tu K. Nguyen ,  Lilian H. Liang ,  Warren J. Seto ,  Julian Quintana ,  Michael J. Beyhs ,  Hojjat Seyed Mousavi ,  Behrooz Shahsavari

IPC: G06V10/00 ,  G06N20/00 ,  G06F3/01 ,  G06F3/04883 ,  G06F18/214 ,  G06N3/08

CPC classification number: G06N20/00 ,  G06F3/015 ,  G06F3/017 ,  G06F3/04883 ,  G06F18/2155 ,  G06N3/08

Abstract: A device implementing a system for machine-learning based gesture recognition includes at least one processor configured to, receive, from a first sensor of the device, first sensor output of a first type, and receive, from a second sensor of the device, second sensor output of a second type that differs from the first type. The at least one processor is further configured to provide the first sensor output and the second sensor output as inputs to a machine learning model, the machine learning model having been trained to output a predicted gesture based on sensor output of the first type and sensor output of the second type. The at least one processor is further configured to determine the predicted gesture based on an output from the machine learning model, and to perform, in response to determining the predicted gesture, a predetermined action on the device.

公开(公告)号：US11599223B1

公开(公告)日：2023-03-07

申请号：US17249791

申请日：2021-03-12

Applicant: Apple Inc.

Inventor： Baboo V. Gowreesunker ,  Behrooz Shahsavari ,  Hojjat Seyed Mousavi ,  Nima Ferdosi ,  Lichen Wang ,  Nariman Farsad

IPC: G06F3/041 ,  G06F3/044 ,  G06N3/08

Abstract: In some examples, touch data can include noise. Machine learning techniques, such as gated recurrent units and convolutional neural networks can be used to mitigate noise present in touch data. In some examples, a gated recurrent unit stage and a convolutional neural network stage can be arranged in series, such as by providing the output of the gated recurrent unit as input to the convolutional neural network. The gated recurrent unit can remove noise caused by a first component of the electronic device and the convolutional neural network can remove noise caused by a second component of the electronic device, for example. Thus, together, the gated recurrent unit and the convolutional neural network can remove or substantially reduce the noise in the touch data.

公开(公告)号：US11301099B1

公开(公告)日：2022-04-12

申请号：US16833394

申请日：2020-03-27

Applicant: Apple Inc.

Inventor： Behrooz Shahsavari ,  Hojjat Seyed Mousavi ,  Nima Ferdosi ,  Baboo V. Gowreesunker

IPC: G06F3/044 ,  G06F3/01 ,  G06F3/042

Abstract: Finger detection and separation techniques on a multi-touch touch sensor panel can be improved using machine learning models (particularly for touch sensor panels with relatively low signal-to-noise ratio). In some examples, a machine learning model can be used to process an input patch to disambiguate whether the input patch corresponds to one contact or two contacts. In some examples, the machine learning model can be implemented using a neural network. The neural network can receive a sub-image including an input patch as an input, and can output a number of contacts. In some examples, the neural network can output one or more sub-image masks representing the one or more contacts.