公开(公告)号：US20190102031A1

公开(公告)日：2019-04-04

申请号：US16143374

申请日：2018-09-26

Applicant: Apple Inc.

Inventor： Julian K. Shutzberg ,  Baboo V. Gowreesunker ,  Collin R. Petty

IPC: G06F3/041

Abstract: Disclosed are electronic devices and methods of their operation that use force sensors to detect user applied forces on an input surface and determine their locations on the input surface, using only force sensors. The locations may be determined using weighted averages of the positions of the force sensors and their values. The methods may compare dynamically updated baseline force values to received force sensor values to distinguish user applied forces from changes in the force sensor values caused other sources. After detection of a user applied force, the baseline force values are frozen, and the force sensor values used to find the location on the input surface where the user applied the force. The electronic device can operate according to a state space model, with a first state in which there is no user applied force, and a second state in which there is user applied force.

公开(公告)号：US20190074730A1

公开(公告)日：2019-03-07

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

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：US09885627B2

公开(公告)日：2018-02-06

申请号：US14696043

申请日：2015-04-24

Applicant: Apple Inc.

Inventor： Baboo V. Gowreesunker ,  Wayne C. Westerman

IPC: G01L25/00

CPC classification number: G01L25/00

Abstract: Disclosed herein are methods and systems for compensating for drift that may be present in a force sensing device. In some embodiments, the force sensing device may be calibrated to compensate for the drift. The calibration may include receiving an input waveform associated with a received amount of force on the force sensing device. A system model that approximates a transfer function that provides an output waveform associated with the input waveform is then determined. Using the system model, an inverse transfer function associated with the system model is also determined. The inverse transfer function may then be applied to the output waveform which compensates for the drift.

公开(公告)号：US09797753B1

公开(公告)日：2017-10-24

申请号：US14601153

申请日：2015-01-20

Applicant: Apple Inc.

Inventor： Baboo V. Gowreesunker ,  Steven P. Hotelling ,  Wayne C. Westerman

IPC: G01D5/38 ,  G01D5/347 ,  G01B11/26

CPC classification number: G01D5/3473 ,  G01B11/26 ,  G01D5/34715

Abstract: Rotary encoders suitable for inclusion within small form factor devices (e.g., as input devices to small form factor electronic devices) are disclosed. In one aspect, a light source can illuminate a pattern on a rotatable shaft in order to reflect the pattern onto an array of optical sensors. Each optical sensor from the array of optical sensors can be polled at the same time to yield a snapshot vector. The snapshot vector can be projected onto a subspace spanned by two vectors selected in part on the pattern of the rotatable shaft and the distance separating the shaft and array. The resulting projection can be used to determine error and phase of the reflected pattern across the array of optical sensors. The phase of the reflected pattern can correlate to rotation of the shaft.

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：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.

公开(公告)号：US10302465B2

公开(公告)日：2019-05-28

申请号：US15594834

申请日：2017-05-15

Applicant: Apple Inc.

Inventor： Baboo V. Gowreesunker ,  Joseph William Colosimo ,  Vladimir Fedorov

IPC: G01D5/347 ,  G05G9/047 ,  G06F3/0362

Abstract: A light source in a rotary optical encoder can illuminate a pattern on a rotatable shaft and an optical sensor can detect either the light that is reflected or transmitted based on the pattern. A sampling rate of the optical sensor is dynamically adjusted based on a rotational speed of the rotatable shaft. A pulse rate of the light source may also be dynamically adjusted based on the sampling rate of the optical sensor.

公开(公告)号：US20190081516A1

公开(公告)日：2019-03-14

申请号：US15875127

申请日：2018-01-19

Applicant: Apple Inc.

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

IPC: H02J50/60 ,  H02J7/02 ,  H02J50/12 ,  H02J50/40 ,  G01R27/26

Abstract: A wireless power transmission system has a wireless power receiving device that is located on a charging surface of a wireless power transmitting device. The wireless power receiving device has a wireless power receiving coil and the wireless power transmitting device has a wireless power transmitting coil array. Signal measurement circuitry coupled to the coil array may make measurements while the control circuitry uses the inverter circuitry to apply excitation signals to each of the coils. Foreign objects on the coil array such as metallic objects without wireless power receiving coils can be detected using foreign object detection. When multiple wireless power receiving devices are present on the wireless power transmitting device, steps may be taken to isolate measurements from the coils associated with each wireless power receiving device. Foreign object detection may then be performed on these modified measurements.