Apple Inc.

Behrooz Shahsavari

Baboo V Gowreesunker

Nima Ferdosi

Hojjat Seyed Mousavi

Christopher Brian Fleizach

Sneha Kadetotad

Tu K Nguyen

Michael J Beyhs

Shawn R Scully

Charles Maalouf

Julian Quintana

Lilian H Liang

Warren J Seto

Lichen Wang

Weiyu Huang

Utkarsh Gaur

Sai Zhang

Jacob E Mattingley

Bongsoo Suh

Steven Porter Hotelling

Ari Y Benbasat

Joseph C Doll

Michael A Cretella

Siddharth Seth

Douglas J Adams

David Steven Graff

J Stephen Smith

Dor Shaviv

Nariman Farsad

Yash S Agarwal

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.

System and machine learning method for separating noise and signal in multitouch sensors

Touch sensor panels/screens can include a first region having a plurality of touch electrodes and a second region without touch electrodes. In some examples, to improve touch sensing performance, a first algorithm or a second algorithm is applied to determine whether an object corresponding to the touch patch is in contact with the touch screen. Whether to apply the first algorithm or the second algorithm is optionally dependent on the location of the touch patch.

Systems and methods for touch sensing on devices including regions with and without touch electrodes

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.

Machine-learning based gesture recognition using multiple sensors

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. In some examples, the electronic device can use machine learning techniques to estimate the (x, y) position and/or tilt and/or azimuth angles of the stylus tip at the touch sensitive surface based on a subset of stylus data.

System and machine learning method for localization of an input device relative to a touch sensitive surface

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.

Machine learning method and system for suppressing display induced noise in touch sensors using information from display circuitry

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.

Methods and apparatus for cross-coupling correction on a touch sensor panel

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.

Methods and apparatus for finger detection and separation on a touch sensor panel using machine learning models

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.

System and machine learning method for detecting input device distance from touch sensitive surfaces

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.

Wireless charging system with machine-learning-based foreign object detection

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.

Foreign object detection in wireless charging systems with multiple power receiving devices present on a power transmitting device

A wireless power transmitting device transmits wireless power signals to a wireless power receiving device. The wireless power receiving device has a rectifier and a wireless power receiving coil that receives wireless power signals. The wireless power transmitting device uses a layer of coils to transmit the wireless power signals. A dielectric layer in the wireless power transmitting device defines a charging surface that receives the wireless power receiving device. A layer of temperature sensors is interposed between the layer of coils and the dielectric layer. Control circuitry in the wireless power transmitting device uses temperature information from the temperature sensors to determine whether a foreign object such as a coin is present on the charging surface.

Growing community of inventors

Hayward, CA, United States of America

Behrooz Shahsavari