Apple Inc.

Carnegie Mellon University

University of Rochester

Disney Interprises, Inc.

Gierad Laput

Christopher Harrison

Jun Gong

Jared L Zerbe

Kevin M Lynch

William C Athas

Brad W Simeral

Andreas Edgar Schobel

Kartik R Venkatraman

Roberto G Yepez

Shawn R Scully

Charles Maalouf

Daniel P Kumar

Yang Zhang

Robert Xiao

Shiwen Zhao

Bo Robert Xiao

Ardra Singh

Daniel J Drusch

Karan Ashok Ahuja

Ricky Wai Kit Yuen

Shashi K Dua

Archana Venkatesh

Joseph F Alverson

Jingran Zhou

Brian H Tsang

Derek J Dicarlo

Gabrielle Andrea Badie Belzberg

Mayank Goel

Carmel Majidi

Alanson P Sample

Eric J Markvicka

Michael D Bartlett

Jeffrey P Bigham

James T Curran

Chouchang Yang

Ke-Yu Chen

Lining Yao

Yi-Chin Lee

Guanyun Wang

Walter S Lasecki

Xiang Chen

Jason Wiese

Mengying Fang

Runchang Kang

Abhijit Hota

Abdelkareem A Bedri

Chen Chen

Sudershan Boovaraghavan

Yuvraj Agarwal

Techniques may include ranging between a mobile device and a ranging device to obtain ranging measurements. In addition, the techniques may include performing inertial measurements, where the inertial measurements include directional measurements of movement of the mobile device. One or more of the ranging measurements or inertial measurements may be used to identify dwell points where the mobile device is stationary. Moreover, the techniques may include determining vectors of movement between the dwell points using inertial measurements. Also, the techniques may include determining a first and second distance from the ranging device by performing a first and second ranging measurement with the ranging device. Further, the techniques may include determining a direction of movement using inertial measurements. The techniques may include determining the mobile device is at the second dwell point by matching the first direction of movement to a vector of movement between the dwell points.

Learning emergent indoor locations of interest with minimal infrastructure

The present disclosure describes systems and methods associated with selective powering of an electronic display in response to operating conditions, additional data, and/or predicting that the electronic display is not going to be viewed or visible. By selectively enabling the electronic display between power states based on a prediction of when a viewer is expected to view the electronic display, a perceivably always-on electronic display may be provided without the electronic display being always-on, thereby balancing consumer interests with technical requirements of a relatively long battery life and correspondingly low power consumption.

Predictive display power control systems and methods

The present disclosure describes systems and methods associated with selective powering of an electronic display in response to sensed data indicating that the electronic display is not visible. By selectively enabling the electronic display between power states based on whether the electronic display is visible, a perceivably always-on electronic display may be provided without the electronic display being always-on, thereby balancing consumer interests with technical requirements of a relatively long battery life and correspondingly low power consumption.

Sensor-based display power control systems and methods

Ranging between a primary electronic device and a secondary electronic device can be used to control functional states for the electronic devices. One or more functions of a primary electronic device can be controlled based on the location of a secondary electronic device. The secondary electronic device can be a mobile device or a wearable computer, and the secondary device's location can be a proxy for a user's position. The functions, that are enabled or disabled, can be functions that are related to the user's use and enjoyment of the primary device.

Secondary device presence for triggering primary device functionality

Individual health related events (e.g., handwashing events) can be detected based on multiple sensors including motion and audio sensors. Detecting a qualifying handwashing event can include detecting a qualifying scrubbing event based on motion data (e.g., accelerometer data) and a qualifying rinsing event based on audio data. In some examples, power consumption can be reduced by implementing one or more power saving mitigations.

Methods and apparatus for detecting individual health related events

Embodiments described herein provide techniques to enable spatial sensor data from multiple devices to be fused into a single coordinate space. This fused sensor data can then be processed into a point cloud. Point cloud data can then be transformed to enable the classification of objects detected within the sensor data. Features within multiple feature spaces can be extracted from the point cloud data for use in classification. Classification of objects can also be used to correlate objects detected by multiple sensor equipped devices to determine a coordinate space transformation between those devices.

Machine learning based object identification

Systems and processes for user identification using headphones associated with a first device are provided. For example, first movement information corresponding to movement of a second electronic device is detected. Second movement information corresponding to movement of a third electronic device is detected. A similarity score is determined based on the first movement information and the second movement information. In accordance with a determination that the similarity score is above a threshold similarity score, a user is identified as an authorized user of the first electronic device and the second electronic device. Based on the identification, an output is provided to the second electronic device.

User identification using headphones

Embodiments are provided to recognize features and activities from an audio signal. In one embodiment, a model is generated from sound effect data, which is augmented and projected into an audio domain to form a training dataset efficiently. Sound effect data is data that has been artificially created or from enhanced sounds or sound processes to provide a more accurate baseline of sound data than traditional training data. The sound effect data is augmented to create multiple variants to broaden the sound effect data. The augmented sound effects are projected into various audio domains, such as indoor, outdoor, urban, based on mixing background sounds consistent with these audio domains. The model is installed on any computing device, such as a laptop, smartphone, or other device. Features and activities from an audio signal are then recognized by the computing device based on the model without the need for in-situ training.

System and method for acoustic activity recognition

An efficient fabrication technique, including an optional design step, is used to create highly customizable wearable electronics. The method of fabrication utilizes rapid laser machining and adhesion-controlled soft materials. The method produces well-aligned, multi-layered materials created from 2D and 3D elements that stretch and bend while seamlessly integrating with rigid components such as microchip integrated circuits (IC), discrete electrical components, and interconnects. The design step can be used to create a 3D device that conforms to different-shaped body parts. These techniques are applied using commercially available materials. These methods enable custom wearable electronics while offering versatility in design and functionality for a variety of bio-monitoring applications.

Method of producing untethered, stretchable, and wearable electronic devices

Systems and techniques for facilitating hand activity sensing are presented. In one example, a system obtains, from a wrist-worn computational device, hand activity data associated with a sustained series of hand motor actions in performance of a human task. The system also employs a machine learning technique to determine classification data indicative of a classification for the human task.

Method and system for hand activity sensing

Internet of Things ('IoT') appliances are gaining consumer traction, from smart thermostats to smart speakers. These devices generally have limited user interfaces, most often small buttons and touchscreens, or rely on voice control. Further, these devices know little about their surroundings&#x2014;unaware of objects, people and activities around them. Consequently, interactions with these 'smart' devices can be cumbersome and limited. The present invention presents an approach that enriches IoT experiences with rich touch and object sensing, offering a complementary input channel and increased contextual awareness. The present invention incorporates a range sensing technology into the computing devices, providing an expansive ad hoc plane of sensing just above the surface with which a device is associated. Additionally, the present invention can recognize and track a wide array of objects, including finger touches and hand gestures. The present invention can also track people and estimate which way they are facing.

System, method and devices for touch, user and object sensing for IoT experiences

Growing community of inventors

Pittsburgh, PA, United States of America

Gierad Laput