Intel Corporation

Atul N Hatalkar

Rita H Wouhaybi

Sharad K Garg

Mark D Yarvis

John B Vicente

Ansuya Negi

Sangeeta Ghangam Manepalli

Kirk Smith

Siew Wen Chin

Aaron R Berck

Robert Chavez

Roderick E Kronschnabel

Casey T Rathbone

Xubo Zhang

Ron Kuruvilla Thomas

Matthew J Schneider

Chris D Lucero

Steven M Brown

Mandeep Shetty

Jeremy Ouillette

Hassnaa Moustafa

Brian David Johnson

Ashwini Asokan

Michael J Payne

Delia Grenville

Fai Yeung

Rowland Lee Brown

Charles Carter Jernigan

Joseph B Petrini

Anna-Marie Mansour

Dzung D Tran

Kahyun Kim

James Lundell

James Lester Memmott

Nicholas Moe Khosravy

Michael Aaron Schroeder

Fu Zhou

Norman T Bright

John Belstner

Eric Lewallen

Jeremy P Duke

Shankar Devansenathipathy

Ali Moradi

Disclosed herein are embodiments of systems and methods for diversified imitation learning for automated machines. In an embodiment, a process-profiling system obtains sensor data captured by a plurality of sensors that are arranged to observe one or more human subjects performing one or more processes to accomplish one or more tasks. The process-profiling system clusters the sensor data based on a set of one or more process-performance criteria. The process-profiling system also performs, based on the clustered sensor data, one or both of generating and updating one or more process profiles in a plurality of process profiles. The process-profiling system selects, for one or more corresponding automated machines, one or more process profiles from among the plurality of process profiles, and the process-profiling system configures the one or more corresponding automated machines to operate according to the selected one or more process profiles.

Diversified imitation learning for automated machines

A robot may include a processor, configured to operate according to a first operational mode or a second operational mode, wherein the first operational mode comprises performing an environmental perception operation using first sensor data, wherein the first sensor data comprise no camera data, and wherein the second operational mode comprises performing the environmental perception operation using second sensor data, wherein the second sensor data comprise camera data; while operating according to the first operational mode, determine a confidence factor representing a confidence of the environmental perception operation; determine whether or not the confidence factor is outside of a range; and if the confidence factor is outside of the range, operate according the second operational mode.

Robot sensor data management

Described herein is a technique that provides a first robot associated with a first trust domain to identify and authenticate a second robot associated with a second trust domain. The identification and authentication technique described herein is based on a robot processing a variety of input signals obtained via sensors, in order to generate robot identification information that can be compared with known or trusted information. Advantageously, the identification technique occurs locally, for example, at the robot and at the location of the robot-to-robot interaction, eliminating any requirement for communicating with an authoritative remote or cloud-based service, at the time and place of the robot-to-robot interaction.

Method to support autonomous robot-to-robot identification and task transfer

Various systems and methods for implementing a software defined industrial system are described herein. For example, an orchestrated system of distributed nodes may run an application, including modules implemented on the distributed nodes. In response to a node failing, a module may be redeployed to a replacement node. In an example, self-descriptive control applications and software modules are provided in the context of orchestratable distributed systems. The self-descriptive control applications may be executed by an orchestrator or like control device and use a module manifest to generate a control system application. For example, an edge control node of the industrial system may include a system on a chip including a microcontroller (MCU) to convert IO data. The system on a chip includes a central processing unit (CPU) in an initial inactive state, which may be changed to an activated state in response an activation signal.

Distributed software-defined industrial systems

Embodiments include apparatuses, systems and methods for a computer device with a casing and a substance in the casing substantially surrounding a computer component in the casing. In embodiments, the computer device may be a command and control computer, such as for example, an autonomous or semi-autonomous vehicle. In embodiments, the substance may be an electrically isolative and shear-thickening fluid to provide thermo-mechanical protection to a computer component. In the described embodiments, the substance may dampen mechanical shock or vibrational impact on the processor and the memory. The shear-thickening gel may further be thermally conductive in embodiments. In the embodiments, the casing may be substantially filled with the substance and the substance is to conduct heat away from the processor and the memory toward an outer edge of the casing. Other embodiments may also be described and claimed.

Apparatuses, methods, and systems for thermomechanical protection of electronics including computer components and sensors

Techniques are disclosed that involve providing enhanced user experiences involving the consumption and management of content. For instance, embodiments provide user interface elements that present information regarding content that overcomes barriers or silos between application and platforms. Examples of such user interface elements include a three dimensional carousel, a preview stack, a favorites button, and a My Channel user interface. Also, embodiments may provide techniques for obtaining contextual content. Such techniques include, but are not limited to, zooming mechanisms and combining (or 'mashup') mechanisms.

Presentation of metadata and enhanced entertainment media content

Particular embodiments described herein provide for an electronic device that can be configured to determine that an unobtrusive gesture has been received on a first electronic device and send a signal to a second electronic device in response to the unobtrusive gesture. The first electronic device can also be configured to receive a signal from the second electronic device, determine an unobtrusive output in response to the signal, and generate an unobtrusive notification in response to the received signal. In an example, the first electronic device is a part of jewelry worn by a user.

User interaction with wearable devices

Techniques are described for the management and presentation of content. In one example a first and a second content item are output. A user selection of an association between the first and the second content item is received and, based on the user selection, contextual content corresponding to the first and second content items is obtained.

Techniques for management and presentation of content

Information about the context of electronic media may be extracted automatically. The extracted information may then be used to select ancillary services or applications that may be of interest to the user. The context information may be developed from ancillary information associated with the media, such as metadata or electronic programming guides. It may also be extracted from the media itself, including identification of image elements, audio elements, or other depicted features within the media in order to obtain information about what is being displayed.

Linking real time media context to related applications and services

The context engine of a context aware platform may comprise a provider manager coupled to context providers and the provider manager may communicate with the context providers using application programming interfaces (API). To optimize the use of system resources, the provider manager may load/unload the context providers based on value of a load field of a hint signal or on prediction values. The context providers is to activate a first set of sensors of the plurality of sensors if the preferred activity level for the first set of sensors is set to activate state in the hint signal. The context providers is to deactivate a second set of sensors of the plurality of sensors if the preferred activity level for the first set of sensors is set to deactivate state in the hint signal.

Handling sensors in a context-aware platform with hint signals

A system and method for the prevention of display burn-in in Motion Picture Experts Group (MPEG) and non-MPEG environments. In one environment, a system may include an image sampler to sample images from a decoded video stream; a static area detector to successively compare the sampled images using a pixel-wise XOR operation, where the static area detector marks an area in the compared images that appear as zero brightness; and a burn-in prevention module to apply a burn-in preventative technique for a period of time to the marked area.

System and method for the prevention of display burn-in

Techniques are described for providing alert management messages in a broadcast environment to individual recipients or to identifiable groups of recipients.

Alert management messaging

Growing community of inventors

Chandler, AZ, United States of America

Atul N Hatalkar