Google Inc.

International Business Machines Corporation

X Development LLC

Gabriel Aaron Cohen

Travis M Grigsby

Alexander James Faaborg

Paul Westbrook

Michael A Paolini

Thomas Alexander Bellwood

Gerald Laverte Mitchell, Jr

Daniel Lehmann

Ronald Eugene Craig

Ficus Kirkpatrick

Michael Negley Abernethy, Jr

Michael Joseph Quinlan

Colin Gibbs

Michael Morrissey

Ashish Sharma

Paul Nicholas Gennai

Attila Bodis

Hiroshi Lockheimer

Thomas R Haynes

Daniel Marc Gatan Shiplacoff

Christopher Richard Wren

Jeffrey Allen Sharkey

Richard Eugene Fulcher

Subir Jhanb

Debajit Ghosh

Michael D Facemire

Andrew Flynn

Daniel Robert Sandler

Punyabrata Ray

Dmitri Plotnikov

Nick Dower

John Spurlock

Frank Jania

Daisuke Miyakawa

Michael Andrew Cleron

Christopher Kent Karstens

Hrishikesh Balkrishna Aradhye

Michael C Wanderski

James M Mathewson, Ii

Benjamin Holson

Vijay Dheap

Jon M Wiley

Dave Burke

Bryan Eric Aupperle

Austin Robison

Srinivasan Muralidharan

Ian Gunn

Renee Marie St Amant

John M Harding

Jonathan C Gellin

Munaf Assaf

Simon Raess

Jeff Sharkey

Jp Abgrall

Travis M Grisby

Bethwyn Morris

Sara Anne Barton Sinclair

William A Smythe

Pavel Vodenski

Paul T Westbrook

Michael Dennis Facemire

Gerald Laverte Mitchell Jr

Methods, systems, and apparatus for receiving a command for controlling a robot, the command referencing an object, receiving sensor data for a portion of an environment of the robot, identifying, from the sensor data, a gesture of a human that indicates a spatial region located outside of the portion of the environment described by the sensor data, searching map data for the object, determining, based at least on searching the map data for the object referenced in the command, that the object referenced in the command is present in the spatial region, and in response to determining that the object referenced in the command is present in the spatial region, controlling the robot to perform an action with respect to the object referenced in the command.

Multimodal object identification

A computer-implemented process includes providing a request to access content associated with a website; receiving web page information associated with the website, and data for displaying a notification that indicates availability of a native computer application that is associated with the website; providing a request to access information associated with the native computer application; receiving information associated with the native computer application that describes interactions between a plurality of users of an application marketplace and a component of the application marketplace that provides and receives information related to the native computer application; and displaying the descriptive information for viewing by a user, including displaying information that indicates the interactions between the plurality of users and the component of the application marketplace.

Computer application promotion

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selective human-robot interaction. In some implementations, sensor data describing an environment of a robot is received, and a person in the environment of the robot is detected based on the sensor data. Scores indicative of properties of the detected person are generated based on the sensor data and processed using a machine learning model. Processing the scores can produce one or more outputs indicative of a likelihood that the detected person will perform a predetermined action in response to communication from the robot. Based on the one or more outputs of the machine learning model, the robot initiates communication with the detected person.

Selective human-robot interaction

Methods, systems, and apparatus, including computer programs stored on a computer-readable storage medium, for selecting a modality for interfacing between a user and a robot. In some implementations, a system determines that a particular action requires user confirmation before being performed. The system receives position data indicating a level of proximity of a user to a robot and environmental data indicating environmental conditions sensed by the robot. The system selects a particular mode for obtaining confirmation of the action from among multiple modes of interfacing with users based on one or more of the position data and the environmental data. The system provides a request confirmation of the action using the particular mode for presentation to the user.

Interfacing with autonomous devices

A method for providing relationship-centric resources includes establishing a communication session between a first device and a second device, determining, during the communication session between the first and second devices, an intersection of mutual topics of interest between users of the first and second devices by cross-referencing sets of interests for the users, retrieving content based on a determination that the content meets a content descriptor, and simultaneously displaying the retrieved content. The content descriptor describes a nature of the communication session. The retrieving is further based on a determination that the content is related to a mutual topic of interest from the intersection of mutual topics of interest between the users of the first and second devices. The determination of relatedness is based on a cross-reference between the content and the mutual topic of interest. The cross-reference is stored in a lookup table.

Relationship-centric portals for communication sessions

Methods, systems, and apparatus for receiving a command for controlling a robot, the command referencing an object, receiving sensor data for a portion of an environment of the robot, identifying, from the sensor data, a gesture of a human that indicates a spatial region located outside of the portion of the environment described by the sensor data, accessing map data indicating locations of objects within a space, searching the map data for the object, wherein the search of the map data is restricted to the spatial region, determining, based at least on searching the map data for the object referenced in the command, that the object referenced in the command is present in the spatial region, and in response to determining that the object referenced in the command is present in the spatial region, controlling the robot to perform an action with respect to the object referenced in the command.

A computing device is described that can receive contextual information related to a user associated with the computing device. The contextual information may relate to at least one of a physiological condition of the user at a current time or a type of activity associated with the user at the current time. The computing device can select, based at least in part on the contextual information, a type of alert to output as an indication of notification data. The type of alert may include at least one of an electric stimulus type alert, a shape-memory alloy type alert, and a vibration type alert. Responsive to selecting the type of alert, the computing device can output an alert based on the notification data, the alert being of the selected type of alert.

Somatosensory type notification alerts

The present disclosure provides a system and method for automatic clustering and recognition of software applications using metadata. The system selects and extracts visual features from software applications which are then classified, analyzed using a cluster analysis, and then used to assign the software application to a cluster group.

Clustering applications using visual metadata

In general, a computing device is described that receives an indication of a particular communication from a particular sender. The computing device determines a relationship score based at least in part on a relationship context between the particular sender and a user of the computing device. The relationship score indicates a degree of strength of a relationship between the particular sender and the user of the computing device. While outputting an alert indicative of the communication, the computing device adjusts one or more characteristics of the alert based at least in part on the relationship score.

Automatically altering characteristics of audio alerts

A computer-implemented method includes identifying, with a computer system that has a network interface, one or more primary categories of content from a social networking system that are of primary relevance to a user of a computing device, as compared to one or more secondary categories of content from the social networking system that are of lower importance to the user of the computing device; causing content from the primary categories to be downloaded from the social networking system to the computing device automatically and without user interaction with a social networking application that is arranged to display the downloaded content; and causing content from the secondary categories to be downloaded from the social networking system to the computing device separately from the content from the primary categories, and in response to a defined user interaction with a social networking application that corresponds to the social networking system.

Prioritized download of social network content

Systems and methods for determining if media files being submitted to a hosting site contain media to which another has rights and informing a submitter of the potential media rights conflict without first divulging such information to a potential third party rights holder. Upon submission, if the media contains material to which another has rights, the submitter will be informed which portion of the submitted media file is infringing and given the opportunity to submit a modified media file. This approach maintains the confidential nature of the submitted media while enforcing the rights of third parties. The system also automatically notifies the appropriate parties in the event that the submitter does not resolve a conflict with media files to which another has rights and includes the ability to automatically remove the offending submitted media content. A method for detecting a possible media rights conflict is also presented.

Automated media rights detection

The subject matter of this specification can be embodied in, among other things, a method that includes receiving, by one or more servers associated with an application marketplace, a policy that includes data that identifies one or more users, and a restricted permission. A request is received, by the servers associated with the application marketplace, to access one or more applications that are distributed through the application marketplace, wherein the request includes data that identifies a particular one of the users. One or more of the applications that are associated with the restricted permission are identified by the servers associated with the application marketplace, and access by the particular user to the applications that are associated with the restricted permission is restricted by the servers associated with the application marketplace.

Application marketplace administrative controls

Growing community of inventors

Alameda, CA, United States of America

Gabriel Aaron Cohen