Sony Interactive Entertainment Inc.

Erik Beran

Michael G Taylor

Ruxin Chen

Todd Tokubo

Javier Fernandez Rico

Masanori Omote

Victoria Dorn

Michael Taylor

Kaoru Yamanoue

Brandon Sangston

Yoshimichi Kitaya

Shunsuke Saito

Yuki Karatsu

Hajime Horikoshi

A method for building an artificial intelligence (AI) model. The method includes accessing data related to monitored behavior of a user. The data is classified, wherein the classes include an objective data class identifying data relevant to a group of users including the user, and a subjective data class identifying data that is specific to the user. Objective data is accessed and relates to monitored behavior of a plurality of users including the user. The method includes providing as a first set of inputs into a deep learning engine performing AI the objective data and the subjective data of the user, and a plurality of objective data of the plurality of users. The method includes determining a plurality of learned patterns predicting user behavior when responding to the first set of inputs. The method includes building a local AI model of the user including the plurality of learned patterns.

Private artificial intelligence (AI) model of a user for use by an autonomous personal companion

Methods and systems are provided for providing real world assistance by a robot utility and interface device (RUID) are provided. A method provides for identifying a position of a user in a physical environment and a surface within the physical environment for projecting an interactive interface. The method also provides for moving to a location within the physical environment based on the position of the user and the surface for projecting the interactive interface. Moreover, the method provides for capturing a plurality of images of the interactive interface while the interactive interface is being interacted with by the use and for determining a selection of an input option made by the user.

Robot utility and interface device

An audio signal processing apparatus in which different pieces of predetermined parameter information regarding acoustic transfer in a head of a listener are retained as preset candidates, a parameter information list including the retained preset candidates is presented, to prompt a user to select parameter information, and an audio signal for the user is generated by using the user-selected parameter information.

Audio signal processing apparatus, method of controlling audio signal processing apparatus, and program

Mobile and autonomous personal companion based on an artificial intelligence (AI) model for a user

An audio rendering method and computer readable medium instructions, comprising obtaining sound object data for a sound object in a first format suitable for rendering into an output signal and obtaining user tracking information for a user at a time subsequent to setting up the sound object data in the first format. The sound object is rendered by converting the sound object data from the first format into the output signal and in conjunction with said rendering a transform is applied to the sound object, wherein the transform depends on the user tracking data. Two or more speakers are driven using the output signal.

Deferred audio rendering

Predictive pre-fetching of streams for 360 degree video is described. User view orientation metadata is obtained for a 360 degree video stream that includes data for a plurality of viewports. Data corresponding to one or more high-resolution frames for a particular one of the viewports is pre-fetched based on the user view orientation metadata and those frames are displayed. The high resolution frames are characterized by a higher resolution than for remaining viewports.

Predictive bitrate selection for 360 video streaming

Methods and systems are provided for providing one or more sound component to a viewer within a media presentation space by a robot having one or more speakers. A method includes an operation for establishing a connection to a media device that is presenting media content to the viewer, and an operation for capturing input from a plurality of sensors for obtaining a map of the media presentation space. The method additionally provides for identifying a position of the viewer and a speaker configuration in the media presentation space. The method allows the robot to move to a location based on the map of the media presentation space, the position of the viewer and the speaker configuration. Moreover, the method provides an operation for receiving one or more sound components for presentation to the user.

Personal robot enabled surround sound

A method is provided, including: using a robot having a plurality of sensors to acquire sensor data about a local environment; processing the sensor data to generate a spatial model of a real object, the spatial model defining virtual surfaces that correspond to real surfaces of the real object; further processing the sensor data to generate texture information that is associated to the virtual surfaces; wherein using the robot to acquire sensor data includes sampling at least one representative portion by moving the robot to different locations and capturing images of a given representative portion from a plurality of angles; wherein processing the sensor data to generate the texture information includes processing the images captured from the plurality of angles to generate texture information; using the spatial model and the texture information to render a virtual object corresponding to the real object in a virtual environment.

Space capture, modeling, and texture reconstruction through dynamic camera positioning and lighting using a mobile robot

A method is provided, including the following method operations: using a robot having a plurality of sensors to acquire sensor data about a local environment; processing the sensor data to generate a spatial model of the local environment, the spatial model defining virtual surfaces that correspond to real surfaces in the local environment; further processing the sensor data to generate texture information that is associated to the virtual surfaces defined by the spatial model; tracking a location and orientation of a head-mounted display (HMD) in the local environment; using the spatial model, the texture information, and the tracked location and orientation of the HMD to render a view of a virtual space that corresponds to the local environment; presenting the view of the virtual environment through the HMD.

User-generated recordings of skeletal animations are provided. Information is stored in a memory regarding a plurality of animated movements in memory. Each animated movement may be mapped to one or more skeletal-based body parts of a game character. A recording of a plurality of user movements may be captured over a period of time. One or more body parts of the user may be identified for each captured user movement. It may then be determined which skeletal-based body parts correspond to the identified body parts of the user. A custom animation may be generated that comprises a plurality of animated movements in which the determined skeletal-based body parts are mapped to the associated animated movement. The custom animation may be stored in memory and played during play of a game as designated by the user.

Generating custom recordings of skeletal animations

A glove interface object is provided, including: a plurality of magnetic objects positioned on a first side of the glove interface object; a plurality of electromagnets positioned on a second side of the glove interface object opposite the first side, the plurality of electromagnets being positioned substantially opposite the plurality of magnetic objects, wherein each electromagnet is configured when activated to attract one or more of the magnetic objects; a controller configured to control activation and deactivation of the electromagnets based on received haptic feedback data.

Growing community of inventors

Belmont, CA, United States of America

Erik Beran