Apple Inc.

Aashi Manglik

Siva Chandra Mouli Sivapurapu

Mark E Drummond

Edward S Ahn

Behrooz Mahasseni

Shaun D Budhram

Payal Jotwani

Mu Qiao

Bo Morgan

Daniel Laszlo Kovacs

Dan Feng

Michael J Gutensohn

Noah Gamboa

Jian Zhang

Amritpal Singh Saini

Noah Jonathan Gamboa

James Moll

In some implementations, the method includes: obtaining a plurality of animations; determining initial and end motion states for each of the plurality of animations; generating an animation graph including nodes for each of the plurality of animations by connecting, with a directional edge, a first node with an end motion state to a second node with an initial motion state that matches the end motion state of the first node; generating a transitional animation that is not included among the plurality of animations from an initial reference motion state to a target motion state that corresponds to a path that traverses the animation graph from a third node associated with the initial reference motion state to a fourth node associated with the target motion state; and updating the animation graph by removing one or more nodes from the animation graph based at least in part on the transitional animation.

Method and device for generating an animation graph

A device obtains a request to display a graphical environment. The graphical environment is associated with a set of saliency values corresponding to respective portions of the graphical environment. A POV for displaying the graphical environment is selected based on the set of saliency values. The graphical environment is displayed from the selected POV on the display.

Displaying an environment from a selected point-of-view

In one implementation, a method of composing a scene content is performed at a device including a display, one or more processors, and non-transitory memory. The method includes generating a definition of a scene based on textual or speech input and a model of a physical environment, wherein the definition includes a constraint that defines a spatial relationship between a virtual asset and an anchor asset that corresponds to one or more physical objects in the physical environment. The method includes generating, based on the definition of the scene and the model of the physical environment, a first instance of the scene that satisfies the constraint with the virtual asset in the spatial relationship with a first one of the one or more physical objects in the physical environment. The method includes presenting, on the display, the first instance of the scene.

Methods and systems for composing and executing a scene

Various implementations disclosed herein include devices, systems, and methods for granular motion control for a virtual agent. In various implementations, a device includes a non-transitory memory and one or more processors coupled with the non-transitory memory. In some implementations, a method includes obtaining an action for a virtual agent. In some implementations, the action is associated with a plurality of time frames. In some implementations, the method includes, for a first time frame of the plurality of time frames, determining respective confidence scores for a plurality of granular motions that advance the virtual agent towards completion of the action. In some implementations, the method includes selecting a subset of the plurality of granular motions based on the respective confidence scores.

Granular motion control for a virtual agent

In one implementation, a method of displaying content is performed at a device including a display, one or more processors, and non-transitory memory. The method includes scanning a first physical environment to detect a first physical object in the first physical environment and a second physical object in the first physical environment, wherein the first physical object meets at least one first object criterion and the second physical object meets at least one second object criterion. The method includes displaying, in association with the first physical environment, a virtual object moving along a first path from the first physical object to the second physical object. The method includes scanning a second physical environment to detect a third physical object in the second physical environment and a fourth physical object in the second physical environment, wherein the third physical object meets the at least one first object criterion and the fourth physical object meets the at least one second object criterion. The method includes displaying, in association with the second physical environment, the virtual object moving along a second path from the third physical object to the fourth physical object, wherein the second path is different than the first path.

A method includes displaying, via a display device, a virtual agent moving according to a motion type. The virtual agent is defined by a plurality of virtual joints and motions of the virtual agent are controllable by providing a corresponding plurality of torques to the plurality of virtual joints. The method includes, while the virtual agent is moving according to the motion type, registering an interaction event with the virtual agent. The interaction event initiates a change to the motion type. The method includes, in response to registering the interaction event, generating, using a motion controller, a plurality of torque values for the virtual agent based on a function of the motion type and the interaction event, and generating an animation for the virtual agent by providing the plurality of torque values to the plurality of virtual joints of the virtual agent.

Controlling joints using learned torques

In one implementation, a method for modeling a behavior with synthetic training data. The method includes: obtaining source content that includes an entity performing one or more actions within an environment; generating a first environment characterization vector characterizing the environment; generating a first set of behavioral trajectories associated with the one or more actions of the entity based on the source content and the first characterization vector for the environment; generating a second environment characterization vector for the environment by perturbing the first environment characterization vector; generating a second set of behavioral trajectories associated with one or more potential actions of the entity based on the source content and the second characterization vector for the environment; and training a behavior model for a virtual agent based on the first and second sets of behavioral trajectories in order to imitate the entity.

Method and device for modeling a behavior with synthetic training data

In one implementation, a method for generating a blended animation. The method includes: obtaining a motion input vector for a current time period; generating a motion output vector and pose information for the current time period based on the motion input vector; selecting an animated motion from a bank of animated motions for the current time period that matches the pose information within a threshold tolerance value; obtaining a blending coefficients vector for the current time period; generating a blended animation for the current time period by blending the motion output vector with the animated motion based on the blending coefficients vector; and generating a reward signal for the blended animation for the current time period.

Method and device for generating a blended animation

A method includes obtaining video data including a representation of a first plurality of motions of a real-world entity. The method includes determining, from the video data, a plurality of estimated torque values using a motion controller. The plurality of estimated torque values is associated with a plurality of real-world joints corresponding to the first plurality of motions. The method includes generating a second plurality of motions of a virtual agent by providing the plurality of estimated torque values to a corresponding plurality of virtual joints of the virtual agent. Movement of the virtual agent is controllable by the plurality of virtual joints, corresponding to the plurality of real-world joints of the real-world entity. The method includes, responsive to a determination that a comparison between the first plurality of motions and the second plurality of motions does not satisfy a performance metric, changing an operational value of the motion controller.

A method includes obtaining, by a motion generator that has been trained to generate torque values for a plurality of joints of a rig associated with a target, a set of parameters associated with a target motion. The method includes, in response to the target motion being a first type of motion, generating a first set of torque values for the plurality of joints based on the set of parameters and a set of previous poses of the target. The method includes, in response to the target motion being a second type of motion, generating a second set of torque values for the plurality of joints based on the set of parameters and the set of previous poses of the target. The method includes triggering a movement of the target in accordance with the first set of torque values or the second set of torque values.

Growing community of inventors

Sunnyvale, CA, United States of America

Aashi Manglik