公开(公告)号：US11430308B1

公开(公告)日：2022-08-30

申请号：US17242856

申请日：2021-04-28

Applicant: Apple Inc.

Inventor： Jian Zhang ,  Siva Chandra Mouli Sivapurapu ,  Aashi Manglik ,  Amritpal Singh Saini ,  Edward S. Ahn

IPC: H04B3/36 ,  G08B6/00

Abstract: 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.

公开(公告)号：US11189052B2

公开(公告)日：2021-11-30

申请号：US16990510

申请日：2020-08-11

Applicant: Apple Inc.

Inventor： Emilio Parisotto ,  Jian Zhang ,  Ruslan Salakhutdinov ,  Devendra Singh Chaplot

IPC: G06T7/73 ,  G01C21/32 ,  H04W64/00 ,  G06N3/08 ,  G06N5/04 ,  G06N3/04

Abstract: In accordance with some embodiments, a method is performed at a device with one or more processors and non-transitory memory. The method includes obtaining location vector data characterizing an object. The method includes determining a neural pose graph associated with a respective time-period based on an initial local pose estimation as a function of respective location vector data. The method includes determining a meta pose estimation associated with the respective time-period by aggregating the neural pose graph associated with the respective time-period and one or more other neural pose graphs associated with one or more temporally adjacent time-periods. The method includes synthesizing a corrected pose estimation by correcting the meta pose estimation associated with the respective time-period based on a function of the meta pose estimation associated with the respective time-period and meta pose estimations associated with one or more temporally adjacent time-periods in order to correct accumulated errors in the initial local pose estimation.

公开(公告)号：US20200372675A1

公开(公告)日：2020-11-26

申请号：US16990510

申请日：2020-08-11

Applicant: Apple Inc.

Inventor： Emilio Parisotto ,  Jian Zhang ,  Ruslan Salakhutdinov ,  Devendra Singh Chaplot

IPC: G06T7/73 ,  G01C21/32 ,  G06N3/08 ,  H04W64/00 ,  G06N5/04 ,  G06N3/04

Abstract: In accordance with some embodiments, a method is performed at a device with one or more processors and non-transitory memory. The method includes obtaining location vector data characterizing an object. The method includes determining a neural pose graph associated with a respective time-period based on an initial local pose estimation as a function of respective location vector data. The method includes determining a meta pose estimation associated with the respective time-period by aggregating the neural pose graph associated with the respective time-period and one or more other neural pose graphs associated with one or more temporally adjacent time-periods. The method includes synthesizing a corrected pose estimation by correcting the meta pose estimation associated with the respective time-period based on a function of the meta pose estimation associated with the respective time-period and meta pose estimations associated with one or more temporally adjacent time-periods in order to correct accumulated errors in the initial local pose estimation.

公开(公告)号：US10776948B1

公开(公告)日：2020-09-15

申请号：US16113647

申请日：2018-08-27

Applicant: Apple Inc.

Inventor： Emilio Parisotto ,  Jian Zhang ,  Ruslan Salakhutdinov ,  Devendra Singh Chaplot

IPC: G06T7/73 ,  G01C21/32 ,  H04W64/00 ,  G06N3/08 ,  G06N5/04 ,  G06N3/04

Abstract: In accordance with some embodiments, a method is performed at a device with one or more processors and non-transitory memory. The method includes obtaining location vector data characterizing an object. The method includes determining a neural pose graph associated with a respective time-period based on an initial local pose estimation as a function of respective location vector data. The method includes determining a meta pose estimation associated with the respective time-period by aggregating the neural pose graph associated with the respective time-period and one or more other neural pose graphs associated with one or more temporally adjacent time-periods. The method includes synthesizing a corrected pose estimation by correcting the meta pose estimation associated with the respective time-period based on a function of the meta pose estimation associated with the respective time-period and meta pose estimations associated with one or more temporally adjacent time-periods in order to correct accumulated errors in the initial local pose estimation.