公开(公告)号：US10850400B2

公开(公告)日：2020-12-01

申请号：US16566468

申请日：2019-09-10

Applicant: LG ELECTRONICS INC.

Inventor： Yongjin Park

IPC: B25J13/00 ,  B25J9/00 ,  B25J9/16 ,  G10K11/178 ,  B25J19/02

Abstract: A robot includes: a microphone assembly to which a voice is input; an accelerometer connected to a noise source; and a controller configured to control the microphone assembly, wherein the microphone assembly includes: a microphone housing formed in one surface thereof with an opening and formed therein with a space; a microphone accommodated in the space; and an anti-noise speaker accommodated in the space and spaced apart from the microphone, and the controller includes an anti-noise generator configured to output a signal corresponding to an anti-noise against the acquired noise to the anti-noise speaker.

公开(公告)号：US11285611B2

公开(公告)日：2022-03-29

申请号：US16420852

申请日：2019-05-23

Applicant: LG ELECTRONICS INC.

Inventor： Yongjin Park ,  Minook Kim ,  Jungkwan Son ,  Tacksung Choi ,  Sewan Gu ,  Jinho Sohn ,  Taegil Cho

IPC: B25J9/16 ,  B25J13/00 ,  B25J13/08 ,  B25J19/02

Abstract: A robot includes a sensing unit including at least one sensor for detecting a user, a face detector configured to acquire an image including a face of the user detected by the sensing unit, a controller configured to detect an interaction intention of the user from the acquired image, and an output unit including at least one of a speaker or a display for outputting at least one of sound or a screen for inducing interaction of the user, when the interaction intention is detected.

公开(公告)号：US11250852B2

公开(公告)日：2022-02-15

申请号：US16853685

申请日：2020-04-20

Applicant: LG ELECTRONICS INC.

Inventor： Yongjin Park

IPC: G10L15/22 ,  G10L21/0232 ,  G06N3/08 ,  G10L13/047 ,  G10L15/16 ,  G10L15/06 ,  G10L13/00 ,  G10L15/08

Abstract: Provided are a trigger recognition model generating method for a robot and a robot to which the method is applied. A trigger recognition model generating method comprises obtaining an input text which expresses a voice trigger, obtaining a first set of voice triggers by voice synthesis from the input text, obtaining a second set of voice triggers by applying a first filter in accordance with an environmental factor to the first set of voice triggers, obtaining a third set of voice triggers by applying a second filter in accordance with a mechanism characteristic of the robot to the second set of voice triggers, and applying the first, second, and third sets of voice triggers to the trigger recognition model as learning data for the voice trigger. By doing this, a trigger recognition model which is capable of recognizing a new trigger is generated.