Method for waking up robot and robot thereof

Patent metadata

Field	Value
Publication number	US-11276402-B2
Application number	US-201916678267-A
Country	US
Kind code	B2
Filing date	Nov 8, 2019
Priority date	May 8, 2017
Publication date	Mar 15, 2022
Grant date	Mar 15, 2022

Abstract

A method for waking up a robot includes: acquiring sight range information when a voice command issuer issues a voice command; if the sight range information of the voice command issuer when issuing the voice command is acquired, determining, based on the sight range information, whether the voice command issuer gazes the robot when the voice command is issued; and determining that the robot is called if the voice command issuer gazes the robot.

First claim

What is claimed is:

1. A method for waking up a robot, applied to a robot, wherein the method comprises:
acquiring sight range information when a voice command issuer issues a voice command;
if the sight range information of the voice command issuer when issuing the voice command is acquired, determining, based on the sight range information, whether the voice command issuer gazes the robot when the voice command is issued; and
determining that the robot is called if the voice command issuer gazes the robot;
interrogating the voice command issuer if the sight range information of the voice command issuer when issuing the voice command is not acquired;
wherein the acquiring sight range information when a voice command issuer issues a voice command comprises:
acquiring voice command information, the voice command information comprising time information of the voice command and information of the voice command issuer;
broadcasting the voice command information;
determining whether a robot that hears the same voice command exists;
enabling the robot that hears the same voice command to join a same candidate group if the robot that hears the same voice command exists;
acquiring visual information and position information of the robot complying with the time information;
acquiring, based on the visual information and the position information of the robot, the sight range information of the voice command issuer when issuing the voice command; and
if the sight range information of the voice command issuer when issuing the voice command exists, broadcasting, in the candidate group, the sight range information of the voice command issuer when issuing the voice command.

2. The method according to claim 1 , wherein the voice command information further comprises a sound pressure level of the voice command, and the acquiring voice command information comprises:
monitoring a voice signal;
parsing out a wake-up word in the voice signal;
determining a sound pressure level of the voice signal;
if the wake-up word indicates a call and the sound pressure level of the voice signal exceeds a predetermined threshold, recording a start time point and an end time point of the voice signal as the time information of the voice command, and recording the sound pressure level of the voice signal as the sound pressure level of the voice command;
identifying a voice signal issuer based on the voice signal; and
recording the voice signal issuer as the information of the voice command issuer.

3. The method according to claim 2 , wherein the wake-up word is a pronoun indicating the call; and
the interrogating the voice command issuer comprises:
determining whether the wake-up word is a pronoun indicating a single form;
determining a robot with a highest sound pressure level in the candidate group if the wake-up word is the pronoun indicating the single form, such that the robot with the highest sound pressure level interrogates whether the voice command issuer calls the robot with the highest sound pressure level;
responding to the voice command issuer if the voice command issuer calls the robot with the highest sound pressure level;
otherwise, in a scenario where the voice command issuer issues a new voice command, acquiring sight range information of the voice command issuer when issuing the new voice command;
determining robots with a highest sound pressure level and a second highest sound pressure level in the candidate group if the wake-up word is not the pronoun indicating the single form, such that the robots with the highest sound pressure level and the second highest sound pressure level interrogate whether the voice command issuer calls only the robots with the highest sound pressure level and the second highest sound pressure level;
responding to the voice command issuer if the voice command issuer calls only the robots with the highest sound pressure level and the second highest sound pressure level;
otherwise, in a scenario where the voice command issuer issues a new voice command, acquiring sight range information of the voice command issuer when issuing the new voice command;
broadcasting, in the candidate group, the sight range information of the voice command issuer when issuing the new voice command; and
the method further comprises:
if the sight range information of the voice command issuer when issuing the new voice command is acquired, determining, based on the sight range information, whether the voice command issuer gazes the robot when the voice command is issued; and
determining that the robot is called if the voice command issuer gazes the robot; and
responding to the voice command issuer.

4. The method according to claim 1 , wherein the voice command information further comprises a sound pressure level of the voice command, and the acquiring voice command information comprises:
monitoring a voice signal;
parsing out a wake-up word in the voice signal;
determining a sound pressure level of the voice signal;
if the wake-up word indicates a call and the sound pressure level of the voice signal exceeds a predetermined threshold, recording a start time point and an end time point of the wake-up word as the time information of the voice command, and recording the sound pressure level of the voice signal as the sound pressure level of the voice command; and
identifying a voice signal issuer based on the voice signal, and recording the voice signal issuer as the information of the voice command issuer.

5. The method according to claim 1 , wherein the acquiring, based on the visual information and the position information of the robot, the sight range information of the voice command issuer when issuing the voice command comprises:
equally dividing the time information of the voice command into a plurality of time points;
at each time point, determining an angle between the face of the voice command issuer and the robot based on the visual information at the time point;
acquiring a sight direction at the time point based on the position information of the robot at the time point and the angle; and
using the acquired sight direction and a time point corresponding to the sight direction as the sight range information.

6. The method according to claim 5 , wherein the determining, based on the sight range information, whether the voice command issuer gazes the robot when the voice command is issued comprises:
acquiring the position information of the robot within a predetermined time period;
determining whether the position information complying with the sight direction of the robot at a time point of the sight range information exists; and
determining that the voice command issuer gazes the robot if the position information of the robot complying with the sight direction at a time point of the sight range information exists.

7. The method according to claim 1 , wherein the acquiring, based on the visual information and the position information of the robot, the sight range information of the voice command issuer when issuing the voice command comprises:
equally dividing the time information of the voice command into a plurality of time points;
at each time point, determining an angle between the face of the voice command issuer and the robot based on the visual information at the time point;
acquiring a sight direction at the time point based on the position information of the robot issuer at the time point and the angle;
acquiring a sight interval and a time range corresponding to the sight interval based on the acquired sight direction and the time point corresponding to the sight direction; and
using the sight interval and the time range as the sight range information.

8. The method according to claim 7

Assignees

• Cloudminds Shenzhen Robotics Systems Co Ltd
• Cloudminds Robotics Co Ltd

Inventors

• Luo Lei

Classifications

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/1822

  Parsing for meaning understanding · CPC title

• B25J9/1697

  Vision controlled systems · CPC title

• B25J13/003

  by means of an audio-responsive input (audible safety signals B25J19/061) · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title