Methods for an autonomous robotic device to identify locations captured in an image

Patent metadata

Field	Value
Publication number	US-12573196-B1
Application number	US-202217884375-A
Country	US
Kind code	B1
Filing date	Aug 9, 2022
Priority date	Dec 15, 2017
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

Provided is a robot, including: a chassis; a plurality of sensors; a processor; and a tangible, non-transitory, machine-readable medium storing instructions that when executed by the processor effectuates operations including: receiving, with the processor, an image of an environment captured by a communication device separate from the robot; extracting, with the processor, objects and features captured in the image; determining, with the processor, an area within a map of the environment corresponding with an area captured in the image by comparing the objects and features captured in the image with objects and features within the map; and actuating, with the processor, the robot to navigate to the area captured in the image to perform work.

First claim

The invention claimed is:

1 . A system, comprising:
a robot, comprising:
a chassis;
a plurality of sensors;
a processor; and
a tangible, non-transitory, machine-readable medium storing instructions that, when executed by the processor of the robot, effectuates operations comprising:
capturing, with an image sensor disposed on the robot, images of an environment of the robot;
extracting, with the processor of the robot, features from the captured images by obtaining, with the processor of the robot, raw pixel intensity values of the captured images, wherein features in the captured images are extracted from raw pixel intensity values;
generating, with the processor of the robot, a map of the environment of the robot at least partly based on the features in the captured images;
associating, with the processor of the robot, areas within the map of the environment with subareas of the environment from which images were captured; and
actuating, with the processor of the robot, the robot to execute work in the environment based on the generated map of the environment within at least a particular sub area or labeled area of the environment upon receiving, with the processor of the robot, at least one voice command comprising an instruction for executing work within the at least particular sub area or labeled area;

a set of instructions and executable code that, when executed by a processor of an external communication and computing device, effectuates operations comprising:
pairing the external communication and computing device with the processor of the robot to communicate with the robot;
receiving the map of the environment created by the robot;
displaying the map of the environment of the robot; and
receiving at least one input designating an instruction for the robot in relation to the at least one subarea within the environment by:
accessing the camera of the communication and computing device for capturing images of the environment;
capturing an image of the environment;
displaying the image; and
receiving at least one input in relation to the displayed image.

2 . The system of claim 1 , wherein the robot executes the instruction according to the virtual boundary.

3 . A system, comprising:
a robot, comprising:
a chassis;
a plurality of sensors;
a processor; and
a tangible, non-transitory, machine-readable medium storing instructions that, when executed by the processor, effectuates operations comprising:
capturing, with an image sensor disposed on the robot, a plurality of images of an environment of the robot;
extracting, with the processor of the robot, at least one feature from the captured plurality of images by obtaining, with the processor of the robot, raw pixel intensity values of the captured images, wherein features in the images are extracted from raw pixel intensity values;
generating, with the processor of the robot, a map of the environment based on at least the plurality of images and the extracted features;
actuating, with the processor of the robot, the robot to execute work in the environment based on the generated map within at least a particular sub area or labeled area of the environment upon receiving, with the processor of the robot, at least one voice command comprising an instruction for executing work within the at least particular sub area or labeled area;

a set of instructions and executable code that, when executed by a processor of an external communication and computing device, effectuates operations comprising:
pairing the external communication and computing device with the processor of the robot to communicate with the robot;
receiving the map of the environment created by the robot;
display the map of the environment of the robot;
receiving at least one input designating an instruction for the robot in relation to the at least one subarea within the environment based on the map of the environment by:
accessing the camera of the communication and computing device for capturing images of the environment;
capturing an image of the environment;
displaying the image; and
receiving at least one input in relation to the displayed image.

4 . The system of claim 3 , wherein the instruction for the robot comprises avoiding the at least one subarea.

5 . The system of claim 3 , wherein the operations further comprise:
collecting, with at least one debris sensor disposed on the robot, a plurality of debris data of the environment; associating, with the processor of the robot, each debris data with a location of the environment from which the respective debris data was collected; and inferring, with the processor of the robot, locations of the environment with debris accumulation based on the plurality of debris data.

6 . The system of claim 5 , wherein the operations further comprise:
adjusting, with the processor of the robot, a coverage path of the robot based on the locations of the environment with debris accumulation.

7 . The system of claim 3 , wherein the operations further comprise:
generating, with the processor of the robot, a first movement path covering at least part of the environment; actuating, with the processor of the robot, the robot to move along the first movement path, wherein actuating the robot to move along at least a portion of the first movement path comprises a repetitive iteration of:
actuating, with the processor of the robot, the robot to traverse a first linear segment;
actuating, with the processor of the robot, the robot to rotate 180 degrees in a first rotation, wherein the first rotation comprises traversing a distance in a direction perpendicular to the first linear segment after starting the first rotation and before finishing the first rotation;
actuating, with the processor of the robot, the robot to traverse a second linear segment; and
actuating, with the processor of the robot, the robot to rotate 180 degrees in a second rotation, wherein the second rotation comprises traversing the distance in a direction perpendicular to the second linear segment after starting the second rotation and before finishing the second rotation.

8 . The system of claim 7 , wherein the distance is less than a coverage width of the robot.

9 . The system of claim 3 , wherein:
the robot further comprises a main brush and a peripheral brush; the peripheral brush comprises a plurality of arms; and at least one arm of the peripheral brush comprises bristles extending from the respective arm, the bristles being secured to the at least one arm and one another with stitching to prevent the bristles from being forcibly plucked during operation of the robot.

10 . The system of claim 9 , wherein the bristles are secured to the at least one arm and one another using one or more of the following techniques: stitching at least one line across the bristles, stitching two lines in opposite directions diagonally across the width of the bristles, or stitching a crisscross pattern across the bristles.

11 . The system of claim 10 , wherein:
the at least one stitched line across the bristles is in a direction perpendicular to the length of the bristles; and the stitched crisscross pattern across the bristles is in a direction perpendicular to the length of the bristles.

12 . The system of claim 3 , wherein generating the map of the environment comprises:
aligning, with the processor of the robot, data of respective images, wherein aligning comprises:
detecting a feature in the first image;
detecting the same feature in the second image; and
determining alignment of data of the first image and data of the second image based on at least a positi

Assignees

• Ebrahimi Afrouzi Ali
• Schweigert Sebastian
• Zhang Chen
• Yuan Hao
• Ai Inc

Inventors

• Ebrahimi Afrouzi Ali
• Schweigert Sebastian
• Zhang Chen
• Yuan Hao

Classifications

• G05D1/648

  Performing a task within a working area or space, e.g. cleaning · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/22

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

• A47L2201/04

  Automatic control of the travelling movement; Automatic obstacle detection · CPC title

• A47L11/4066

  Propulsion of the whole machine · CPC title