Intelligent robot cleaner for setting travel route based on video learning and managing method thereof

Patent metadata

Field	Value
Publication number	US-11565411-B2
Application number	US-201916489288-A
Country	US
Kind code	B2
Filing date	May 29, 2019
Priority date	May 29, 2019
Publication date	Jan 31, 2023
Grant date	Jan 31, 2023

Abstract

An intelligent robot cleaner setting a travel path based on a video learning includes a travel driver, a suction unit, an image acquisition unit, and a controller. The travel driver moves to an area to be cleaned along the travel path. The suction unit sucks foreign substances on the travel path. The image acquisition unit acquires an image on the travel path. The controller analyzes the image, decides whether an object is present on the travel path, classifies a type of the object, and sets a bypass travel path that avoids the object if the object is an avoidance object.

First claim

The invention claimed is:

1. An intelligent robot cleaner for setting a travel path based on a video learning, the intelligent robot cleaner comprising:
a travel driver configured to move to an area to be cleaned along the travel path;
a suction unit configured to suck foreign substances on the travel path;
an image acquisition unit configured to acquire an image on the travel path; and
a controller configured to analyze the image, decide whether an object is present on the travel path, classify whether a type of the object is an avoidance object or an ignorance object, and set a bypass travel path that avoids the object if the object is the avoidance object,
wherein the controller sets the travel path in different ways based on the classification result.

2. The intelligent robot cleaner of claim 1 , further comprising a memory configured to store image information of the avoidance object,
wherein the controller is configured to check whether an image feature of an object extracted from the image is matched to image information of the avoidance object stored in the memory.

3. The intelligent robot cleaner of claim 2 , wherein the memory stores, as the image information of the avoidance object, an image of at least one of an immovable object, a fragile object, a viscous or liquid contaminant, or a no-suction object.

4. The intelligent robot cleaner of claim 3 , wherein the controller is configured to classify the object as the ignorance object if the object does not belong to the avoidance object, and maintain the travel path.

5. The intelligent robot cleaner of claim 4 , wherein the controller is configured to maintain the travel path if the object is a movable object due to the movement of the robot cleaner.

6. The intelligent robot cleaner of claim 3 , further comprising an event output unit configured to output an event that the avoidance object has been found if the controller finds the avoidance object.

7. The intelligent robot cleaner of claim 6 , further comprising a user input unit configured to receive a processing instruction corresponding to the event.

8. The intelligent robot cleaner of claim 7 , wherein if the event is output and then an instruction of ignoring the avoidance object is received from the user input unit, the controller is configured to control the travel driver so that the travel driver travels on an area in which the avoidance object is found.

9. The intelligent robot cleaner of claim 7 , wherein if the event is output and then a processing instruction for the avoidance object is not received from the user input unit for a predetermined period of time, the controller is configured to set the bypass travel path.

10. The intelligent robot cleaner of claim 3 , wherein if the controller decides the object as the no-suction object, the controller is configured to store, in the memory, a name and location information of the no-suction object in the acquired image.

11. A method of managing an intelligent robot cleaner setting a travel path based on a video learning, the method comprising:
acquiring an image on the travel path;
analyzing the image and deciding whether an object is present on the travel path;
classifying, by the intelligent robot cleaner, whether a type of the object is an avoidance object or an ignorance object; and
setting, by the intelligent robot cleaner, a bypass travel path that bypasses the travel path if the classified object is the avoidance object,
wherein the intelligent robot cleaner sets the travel path in different ways based on the classification result.

12. The method of claim 11 , wherein the classifying of the type of the object is determined based on a result of learning the acquired image.

13. The method of claim 12 , wherein the classifying of the type of the object comprises classifying the object as the avoidance object if the object is an immovable object, a fragile object, a viscous or liquid contaminant, or a no-suction object.

14. The method of claim 13 , wherein the classifying of the type of the object further comprises:
classifying the object as the avoidance object or the ignorance object and classifying the object as the ignorance object if the object does not belong to the avoidance object; and
maintaining the travel path if the classified object is the ignorance object.

15. The method of claim 14 , wherein the classifying of the type of the object further comprises classifying the object as the ignorance object if the object is a movable object due to the movement of the robot cleaner.

16. The method of claim 13 , further comprising, if the object is the avoidance object, outputting an event that the avoidance object has been found.

17. The method of claim 16 , further comprising, after outputting the event that the avoidance object has been found, preparing to receive a processing instruction corresponding to the event.

18. The method of claim 17 , further comprising, if the processing instruction corresponding to the event is an instruction of ignoring the avoidance object, traveling by the intelligent robot cleaner on an area in which the avoidance object is found.

19. The method of claim 17 , further comprising, if the processing instruction corresponding to the event is not received for a predetermined period of time, setting by the intelligent robot cleaner the bypass travel path.

20. The method of claim 13 , further comprising, if the object is classified as the no-suction object in the classifying of the object, storing a name and location information of the no-suction object.

Assignees

• Lg Electronics Inc

Inventors

• Kim Beomoh
• Kim Taehyun
• Maeng Jichan
• Chae Jonghoon

Classifications

• G06K9/628

  Physics · mapped topic

• G06V20/10

  Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59) · CPC title

• G06V10/751

  Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching · CPC title

• B25J9/1664 Primary

  characterised by motion, path, trajectory planning · CPC title

• G06V10/40

  Extraction of image or video features · CPC title