Robot and control method therefor
The present invention relates to a robot and a control method therefor and, more particularly, to a robot and a control method therefor, the robot detecting peripheral obstacles and structures by using an image in front of same, thereby providing an efficient and safe moving path. A robot control method according to one embodiment of the present invention comprises the steps of: capturing an image; acquiring a first image of which the bottom surface is separated in the image; recognizing obstacles included in the image by using a learned first artificial intelligence model; allowing a robot to acquire and store a second image in order to perform a task on the basis of the information about the first image and the region including the recognized obstacles; and allowing the robot to move on the basis of the second image.
1. A control method of a robot, the method comprising:
capturing an image;
obtaining a first image which segments a floor surface from the image;
recognizing a type of obstacle included in the image using a trained first artificial intelligence model;
identifying an access forbidden region based on the type of the obstacle;
obtaining and storing a second image for the robot to perform a task by overlapping the access forbidden regions-region on the first image; and
moving the robot based on the second image,
wherein a size of the access forbidden region is identified based on the type of the obstacle and a size of the obstacle,
wherein identifying the access forbidden region comprises determining a boundary of the forbidden access region as a predetermined multiple of a dimension of the obstacle, wherein the predetermined multiple is based on the type of obstacle, and
wherein the moving the robot comprises, until a distance between the robot and the access forbidden region reaches within a predetermined first distance, moving at a first speed, and based on the distance between the robot and the access forbidden region being smaller than the predetermined first distance, moving at a second speed less than the first speed.
2. The method of claim 1 , further comprising:
obtaining moving state information and capturing direction information of the robot which captures an image,
wherein the storing further comprises storing the moving state information and the direction information together with the second image.
3. The method of claim 2 , further comprising:
identifying a distance between the robot and a wall using the second image and the moving state information.
4. The method of claim 3 , further comprising:
determining a moving speed of the robot based on the distance to the wall.
5. The method of claim 2 , further comprising:
generating a navigation map of a movable region of the robot using the second image stored together with the moving state information and the capturing direction information.
6. The method of claim 5 , further comprising:
identifying a position of a robot and establishing a moving plan using the navigation map and the second image stored together with the capturing direction information.
7. The method of claim 1 , wherein the obtaining the first image comprises obtaining the first image using a second artificial intelligence model trained to detect a floor surface region in the image.
8. The method of claim 1 , wherein a size of the region including the obstacle varies according to a type of an obstacle recognized by the first artificial intelligence model.
9. The method of claim 1 , further comprising:
obtaining a depth map image including depth information of the captured image;
obtaining and storing a third image for the robot to perform a task based on the depth map image and information about a region including the recognized obstacle; and
moving the robot based on the third image.
10. The method of claim 1 , wherein the forbidden access region is based on a space occupied by the obstacle as shown in the captured image.
11. A robot for cleaning, comprising:
a camera;
a driver;
a memory; and
a processor configured to:
control the camera to capture an image, obtain a first image which segments a floor surface from the image,
recognize a type of obstacle included in the image using a trained first artificial intelligence model and identifying an access forbidden region based on the type of obstacle,
obtain and store a second image for the robot to perform a task by overlapping the access forbidden region on the first image and, wherein a size of the access forbidden region is identified based on the type of obstacle and a size of the obstacle, and
control the driver to move the robot based on the second image,
wherein the processor determines a boundary of the forbidden access region as a predetermined multiple of a dimension of the obstacle, wherein the predetermined multiple is based on the type of obstacle, and
wherein the processor controls the driver to, until a distance between the robot and the access forbidden region reaches within a predetermined first distance, move at a first speed, and based on the distance between the robot and the access forbidden region being smaller than the predetermined first distance, move at a second speed less than the first speed.
12. The robot of claim 11 , wherein the robot further comprises:
a sensor,
wherein the processor is further configured to, based on obtaining moving state information and capturing direction information of the robot which captures an image through the sensor, store the moving state information and the direction information together with the second image in the memory.
13. The robot of claim 12 , wherein the processor is further configured to identify a distance between the robot and a wall using the second image and the moving state information.
14. The robot of claim 13 , wherein the processor is further configured to determine a moving speed of the robot based on the distance to the wall.
15. The robot of claim 12 , wherein the processor is further configured to generate a navigation map of a movable region of the robot using the second image stored together with the moving state information and the capturing direction information and store the same in the memory.
16. The robot of claim 15 , wherein the processor is further configured to identify a position of a robot and establish a moving plan using the navigation map and the second image stored together with the capturing direction information.
17. The robot of claim 11 , wherein the processor determines the type of obstacle from a plurality of categories.
18. The robot of claim 11 , wherein the processor determines the forbidden access region based on a space occupied by the obstacle as shown in the captured image.