Granted Patent B2

US 12,422,848 · App. 18/135,540 · Granted Sep 23, 2025

Inventors: Aron Baik (Suwon-si, KR); Soonbeom Kwon (Suwon-si, KR); Dohoon Kim (Suwon-si, KR)

Assignee: SAMSUNG ELECTRONICS CO., LTD.

G05D1/0212G05D1/0238G05D1/0274

Abstract

Claims (67)

1. A robot comprising:

a sensor configured to sense an environment of the robot;

a driver configured to drive movement of the robot;

at least one memory storing one or more instructions; and

at least one processor configured to execute the one or more instructions,

wherein the one or more instructions, when executed by the at least one processor, cause the robot to:

based on identifying at least one wall through the sensor, control the driver to cause the robot to perform wall following in which the robot travels along the at least one wall,

generate a map of an explored area by exploring an area in a vicinity of the robot through the sensor while the robot travels,

store information on the generated map in the at least one memory,

based on the robot completing the wall following, control the driver to cause the robot to move to an exploration point in an unexplored area in the vicinity of the robot,

based on identifying a plurality of walls through the sensor, determine priorities of the plurality of walls based on a corner direction of each wall of the plurality of walls and a distance between each wall of the plurality of walls and the robot, wherein for each wall of the plurality of walls the corner direction comprises a direction facing away from a vertex of a reflex angle formed by a corner in the wall, and

store information related to the plurality of walls in the at least one memory according to the determined priorities.

2. The robot of claim 1 , wherein the one or more instructions, when executed by the at least one processor, cause the robot to:

store information related to the at least one wall in the at least one memory, and

control, based on the stored information related to the at least one wall, the driver to cause the robot to perform the wall following.

3. The robot of claim 2 , wherein the one or more instructions, when executed by the at least one processor, cause the robot to, based on identifying a new wall through the sensor while the robot performs the wall following along the at least one wall, store information on the new wall in the at least one memory and control the driver to cause the robot to perform wall following along the new wall based on the stored information.

4. The robot of claim 1 , wherein the one or more instructions, when executed by the at least one processor, cause the robot to:

identify the at least one wall, from among the plurality of walls, based on the at least one wall having a corner direction facing the robot,

determine that the at least one wall having the corner direction facing the robot has a higher priority than remaining walls among the plurality of walls,

determine that the at least one wall has a higher priority than a wall closest to the robot from among the plurality of walls, and

determine, for each respective remaining wall of the plurality of walls other than the at least one wall, that the respective remaining wall has a higher priority than the wall closest to the robot, and

wherein a priority of a given wall among the plurality of walls is inversely proportional to a distance between the given wall and the robot.

5. The robot of claim 1 , wherein the one or more instructions, when executed by the at least one processor, cause the robot to, based on the priorities of the plurality of walls and the stored information related to the plurality of walls, control the driver to cause the robot to sequentially perform wall following along each wall of the plurality of walls.

6. The robot of claim 1 , wherein the one or more instructions, when executed by the at least one processor, cause the robot to:

based on information obtained through the sensor, identify that the robot has returned to a position where the wall following along the at least one wall began, and

based on the identifying that the robot has returned to the position where the wall following along the at least one wall began, determine that the wall following along the at least one wall is complete.

7. The robot of claim 1 , wherein the one or more instructions, when executed by the at least one processor, cause the robot to, based on at least one of the robot moving a predetermined distance from a position where the wall following along the at least one wall began, a predetermined time elapsing from a time when the wall following along the at least one wall began, or a moving direction of the robot remaining unchanged for a predetermined time after the wall following along the at least one wall began, control the driver to cause the robot to stop the wall following along the at least one wall.

8. The robot of claim 1 , wherein the one or more instructions, when executed by the at least one processor, cause the robot to:

identify a boundary between the explored area and the unexplored area, wherein the boundary is part of the unexplored area, and

wherein the exploration point is adjacent to the boundary.

9. The robot of claim 1 , wherein the one or more instructions, when executed by the at least one processor, cause the robot to, based on identifying at least one wall through the sensor while the robot moves to the exploration point, control the driver to cause the robot to travel along the at least one wall.

10. A method of generating a map using a robot including a sensor, the method comprising:

identifying at least one wall through the sensor of the robot;

performing wall following in which the robot travels along the at least one wall;

generating a map of an explored area by exploring an area in a vicinity of the robot through the sensor while the robot travels;

storing information on the generated map in a memory of the robot;

based on the robot completing the wall following, moving the robot to an exploration point in an unexplored area in the vicinity of the robot;

identifying a plurality of walls through the sensor including the at least one wall;

based on the identifying the plurality of walls through the sensor, determining priorities of the plurality of walls based on corner directions of each wall of the plurality of walls and a distance between each wall of the plurality of walls and the robot, wherein for each wall of the plurality of walls the corner direction comprises a direction facing away from a vertex of a reflex angle formed by a corner in the wall; and

storing information related to the plurality of walls in the memory according to the priorities.

11. The method of claim 10 , wherein the performing wall following comprises storing information related to the at least one wall and performing the wall following along the at least one wall based on the stored information.

12. The method of claim 10 , wherein the identifying the at least one wall through the sensor further comprises:

identifying the at least one wall, from among the plurality of walls, based on the at least one wall having a corner direction facing the robot;

determining that the at least one wall having the corner direction facing the robot has a higher priority than remaining walls among the plurality of walls,

determining that the at least one wall has a higher priority than a wall closest to the robot from among the plurality of walls; and

determining, for each respective remaining wall of the plurality of walls other than the at least one wall, that the respective remaining wall has a higher priority than the wall closest to the robot, and

wherein a priority of a given wall among the plurality of walls is inversely proportional to a distance between the given wall and the robot.

13. The method of claim 10 , further comprising:

based on the robot completing the wall following, sequentially performing wall following along each remaining wall of the plurality of walls based on the priorities and the stored information.

14. A non-transitory computer readable recording medium storing computer instructions, which when executed by at least one processor, cause the at least one processor to execute a method of generating a map using a robot including a sensor, the method comprising:

identifying at least one wall through the sensor;

performing wall following in which the robot travels along the at least one wall;

generating a map of an explored area by exploring an area in a vicinity of the robot through the sensor while the robot travels;

storing information on the generated map in a memory of the robot;

based on the robot completing the wall following, moving the robot to an exploration point in an unexplored area in the vicinity of the robot;

identifying a plurality of walls through the sensor including the at least one wall;

based on the identifying the plurality of walls through the sensor, determining priorities of the plurality of walls based on corner directions of each wall of the plurality of walls and a distance between each wall of the plurality of walls and the robot, wherein for each wall of the plurality of walls the corner direction comprises a direction facing away from a vertex of a reflex angle formed by a corner in the wall; and

storing information related to the plurality of walls in the memory according to the priorities.

15. The non-transitory computer readable recording medium of claim 14 , wherein the performing wall following comprises storing information related to the at least one wall and performing the wall following along the at least one wall based on the stored information.

16. The non-transitory computer readable recording medium of claim 14 , wherein the identifying the at least one wall through the sensor further comprises:

identifying the at least one wall, from among the plurality of walls, based on the at least one wall having a corner direction facing the robot;

determining that the at least one wall having the corner direction facing the robot has a higher priority than remaining walls among the plurality of walls,

determining that the at least one wall has a higher priority than a wall closest to the robot from among the plurality of walls; and

determining, for each respective remaining wall of the plurality of walls other than the at least one wall, that the respective remaining wall has a higher priority than the wall closest to the robot, and

wherein a priority of a given wall among the plurality of walls is inversely proportional to a distance between the given wall and the robot.

17. The non-transitory computer readable recording medium of claim 14 , wherein the method further comprises:

based on the robot completing the wall following, sequentially performing wall following along each remaining wall of the plurality of walls based on the priorities and the stored information.

Assignments (1)

Priority Claims (1)

Continuity (2)

References Cited (41)