Method of detecting object using structured light and robot using the same

• US 7,507,948 B2
• Filed: 11/01/2006
• Issued: 03/24/2009
• Est. Priority Date: 05/17/2006
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Lee, Hyoung-ki, Bang, Seok-won, Park, Dong-ryeol, Kim, Dong-jo
• Primary Examiner(s): Sohn; Seung C
• Application Number:
  US11/590,744
• Publication Number:
  US 20070267570A1
• Time in Patent Office: 874 Days
• Field of Search: 250/221, 250/559.19, 250/559.33
• US Class Current: 250/221
• CPC Class Codes: A47L 2201/04 Automatic control of the travelling movement; Automatic obstacle detection
• CPC Class Codes: A47L 9/009 Carrying-vehicles; Arrangements of trollies or wheels; Means for avoiding mechanical obstacles
• CPC Class Codes: A47L 9/2826 the condition of the floor
• CPC Class Codes: A47L 9/2852 Elements for displacement of the vacuum cleaner or the accessories therefor, e.g. wheels, casters or nozzles
• CPC Class Codes: A47L 9/30 Arrangement of illuminating devices
• CPC Class Codes: B25J 19/021 Optical sensing devices
• CPC Class Codes: B25J 5/007 mounted on wheels
• CPC Class Codes: G01B 11/25 by projecting a pattern, e.g. one or more lines, moiré fringes on the object G01B11/255 takes precedence ; image analysis for depth or shape recovery G06T7/50
• CPC Class Codes: G05D 1/0248 in combination with a laser lasers per se H01S
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30

Abstract

A method of detecting an object using a structured light and a robot using the same are disclosed. The method of detecting a floor object using a structured light includes measuring a height difference of a position onto which a specified structured light is projected with a reference position, and detecting the floor object using the measured height difference.

Claims

1. A robot comprising:

an imaging unit providing an image frame of an area onto which a structured light is projected;

a traveling unit tracking a boundary of a floor object using a position of the structured light in the image frame;

a detection unit detecting the floor object using a traveling path of the traveling unit; and

a boundary measurement unit measuring a third boundary direction of the floor object through a sum of a weight value of a first boundary direction measured using the position of the structured light in the image frame and a weight value of a second boundary direction measured using a difference between color information of the floor object and color information of a floor in the image frame,

wherein the traveling unit tracks the floor object in parallel with the third boundary direction.

2. The robot of claim 1, further comprising:

a projection unit projecting the structured light;

a distance calculator calculating a height difference of a position onto which the structured light is projected from a reference position, using the position of the structured light in the image frame.

3. The robot of claim 1, wherein the structured light is a single linear type, a plurality of linear types, or a matrix shaped linear type.

4. The robot of claim 1, further comprising a boundary measurement unit measuring a boundary direction of the floor object using the position of the structured light in the image frame.

5. The robot of claim 1, wherein the detection unit determines that a tracking path of the traveling unit is an area of the floor object, when the tracking path forms a closed loop.

6. The robot of claim 1, wherein the detection unit determines that a closed loop obtained by connecting both end points of the tracking path is an area of the floor object, when the tracking path forms three lines connected at a specified angle.

7. The robot of claim 1, wherein the detection unit determines a closed loop, which is obtained by subjecting a segment that connects both end points of the tracking path to symmetry processing, is an area of the floor object, when the tracking path forms two lines connected at a specified angle.

8. The robot of claim 1, wherein the detection unit calculates a width of the floor object using distance information between two boundaries of the floor object in an image frame generated by allowing the imaging unit to take the floor object in a direction vertical to the tracking path, when the tracking path is a single segment, and determines an area of the floor object using the tracking path and the calculated width.

9. The robot of claim 1, wherein the detection unit categorizes a type of the floor object in accordance with a size of the floor object.

10. The robot of claim 1, wherein the detection unit categorizes a material of the floor object using height information of a surface of the floor object, the height information being obtained through the structured light projected onto the floor object.

11. The robot of claim 1, further comprising a distance calculator calculating a distance to the position onto which the structured light is projected, when the presence of the floor object is identified after the height difference is measured, wherein the traveling unit moves within a specified distance from the floor object using the calculated distance.

12. The robot of claim 1, further comprising a map management unit updating a reference map to reflect information of the detected floor object.

13. The robot of claim 1, further comprising a projection unit projecting the structured light.

14. A method of detecting a floor object using a structured light, comprising:

measuring a height difference of a position onto which a structured light is projected from a reference position; and

detecting the floor object using the measured height difference,

wherein the detecting the floor object comprises tracking a boundary of the floor object using the structured light, and detecting the floor object in accordance with a tracking path of the boundary of the floor object, and

wherein the tracking the boundary comprises providing an image frame of the position onto which the structured light is projected, measuring a first boundary direction of the floor object using the position of the structured light in the image frame corresponding to the position onto which the structured light is projected, measuring a second boundary direction of the floor object using a difference between color information of the floor object and color information of a floor in the image frame, calculating a third boundary direction of the floor object through a sum of weight values of the first and second boundary directions, and moving in a direction parallel with the third boundary direction.

15. The method of claim 14, wherein the measuring a height difference comprises:

projecting the structured light;

providing an image frame of the position onto which the structured light is projected; and

calculating the height difference of the position of the structured light, using a position of the structured light in the image frame.

16. The method of claim 14, wherein the structured light is a single linear type, a plurality of linear types, or a matrix shaped linear type.

17. The method of claim 14, wherein the tracking the boundary comprises:

providing an image frame of the position onto which the structured light is projected;

measuring a boundary direction of the floor object using the position of the structured light in the image frame, which corresponds to the position onto which the structured light is projected; and

moving in a direction parallel with the boundary direction.

18. The method of claim 14, wherein the detecting the floor object comprises determining that the tracking path is an area of the floor object, when the tracking path forms a closed loop.

19. The method of claim 14, wherein the detecting the floor object comprises determining that a closed loop obtained by connecting both end points of the tracking path is an area of the floor object, when the tracking path forms three lines connected at a specified angle.

20. The method of claim 14, wherein the detecting the floor object comprises determining that a closed loop, which is obtained by subjecting a segment that connects both end points of the tracking path to symmetry processing, is an area of the floor object, when the tracking path forms two lines connected at a specified angle.

21. The method of claim 14, wherein the detecting the floor object comprises:

generating an image frame, in which two boundaries of the floor object are captured, by capturing the floor object in a direction vertical to the tracking path, when the tracking path is a single segment;

calculating a width of the floor object using distance information between the two boundaries captured in the image frame; and

determining an area of the floor object using the tracking path and the calculated width.

22. The method of claim 14, wherein the detecting the floor object comprises categorizing a type of the floor object in accordance with a size of the floor object.

23. The method of claim 14, wherein the detecting the floor object comprises:

projecting the structured light onto a surface of the floor object; and

categorizing a material of the floor object using height information of the surface of the floor object, the height information being obtained through the structured light projected onto the floor object.

24. The method of claim 14, further comprising:

calculating a distance to the position onto which the structured light is projected, when the presence of the floor object is identified after the measuring a height difference; and

moving within a specified distance from the floor object using the calculated distance.

25. The method of claim 14, further comprising updating a reference map to reflect information of the detected floor object.

26. A computer-readable storage medium encoded with processing instructions for causing a processor to execute the method of claim 14 of detecting a floor object using a structured light.