METHOD AND SYSTEM FOR LOCALIZING MOBILE ROBOT USING EXTERNAL SURVEILLANCE CAMERAS

• US 20170252925A1
• Filed: 06/21/2016
• Published: 09/07/2017
• Est. Priority Date: 03/02/2016
• Status: Active Grant

• Current Assignee: Gachon University of Industry-Academic Cooperation Foundation
• Original Assignee: Gachon University of Industry-Academic Cooperation Foundation
• Inventors: CHO, Young-Im
• Granted Patent: US 9,849,589 B2
• Time in Patent Office: Days
• CPC Class Codes: B25J 19/021 Optical sensing devices
• CPC Class Codes: B25J 9/1666 Avoiding collision or forbidden zones
• CPC Class Codes: G05B 2219/40476 Collision, planning for collision free path
• CPC Class Codes: G05B 2219/40519 Motion, trajectory planning
• CPC Class Codes: G05D 1/028 using a RF signal
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 10/42 Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
• CPC Class Codes: G06V 10/757 Matching configurations of points or features
• CPC Class Codes: Y10S 901/01 Mobile robot

Abstract

A mobile robot employing a method and a system for localizing the mobile robot using external surveillance cameras acquires images from the surveillance cameras installed indoors adjacent to each other, recognizes objects included in the images by removing shadows from the images and performing a homography scheme, and avoids the recognized objects. The mobile robot employing the method and the system for localizing the mobile robot using the external surveillance cameras enables rapider localization and lower price as compared with a conventional image-based autonomous robot, so that the commercialization of a service robot is accelerated.

Claims

1. A system for localizing a mobile robot using external surveillance cameras, the system comprising:

a control unit that recognizes an object and an obstacle included in received surveillance camera images through a shadow removing scheme and a homography scheme, creates a moving path to allow travelling while avoiding the object and the obstacle, and generates a corresponding control signal to control components other than the control unit;

a sensing unit that senses a steering angle and rotation of a driving motor and transmits the steering angle and the rotation of the driving motor to the control unit;

a traveling unit that generates driving force by the control signal;

a steering unit that performs steering along the moving path by the control signal;

a communication unit that transmits images, which are obtained from the surveillance cameras, to the control unit; and

a power supply unit that supplies power to components other than the power supply unit.

2. The system of claim 1,

further comprising a proximity sensor or a distance sensor provided on one side of an outer portion of a shadow removing system.

3. The system of claim 1,

wherein a communication protocol applied to the communication unit is a Zigbee wireless communication protocol.

4. The system of claim 1,

wherein one wireless communication protocol or a plurality of wireless communication protocols are applied to the communication unit.

5. The system of claim 1,

wherein the traveling unit comprises a moving unit including a wheel, a caterpillar, or a leg for walking.

6. The system of one of claim 1,

wherein the sensing unit comprises a camera or a vision sensor.

7. The system of one of claim 2,

wherein the sensing unit comprises a camera or a vision sensor.

8. The system of one of claim 3,

wherein the sensing unit comprises a camera or a vision sensor.

9. The system of one of claim 4,

wherein the sensing unit comprises a camera or a vision sensor.

10. The system of one of claim 5,

wherein the sensing unit comprises a camera or a vision sensor.

11. A method of localizing a mobile robot using external surveillance cameras, the method comprising:

converting original images acquired from indoor surveillance cameras installed adjacent to each other to binary images and removing shadows from the binary images;

merging the binary images having no shadows with each other through a homography scheme;

recognizing locations and sizes of objects included into the original images through a contour scheme; and

compensating for errors of the recognized locations and sizes of the objects, and mapping the objects having the compensated locations and sizes with an image of a real floor, which is merged with a grid.

12. The method of claim 11,

wherein, in the merging of the binary images having no shadows with each other through the homography scheme,

Equations 1 and 2 are applied to the binary images having no shadows,

q=HQ, 

 

Equation 1

in which q and Q represent planes q and Q, respectively, in Equation 1, and

13. The method of claim 11,

further comprising planning a moving path based on the mapping after the mapping of the objects having the compensated locations and sizes.

14. The method of claim 12,

further comprising planning a moving path based on the mapping after the mapping of the objects having the compensated locations and sizes.

15. The method of claim 13,

further comprising:

marking the planed moving path and an actual traveling path on a same map and calculating an error bound between the moving path and the traveling path; and

transmitting the error bound to an external system,

after the planning of the moving path and the actual traveling of the mobile robot along the planed moving path.

16. The method of claim 14,

further comprising:

marking the planed moving path and an actual traveling path on a same map and calculating an error bound between the moving path and the traveling path; and

transmitting the error bound to an external system,

after the planning of the moving path and the actual traveling of the mobile robot along the planed moving path.

17. The method of claim 15,

wherein a square lattice or grid including gradations spaced at a predetermined interval is displayed together with the moving path and the traveling path on the map having the planed moving path and the actual traveling path that are marked thereon.

18. The method of claim 16,

wherein a square lattice or grid including gradations spaced at a predetermined interval is displayed together with the moving path and the traveling path on the map having the planed moving path and the actual traveling path that are marked thereon.

19. The method of claim 15,

wherein the external system, to which the error bound is transmitted, stores and processes error bounds transmitted from a plurality of mobile robots, and transmits the stored error bound or a processing result to an outside.

20. The method of claim 16,

wherein the external system, to which the error bound is transmitted, stores and processes error bounds transmitted from a plurality of mobile robots, and transmits the stored error bound or a processing result to an outside.