Mobile robot, and control method and program for the same

• US 20070276541A1
• Filed: 08/30/2006
• Published: 11/29/2007
• Est. Priority Date: 05/26/2006
• Status: Abandoned Application

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Sawasaki, Naoyuki
• Application Number:
  US11/512,338
• Publication Number:
  US 20070276541A1
• Time in Patent Office: Days
• US Class Current: 700/253
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0272 comprising means for registering the travel distance, e.g. revolutions of wheels measuring distance traversed on the ground by vehicles, e.g. using odometers G01C22/00

Abstract

A path planning unit plans a travel path to a destination based on an estimated current travel position and outputs a travel command to a travel control unit to perform travel control so as to follow the travel path. A travel position prediction unit accumulates a travel distance, which is detected by a wheel turning-angle sensor, to the estimated current travel position so as to predict the current travel position. A predictive image generating unit generates a plurality of predictive edge images which are composed of edge information and captured when a camera is virtually disposed at the predicted current travel position and candidate positions in the vicinity of it based on layout information of the environment, and an edge image generating unit generates an actual edge image from the actual image captured by the camera. A position estimation unit compares the edge image with the plurality of predictive edge images, estimates the candidate position of the predictive edge image at which the degree of similarity is the maximum, and updates the travel position of the path planning unit and the travel position prediction unit.

Claims

1. A mobile robot which travels in an environment such as a facility, characterized by having

a path planning unit which plans a travel path to a destination based on an estimated current travel position and outputs a travel command;

a travel control unit which performs travel control so as to follow the travel path based on the travel command of the path planning unit;

a position prediction unit which accumulates a travel distance, which is detected by a turning-angle sensor of a wheel, to the estimated current travel position and predicts the current travel position;

a predictive image generating unit which generates a plurality of predictive edge images, which are composed of edge information and captured when the imaging unit is virtually disposed at the current travel position predicted by the position prediction unit and candidate positions in the vicinity of it, based on layout information of the environment;

an edge image generating unit which extracts edge information from an actual image of the traveling direction which is captured by the imaging unit and generates an actual edge image; and

a position estimation unit which compares the actual edge image with the plurality of predictive edge images, estimates a candidate position of the predictive edge image at which the degree of similarity is the maximum as a travel position, and updates the travel position of the path planning unit and the position prediction unit.

2. The mobile robot according to claim 1, characterized in that the position estimation unit calculates a correlation between the actual edge image generated by differentiating processing of the actual image and each of the predictive edge images and estimates the candidate position of the predictive edge image at which the correlation is the maximum as the travel position.

3. The mobile robot according to claim 1, characterized in that the position estimation unit calculates the number of overlapping pixels of the actual edge image generated by differentiating processing of the actual image and each of the predictive edge images and estimates the candidate position of the predictive edge image at which the number of overlapping pixels is the maximum as the travel position.

4. The mobile robot according to claim 2, characterized in that

the predictive image generating unit changes the image-capturing direction of the imaging unit for each of the candidate positions and generates the plurality of predictive edge images.

5. The mobile robot according to claim 3, characterized in that

the predictive image generating unit changes the image-capturing direction of the imaging unit for each of the candidate positions and generates the plurality of predictive edge images.

6. The mobile robot according to claim 1, characterized in that the predictive image generating unit generates the predictive edge images based on camera parameters of the imaging unit and three-dimensional coordinates of the layout information.

7. The mobile robot according to claim 1, characterized in that the estimation process of the current travel position based on the actual edge image and the plurality of predictive edge images is repeated every predetermined travel distance or predetermined movement time.

13. The control method of the mobile robot according to claim 7, characterized in that, in the predictive image generating step, the predictive edge images are generated based on camera parameters of the imaging step and three-dimensional coordinates of the layout information.

8. A control method of a mobile robot which travels in an environment such as a facility, characterized by having

a path planning step in which a travel path to a destination is planned based on an estimated current travel position and a travel command is output;

a travel control step in which travel control is performed so as to follow the travel path based on the travel command of the path planning step;

a position prediction step in which a travel distance, which is detected by a turning-angle sensor of a wheel, is accumulated to the estimated current travel position and the current travel position is predicted;

a predictive image generating step in which a plurality of predictive edge images, which are composed of edge information and captured when the imaging unit is virtually disposed at the current travel position predicted in the position prediction step and candidate positions in the vicinity of it, are generated based on layout information of the environment;

an edge image generating step in which edge information is extracted from an actual image of the traveling direction which is captured by the imaging unit and an actual edge image is generated; and

a position estimation step in which the actual edge image is compared with the plurality of predictive edge images, a candidate position of the predictive edge image at which the degree of similarity is the maximum is estimated as a travel position, and the travel position in the path planning step and the position prediction step is updated.

9. The control method of the mobile robot according to claim 8, characterized in that, in the position estimation step, a correlation between the actual edge image generated by differentiating processing of the actual image and each of the predictive edge images is calculated and the candidate position of the predictive edge image at which the correlation is the maximum is estimated as the travel position.

10. The control method of the mobile robot according to claim 8, characterized in that, in the position estimation step, the number of overlapping pixels of the actual edge image generated by differentiating processing of the actual image and each of the predictive edge images is calculated and the candidate position of the predictive edge image at which the number of overlapping pixels is the maximum is estimated as the travel position.

11. The control method of the mobile robot according to claim 9, characterized in that,

in the predictive image generating step, the image-capturing direction of the imaging step is changed for each of the candidate positions and the plurality of predictive edge images are generated.

12. The control method of the mobile robot according to claim 10, characterized in that,

in the predictive image generating step, the image-capturing direction of the imaging step is changed for each of the candidate positions and the plurality of predictive edge images are generated.

14. The control method of the mobile robot according to claim 8, characterized in that the estimation process of the current travel position based on the actual edge image and the plurality of predictive edge images is repeated every predetermined travel distance or predetermined movement time.

15. A computer-readable storage medium which stores a program characterized by causing a computer of a mobile robot which travels in an environment such as a facility to execute,

a path planning step in which a travel path to a destination is planned based on an estimated current travel position and a travel command is output;

a travel control step in which travel control is performed so as to follow the travel path based on the travel command of the path planning step;

a position prediction step in which a travel distance, which is detected by a turning-angle sensor of a wheel, is accumulated to the estimated current travel position and the current travel position is predicted;

a predictive image generating step in which a plurality of predictive edge images, which are composed of edge information and captured when the imaging unit is virtually disposed at the current travel position predicted in the position prediction step and candidate positions in the vicinity of it, are generated based on layout information of the environment;

an edge image generating step in which edge information is extracted from an actual image of the traveling direction which is captured by the imaging unit and an actual edge image is generated; and

a position estimation step in which the actual edge image is compared with the plurality of predictive edge images, a candidate position of the predictive edge image at which the degree of similarity is the maximum is estimated as a travel position, and the travel position in the path planning step and the position prediction step is updated.

16. The storage medium according to claim 15, characterized in that, in the position estimation step, a correlation between the actual edge image generated by differentiating processing of the actual image and each of the predictive edge images is calculated and the candidate position of the predictive edge image at which the correlation is the maximum is estimated as the travel position.

17. The storage medium according to claim 15, characterized in that, in the position estimation step, the number of overlapping pixels of the actual edge image generated by differentiating processing of the actual image and each of the predictive edge images is calculated and the candidate position of the predictive edge image at which the number of overlapping pixels is the maximum is estimated as the travel position.

18. The storage medium according to claim 16, characterized in that,

in the predictive image generating step, the image-capturing direction of the imaging step is changed for each of the candidate positions and the plurality of predictive edge images are generated.

19. The storage medium according to claim 17, characterized in that,

in the predictive image generating step, the image-capturing direction of the imaging step is changed for each of the candidate positions and the plurality of predictive edge images are generated.

20. The storage medium according to claim 15, characterized in that, in the predictive image generating step, the predictive edge images are generated based on camera parameters of the imaging step and three-dimensional coordinates of the layout information.

21. The storage medium according to claim 15, characterized in that the estimation process of the current travel position based on the actual edge image and the plurality of predictive edge images is repeated every predetermined travel distance or predetermined movement time.