METHOD OF CONTROLLING A ROBOTIC TOOL

• US 20110282492A1
• Filed: 02/03/2010
• Published: 11/17/2011
• Est. Priority Date: 02/03/2009
• Status: Active Grant

• Current Assignee: Fanuc Robotics America Incorporated (Fanuc Corporation)
• Original Assignee: Fanuc Robotics America Incorporated (Fanuc Corporation)
• Inventors: Dinsmoor, Claude, Coldren, Bruce E., Krause, Ken, Roney, Edward, Sharpe, Michael M., Prehn, Steven
• Granted Patent: US 8,706,300 B2
• Time in Patent Office: Days
• US Class Current: 700/259
• CPC Class Codes: B25J 9/1664 characterised by motion, path, trajectory planning
• CPC Class Codes: G05B 2219/37555 Camera detects orientation, position workpiece, points of workpiece
• CPC Class Codes: G05B 2219/40425 Sensing, vision based motion planning

Abstract

A method of controlling a robot system includes the steps of providing a tool supported by a moveable mechanism of the robot system, providing a workpiece supported by a holder, generating an image of the workpiece, extracting a data from the image, the data relating to a feature of the workpiece, generating a continuous three-dimensional path along the workpiece using data extracted from the image, and moving the tool along the path.

Claims

1. A method of controlling a robot system, the method comprising the steps of:

a. providing a tool supported by a moveable mechanism of the robot system;

b. providing a workpiece supported by a holder;

c. generating an image of the workpiece;

d. extracting a data from the image, the data relating to a feature of the workpiece;

e. generating a continuous three-dimensional path along the workpiece using data extracted from the image; and

f. moving the tool along the path.

2. The method according to claim 1, wherein the image is a two-dimensional image.

3. The method according to claim 1, wherein the image is generated by a three dimensional vision sensor.

4. The method according to claim 2, further comprising the step of providing image points which constitute a three-dimensional data not readily detectable in the two-dimensional image.

5. The method according to claim 2, further comprising the step of providing a secondary model of a third dimension of the workpiece not readily detectable in the two-dimensional image via prior knowledge of an expected geometry of the workpiece.

6. The method according to claim 1, further comprising the step of manually teaching a point on the path.

7. The method according to claim 1, where the generated path is used to generate motion commands for the mechanism to trace the path.

8. The method according to claim 1, further comprising the step of offsetting a pre-set path based upon at least one of the data extracted from the image and the generated path.

9. The method according to claim 1, wherein the path is overlayed on the feature of the workpiece.

10. The method according to claim 1, further comprising the step of filtering the data extracted from the image.

11. The method according to claim 10, wherein the step of filtering the data is based upon at least one of a contrast threshold, a maximum deviation, and a point spacing.

12. A method of controlling a robot system, the method comprising the steps of:

a. providing a tool supported by a moveable mechanism of the robot system;

b. providing a workpiece supported by a holder;

c. calibrating the moveable mechanism to the holder;

d. generating an image of the workpiece;

e. extracting a data from the image, the data representing a feature of the workpiece;

f. assigning a node to each of a plurality of points along the feature of the workpiece using data extracted from the image and data from the calibration of the moveable mechanism;

g. generating a continuous three-dimensional path along the nodes; and

h. moving the tool along the path.

13. The method according to claim 12, wherein the image is generated by a three dimensional vision sensor.

14. The method according to claim 12, further comprising the step of providing a secondary model of a third dimension of the workpiece not readily detectable in the two-dimensional image via prior knowledge of an expected geometry of the workpiece.

15. The method according to claim 12, further comprising the step of manually teaching a point on the path.

16. The method according to claim 12, where the generated path is used to generate motion commands for the mechanism to trace the path.

17. The method according to claim 12, wherein data relating to each node includes at least one of a magnitude of a gradient of the node, a length of the feature with which the node is associated;

a numeric identification of a chain of associated nodes, and a position of the node in a pre-defined coordinate system.

18. A method of controlling a robot system, the method comprising the steps of:

a. providing a tool;

b. providing a workpiece;

c. applying a guide line to the workpiece;

d. extracting a data relating to a feature of the workpiece;

e. locating the workpiece;

f. generating an ideal path of the tool along the workpiece using the extracted data;

g. moving the tool along at least a portion of the ideal path; and

h. adjusting a position of the tool to follow the guide line.

19. The method according to claim 18, wherein the step of locating the workpiece is executed by a vision system.

20. The method according to claim 18, wherein the data relating to a feature of the workpiece is extracted from a computer aided drawing data for an ideal part.