Robot vision using target holes, corners and other object features

• US 6,044,183 A
• Filed: 06/06/1995
• Issued: 03/28/2000
• Est. Priority Date: 02/16/1982
• Status: Expired due to Term

• Current Assignee: Laser Measurement International Inc.
• Original Assignee: Laser Measurement International Inc.
• Inventors: Pryor, Timothy R.
• Primary Examiner(s): Johns, Andrew W.
• Application Number:
  US08/468,358
• Time in Patent Office: 1,757 Days
• Field of Search: 382/151, 382/103, 382/104, 382/106, 382/141, 382/153, 382/154, 382/286, 382/287, 382/291, 348/94, 702/150, 702/152
• US Class Current: 382/287
• CPC Class Codes: A01B 69/008 automatic
• CPC Class Codes: B23P 19/10 Aligning parts to be fitted together
• CPC Class Codes: B25J 9/1697 Vision controlled systems
• CPC Class Codes: F02F 2007/0063 Head bolts; Arrangements of cylinder head bolts
• CPC Class Codes: G01B 11/00 Measuring arrangements characterised by the use of optical techniques
• CPC Class Codes: G05B 19/401 characterised by control arrangements for measuring, e.g. calibration and initialisation, measuring workpiece for machining purposes G05B19/19 takes precedence
• CPC Class Codes: G05B 2219/34033 Control processor and signal processor cooperate
• CPC Class Codes: G05B 2219/39393 Camera detects projected image, compare with reference image, position end effector
• CPC Class Codes: G05B 2219/45064 Assembly robot

Abstract

A method and apparatus uses naturally occurring object features as targets in a machine vision based robot (or other) guidance system. In one embodiment, a special high speed processor finds at least 3 pre-selected feature points on an object, which when considered with the data base for the object, allows a rapid 6 degree of freedom solution for the object location relative to the camera and thence connected automation. While primarily envisioned for industrial robots, the invention is useful for all sorts of machines including vehicles, construction machinery and the like--anywhere the target object has a known data base relative to the features in question.

Claims

1. A method for object position determination, said object having natural features and artificial targets, said method comprising the steps of:

providing a data base of said natural features and artificial targets of said object,

selecting at least one of said features and at least one of said targets,

providing an electro-optical system to acquire data from said selected features and targets, and

analyzing data from said system to find said selected features and targets and determine their locations.

2. A method according to claim 1 wherein said electro-optical system comprises at least one TV camera.

3. A method according to claim 2 wherein at least two TV cameras are used to provide stereo information concerning the location of said features.

4. A method according to claim 1 wherein said object position in 3D space is determined.

5. A method according to claim 4 wherein said object position in space is calculated photogrammetrically.

6. A method according to claim 1 wherein range data to said object is first determined.

7. A method according to claim 1 wherein one feature is first found, and at least one other located therefrom using said data base.

8. A method according to claim 7 wherein at least two features are selected and said at least two selected features are different from one another.

9. A method according to claim 7 wherein said at least one selected feature comprises a corner, edge segment, notch or other feature which is definable in more than one dimension.

10. A method according to claim 7 wherein said selected features are redundant and alternative features.

11. A method according to claim 7 wherein said features are downloaded from a data base for a given part.

12. A method according to claim 7 further comprising determining the nature of the object.

13. A method according to claim 7 including processing to track said object features when said features are found.

14. A method according to claim 7 wherein said electro-optical sensor operates at 15 data readings/sec or greater.

15. A method according to claim 7 wherein said at least one selected feature is a hole, whose position is precisely known with respect to other object features of interest.

16. A method according to claim 15 wherein said hole centroid is determined.

17. A method according to claim 7 wherein edges of a object are located, and by using edge location information, said features are found.

18. A method according to claim 7 wherein said at least one selected feature is selected from a feature which is at least one of stamped or cast or other wise formed or impressed or colored into the surface of said object.

19. A method according to claim 18 wherein the signature of said at least one selected feature is obtained to identify its location.

20. A method according to claim 7 including the further step of providing a machine readable code on said object indicative of where said features are.

21. A method according to claim 7 wherein said at least one selected feature is a hole placed on said object to act as an optically visible feature.

22. A method according to claim 7 wherein two or more sensors are used to observe said object in the same zone, and coincidence in their output appears at the same point where a given characteristic or said at least one selected feature is selected.

23. A method according to claim 1 including the additional step of providing position information to a robot for manipulating or working said object.

24. A method according to claim 1 wherein said feature is a special feature put on said object to aid said position determination.

25. A method according to claim 1 wherein said position determination is simulated a priori.

26. A method according to claim 21 wherein said position is determined a plurality of times as a robot attempts to grab said object.

27. A method according to claim 1 wherein said analysis is performed using special processing for the feature or features to be acquired.

28. A method according to claim 1 wherein said analysis is also with target on tool or fixture.

29. A method according to claim 1 at least one of said features is a hole, corner, logo, indentation, protrusion, slot, or lettering.

30. A method according to claim 1 at least one of said features is projected onto said object.

31. A method according to claim 1 wherein three or more object features are used.

32. A method according to claim 1 including further step of selecting different features for different objects having the same data base.

33. A method according to claim 32 wherein alternative features are selected if one or more of said at least one selected features cannot be used.

34. A method according to claim 1 wherein said electro-optical system views a plurality of features simultaneously.

35. A method according to claim 1 wherein said at least one selected feature is an edge of said object.

36. A method according to claim 35 wherein said edge is the rolled edge formed by the intersection of two surfaces of a stamped object.

37. A method according to claim 1 wherein said data analysis step includes the step of determining a feature size, shape or reflectance characteristic.

38. A method according to claim 1 wherein illumination is used for said electro-optical system and is compensated to account for object reflectance, dirty windows or other variables.

39. A method according to claim 1 wherein illumination is used for said electro-optical system and is selected to accentuate said features.

40. A method according to claim 1 wherein an initial feature is found, and said data base is used to determine the region of search for additional features.

41. A method according to claim 1 including the further step of downloading data concerning said object from a CAD system.

42. A method according to claim 1 including the step of determining a characteristic of said at least one selected feature said characteristic allowing identification of said at least one selected feature.

43. A method according to claim 1 wherein said analysis is performed using a specialized processor.

44. A method according to claim 1 wherein said feature is designed in to be part of said object.

45. A method according to claim 1 wherein the field of scan of said electro-optical system is segmented to allow different feature processing within segments.

46. A method according to claim 1 wherein said object is in motion relative to said electro-optical system, and said data is acquired sufficiently rapidly.

47. A method according to claim 46 wherein said object is tracked.

48. A method according to claim 1 wherein said selected features of said object are found in the presence of other objects or features.

49. A method as in claim 1, further comprising determining, from said determined locations, the positions of further portions of said object.

50. A method for determining the position of a 3D object, said object having natural features and artificial targets, said method comprising the steps of:

providing a data base of natural features of said 3D object,

selecting at least one of said features and at least one of said targets,

providing an electro-optical system to acquire data from said at least one selected feature and target,

analyzing the data from said system to find and determine the location of said at least one selected object feature and target, and

from the locations of said at least one selected feature and target, determining the 3D position of said object.

51. Apparatus for determining the position of a 3D object, said object having natural features and artificial targets, said apparatus comprising;

means for storing design data concerning natural features of said object,

means for selecting at least one of said features and at least one of said targets,

electro-optical means to obtain data from said at least one selected feature and target,

means to analyze said data to find said at least one selected feature and target on said object,

means to analyze said data to determine the location of said at least one selected feature and target, and

means for determining the 3D position of said object.

52. A method for determination of object position or orientation, said object having natural features and artificial targets, said method comprising the steps of:

providing a data base of said natural features and artificial targets of said object,

selecting a plurality of at least one of said features and at least one of said targets,

providing an electro-optical system to acquire data from said selected features and targets,

analyzing data from said system to find said selected features and targets and determine their locations, and

from said determined locations, determining the position or orientation of said object.