Electronic system with simulated sense perception and method of providing simulated sense perception

• US 8,086,551 B2
• Filed: 04/16/2008
• Issued: 12/27/2011
• Est. Priority Date: 04/16/2007
• Status: Active Grant

• Current Assignee: Blue Oak Mountain Technologies Incorporated
• Original Assignee: Blue Oak Mountain Technologies Incorporated
• Inventors: Czora, Gregory J.
• Primary Examiner(s): Rivas, Omar Fernandez
• Assistant Examiner(s): COUGHLAN, PETER D
• Application Number:
  US12/148,141
• Publication Number:
  US 20080294400A1
• Time in Patent Office: 1,350 Days
• Field of Search: None
• US Class Current: 706/46
• CPC Class Codes: G06N 3/004 Artificial life, i.e. computing arrangements simulating life
• CPC Class Codes: G06N 3/02 Neural networks

Abstract

A method of providing sense perception to an electronic system includes capturing a plurality of data sets, each data set representing an observation of a scene from a different perspective, comparing the data sets to identify invariants in the data sets, comparing the invariants to identify objects including the invariants, comparing the identified invariants and objects to other identified invariants and objects to identify additional objects including invariants not yet included in previously identified objects, and outputting data indicative of the identified objects and invariants. The different perspectives can be temporal (e.g., time sequenced), positional (e.g., movement of sensors), etc. The data sets can include data indicative of optical images, sound, and/or any other type of sensory data. The invariants can be data representations of color patches in an optical image. The data sets can include data indicative of at least three different types of sense perceptions.

Claims

1. A method of providing sense perception to an electronic system, said method comprising:

capturing a plurality of data sets, each data set representing an observation from a different perspective;

comparing said data sets to one another to identify invariants in said data sets;

comparing said invariants of said data sets to identify objects including said invariants;

comparing said identified invariants and objects to other invariants and objects identified in another plurality of data sets to identify additional objects including invariants not yet included in previously identified objects; and

outputting data indicative of said identified objects and invariants.

2. The method of claim 1, wherein said different perspectives are temporal.

3. The method of claim 1, wherein said different perspectives are positional.

4. The method of claim 1, wherein said data sets include data indicative of optical images.

5. The method of claim 4, wherein said data sets include data indicative of sound.

6. The method of claim 1, wherein said data sets include data indicative of sound.

7. The method of claim 1, wherein said data sets include data indicative of at least three different types of sense perceptions.

8. The method of claim 1, wherein said step of comparing said data sets to one another to identify said invariants includes:

determining the difference in perspective of said data sets;

comparing the data sets using the difference in perspective to determine differences and/or similarities;

grouping particular data satisfying one or more predetermined measurement ranges; and

generating sensation data indicative of said grouped data to represent said invariants.

9. The method of claim 1, wherein said step of identifying objects including said invariants includes:

determining the difference in perspective of said data sets;

comparing said invariants to determine relative position;

grouping said invariants based on relative position; and

generating object data indicative of said grouped invariants to represent perceived objects.

10. The method of claim 9, further comprising integrating all object data and any ungrouped sensation data into a single data structure representative of the observation.

11. The method of claim 1, wherein said step of comparing said identified invariants and objects to other invariants and objects identified in another plurality of data sets includes:

determining the difference in perspective between said plurality of data sets and said another plurality of data sets;

comparing ungrouped invariants of said plurality of data sets with said ungrouped invariants of said another plurality of data sets to determine relative movement of said ungrouped invariants;

grouping any of said ungrouped invariants that exhibit group movement; and

generating object data indicative of said grouped invariants that exhibit group movement to represent perceived moving objects.

12. The method of claim 11, further comprising integrating all object data and any ungrouped invariants into a single data structure representative of the observation.

13. The method of claim 1, wherein said invariants include color patches in an optical image represented by said data sets.

14. A computer-readable storage medium having code embodied therein for causing a computer to perform a method of providing sense perception to an electronic system, said method comprising:

capturing a plurality of data sets, each data set representing an observation from a different perspective;

comparing said data sets to one another to identify invariants in said data sets;

comparing said invariants of said data sets to identify objects including said invariants;

comparing said identified invariants and objects to other invariants and objects identified in another plurality of data sets to identify additional objects including invariants not yet included in previously identified objects; and

outputting data indicative of said identified objects and invariants.

15. The computer-readable storage medium of claim 14, wherein said different perspectives are temporal.

16. The computer-readable storage medium of claim 14, wherein said different perspectives are positional.

17. The computer-readable storage medium of claim 14, wherein said data sets include data indicative of optical images.

18. The computer-readable storage medium of claim 17, wherein said data sets include data indicative of sound.

19. The computer-readable storage medium of claim 14, wherein said data sets include data indicative of sound.

20. The computer-readable storage medium of claim 14, wherein said data sets include data indicative of at least three different types of sense perceptions.

21. The computer-readable storage medium of claim 14, wherein said step of comparing said data sets to one another to identify said invariants includes:

determining the difference in perspective of said data sets;

comparing the data sets using the difference in perspective to determine differences and/or similarities;

grouping particular data satisfying one or more predetermined measurement ranges; and

generating sensation data indicative of said grouped data to represent said invariants.

22. The computer-readable storage medium of claim 14, wherein said step of identifying objects including said invariants includes:

determining the difference in perspective of said data sets;

comparing said invariants to determine relative position;

grouping said invariants based on relative position; and

generating object data indicative of said grouped invariants to represent perceived objects.

23. The computer-readable storage medium of claim 22, wherein said method further comprises integrating all object data and any ungrouped sensation data into a single data structure representative of the observation.

24. The computer-readable storage medium of claim 14, wherein said step of comparing said identified invariants and objects to other invariants and objects identified in another plurality of data sets includes:

determining the difference in perspective between said plurality of data sets and said another plurality of data sets;

comparing ungrouped invariants of said plurality of data sets with said ungrouped invariants of said another plurality of data sets to determine relative movement of said ungrouped invariants;

grouping any of said ungrouped invariants that exhibit group movement; and

generating object data indicative of said grouped invariants that exhibit group movement to represent perceived moving objects.

25. The computer-readable storage medium of claim 24, wherein said method further includes integrating all object data and any ungrouped invariants into a single data structure representative of the observation.

26. The computer-readable storage medium of claim 14, wherein said invariants include color patches in an optical image represented by said data sets.

27. A system comprising:

a sensor set;

a sensor interface operative to communicate with said sensor set to capture a plurality of data sets, each data set representing an observation from a different perspective; and

a processing unit for processing data and code, said code including a sense perception routine operative to compare said data sets to one another to identify invariants in said data sets, to compare said invariants of said data sets to identify objects including said invariants, to compare said identified invariants and objects to other invariants and objects identified in another plurality of data sets to identify additional objects including invariants not yet included in previously identified objects, and to provide data indicative of said identified objects and invariants.

28. The system of claim 27, wherein said different perspectives are temporal.

29. The system of claim 27, wherein said different perspectives are positional.

30. The system of claim 27, wherein said sensor set includes an optical sensor.

31. The system of claim 30, wherein said sensor set includes an acoustical sensor.

32. The system of claim 27, wherein said sensor set includes an acoustical sensor.

33. The system of claim 27, wherein:

said sensor set includes at least three different types of sensors; and

said data sets include data indicative of at least three different types of sense perceptions.

34. The system of claim 27, wherein said sense perception routine is operative to:

determine the difference in perspective of said data sets;

compare the data sets using the difference in perspective to determine differences and/or similarities in said data sets;

group particular data satisfying one or more predetermined measurement ranges; and

generate sensation data indicative of said grouped data to represent said invariants.

35. The system of claim 27, wherein said sense perception routine is operative to:

determine the difference in perspective of said data sets;

compare said invariants to determine relative position;

group said invariants based on relative position; and

generate object data based on said grouped invariants to represent perceived objects.

36. The system of claim 35, wherein said sense perception routine is further operative to integrate all object data and any ungrouped sensation data into a single data structure representative of said observation.

37. The system of claim 27, wherein said sense perception routine is operative to:

determine the difference in perspective between said plurality of data sets and said another plurality of data sets;

compare ungrouped invariants of said plurality of data sets with said ungrouped invariants of said another plurality of data sets to determine relative movement of said ungrouped invariants;

group any of said ungrouped invariants that exhibit group movement; and

generate object data indicative of said grouped invariants that exhibit group movement to represent perceived moving objects.

38. The system of claim 37, wherein said sense perception routine is further operative to integrate all object data and any ungrouped invariants into a single data structure representative of the observation.

39. The system of claim 27, wherein said invariants include color patches in an optical image represented by said data sets.