Systems and methods for determining whether a driving environment has changed

• US 8,949,016 B1
• Filed: 09/28/2012
• Issued: 02/03/2015
• Est. Priority Date: 09/28/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Ferguson, David I., Dolgov, Dmitri A.
• Primary Examiner(s): Black, Thomas G
• Assistant Examiner(s): Page, Tyler
• Application Number:
  US13/630,039
• Time in Patent Office: 858 Days
• Field of Search: 701/26, 701/70, 701/301, 701/23, 340/436
• US Class Current: 701/301
• CPC Class Codes: B60W 30/00 Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
• CPC Class Codes: B60W 40/04 Traffic conditions
• CPC Class Codes: B60W 50/0097 Predicting future conditions
• CPC Class Codes: G01S 17/89 for mapping or imaging
• CPC Class Codes: G05D 1/024 in combination with a laser lasers per se H01S
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30

Abstract

A autonomous driving computer system determines whether a driving environment has changed. One or more objects and/or object types in the driving environment may be identified as primary objects. The autonomous driving computer system may be configured to detect the primary objects and/or object types, and compare the detected objects and/or object types with the previous known location of the detected object and/or object types. The autonomous driving computer system may obtain several different metrics to facilitate the comparison. A confidence probability obtained from the comparison may indicate the degree of confidence that the autonomous driving computer system has in determining that the driving environment has actually changed.

Claims

1. An apparatus:

memory configured to store map information including first location information including an expected location of a first object corresponding to a prior observation of the first object in a driving environment of a vehicle, the first object having been identified as a primary object for use in determining whether the driving environment has changed; and

a processor in communication with the computer-readable memory, the processor being configured to;

receive sensor information for a second object having been detected in the driving environment corresponding to the first object;

determine second location information for the second object based on the received sensor information;

determine a first discrepancy metric by comparing the first location information with the second location information;

determine a confidence probability that the driving environment has changed based on the first discrepancy metric; and

,

determine that the driving environment has changed when the confidence probability exceeds a confidence probability threshold.

2. The apparatus of claim 1, wherein the first discrepancy metric comprises a maximum deviation metric that indicates a maximum deviation value between the first location information and the second location information.

3. The apparatus of claim 1, wherein the first discrepancy metric comprises an average deviation metric that indicates an average deviation value between the first location information and the second location information.

4. The apparatus of claim 1, wherein the first discrepancy metric comprises an average signed deviation metric that indicates a signed deviation value between the first location information and the second location information.

5. The apparatus of claim 1, wherein:

the map information further includes third location including an expected location of a third object corresponding to a prior observation of a location of a third object in the driving environment of the vehicle, wherein;

the third object has been identified as another primary object for use in determining whether the driving environment has changed; and

the third object is of a different object type than an object type of the first object; and

the processor is further configured to;

obtain fourth location information for a fourth object detected in the driving environment, wherein the fourth object corresponds to the third object;

determine a second discrepancy metric by comparing the third location information with the fourth location information; and

re-determine the confidence probability based on the second discrepancy metric and the comparison of the confidence probability with the confidence probability threshold.

6. The apparatus of claim 1, wherein:

the computer-readable memory is further configured to store a hierarchy of object types, the hierarchy of object types indicating which of the object types are to be used first in determining whether the driving environment has changed; and

the processor is further configured to determine the confidence probability based on the hierarchy of object types.

7. The apparatus of claim 1, wherein the first location information indicates that the first object is in a first location and the second location information indicates that the second object is in a second location, the second location being a different location than the first location.

8. The apparatus of claim 1, wherein the processor determines the confidence probability based on the first discrepancy metric when the first discrepancy metric exceeds a first discrepancy threshold and a second discrepancy threshold.

9. The apparatus of claim 1, wherein:

the first location information comprises a first plurality of laser data points obtained from a prior detection of the first object;

the second location information comprises a second plurality of laser data points obtained from the detection of the first object; and

the processor determines the first discrepancy metric by comparing the first plurality of laser data points with the second plurality of laser data points.

10. A method comprising:

receiving, by a processor, sensor information from a sensor identifying a first object having been detected in the driving environment;

determining, by the processor, first location information for the first object based on the received sensor information;

retrieving, by the processor, map information corresponding to the first object including second location information including an expected location of a second object based on a prior observed location of the first object in the driving environment of the vehicle, the second object having been identified as a primary object for use in determining whether a driving environment has changed;

determining, by the processor, a first discrepancy metric by comparing the first location information with the second location information;

determining, by the processor, a confidence probability that the driving environment has changed from the prior observation based on the first discrepancy metric; and

,

determining, by the processor, that the driving environment has changed from the prior observation by comparing the confidence probability with a confidence probability threshold.

11. The method of claim 10, wherein the first discrepancy metric comprises a maximum deviation metric that indicates a maximum deviation value between the first location information and the second location information.

12. The method of claim 10, wherein the first discrepancy metric comprises an average deviation metric that indicates an average deviation value between the first location information and the second location information.

13. The method of claim 10, wherein the first discrepancy metric comprises an average signed deviation metric that indicates a signed deviation value between the first location information and the second location information.

14. The method of claim 10,

further comprising:

determining, by the processor, third location information for a third object detected in the driving environment;

retrieving fourth location information from the map information, wherein the fourth location information includes an expected location of a fourth object corresponding to a prior observed location of the fourth object in the driving environment, the fourth object corresponding to the third object;

determining, with the processor, a second discrepancy metric by comparing the third location information with fourth location information; and

re-determining the confidence probability based on the second discrepancy metric and the comparison of the confidence probability with the confidence probability threshold.

15. The method of claim 10, further comprising:

determining, by the processor, the confidence probability based on a hierarchy of object types, the hierarchy of object types being stored in the computer-readable memory and indicating which of the object types are to be used first in determining whether the driving environment has changed.

16. The method of claim 10, wherein the first location information indicates that the first object is in a first location and the second location information indicates that the second object is in a second location, the second location being a different location than the first location.

17. The method of claim 10, further comprising:

determining, by the processor, the confidence probability based on the first discrepancy metric when the first discrepancy metric exceeds a first discrepancy threshold and a second discrepancy threshold.

18. The method of claim 10, wherein:

the first location information comprises a first plurality of laser data points obtained from a prior detection of the first object; and

the second location information comprises a second plurality of laser data points obtained from the detection of the first object; and

the method further comprises;

determining, by the processor, the first discrepancy metric by comparing the first plurality of laser data points with the second plurality of laser data points.

20. The method of claim 10, further comprising controlling the vehicle, by the processor, based on the determination that the driving environment has changed.

19. A non-transitory, tangible computer-readable medium on which instructions are stored, the instructions, when executed by one or more processors, cause the one or more processors to perform a method, the method comprising:

receiving sensor information from a sensor identifying a first object having been detected in the driving environment;

determining first location information for the first object based on the received sensor information;

retrieving map information corresponding to the first object including second location information including an expected location of a second object based on a prior observed location of the first object in the driving environment of the vehicle, the second object having been identified as a primary object for use in determining whether a driving environment has changed;

determining a first discrepancy metric by comparing the first location information with the second location information;

determining a confidence probability that the driving environment has changed from the prior observation based on the first discrepancy metric; and

,

determining that the driving environment has changed from the prior observation by comparing the confidence probability with a confidence probability threshold.