Use of uncertainty regarding observations of traffic intersections to modify behavior of a vehicle

• US 8,761,991 B1
• Filed: 04/09/2012
• Issued: 06/24/2014
• Est. Priority Date: 04/09/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Ferguson, David I., Fairfield, Nathaniel
• Primary Examiner(s): Black, Thomas
• Assistant Examiner(s): HUYNH, LUAT T
• Application Number:
  US13/441,996
• Time in Patent Office: 806 Days
• Field of Search: 701/28, 701/117, 701/118, 701/301, 701/454, 701/410, 340/917, 340/933, 340/906, 340/988, 340/916, 340/435, 340/903, 340/936, 340/910, 340/904
• US Class Current: 701/28
• CPC Class Codes: B60W 2555/60 Traffic rules, e.g. speed limits or right of way
• CPC Class Codes: B60W 30/18154 Approaching an intersection
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G08G 1/09623 Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle G08G1/0967 takes precedence
• CPC Class Codes: G08G 1/096725 where the received information generates an automatic action on the vehicle control
• CPC Class Codes: G08G 1/096758 where no selection takes place on the transmitted or the received information
• CPC Class Codes: G08G 1/096783 where the origin of the information is a roadside individual element

Abstract

Methods and devices for using uncertainty regarding observations of traffic intersections to modify behavior of a vehicle are disclosed. In one embodiment, an example method includes determining a state of a traffic intersection using information from one or more sensors of a vehicle. The vehicle may be configured to operate in an autonomous mode. The method may also include determining an uncertainty associated with the determined state of the traffic intersection. The method may further include controlling the vehicle in the autonomous mode based on the determined state of the traffic intersection and the determined uncertainty.

Claims

1. A method comprising:

determining a state of a traffic intersection using information from one or more sensors of a vehicle, wherein determining the state of the traffic intersection comprises determining a state of a traffic signal of the traffic intersection, and wherein the vehicle is configured to operate in an autonomous mode;

determining a confidence in the state of the traffic signal;

determining an uncertainty associated with the determined state of the traffic intersection based on the confidence in the state of the traffic signal; and

controlling the vehicle in the autonomous mode based on the determined state of the traffic intersection and the determined uncertainty.

2. The method of claim 1, wherein controlling the vehicle in the autonomous mode based on the determined state of the traffic intersection and the determined uncertainty comprises (i) selecting a presumed state of the traffic intersection based on the determined state of the traffic intersection and the determined uncertainty and (ii) controlling the vehicle in the autonomous mode based on the presumed state of the traffic intersection.

3. The method of claim 2, wherein selecting a presumed state of the traffic intersection based on the determined state of the traffic intersection and the determined uncertainty comprises:

selecting the determined state of the traffic intersection as the presumed state of the traffic intersection if the determined uncertainty is less than a predetermined uncertainty; and

selecting a different state of the traffic intersection as the presumed state of the traffic intersection if the determined uncertainty is greater than the predetermined uncertainty, wherein the different state of the traffic intersection is a more restrictive state than the determined state of the traffic intersection.

4. The method of claim 1, wherein determining the state of the traffic signal comprises obtaining an image of the traffic signal, and wherein determining the confidence in the state of the traffic signal comprises determining a clarity of the traffic signal in the image.

5. The method of claim 1, further comprising:

determining a score associated with the traffic signal, wherein the score is indicative of a historical ability to determine the state of the intersection based on the state of the traffic signal.

6. The method of claim 1, further comprising:

determining respective states of multiple traffic signals of the traffic intersection; and

wherein the uncertainty associated with the determined state of the traffic intersection is determined based on the respective states of the multiple traffic signals.

7. The method of claim 1, wherein controlling the vehicle in the autonomous mode based on the determined state of the traffic intersection and the determined uncertainty comprises:

moving the vehicle to an adjusted position;

obtaining from the adjusted position, using the one or more sensors of the vehicle, additional information that is indicative of the state of the traffic intersection; and

controlling the vehicle in the autonomous mode based on the additional information.

8. A non-transitory computer readable medium having stored therein instructions executable by a computing device to cause the computing device to perform functions comprising:

determining a state of a traffic intersection using information from one or more sensors of a vehicle, wherein determining the state of the traffic intersection comprises determining a state of a traffic signal of the traffic intersection, and wherein the vehicle is configured to operate in an autonomous mode;

determining a confidence in the state of the traffic signal;

determining an uncertainty associated with the determined state of the traffic intersection based on the confidence in the state of the traffic signal; and

controlling the vehicle in the autonomous mode based on the determined state of the traffic intersection and the determined uncertainty.

9. The non-transitory computer readable medium of claim 8, wherein determining the state of the traffic signal comprises obtaining an image of the traffic signal, and wherein determining the confidence in the state of the traffic signal comprises determining a clarity of the traffic signal in the image.

10. The non-transitory computer readable medium of claim 8, wherein controlling the vehicle in the autonomous mode based on the determined state of the traffic intersection and the determined uncertainty comprises (i) selecting a presumed state of the traffic intersection based on the determined state of the traffic intersection and the determined uncertainty and (ii) controlling the vehicle in the autonomous mode based on the presumed state of the traffic intersection.

11. The non-transitory computer readable medium of claim 8, wherein controlling the vehicle in the autonomous mode based on the determined state of the traffic intersection and the determined uncertainty comprises:

moving the vehicle to an adjusted position;

obtaining from the adjusted position, using one or more sensors of the vehicle, additional information that is indicative of the state of the traffic intersection; and

controlling the vehicle in the autonomous mode based on the additional information.

12. A vehicle configured to be operated in autonomous mode, comprising:

one or more sensors configured to obtain information associated with a traffic intersection;

a memory;

a processor; and

instructions stored in the memory and executable by the processor to;

determine a state of the traffic intersection based on the obtained information, wherein determining the state of the traffic intersection comprises determining a state of a traffic signal of the traffic intersection;

determine a confidence in the state of the traffic signal;

determine an uncertainty associated with the determined state of the traffic intersection based on the confidence in the state of the traffic signal; and

control the vehicle in the autonomous mode based on the determined state of the traffic intersection and the determined uncertainty.

13. The vehicle of claim 12, wherein the instructions stored in the memory and executable by the processor to control the vehicle in the autonomous mode based on the determined state of the traffic intersection and the determined uncertainty comprise instructions stored in the memory and executable by the processor to:

(i) select a presumed state of the traffic intersection based on the determined state of the traffic intersection and the determined uncertainty and (ii) control the vehicle in the autonomous mode based on the presumed state of the traffic intersection.

14. The vehicle of claim 13, wherein the instructions stored in the memory and executable by the processor to select a presumed state of the traffic intersection based on the determined state of the traffic intersection and the determined uncertainty comprise instructions stored in the memory and executable by the processor to:

select the determined state of the traffic intersection as the presumed state of the traffic intersection if the determined uncertainty is less than a predetermined uncertainty; and

select a different state of the traffic intersection as the presumed state of the traffic intersection if the determined uncertainty is greater than the predetermined uncertainty, wherein the different state of the traffic intersection is a more restrictive state than the determined state of the traffic intersection.