Detecting road weather conditions

• US 9,110,196 B2
• Filed: 09/20/2012
• Issued: 08/18/2015
• Est. Priority Date: 09/20/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Urmson, Christopher Paul, Montemerlo, Michael Steven, Zhu, Jiajun
• Primary Examiner(s): Kundu, Sujoy
• Assistant Examiner(s): Lee, Paul D
• Application Number:
  US13/623,397
• Publication Number:
  US 20140081573A1
• Time in Patent Office: 1,062 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G01S 17/42 Simultaneous measurement of distance and other co-ordinates indirect measurement G01S17/46
• CPC Class Codes: G01S 17/95 for meteorological use
• CPC Class Codes: G01S 7/4802 using analysis of echo signal for target characterisation; Target signature; Target cross-section
• CPC Class Codes: G01W 1/02 Instruments for indicating weather conditions by measuring two or more variables, e.g. humidity, pressure, temperature, cloud cover or wind speed G01W1/10 takes precedence
• CPC Class Codes: G01W 1/10 Devices for predicting weather conditions computers per se G06; display devices G09
• CPC Class Codes: Y02A 90/10 Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

Aspects of the disclosure relate generally to detecting road weather conditions. Vehicle sensors including a laser, precipitation sensors, and/or camera may be used to detect information such as the brightness of the road, variations in the brightness of the road, brightness of the world, current precipitation, as well as the detected height of the road. Information received from other sources such as networked based weather information (forecasts, radar, precipitation reports, etc.) may also be considered. The combination of the received and detected information may be used to estimate the probability of precipitation such as water, snow or ice in the roadway. This information may then be used to maneuver an autonomous vehicle (for steering, accelerating, or braking) or identify dangerous situations.

Claims

1. A method comprising:

receiving laser data collected for a roadway as a vehicle is driven along the roadway, wherein the laser data includes a plurality of laser data points, each data point of the plurality of laser data points having location and intensity information associated therewith;

determining an average intensity of the plurality laser data points associated with locations within the roadway;

comparing the average intensity to a threshold value associated with an expected average intensity of the roadway under dry weather conditions;

when the average intensity is below the threshold value, identifying an indication that the roadway is wet;

estimating, by a processor, a driving condition of the roadway based on the indication the roadway is wet; and

using the estimate, by the processor, to make a driving decision for the vehicle.

2. The method of claim 1, wherein the expected average intensity of the roadway under dry weather conditions is based on a composition of the surface of the roadway.

3. The method of claim 1, further comprising:

determining a distribution of intensity values for the roadway;

comparing the determined distribution to an expected distribution for dry conditions;

when the determined distribution is shifted towards a darker end of an intensity scale relative to the expected distribution for dry conditions, identifying a second indication that the roadway is wet; and

wherein the second indication that the roadway is wet is used by the processor to estimate the driving conditions.

4. The method of claim 1, further comprising:

detecting a cloud of laser data points of the plurality of laser data points which do not indicate a particular structure located proximate to a rear portion of the vehicle;

when the cloud is detected, identifying a second indication that the roadway is wet; and

wherein the second indication that the roadway is wet is used by the processor to estimate the driving conditions.

5. The method of claim 1, further comprising:

detecting a moving object in the roadway from the plurality of laser data points;

detecting a cloud of laser data points of the plurality of laser data points which do not indicate a particular structure located proximate to the moving object;

when the cloud is detected, identifying a second indication that the roadway is wet; and

wherein the second indication that the roadway is wet is used by the processor to estimate the driving conditions.

6. The method of claim 1,

further comprising:

accessing detailed map information for the roadway indicating an expected elevation of the roadway;

identifying a cloud of laser data points from the received laser data points associated with location data proximate to an expected surface of the roadway;

comparing the laser data points of the cloud to a first threshold value above the expected roadway surface and a second threshold value below the expected roadway surface;

when the laser data points of the cloud include at least one laser data point above the first threshold value and at least one laser data point below the second threshold value, identifying a second indication that the roadway is wet; and

wherein the second indication that the roadway is wet is used by the processor to estimate the driving conditions.

7. The method of claim 1, further comprising:

receiving images captured from a camera as the vehicle is driven along the roadway; and

identifying an additional indication that the roadway is wet based on the images,

wherein the additional indication that the roadway is wet is used by the processor to estimate the driving conditions.

8. The method of claim 1, further comprising:

receiving precipitation data from a precipitation sensor associated with the vehicle; and

identifying a second indication that the roadway is wet based on the precipitation data,

wherein the second indication that the roadway is wet is used by the processor to estimate the driving condition.

9. The method of claim 1, wherein estimating the driving condition includes using a Bayesian estimate.

10. The method of claim 1, further comprising:

accessing detailed map information for the roadway indicating an expected elevation of the roadway;

determining an average elevation for a portion of the roadway;

identifying a second indication that the roadway is wet based on whether the average elevation of the portion of the roadway is at least a second threshold value greater than the expected elevation; and

wherein the second indication that the roadway is wet is used by the processor to estimate the driving condition.

11. The method of claim 1, further comprising:

receiving weather information for a current location of the vehicle from a server over a network; and

identifying a second indication that the roadway is wet based on the weather related information,

wherein the second indication that the roadway is wet is used by the processor to estimate the driving condition.

12. A system comprising:

memory storing an expected average intensity of the roadway under dry weather conditions; and

a processor configured to;

receive laser data collected for a roadway as a vehicle is driven along the roadway, wherein the laser data includes a plurality of laser data points, each data point of the plurality of laser data points having location and intensity information associated therewith;

determine an average intensity of the plurality laser data points associated with locations within the roadway;

compare the average intensity to a threshold value associated with the expected average intensity of the roadway under dry weather conditions;

when the average intensity is below the threshold value, identify an indication that the roadway is wet;

estimate a driving condition of the roadway based on the indication the roadway is wet; and

using the estimate to make a driving decision for the vehicle.

13. The system of claim 12, wherein the expected average intensity of the roadway under dry weather conditions is based on a composition of the surface of the roadway.

14. The system of claim 12, wherein the processor is further configured to:

determine a distribution of intensity values for the roadway;

compare the determined distribution to an expected distribution for dry conditions;

when the determined distribution is shifted towards a darker end of an intensity scale relative to the expected distribution for dry conditions, identify a second indication that the roadway is wet; and

wherein the second indication that the roadway is wet is used by the processor to estimate the driving conditions.

15. The system of claim 12, wherein the processor is further configured to:

detect a cloud of laser data points of the plurality of laser data points which do not indicate a particular structure located proximate to a rear portion of the vehicle;

when the cloud is detected, identify a second indication that the roadway is wet; and

wherein the second indication that the roadway is wet is used by the processor to estimate the driving conditions.

16. The system of claim 12, wherein the processor is further configured to:

detect a moving object in the roadway from the plurality of laser data points;

detect a cloud of laser data points of the plurality of laser data points which do not indicate a particular structure located proximate to the moving object;

when the cloud is detected, identifying a second indication that the roadway is wet; and

wherein the second indication that the roadway is wet is used by the processor to estimate the driving conditions.

17. The system of claim 12, wherein the processor is further configured to:

access detailed map information for the roadway indicating an expected elevation of the roadway;

identify a cloud of laser data points from the received laser data points associated with location data proximate to an expected surface of the roadway;

compare the laser data points of the cloud to a first threshold value above the expected roadway surface and a second threshold value below the expected roadway surface;

when the laser data points of the cloud include at least one laser data point above the first threshold value and at least one laser data point below the second threshold value, identify a second indication that the roadway is wet; and

wherein the second indication that the roadway is wet is used by the processor to estimate the driving conditions.

18. The system of claim 12, wherein the processor is further configured to:

receive images captured from a camera as the vehicle is driven along the roadway; and

identify an additional indication that the roadway is wet based on the images,

wherein the additional indication that the roadway is wet is used by the processor to estimate the driving conditions.

19. The system of claim 12, wherein the processor is further configured to:

receive precipitation data from a precipitation sensor associated with the vehicle; and

identify a second indication that the roadway is wet based on the precipitation data,

wherein the second indication that the roadway is wet is used by the processor to estimate the driving condition.

20. The system of claim 12, wherein when estimating the driving condition the processor is configured to use a Bayesian estimate.

21. The system of claim 12, wherein the processor is further configured to:

access detailed map information for the roadway indicating an expected elevation of the roadway;

determine an average elevation for a portion of the roadway;

identify a second indication that the roadway is wet based on whether the average elevation of the portion of the roadway is at least a second threshold value greater than the expected elevation; and

wherein the second indication that the roadway is wet is used by the processor to estimate the driving condition.

22. The system of claim 12, wherein the processor is further configured to:

receive weather information for a current location of the vehicle from a server over a network; and

identify a second indication that the roadway is wet based on the weather related information,

wherein the second indication that the roadway is wet is used by the processor to estimate the driving condition.