Vehicle traction map for autonomous vehicles

• US 10,712,160 B2
• Filed: 12/12/2016
• Issued: 07/14/2020
• Est. Priority Date: 12/10/2015
• Status: Active Grant

• Current Assignee: Uatc, LLC (Uber Technologies, Inc.)
• Original Assignee: Uatc, LLC (Uber Technologies, Inc.)
• Inventors: Rander, Peter, Bradley, David McAllister, Wood, Matthew
• Primary Examiner(s): Antonucci, Anne Marie
• Application Number:
  US15/376,574
• Publication Number:
  US 20170167881A1
• Time in Patent Office: 1,310 Days
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2420/408 Radar; Laser, e.g. lidar
• CPC Class Codes: B60W 2552/15 Road slope, i.e. the inclination of a road segment in the longitudinal direction
• CPC Class Codes: B60W 2552/40 Coefficient of friction
• CPC Class Codes: B60W 2555/20 Ambient conditions, e.g. wind or rain
• CPC Class Codes: B60W 30/18172 Preventing, or responsive to skidding of wheels
• CPC Class Codes: B60W 40/068 Road friction coefficient
• CPC Class Codes: B60W 60/0011 involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
• CPC Class Codes: B60W 60/0016 of the vehicle or its occupants
• CPC Class Codes: G01C 21/3822 Road feature data, e.g. slope data
• CPC Class Codes: G01C 21/3837 Data obtained from a single source
• CPC Class Codes: G01C 21/3848 Data obtained from both position sensors and additional sensors
• CPC Class Codes: G01C 7/04 involving a vehicle which moves along the profile to be traced
• CPC Class Codes: G01N 21/4738 Diffuse reflection precedence is given to G01N21/55 - G01N21/57 if specular component is taken into consideration, e.g. also for testing fluids, fibrous materials
• CPC Class Codes: G05D 1/0214 in accordance with safety or protection criteria, e.g. avoiding hazardous areas monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30

Abstract

A vehicle determines a traction value for a surface of a road segment, and associates the traction value with a location of the surface. The vehicle stores the traction value and location as part of a traction map.

Claims

1. A method of operating an autonomous vehicle, the method comprising:

receiving, by a computing system comprising one or more computing devices, sensor data from at least one sensor of the autonomous vehicle;

determining, by the computing system, a first traction value based on the sensor data from the at least one sensor of the autonomous vehicle, the first traction value being correlative to a coefficient of friction;

associating, by the computing system, the first traction value with a first location of a first road surface;

determining, by the computing system, a second traction value of a second location of a second road surface by spatially extrapolating the first traction value of the first location with respect to the second location based on a comparison of respective road characteristics of the first location and the second location, the second location being spaced apart from the first location; and

storing, by the computing system, the first traction value with the first location and the second traction value with the second location.

2. The method of claim 1, wherein determining the first traction value includes classifying a traction condition at the first location of the first road surface.

3. The method of claim 2, wherein the traction condition corresponds to an accumulated precipitation condition.

4. The method of claim 2, wherein the traction condition corresponds to accumulated snow, rain or ice.

5. The method of claim 1, wherein determining, by the computing system, the first traction value includes remotely determining, by the computing system, the first traction value.

6. The method of claim 5, wherein remotely determining, by the computing system, the first traction value includes using, by the computing system, image data from a light-sensitive device.

7. The method of claim 6, wherein using, by the computing system, image data includes using, by the computing system, a variation in a reflectance of a directed light.

8. The method of claim 6, wherein using, by the computing system, image data includes using, by the computing system, an image of the first road surface to determine a type of accumulated precipitation.

9. The method of claim 1, wherein determining, by the computing system, the first traction value includes measuring, by the computing system, a sensor characteristic that is correlative to the coefficient of friction when the autonomous vehicle is at the first location.

10. The method of claim 1, further comprising transmitting, by the computing system, the first traction value and the first location to a network service.

11. The method of claim 1, wherein determining the first traction value includes receiving, on a network computer, a set of sensor data transmitted from at least the autonomous vehicle, wherein the set of sensor data is correlative to the first traction value.

12. The method of claim 11, wherein associating, by the computing system, the first traction value to the first location includes receiving, by the computing system, the set of sensor data along with location data to identify the first location where the set of sensor data was determined.

13. The method of claim 1, further comprising determining, by the computing system, respective additional traction values of a plurality of additional vehicles by receiving, on a network computer, a set of additional sensor data transmitted from each of the additional vehicles, wherein the set of additional sensor data is (i) correlative to respective additional traction values, and (ii) associated with respective locations of the plurality of additional vehicles.

14. The method of claim 1, further comprising:

aggregating, by the computing system, the first and the second traction values; and

storing, b the computing system the aggregated first and second traction values in a geographic data structure that pairs the first location and the second location with the first and the second traction values and at least one additional traction value determined at least in part from additional sensor data transmitted from one or more additional vehicles.

15. The method of claim 1, wherein at least one of determining, by the computing system, the first traction value or determining the second traction value includes applying, by the computing system, a timing function to at least one of the first traction value or the second traction value based on an environmental condition.

16. The method of claim 1, further comprising:

communicating, by the computing system, with multiple additional vehicles that operate over a geographic region to receive, by the computing system, a set of additional sensor data and a set of additional location data, the set of additional sensor data being generated from one or more sensor components of each of the multiple additional vehicles at respective corresponding locations of the multiple additional vehicles identified by the respective additional location data associated with the respective additional vehicle of the multiple additional vehicles;

determining, by the computing system, additional traction values from the set of additional sensor data received from each of the multiple additional vehicles; and

associating by the computing system, the additional traction values determined from each set of additional sensor data with the corresponding location where the respective additional sensor data was generated.

17. The method of claim 1, further comprising:

on the autonomous vehicle, receiving, by the computing system, a set of additional traction values from a network computer, each additional traction value being associated with a respective additional location within a geographic region; and

comparing, by the computing system, the first traction value to at least one additional traction value in the set of additional traction values.

18. An autonomous vehicle comprising:

memory to store instructions; and

one or more processors to execute the instructions to;

receive sensor data from at least one sensor of the autonomous vehicle;

determine a first traction value based on the sensor data from the at least one sensor of the autonomous vehicle, the first traction value being correlative to a coefficient of friction;

associate the first traction value with a first location of a first road surface;

determine a second traction value of a second location of a second road surface by spatially extrapolating the first traction value of the first location with respect to the second location based on a comparison of respective road characteristics of the first location and the second location, the second location being spaced apart from the first location; and

store the first traction value with the first location and the second traction value with the second location.

19. A non-transitory computer readable medium that stores instructions, which when executed by one or more processors of an autonomous vehicle, cause the autonomous vehicle to perform operations that include:

receiving sensor data from at least one sensor of the autonomous vehicle;

determining a first traction value based on the sensor data from the at least one sensor of the autonomous vehicle, the first traction value being correlative to a coefficient of friction;

associating the first traction value with a first location of a first road surface;

determining a second traction value of a second location of a second road surface by spatially extrapolating the first traction value of the first location with respect to the second location based on a comparison of respective road characteristics of the first location and the second location, the second location being spaced apart from the first location; and

storing the first traction value with the first location and the second traction value, with the second location.