Combining multiple estimates of an environment into a consolidated estimate for an autonomous vehicle

• US 9,684,836 B1
• Filed: 11/12/2015
• Issued: 06/20/2017
• Est. Priority Date: 07/31/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Waymo LLC (Alphabet Inc.)
• Inventors: Ferguson, David Ian Franklin, Silver, David Harrison
• Primary Examiner(s): Bella, Matthew
• Assistant Examiner(s): SHIN, SOO JUNG
• Application Number:
  US14/939,232
• Time in Patent Office: 586 Days
• Field of Search: None
• 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 2420/54 Audio sensitive means, e.g. ultrasound
• CPC Class Codes: B60W 2552/53 Road markings, e.g. lane marker or crosswalk
• CPC Class Codes: B60W 2556/20 Data confidence level
• CPC Class Codes: B60W 2556/35 Data fusion
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: B60W 60/0016 of the vehicle or its occupants
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06F 18/25 Fusion techniques
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 10/80 Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level multimodal speaker identification or verification G10L17/10
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

A vehicle is provided that may combine multiple estimates of an environment into a consolidated estimate. The vehicle may receive first data indicative of the region of interest in an environment from a sensor of the vehicle. The first data may include a first accuracy value and a first estimate of the region of interest. The vehicle may also receive second data indicative of the region of interest in the environment, and the second data may include a second accuracy value and a second estimate of the region of interest. Based on the first data and the second data, the vehicle may combine the first estimate of the region of interest and the second estimate of the region of interest.

Claims

1. A method performed by a computing device comprising one or more processors, the method comprising:

receiving, via at least one sensor coupled to an autonomous vehicle operating in a lane of travel, first data including a first estimate of a boundary location of a boundary of the lane of travel, the first data having been acquired at a first time;

based on the first data, determining a first variance in the first estimate of the boundary location;

receiving, via the at least one sensor, second data including a second estimate of the boundary location, the second data having been acquired at a second time different from the first time;

based on the second data, determining a second variance in the second estimate of the boundary location; and

based on the first estimate, the first variance, the second estimate, and the second variance, determining third data including a combined estimate of the boundary location and further including a combined variance in the combined estimate.

2. The method of claim 1, further comprising:

based on the third data, providing instructions to control the autonomous vehicle in the lane of travel.

3. The method of claim 1, wherein the first estimate comprises a first plurality of coordinate points corresponding to the boundary location, and

wherein the second estimate comprises a second plurality of coordinate points corresponding to the boundary location.

4. The method of claim 3, wherein the first variance is determined further based on one or more of (i) an operational state of the at least one sensor, (ii) a distance between the first plurality of coordinate points and the at least one sensor, and (iii) first sensor data indicative of environmental conditions present at the first time, and

wherein the second variance is determined further based on one or more of (i) the operational state of the at least one sensor, (ii) a distance between the second plurality of coordinate points and the at least one sensor, and (iii) second sensor data indicative of environmental conditions present at the second time.

5. The method of claim 1, wherein the first estimate comprises a first image portion, and

wherein the second estimate comprises a second image portion.

6. The method of claim 1, wherein the first estimate comprises a first plurality of coordinate points corresponding to the boundary location,

wherein the second estimate comprises a second plurality of coordinate points corresponding to the boundary location,

wherein the combined estimate comprises a third plurality of coordinate points corresponding to the boundary location,

wherein the first variance comprises, for each coordinate point of the first plurality of coordinate points, an associated respective variance value that indicates how accurately the coordinate point corresponds to the boundary location,

wherein the second variance comprises, for each coordinate point of the second plurality of coordinate points, an associated respective variance value that indicates how accurately the coordinate point corresponds to the boundary location, and

wherein the combined variance comprises, for each coordinate point of the third plurality of coordinate points, an associated respective variance value that indicates how accurately the coordinate point corresponds to the boundary location.

7. The method of claim 6, wherein the each of the first, second, and third pluralities of coordinate points is a plurality of two-dimensional (2D) coordinate points.

8. An autonomous vehicle comprising:

at least one sensor configured to sense a lane of travel in an environment of the autonomous vehicle, wherein the autonomous vehicle is operating in the lane of travel in the environment;

at least one processor; and

data storage comprising instructions executable by the at least one processor to cause the system to perform operations comprising;

receiving, via the at least one sensor, first data including a first estimate of a boundary location of a boundary of the lane of travel, the first data having been acquired at a first time;

based on the first data, determining a first variance in the first estimate of the boundary location;

receiving, via the at least one sensor, second data including a second estimate of the boundary location, the second data having been acquired at a second time different from the first time;

based on the second data, determining a second variance in the second estimate of the boundary location; and

based on the first estimate, the first variance, the second estimate, and the second variance, determining third data including a combined estimate of the boundary location and further including a combined variance in the combined estimate.

9. The vehicle of claim 8, wherein the operations further comprise:

based on the third data, providing instructions to control the autonomous vehicle in the lane of travel.

10. The vehicle of claim 8, wherein the at least one sensor includes a first sensor and a second, different sensor,

wherein the first data is received via the first sensor, and

wherein the second data is received via the second sensor.

11. The vehicle of claim 8, wherein the first estimate comprises a first plurality of coordinate points corresponding to the boundary location,

wherein the second estimate comprises a second plurality of coordinate points corresponding to the boundary location,

wherein the first variance is determined further based on one or more of (i) an operational state of the at least one sensor, (ii) a distance between the first plurality of coordinate points and the at least one sensor, and (iii) first sensor data indicative of environmental conditions present at the first time, and

wherein the second variance is determined further based on one or more of (i) the operational state of the at least one sensor, (ii) a distance between the second plurality of coordinate points and the at least one sensor, and (iii) second sensor data indicative of environmental conditions present at the second time.

12. The vehicle of claim 8, wherein one or more of the first estimate, the second estimate, and the combined estimate is based on a predetermined map of the environment, the predetermined map including the boundary location.

13. The vehicle of claim 8,

wherein the first estimate comprises a first plurality of coordinate points corresponding to the boundary location,

wherein the second estimate comprises a second plurality of coordinate points corresponding to the boundary location,

wherein the combined estimate comprises a third plurality of coordinate points corresponding to the boundary location,

wherein the first variance comprises, for each coordinate point of the first plurality of coordinate points, an associated respective variance value that indicates how accurately the coordinate point corresponds to the boundary location,

wherein the second variance comprises, for each coordinate point of the second plurality of coordinate points, an associated respective variance value that indicates how accurately the coordinate point corresponds to the boundary location, and

wherein the combined variance comprises, for each coordinate point of the third plurality of coordinate points, an associated respective variance value that indicates how accurately the coordinate point corresponds to the boundary location.

14. The vehicle of claim 8, wherein determining the third data based on the first estimate, the first variance, the second estimate, and the second variance comprises:

making a comparison between one or both of the first and second variances and a predetermined threshold;

in response to the comparison indicating that one or both of the first and second variances is below the predetermined threshold, (i) causing the at least one sensor to acquire additional data including another estimate of the boundary location and (ii) based on the additional data, determining another variance in the other estimate of the boundary location;

determining that the other variance is above the predetermined threshold; and

in response to determining that the other variance is above the predetermined threshold, determining the third data based at least in part on the other estimate and the other variance.

15. A non-transitory computer readable medium having stored therein instructions that when executed by a computing system cause the computing system to perform operations comprising:

receiving, via at least one sensor coupled to an autonomous vehicle operating in a lane of travel, first data including a first estimate of a boundary location of a boundary of the lane of travel, the first data having been acquired at a first time;

based on the first data, determining a first variance in the first estimate of the boundary location;

receiving, via the at least one sensor, second data including a second estimate of the boundary location, the second data having been acquired at a second time different from the first time;

based on the second data, determining a second variance in the second estimate of the boundary location; and

based on the first estimate, the first variance, the second estimate, and the second variance, determining third data including a combined estimate of the boundary location and further including a combined variance in the combined estimate.

16. The non-transitory computer readable medium of claim 15, wherein the operations further comprise:

based on the third data, providing instructions to control the autonomous vehicle in the lane of travel.

17. The non-transitory computer readable medium of claim 15, wherein the at least one sensor includes at least one first sensor and further includes at least one second sensor different from the at least one first sensor,

wherein the first data is received via the at least one first sensor, and

wherein the second data is received via the at least one second sensor.

18. The non-transitory computer readable medium of claim 15, wherein the first estimate comprises a first plurality of coordinate points, each coordinate point of the first plurality corresponding to a respective lane marker that makes up a distinct portion of the boundary of the lane of travel,

wherein the second estimate comprises a second plurality of coordinate points, each coordinate point of the second plurality corresponding to a respective lane marker that makes up a distinct portion of the boundary of the lane of travel, and

wherein the combined estimate comprises a third plurality of coordinate points, each coordinate point of the third plurality corresponding to a respective lane marker that makes up a distinct portion of the boundary of the lane of travel.

19. The non-transitory computer readable medium of claim 18, wherein the first variance comprises, for each coordinate point of the first plurality of coordinate points, an associated respective variance value that indicates how accurately the coordinate point corresponds to the respective lane marker,

wherein the second variance comprises, for each coordinate point of the second plurality of coordinate points, an associated respective variance value that indicates how accurately the coordinate point corresponds to the respective lane marker, and

wherein the combined variance comprises, for each coordinate point of the third plurality of coordinate points, an associated respective variance value that indicates how accurately the coordinate point corresponds to the respective lane marker.

20. The non-transitory computer readable medium of claim 18, wherein the each of the first, second, and third pluralities of coordinate points is a plurality of three-dimensional (3D) coordinate points.