Localization adaptation based on weather estimation

Patent metadata

Field	Value
Publication number	US-2022011116-A1
Application number	US-202016922052-A
Country	US
Kind code	A1
Filing date	Jul 7, 2020
Priority date	Jul 7, 2020
Publication date	Jan 13, 2022
Grant date	—

Abstract

Aspects of the disclosure provide for localizing a vehicle. In one instance, a weather condition in which the vehicle is currently driving may be identified. A plurality of sensor inputs including intensity information, elevation information, and radar sensor information may be received. For each of the plurality of sensor inputs, an alignment score is determined by comparing the intensity information, elevation information, and radar sensor information to a corresponding pre-stored image for each of the intensity information, the elevation information, and the radar sensor information. A set of weights for the plurality of sensor inputs may be determined based on the identified weather condition. The alignment scores may then be combined using the set of weights in order to localize the vehicle.

First claim

1 . A method of localizing a vehicle, the method comprising:
identifying, by one or more processors, a weather condition in which the vehicle is currently driving; receiving, by the one or more processors, a first sensor input having intensity information, a second sensor input having elevation information, and a third sensor input having radar sensor information; determining, by the one or more processors, for each of the first, second, and third sensor inputs, an alignment and a corresponding alignment score by comparing that sensor input to a corresponding pre-stored image for that sensor input; determining, by the one or more processors, a set of weights based on the identified weather condition; and combining, by the one or more processors, the alignments and alignment scores using the set of weights in order to localize the vehicle.

2 . The method of claim 1 , wherein the intensity information and elevation information are generated by one or more LIDAR sensors.

3 . The method of claim 1 , wherein when the weather condition is identified from weather information received from a remote source.

4 . The method of claim 1 , wherein the weather condition is identified from a sensor of the vehicle.

5 . The method of claim 1 , wherein determining the set of weights includes adjusting default weights one or more of the first, second, and third sensor inputs.

6 . The method of claim 1 , wherein determining the set of weights includes identifying a pre-stored set of weights for the identified weather condition.

7 . The method of claim 1 , wherein when the identified weather condition corresponds to a snowy condition, the determined set of weights includes an increased weight for radar sensor information as compared to a default weight for intensity information for non-snowy conditions.

8 . The method of claim 1 , wherein when the identified weather condition corresponds to a snowy condition, the determined set of weights includes a decreased weight for intensity information as compared to a default weight for intensity information for non-snowy conditions.

9 . The method of claim 1 , wherein when the identified weather condition corresponds to a snowy condition, the determined set of weights includes a decreased weight for elevation information as compared to a default weight for elevation information for non-snowy conditions.

10 . The method of claim 1 , wherein when the identified weather condition corresponds to a snowy condition, the determined set of weights includes a decreased weight for sensor input corresponding to objects within a roadway as compared to a default weight for sensor input corresponding to objects within a roadway for non-snowy conditions.

11 . The method of claim 1 , wherein when the identified weather condition corresponds to a snowy condition, the determined set of weights includes an increased weight for sensor input corresponding to objects outside a roadway as compared to a default weight for sensor input corresponding to objects outside a roadway for non-snowy conditions.

12 . The method of claim 1 , wherein when the identified weather condition corresponds to a rainy or wet condition, the determined set of weights includes an increased weight for elevation information as compared to a default weight for elevation information for dry conditions.

13 . The method of claim 1 , wherein when the identified weather condition corresponds to a rainy or wet condition, the determined set of weights includes a decreased weight for intensity information as compared to a default weight for intensity information for dry conditions.

14 . The method of claim 1 , further comprising, identifying a weather impacted area on a roadway, and wherein determining the set of weights includes determining one or more weights for one or more of the first, second, or third sensor inputs for the weather impacted area.

15 . The method of claim 14 , wherein the weather impacted area is one of a puddle, snow pile, or ice patch.

16 . The method of claim 14 , wherein the determined set of weights includes a decreased weight for a sensor input for the weather impacted area as compared to a default weight for non-weather impacted areas.

17 . The method of claim 1 , wherein determining an alignment, for each of the first, second, and third sensor inputs, includes determining a physical positioning between each sensor input and the corresponding pre-stored image for that sensor input.

18 . The method of claim 1 , wherein determining an alignment, for each of the first, second, and third sensor inputs, includes determining an offset between each sensor input and the corresponding pre-stored image for that sensor input.

19 . The method of claim 1 , wherein determining an alignment, for each of the first, second, and third sensor inputs, includes determining an image correlation between each sensor input and the corresponding pre-stored image for that sensor input.

20 . The method of claim 19 , wherein the image correlation includes determining a sum of products of corresponding pixels between each sensor input and the corresponding pre-stored image for that sensor input.

Assignees

• Waymo Llc

Inventors

• Panzer Samuel
• Montemerlo Michael
• James Michael

Classifications

• G01S13/865 Primary

  Combination of radar systems with lidar systems · CPC title

• G01S13/931

  of land vehicles · CPC title

• G01S17/89

  for mapping or imaging · CPC title

• G01S2013/9322

  using additional data, e.g. driver condition, road state or weather data · CPC title

• G01S13/89

  for mapping or imaging · CPC title