Filtering noisy/high-intensity regions in laser-based lane marker detection

• US 9,440,652 B1
• Filed: 01/04/2016
• Issued: 09/13/2016
• Est. Priority Date: 08/01/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Ferguson, David I., Silver, David
• Primary Examiner(s): CASS, JEAN PAUL
• Application Number:
  US14/987,031
• Time in Patent Office: 253 Days
• Field of Search: 701/28
• US Class Current: 1/1
• CPC Class Codes: B60W 10/04 including control of propulsion units
• CPC Class Codes: B60W 10/18 including control of braking systems
• CPC Class Codes: B60W 10/20 including control of steering systems
• 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 2420/42 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2552/53 Road markings, e.g. lane marker or crosswalk
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 2554/20 Static objects
• CPC Class Codes: B60W 2554/4029 Pedestrians
• CPC Class Codes: B60W 2554/806 Relative heading
• CPC Class Codes: B60W 2555/20 Ambient conditions, e.g. wind or rain
• CPC Class Codes: B60W 2710/18 Braking system
• CPC Class Codes: B60W 2710/20 Steering systems
• CPC Class Codes: B60W 2720/10 Longitudinal speed
• CPC Class Codes: B60W 2900/00 Indexing codes relating to the purpose of, or problem solved of road vehicle drive control systems not otherwise provided for in groups B60W30/00
• CPC Class Codes: B60W 30/10 Path keeping cruise control for automatically following a preceding vehicle B60W30/165
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: B60W 30/18163 Lane change; Overtaking manoeuvres
• CPC Class Codes: B60W 60/001 Planning or execution of driving tasks
• CPC Class Codes: G01S 17/931 : of land vehicles
• CPC Class Codes: G05D 1/0236 : in combination with a laser lasers per se H01S

Abstract

An autonomous vehicle may be configured to receive, using a computer system, a plurality of remission signals from a portion of a lane of travel in an environment in response to at least one sensor of the vehicle sensing the portion of the lane of travel. A given remission signal of the plurality of remission signals may include a remission value indicative of a level of reflectiveness for the portion of the lane of travel. The vehicle may also be configured to compare the plurality of remission signals to a known remission value indicative of a level of reflectiveness for a lane marker in the lane of travel. Based on the comparison, the vehicle may additionally be configured to determine whether the portion of the lane of travel in the environment is indicative of a presence of the lane marker.

Claims

1. A method comprising:

receiving, by one or more processors, from at least one sensor of an autonomous vehicle, a plurality of remission signals based on a portion of a lane of travel in an environment, wherein a given remission signal of the plurality of remission signals comprises a respective remission value indicative of a level of reflectiveness for the portion of the lane of travel, wherein the autonomous vehicle is substantially in the lane of travel in the environment;

determining, by the one or more processors, an average remission value based on respective remission signals of the plurality of remission signals, wherein the average remission value is indicative of an average level of reflectiveness for the portion of the lane of travel;

comparing, by the one or more processors, the average remission value to a known remission threshold indicative of a minimum level of reflectiveness for a lane marker in the lane of travel;

based on the comparison, the one or more processors adjusting the known remission threshold to be an adjusted known remission threshold, wherein the adjusted remission threshold is used for only a predetermined period of time as the autonomous vehicle navigates in the lane of travel; and

responsive to the adjusting, the one or more processors (i) determining, based on the adjusted known remission threshold, that the portion of the lane of travel includes at least one lane marker demarcating the lane of travel, and (ii) controlling the autonomous vehicle to navigate the lane of travel within the determined at least one lane marker demarcating the lane of travel.

2. The method of claim 1, wherein determining that the portion of the lane of travel includes the at least one lane marker demarcating the lane of travel based on the adjusted known remission threshold comprises:

comparing the plurality of remission signals to the adjusted known remission threshold; and

based on the comparison of the plurality of remission signals to the adjusted known remission threshold, determining that the portion of the lane of travel includes at least one lane marker demarcating the lane of travel.

3. The method of claim 1, wherein adjusting the known remission threshold to be an adjusted known remission threshold based on the comparison comprises:

based on the comparison indicating that the average remission value is greater than the known remission threshold, the one or more processors adjusting the known remission threshold to be higher such that the adjusted known remission threshold is greater than the average remission value.

4. The method of claim 1, wherein adjusting the known remission threshold to be an adjusted known remission threshold based on the comparison comprises:

based on the comparison indicating that the average remission value is less than the known remission threshold, the one or more processors adjusting the known remission threshold to be lower such that the adjusted known remission threshold is less than the average remission value.

5. The method of claim 1, wherein the predetermined period of time is a period of time during which at least a portion of the autonomous vehicle travels past the portion of the lane of travel.

6. The method of claim 1, wherein determining that the portion of the lane of travel includes the at least one lane marker demarcating the lane of travel comprises determining that the portion of the lane of travel includes at least one lane marker on one side of the lane of travel and further includes at least one other lane marker on an opposite side of the lane of travel, and

wherein controlling the autonomous vehicle to navigate the lane of travel within the determined at least one lane marker demarcating the lane of travel comprises controlling the autonomous vehicle to navigate between the at least one lane marker and the at least one other lane marker.

7. The method of claim 1, wherein the portion of the lane of travel is a first portion of the lane of travel, the method further comprising:

receiving, by the one or more processors, a second plurality of remission signals based on a second portion of the lane of travel in the environment different from the first portion, wherein a given remission signal of the second plurality of remission signals comprises a respective second remission value indicative of a level of reflectiveness for the second portion of the lane of travel; and

determining, by the one or more processors, a region of the lane of travel, wherein the region comprises the first portion and the second portion,

wherein determining the average remission value is further based on respective remission signals of the second plurality of remission signals,

wherein the average remission value is further indicative of an average level of reflectiveness for the region of the lane of travel, and

wherein the known remission threshold is further indicative of a minimum level of reflectiveness for a lane marker in the region of the lane of travel.

8. The method of claim 7, further comprising:

responsive to the adjusting, the one or more processors (i) determining, based on the adjusted known remission threshold, that the region of the lane of travel includes at least one lane marker demarcating the lane of travel, and (ii) controlling the autonomous vehicle to navigate in the region of the lane of travel within the determined at least one lane marker demarcating the lane of travel.

9. The method of claim 1, further comprising:

based on the plurality of remission signals and further based on the known remission threshold, determining that the portion of the lane of travel in the environment includes a particular number of lane markers;

comparing the particular number of lane markers to a particular threshold number of lane markers; and

based on the comparison indicating that the particular number of lane markers exceeds the particular threshold, making a determination that the particular number of lane markers includes at least one false positive lane marker,

wherein adjusting the known remission threshold to be the adjusted known remission threshold is further based on the determination that the particular number of lane markers includes at least one false positive lane marker.

10. 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 substantially in the lane of travel in the environment;

a computer system, wherein the computer system is configured to;

receive, from the at least one sensor, a plurality of remission signals based on a portion of the lane of travel in the environment, wherein a given remission signal of the plurality of remission signals comprises a respective remission value indicative of a level of reflectiveness for the portion of the lane of travel;

determine an average remission value based on respective remission signals of the plurality of remission signals, wherein the average remission value is indicative of an average level of reflectiveness for the portion of the lane of travel;

compare the average remission value to a known remission threshold indicative of a minimum level of reflectiveness for a lane marker in the lane of travel;

based on the comparison, adjust the known remission threshold to be an adjusted known remission threshold, wherein the adjusted remission threshold is used for only a predetermined period of time as the autonomous vehicle navigates in the lane of travel; and

responsive to the adjusting, (i) determine, based on the adjusted known remission threshold, that the portion of the lane of travel includes at least one lane marker demarcating the lane of travel, and (ii) control the autonomous vehicle to navigate the lane of travel within the determined at least one lane marker demarcating the lane of travel.

11. The autonomous vehicle of claim 10, wherein the at least one sensor comprises a laser detection and ranging system.

12. The autonomous vehicle of claim 10, wherein the portion of the lane of travel is a first portion of the lane of travel, and wherein the computer system is further configured to:

receive a second plurality of remission signals based on a second portion of the lane of travel in the environment different from the first portion, wherein a given remission signal of the second plurality of remission signals comprises a respective second remission value indicative of a second level of reflectiveness for the second portion of the lane of travel;

determine a region of the lane of travel, wherein the region comprises the first portion and the second portion;

determine a second average remission value based on respective remission signals of the second plurality of remission signals, wherein the second average remission value is indicative of an average level of reflectiveness for the second portion of the lane of travel;

compare the average remission value to the known remission threshold;

based on the comparison, determine a second adjusted known remission threshold different from the adjusted known remission threshold, wherein the adjusted known remission threshold is associated with the first portion of the lane of travel, and wherein the second adjusted known remission threshold is associated with the second portion of the lane of travel; and

responsive to determining the second adjusted known remission threshold, (i) determine, based on the second adjusted known remission threshold, that the second portion of the lane of travel includes at least one second lane marker demarcating the lane of travel, and (ii) control the autonomous vehicle to navigate the region of the lane of travel within the determined at least one second lane marker demarcating the lane of travel substantially simultaneously as the controlling of the autonomous vehicle to navigate the lane of travel within the determined at least one lane marker.

13. The autonomous vehicle of claim 10, wherein the predetermined period of time is a period of time during which at least a portion of the autonomous vehicle travels past the portion of the lane of travel.

14. The autonomous vehicle of claim 10, wherein determining that the portion of the lane of travel includes the at least one lane marker demarcating the lane of travel comprises determining that the portion of the lane of travel includes at least one lane marker on one side of the lane of travel and further includes at least one other lane marker on an opposite side of the lane of travel, and

wherein controlling the autonomous vehicle to navigate the lane of travel within the determined at least one lane marker demarcating the lane of travel comprises controlling the autonomous vehicle to navigate between the at least one lane marker and the at least one other lane marker.

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

receiving, from at least one sensor of the autonomous vehicle, a plurality of remission signals based on a portion of a lane of travel in an environment, wherein a given remission signal of the plurality of remission signals comprises a respective remission value indicative of a level of reflectiveness for the portion of the lane of travel, wherein the autonomous vehicle is substantially in the lane of travel in the environment;

determining an average remission value based on respective remission signals of the plurality of remission signals, wherein the average remission value is indicative of an average level of reflectiveness for the portion of the lane of travel;

comparing the average remission value to a known remission threshold indicative of a minimum level of reflectiveness for a lane marker in the lane of travel;

based on the comparison, adjusting the known remission threshold to be an adjusted known remission threshold, wherein the adjusted remission threshold is used for only a predetermined period of time as the autonomous vehicle navigates in the lane of travel; and

responsive to the adjusting, (i) determining, based on the adjusted known remission threshold, that the portion of the lane of travel includes at least one lane marker demarcating the lane of travel, and (ii) controlling the autonomous vehicle to navigate the lane of travel within the determined at least one lane marker demarcating the lane of travel.

16. The non-transitory computer readable medium of claim 15, wherein determining that the portion of the lane of travel includes the at least one lane marker demarcating the lane of travel based on the adjusted known remission threshold comprises:

comparing the plurality of remission signals to the adjusted known remission threshold; and

based on the comparison of the plurality of remission signals to the adjusted known remission threshold, determining that the portion of the lane of travel includes at least one lane marker demarcating the lane of travel.

17. The non-transitory computer readable medium of claim 15, wherein adjusting the known remission threshold to be an adjusted known remission threshold based on the comparison comprises:

based on the comparison indicating that the average remission value is greater than the known remission threshold, the one or more processors adjusting the known remission threshold to be higher such that the adjusted known remission threshold is greater than the average remission value.

18. The non-transitory computer readable medium of claim 15, wherein adjusting the known remission threshold to be an adjusted known remission threshold based on the comparison comprises:

based on the comparison indicating that the average remission value is less than the known remission threshold, the one or more processors adjusting the known remission threshold to be lower such that the adjusted known remission threshold is less than the average remission value.

19. The non-transitory computer readable medium of claim 15, wherein the predetermined period of time is a period of time during which at least a portion of the autonomous vehicle travels past the portion of the lane of travel.

20. The non-transitory computer readable medium of claim 15, the operations further comprising:

based on the plurality of remission signals and further based on the known remission threshold, determining that the portion of the lane of travel in the environment includes a particular number of lane markers;

comparing the particular number of lane markers to a particular threshold number of lane markers; and

based on the comparison indicating that the particular number of lane markers exceeds the particular threshold, making a determination that the particular number of lane markers includes at least one false positive lane marker,

wherein adjusting the known remission threshold to be the adjusted known remission threshold is further based on the determination that the particular number of lane markers includes at least one false positive lane marker.