Safely navigating crosswalks

• US 9,440,647 B1
• Filed: 09/22/2014
• Issued: 09/13/2016
• Est. Priority Date: 09/22/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Sucan, Ioan-Alexandru, Fairfield, Nathaniel
• Primary Examiner(s): Figueroa, Jaime
• Application Number:
  US14/492,459
• Time in Patent Office: 722 Days
• Field of Search: 701/1, 701/23, 701/70, 701/117, 701/118, 701/119
• US Class Current: 1/1
• 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 2556/40 High definition maps
• CPC Class Codes: B60W 2720/10 Longitudinal speed
• CPC Class Codes: B60W 30/08 Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
• CPC Class Codes: B60W 30/18154 Approaching an intersection
• CPC Class Codes: B60W 60/0015 specially adapted for safety
• CPC Class Codes: G05D 1/021 specially adapted to land vehicles
• CPC Class Codes: G05D 2201/0213 Road vehicle, e.g. car or truck

Abstract

Aspects of the disclosure relate to safely navigating crosswalks by responding to potentially occluded objects in such crosswalks. For example, a vehicle approaches a crosswalk and the vehicle'"'"'s one more computing devices may generate a set of samples corresponding to locations in the crosswalk. Sensor data is periodically received by the one or more computing devices. For each given sample of the set of samples a probability value indicative of a probability of sample being occluded is set to an initial value by the one or more computing devices. As the vehicle approaches the crosswalk, probability values for the given sample are periodically adjusted by the one or more computing devices based on the periodically received sensor data. The speed of the vehicle then changed by the one or more computing devices based upon a determination that a sample of the set of samples has met the threshold value.

Claims

1. A computer-implemented method comprising:

identifying, by one or more computing devices, that a first vehicle is approaching a crosswalk;

generating, by the one or more computing devices, a set of samples corresponding to locations in the crosswalk;

periodically receiving, by the one or more computing devices, sensor data;

for each given sample of the set of samples;

setting, by the one or more computing devices, a probability value to an initial value, wherein the probability value indicates a probability that the given sample is occluded, and

as the first vehicle approaches the crosswalk periodically adjusting, by the one or more computing devices, probability value for the given sample based on the periodically received sensor data;

determining, by the one or more computing devices, that an updated probability value for a particular sample of the set of samples has met a threshold value; and

changing, by the one or more computing devices, the speed of the first vehicle based on the determination that a sample of the set of samples has met the threshold value.

2. The method of claim 1, wherein adjusting the probability value for a first given sample of the set of samples is further based on whether the sensor data indicates that a second vehicle is crossing through the location of the first given sample.

3. The method of claim 2, wherein adjusting the probability value for the first given sample includes decreasing the probability value for the first given sample when the sensor data indicates that the second vehicle is crossing through the location of the first given sample.

4. The method of claim 1, wherein adjusting the probability value for a first given sample of the set of samples is further based on whether the sensor data indicates that another vehicle is crossing through the crosswalk and the location of the first given sample is on a far side of the another vehicle, further from the first vehicle.

5. The method of claim 1, wherein adjusting the probability value for a first given sample of the set of samples includes decreasing the probability value for the first given sample when the sensor data indicates that another vehicle is crossing through the location of the given sample.

6. The method of claim 1, wherein adjusting the probability value for a first given sample of the set of samples is further based on whether the sensor data indicates the first given sample is visible to a sensor of the first vehicle.

7. The method of claim 6, wherein adjusting the probability value for the first given sample includes decreasing the probability value for the first given sample when the sensor data indicates that the first given sample is visible to a sensor of the first vehicle.

8. The method of claim 6, wherein adjusting the probability value for the first given sample includes increasing the probability value for the first given sample when the sensor data indicates that the first given sample is not visible to a sensor of the first vehicle.

9. A system comprising one or more computing devices, having one or more processors, the one or more computing devices configured to:

identify that a first vehicle is approaching a crosswalk;

generate a set of samples corresponding to locations in the crosswalk;

periodically receive sensor data;

for each given sample of the set of samples;

set a probability value to an initial value, wherein the probability value indicates a probability that the given sample is occluded, and

as the first vehicle approaches the crosswalk, periodically adjust probability value for the given sample based on the periodically received sensor data;

determine that an updated probability value for a particular sample of the set of samples has met a threshold value; and

change the speed of the first vehicle based on the determination that a sample of the set of samples has met the threshold value.

10. The system of claim 9, wherein the one or more computing devices are further configured to adjust the probability value for a first given sample of the set of samples further based on whether the sensor data indicates that a second vehicle is crossing through the location of the first given sample.

11. The system of claim 10, wherein the one or more computing devices are further configured to adjust the probability value for the first given sample by decreasing the probability value for the first given sample when the sensor data indicates that the second vehicle is crossing through the location of the first given sample.

12. The system of claim 9, wherein the one or more computing devices are further configured to adjust the probability value for a first given sample of the set of samples further based on whether the sensor data indicates that another vehicle is crossing through the crosswalk and the location of the first given sample is on a far side of the another vehicle, further from the first vehicle.

13. The system of claim 9, wherein the one or more computing devices are further configured to adjust a probability value for a first given sample of the set of samples by decreasing the probability value for the first given sample when the sensor data indicates that another vehicle is crossing through the location of the first given sample.

14. The system of claim 9, wherein the one or more computing devices are further configured to adjust the probability value for a first given sample of the set of samples further based on whether the sensor data indicates the first given sample is visible to a sensor of the first vehicle.

15. The system of claim 14, wherein the one or more computing devices are further configured to adjust the probability value for the first given sample by decreasing the probability value for the first given sample when the sensor data indicates that the first given sample is visible to a sensor of the first vehicle.

16. The system of claim 14, wherein the one or more computing devices are further configured to adjust the probability value for the first given sample by increasing the probability value for the first given sample when the sensor data indicates that the first given sample is not visible to a sensor of the first vehicle.

17. The system of claim 9, further comprising the first vehicle.

18. A non-transitory, tangible machine readable medium on which instructions are stored, the instructions, when executed by one or more processors, cause the one or more processors to perform a method, the method comprising:

identifying that a first vehicle is approaching a crosswalk;

generating a set of samples corresponding to locations in the crosswalk;

periodically receiving sensor data;

for each given sample of the set of samples;

setting a probability value to an initial value, wherein the probability value indicates a probability that the given sample is occluded, and

as the first vehicle approaches the crosswalk, periodically adjusting probability value for the given sample based on the periodically received sensor data;

determining that an updated probability value for a particular sample of the set of samples has met a threshold value; and

changing the speed of the first vehicle based on the determination that a sample of the set of samples has met the threshold value.

19. The medium of claim 18, wherein adjusting the probability value for a first given sample of the set of samples is further based on whether the sensor data indicates that a second vehicle is crossing through the location of the first given sample.

20. The medium of claim 18, wherein adjusting the probability value for the first given sample is further based on whether the sensor data indicates that another vehicle is crossing through the crosswalk and the location of the first given sample is on a far side of the another vehicle, further from the first vehicle.