Static obstacle detection

• US 10,204,278 B2
• Filed: 04/08/2016
• Issued: 02/12/2019
• Est. Priority Date: 12/06/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Waymo LLC (Alphabet Inc.)
• Inventors: Silver, David Harrison, Dowdall, Jonathan Baldwin, Ferguson, David Ian
• Primary Examiner(s): Whittington, Jess
• Application Number:
  US15/094,776
• Publication Number:
  US 20160224850A1
• Time in Patent Office: 1,040 Days
• CPC Class Codes: B60W 2552/53 Road markings, e.g. lane marker or crosswalk
• CPC Class Codes: B60W 2554/20 Static objects
• CPC Class Codes: B60W 60/0016 of the vehicle or its occupants
• CPC Class Codes: G01S 13/04 Systems determining presence of a target based on relative movement of target G01S13/56
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G01S 17/04 Systems determining the presence of a target
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G01S 19/13 Receivers
• CPC Class Codes: G01V 11/00 Prospecting or detecting by methods combining techniques covered by two or more of main groups G01V1/00 - G01V9/00
• CPC Class Codes: G05D 1/0238 using obstacle or wall sensors G05D1/0246 and G05D1/0289 take precedence; lidar systems designed for anti-collision purposes G01S17/93
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/2415 based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
• CPC Class Codes: G06F 18/2431 Multiple classes
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads

Abstract

A vehicle is provided that may distinguish between dynamic obstacles and static obstacles. Given a detector for a class of static obstacles or objects, the vehicle may receive sensor data indicative of an environment of the vehicle. When a possible object is detected in a single frame, a location of the object and a time of observation of the object may be compared to previous observations. Based on the object being observed a threshold number of times, in substantially the same location, and within some window of time, the vehicle may accurately detect the presence of the object and reduce any false detections.

Claims

1. A method comprising:

receiving, by a computing device, a first set of sensor data representing a forward-looking environment of a vehicle, wherein the first set of sensor data is received from one or more forward-looking sensors as the vehicle navigates in a first environment;

based on detections of objects performed using the first set of sensor data from the one or more forward-looking sensors received while the vehicle navigated in the first environment, determining a threshold number of detections of an object positioned in the forward-looking environment of the vehicle and a threshold amount of time between an initial detection and a subsequent detection of the object that together indicate the object is stationary when using subsequent sensor data received as the vehicle navigates in an environment similar to the first environment;

receiving, by the computing device, a second set of sensor data representing the forward-looking environment of the vehicle, wherein the second set of sensor data is received from the one or more forward-looking sensors as the vehicle navigates in a second environment, and wherein the second environment is similar to the first environment;

detecting a given object in a plurality of frames of the second set of sensor data received from the one or more forward-looking sensors as the vehicle navigates in the second environment;

determining that the given object is at a stationary position when a duration between an initial detection and a subsequent detection of the given object in the plurality of frames exceeds the threshold amount of time and a quantity of detections of the given object in the plurality of frames exceeds the threshold number of detections; and

controlling the vehicle in the second environment using a navigation strategy that is based in part on the stationary position of the given object in the forward-looking environment of the vehicle.

2. The method of claim 1, wherein the detections are associated with vehicle operations related to a corresponding vehicle operation of the vehicle.

3. The method of claim 1, wherein receiving the first set of sensor data comprises receiving additional sensor data from another vehicle operating in the first environment.

4. The method of claim 1, wherein a particular frame of the plurality of frames is indicative of detection of a particular object by a particular sensor.

5. The method of claim 4, further comprising:

determining whether the particular object is stationary in the environment based on a comparison between the particular frame and other frames of the plurality of frames.

6. The method of claim 4, wherein the particular object is associated with a category of objects, wherein the particular sensor is configured to detect objects associated with the category of objects, the method further comprising:

identifying, from the plurality of frames, other frames based on respective detections indicated by the other frames being associated with the category of objects.

7. The method of claim 4, further comprising:

determining whether the detection indicated by the particular frame and respective detections indicated by other frames of the plurality of frames correspond to detections of the same object.

8. The method of claim 7, further comprising:

comparing a number of the respective detections indicated by the other frames to the threshold number of detections; and

wherein determining whether the detection indicated by the particular frame and the respective detections indicated by the other frames correspond to detections of the same object is based on the comparison.

9. The method of claim 7, further comprising:

comparing a time window between a first time of detection associated with the particular frame and a second time of detection associated with one or more of the other frames to threshold amount of time; and

wherein determining whether the detection indicated by the particular frame and the respective detections indicated by the other frames correspond to detections of the same object is based on the comparison.

10. The method of claim 7, further comprising:

comparing an object location associated with the detection indicated by the particular frame to object locations associated with the respective detections indicated by the other frames, wherein determining whether the detection indicated by the particular frame and the respective detections indicated by the other frames correspond to detections of the same object is based on the comparison.

11. A vehicle comprising:

one or more forward-looking sensors; and

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

receive a first set of sensor data representing a forward-looking environment of the vehicle, wherein the first set of sensor data is received from the one or more forward-looking sensors as the vehicle navigates in a first environment;

based on detections of objects performed using the first set of sensor data from the one or more forward-looking sensors received while the vehicle navigated in the first environment, determine a threshold number of detections of an object positioned in the forward-looking environment of the vehicle and a threshold amount of time between an initial detection and subsequent detection of the object that together indicate the object is stationary when using subsequent sensor data received as the vehicle navigates in an environment similar to the first environment;

receive a second set of sensor data representing the forward-looking environment of the vehicle, wherein the second set of sensor data is received from the one or more forward-looking sensors as the vehicle navigates in a second environment, and wherein the second environment is similar to the first environment;

detect a given object in a plurality of frames of the second set of sensor data received from the one or more sensors as the vehicle navigates in the second environment;

determine that the given object is at a stationary position when a duration between an initial detection and a subsequent detection of the given object in the plurality of frames exceeds the threshold amount of time and a quantity of detections of the given object in the plurality of frames exceeds the threshold number of detections; and

control the vehicle in the second environment using a navigation strategy that is based in part on the stationary position of the given object in the forward-looking environment of the vehicle.

12. The vehicle of claim 11, wherein the first set of sensor data comprises additional sensor data received from another vehicle operating in the first environment.

13. A non-transitory computer readable medium storing instructions, that when executed by a computer system, cause the computer system to perform functions comprising:

receiving a first set of sensor data representing a forward-looking environment of a vehicle, wherein the first set of sensor data is received from one or more forward-looking sensors as the vehicle navigates in a first environment;

based on detections of objects performed using the first set of sensor data from the one or more forward-looking sensors received while the vehicle navigated in the first environment, determining a threshold number of detections of an object positioned in the forward-looking environment of the vehicle and a threshold amount of time between an initial detection and a subsequent detection of the object that together indicate the object is stationary when using subsequent sensor data received as the vehicle navigates in an environment similar to the first environment;

receiving a second set of sensor data representing the forward-looking environment of the vehicle, wherein the second set of sensor data is received from the one or more forward-looking sensors as the vehicle navigates in a second environment, and wherein the second environment is similar to the first environment;

detecting a given object in a plurality of frames of the second set of sensor data received from the one or more sensors as the vehicle navigates in the second environment;

determining that the given object is at a stationary position when a duration between an initial detection and a subsequent detection of the given object in the plurality of frames exceeds the threshold amount of time and a quantity of detections of the given object in the plurality of frames exceeds the threshold number of detections; and

controlling the vehicle in the second environment using a navigation strategy that is based in part on the stationary position of the given object in the forward-looking environment of the vehicle.

14. The non-transitory computer readable medium of claim 13, wherein a particular frame of the plurality of frames is indicative of detection of a particular object by a particular sensor, the functions further comprising:

determining that the particular object is stationary in the environment based on the detection indicated by the particular frame and respective detections indicated by other frames of the plurality of frames corresponding to detections of the same object.

15. The non-transitory computer readable medium of claim 14, the functions further comprising:

determining that the detection indicated by the particular frame and the respective detections indicated by the other frames correspond to detections of the same object based on a number of the respective detections indicated by the other frames being greater than the threshold number of detections.

16. The non-transitory computer readable medium of claim 14, the functions further comprising:

determining that the detection indicated by the particular frame and the respective detections indicated by the other frames correspond to detections of the same object based on a time window between a first time of detection associated with the particular frame and a second time of detection associated with one or more of the other frames being greater than the threshold amount of time.

17. The non-transitory computer readable medium of claim 14, the functions further comprising:

determining that the detection indicated by the particular frame and the respective detections indicated by the other frames correspond to detections of the same object based on an extent of similarity between an object location associated with the detection indicated by the particular frame and object locations associated with the respective detections indicated by the other frames.