Static obstacle detection

• US 9,335,766 B1
• Filed: 12/06/2013
• Issued: 05/10/2016
• Est. Priority Date: 12/06/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Silver, David Harrison, Dowdall, Jonathan Baldwin, Ferguson, David Ian Franklin
• Primary Examiner(s): Olszewski, John R
• Assistant Examiner(s): Whittington, Jess
• Application Number:
  US14/099,004
• Time in Patent Office: 886 Days
• Field of Search: None
• US Class Current: 1/1
• 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 sensor data associated with a vehicle, wherein the sensor data comprises a plurality of frames of sensor data indicative of an environment, wherein the sensor data comprises sensor data from a sensor, and wherein the vehicle is configured to operate in an autonomous mode in the environment;

determining, by a computing device, that a first respective frame of the plurality of frames of sensor data indicates detection of an object in the environment;

identifying, from within the plurality of frames of sensor data, other respective frames that indicate detection of a second object in the environment;

comparing, by the computing device, the first respective frame of the plurality of frames of sensor data that indicates detection of the object in the environment to the other respective frames of the plurality of frames of sensor data that indicate detection of the second object in the environment;

based on the comparison, determining;

(i) whether a location of the object indicated by the first respective frame of the plurality of frames of sensor data is substantially the same as a location of the second object indicated by the other respective frames of the plurality of frames of sensor data, and

(ii) a time window indicative of a time between collection of the first respective frame of the plurality of frames of sensor data that indicates detection of the object and collection of the other respective frames of the plurality of frames of sensor data that indicate detection of the second object;

based on prior detections of objects by the sensor, determining (i) an expected number of detections of the object by the sensor in response to the object being a stationary object in the environment and (ii) an expected amount of time between the expected number of detections;

making a determination that the object indicated by the first respective frame of the plurality of frames of sensor data is the same as the second object indicated by the other respective frames of the plurality of frames of sensor data based on;

(i) detection of the second object being indicated more than a threshold number of times in the other respective frames of the plurality of frames of the sensor data, wherein the threshold number of times is based on the expected number of detections,

(ii) the location of the object indicated by the first respective frame of the plurality of frames of sensor data being substantially the same as the location of the second object indicated by the other respective frames of the plurality of frames of sensor data, and

(iii) the time window being greater than a time threshold, wherein the time threshold is based on the expected amount of time; and

based on the determination, providing instructions to control the vehicle in the environment.

2. The method of claim 1, further comprising:

making a second determination that the object indicated by the first respective frame of the plurality of frames of sensor data is different than the second object indicated by the other respective frames of the plurality of frames of sensor data based on;

(i) detection of the second object being indicated less than the threshold number of times in the other respective frames of the plurality of frames of the sensor data,

(ii) the location of the object indicated by the first respective frame of the plurality of frames of sensor data being substantially different than the location of the second object indicated by the other respective frames of the plurality of frames of sensor data, or

(iii) the time window being less than the time threshold.

3. The method of claim 2, wherein providing the instructions to control the vehicle in the environment is based also on the second determination.

4. The method of claim 1,

wherein the object is associated with a category of objects,

wherein the second object is associated with the category of objects, and

wherein the sensor is configured to detect objects in the category of objects.

5. The method of claim 4, wherein the category of objects comprises a reflector.

6. The method of claim 1, wherein the sensor data comprises sensor data received from a second vehicle operating in the environment.

7. A vehicle comprising:

a sensor; and

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

receive sensor data associated with the vehicle, wherein the sensor data comprises a plurality of frames of sensor data indicative of an environment, wherein the sensor data comprises sensor data received using the sensor, and wherein the vehicle is configured to operate in an autonomous mode in the environment;

determine that a first respective frame of the plurality of frames of sensor data indicates detection of an object in the environment;

identify, from within the plurality of frames of sensor data, other respective frames that indicate detection of a second object in the environment;

compare the first respective frame of the plurality of frames of sensor data that indicates detection of the object in the environment to the other respective frames of the plurality of frames of sensor data that indicate detection of the second object in the environment;

based on the comparison, determine;

(i) whether a location of the object indicated by the first respective frame of the plurality of frames of sensor data is substantially the same as a location of the second object indicated by the other respective frames of the plurality of frames of sensor data, and

(ii) a time window indicative of a time between collection of the first respective frame of the plurality of frames of sensor data that indicates detection of the object and collection of the other respective frames of the plurality of frames of sensor data that indicate detection of the second object;

based on prior detections of objects by the sensor, determine (i) an expected number of detections of the object by the sensor in response to the object being a stationary object in the environment and (ii) an expected amount of time between the expected number of detections;

make a determination that the object indicated by the first respective frame of the plurality of frames of sensor data is the same as the second object indicated by the other respective frames of the plurality of frames of sensor data based on;

(i) detection of the second object being indicated more than a threshold number of times in the other respective frames of the plurality of frames of the sensor data, wherein the threshold number of times is based on the expected number of detections,

(ii) the location of the object indicated by the first respective frame of the plurality of frames of sensor data being substantially the same as the location of the second object indicated by the other respective frames of the plurality of frames of sensor data, and

(iii) the time window being greater than a time threshold, wherein the time threshold is based on the expected amount of time; and

based on the determination, provide instructions to control the vehicle in the environment.

8. The vehicle of claim 7, wherein the computer system is further configured to:

make a second determination that the object indicated by the first respective frame of the plurality of frames of sensor data is different than the second object indicated by the other respective frames of the plurality of frames of sensor data based on;

(i) detection of the second object being indicated less than the threshold number of times in the other respective frames of the plurality of frames of the sensor data,

(ii) the location of the object indicated by the first respective frame of the plurality of frames of sensor data being substantially different than the location of the second object indicated by the other respective frames of the plurality of frames of sensor data, or

(iii) the time window being less than the time threshold.

9. The vehicle of claim 8, wherein the computer system is configured to provide the instructions to control the vehicle in the environment based also on the second determination.

10. The vehicle of claim 7,

wherein the object is associated with a category of objects,

wherein the second object is associated with the category of objects, and

wherein the sensor is configured to detect objects in the category of objects.

11. The vehicle of claim 10, wherein the category of objects comprises a reflector.

12. The vehicle of claim 7, wherein the sensor data comprises sensor data received from a second vehicle operating in the environment.

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

receiving sensor data associated with the vehicle, wherein the sensor data comprises a plurality of frames of sensor data indicative of an environment, wherein the sensor data comprises sensor data from a sensor, and wherein the vehicle is configured to operate in an autonomous mode in the environment;

determining that a first respective frame of the plurality of frames of sensor data indicates detection of an object in the environment;

identifying, from within the plurality of frames of sensor data, other respective frames that indicate detection of a second object in the environment;

comparing the first respective frame of the plurality of frames of sensor data that indicates detection of the object in the environment to the other respective frames of the plurality of frames of sensor data that indicate detection of the second object in the environment;

based on the comparison, determining;

(i) whether a location of the object indicated by the first respective frame of the plurality of frames of sensor data is substantially the same as a location of the second object indicated by the other respective frames of the plurality of frames of sensor data, and

(ii) a time window indicative of a time between collecting the first respective frame of the plurality of frames of sensor data that indicates detection of the object and collecting the other respective frames of the plurality of frames of sensor data that indicate detection of the second object;

based on prior detections of objects by the sensor, determining (i) an expected number of detections of the object by the sensor in response to the object being a stationary object in the environment and (ii) an expected amount of time between the expected number of detections;

making a determination that the object indicated by the first respective frame of the plurality of frames of sensor data is the same as the second object indicated by the other respective frames of the plurality of frames of sensor data based on;

(i) detection of the second object being indicated more than a threshold number of times in the other respective frames of the plurality of frames of the sensor data, wherein the threshold number of times is based on the expected number of detections,

(ii) the location of the object indicated by the first respective frame of the plurality of frames of sensor data being substantially the same as the location of the second object indicated by the other respective frames of the plurality of frames of sensor data, and

(iii) the time window being greater than a time threshold, wherein the time threshold is based on the expected amount of time; and

based on the determination, providing instructions to control the vehicle in the environment.

14. The non-transitory computer readable medium of claim 13, wherein the instructions are further executable by the computer system in the vehicle to cause the computer system to perform functions comprising:

making a second determination that the object indicated by the first respective frame of the plurality of frames of sensor data is different than the second object indicated by the other respective frames of the plurality of frames of sensor data based on;

(i) detection of the second object being indicated less than the threshold number of times in the other respective frames of the plurality of frames of the sensor data,

(ii) the location of the object indicated by the first respective frame of the plurality of frames of sensor data being substantially different than the location of the second object indicated by the other respective frames of the plurality of frames of sensor data, or

(iii) the time window being less than the time threshold.

15. The non-transitory computer readable medium of claim 14, wherein providing the instructions to control the vehicle in the environment is based also on the second determination.

16. The non-transitory computer readable medium of claim 13,

wherein the object is associated with a category of objects,

wherein the second object is associated with the category of objects, and

wherein the sensor is configured to detect objects in the category of objects.

17. The non-transitory computer readable medium of claim 13, wherein the sensor data comprises sensor data received from a second vehicle operating in the environment.