Predictive sensor array configuration system for an autonomous vehicle

• US 9,841,763 B1
• Filed: 12/16/2015
• Issued: 12/12/2017
• Est. Priority Date: 12/16/2015
• Status: Active Grant

• Current Assignee: Aurora Operations Incorporated (Aurora Innovation, Inc.)
• Original Assignee: Uber Technologies, Inc.
• Inventors: Valois, Jean-Sebastien
• Primary Examiner(s): Tissot, Adam
• Assistant Examiner(s): Evans, Garrett
• Application Number:
  US14/971,866
• Time in Patent Office: 727 Days
• Field of Search: None
• CPC Class Codes: G01S 13/865 Combination of radar systems with lidar systems
• CPC Class Codes: G01S 13/867 Combination of radar systems with cameras
• CPC Class Codes: G01S 13/931 of land vehicles
• CPC Class Codes: G01S 17/02 Systems using the reflection of electromagnetic waves other than radio waves G01S17/66 takes precedence
• CPC Class Codes: G01S 17/86 Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G01S 17/95 for meteorological use
• CPC Class Codes: G01S 7/40 Means for monitoring or calibrating
• CPC Class Codes: G01S 7/497 Means for monitoring or calibrating
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0231 using optical position detecting means position-fixing by using electromagnetic waves other than radio waves, e.g. optical position detecting means G01S5/16
• CPC Class Codes: G05D 1/0257 using a radar radar systems designed for anti-collision purposes between land vehicles or between land vehicle and fixed obstacles G01S13/931
• CPC Class Codes: Y02A 90/10 Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

An autonomous vehicle (AV) can include a predictive sensor configuration system that can dynamically detect reflectance anomalies that affect detectability by sensor array of the AV as the AV travels a current route. The predictive sensor configuration system can dynamically determine one or more configurations for the sensor array to attempt to positively identify the reflectance anomalies, and preemptively execute the one or more configurations for the sensor array as the AV travels the current route.

Claims

1. A predictive sensor array configuration system for an autonomous vehicle (AV) comprising:

one or more processors; and

one or more memory resources storing instructions that, when executed by the one or more processors, cause the predictive sensor array configuration system to;

as the AV travels a current route, dynamically detect reflectance anomalies that affect detectability by a sensor array of the AV;

maintain a lookup table comprising a plurality of sensor configurations for each respective one of a plurality of active sensor systems included in the sensor array;

dynamically determine one or more configurations for the sensor array to positively identify the detected reflectance anomalies, wherein the one or more configurations are included in the plurality of sensor configurations; and

dynamically execute the one or more configurations for the sensor array as the AV travels the current route.

2. The predictive sensor array configuration system of claim 1, wherein sensor array comprises a light-detection and ranging (LiDAR) system, and wherein the one or more dynamically executed configurations configure one or more of a scan rate of the LiDAR system, a photodetector sensitivity of the LiDAR system, or a laser power level of the LiDAR system.

3. The predictive sensor array configuration system of claim 1, wherein sensor array comprises a radar system, and wherein the one or more dynamically executed configurations configure a pulse width of a carrier signal of the radar system.

4. The predictive sensor array configuration system of claim 1, wherein each of the plurality of active sensor systems emit one or more of sounds waves or electromagnetic waves.

5. The predictive sensor array configuration system of claim 1, wherein the executed instructions cause the predictive sensor array configuration system to dynamically determine the one or more configurations by performing a lookup in the lookup table based on a reflectance of each of the detected reflectance anomalies.

6. The predictive sensor array configuration system of claim 1, wherein the executed instructions cause the predictive sensor array configuration system to dynamically determine the one or more configurations by performing an optimization utilizing a plurality of possible configurations for each of the plurality of active sensor systems based on a reflectance of each of the identified surface features, and wherein the optimization converges on the one or more configurations in the lookup table.

7. The predictive sensor array configuration system of claim 1, wherein the plurality of active sensor systems comprise a LiDAR system and a radar system, and wherein the sensor array further includes one or more passive sensor systems that detect reflected natural light.

8. The predictive sensor array configuration system of claim 7, wherein the one or more passive sensor systems of the sensor array comprise a stereo camera system.

9. The predictive sensor array configuration system of claim 8, wherein the LiDAR system, the radar system, and the stereo camera system each provides sensor data to a control system of the AV to enable the AV to maneuver along the current route.

10. The predictive sensor array configuration system of claim 9, wherein the control system dynamically processes the sensor data from the sensor array to maneuver the AV along the current route.

11. The predictive sensor array configuration system of claim 10, wherein the detected reflectance anomalies comprise surface features of an environment around the AV and weather features indicating precipitation.

12. The predictive sensor array configuration system of claim 11, wherein the executed instructions further cause the predictive sensor array configuration system to:

in response to identifying the weather features indicating precipitation, deprioritize sensor data from the LiDAR system for processing by the control system.

13. The predictive sensor array configuration system of claim 11, wherein the executed instructions further cause the predictive sensor array configuration system to:

in response to identifying the weather features indicating precipitation, deactivate the LiDAR system.

14. The predictive sensor array configuration system of claim 1, wherein the executed instructions cause the predictive sensor array configuration system to dynamically identify the one or more reflectance anomalies by receiving reflectance data from a number of proximate AVs traveling on the current route.

15. The predictive sensor array configuration system of claim 14, wherein the executed instructions cause the predictive sensor array configuration system to receive the reflectance data from the proximate AVs by establishing a mesh network with the proximate AVs.

16. The predictive sensor array configuration system of claim 1, wherein the executed instructions further cause the predictive sensor array configuration system to:

maintain a sub-map database comprising 3D surface data of an operational region of the AV; and

identify, using a current position of the AV, a correlated sub-map from the sub-map database that provides 3D surface data surrounding the current position of the AV;

wherein the executed instructions cause the predictive sensor array configuration system to dynamically identify the reflectance anomalies that affect detectability by the sensor array from the 3D surface data provided by the correlated sub-map.

19. The predictive sensor array configuration system of claim 11, wherein the executed instructions further cause the predictive sensor array configuration system to:

in response to identifying the weather features indicating precipitation, prioritize sensor data from one or more passive sensor systems of the sensor array for processing by the control system of the AV.

20. The predictive sensor array configuration system of claim 2, wherein the reflectance anomalies comprise at least one of dust, smoke, fog, precipitation, or a dark object.

17. An autonomous vehicle (AV) comprising:

a sensor array to continuously detect a situational environment of the AV and generate sensor data indicating the situational environment;

an on-board data processing system to process the sensor data by comparing the sensor data to stored sub-maps that provide detailed surface data of a current route traveled by the AV;

a memory resource to store the sub-maps and a lookup table comprising a plurality of sensor configurations for each respective one of a plurality of sensor systems included in the sensor array;

acceleration, braking, and steering systems; and

an AV control system to;

utilize the processed sensor data to operate the acceleration, braking, and steering systems along the current route;

as the AV travels the current route, dynamically detect reflectance anomalies that affect detectability by a sensor array of the AV;

dynamically determine one or more configurations for the sensor array to positively identify the detected reflectance anomalies; and

dynamically execute the one or more configurations for the sensor array as the AV travels the current route;

wherein the executed instructions cause the predictive sensor array configuration system to dynamically determine the one or more configurations by performing a lookup in the lookup table based on the detected reflectance anomalies.

18. A non-transitory computer readable medium storing instructions for predictively configuring a sensor array of an autonomous vehicle (AV), wherein the instructions, when executed by the one or more processors, cause the one or more processors to:

as the AV travels a current route, dynamically detect reflectance anomalies that affect detectability by the sensor array;

maintain a lookup table comprising a plurality of sensor configurations for each respective one of a plurality of active sensor systems included in the sensor array;

dynamically determine one or more configurations for the sensor array to positively identify the detected reflectance anomalies, wherein the one or more configurations are included in the plurality of sensor configurations; and

dynamically execute the one or more configurations for the sensor array as the AV travels the current route.