Predictive sensor array configuration system for an autonomous vehicle

• US 10,712,742 B2
• Filed: 09/26/2017
• Issued: 07/14/2020
• Est. Priority Date: 12/16/2015
• Status: Active Grant

• Current Assignee: Uatc, LLC (Uber Technologies, Inc.)
• Original Assignee: Uatc, LLC (Uber Technologies, Inc.)
• Inventors: Valois, Jean-Sebastien
• Primary Examiner(s): Dager, Jonathan M
• Assistant Examiner(s): Evans, Garrett F
• Application Number:
  US15/716,144
• Publication Number:
  US 20180032075A1
• Time in Patent Office: 1,022 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. An autonomous vehicle (AV) comprising:

a LIDAR sensor generating sensor data corresponding to a surrounding environment of the AV; and

a control system comprising one or more processors executing an instruction set, causing the control system to;

analyze a current sub-map comprising previously recorded surface data of a current route of the AV to predict one or more imminent reflectance anomalies for a future location of the AV on the current route of the AV;

store, in a database, a lookup table (LUT) comprising a plurality of sensor configurations for the LIDAR sensor;

based on the one or more predicted imminent reflectance anomalies, perform a lookup in the LUT to determine a set of configurations for the LIDAR sensor; and

preemptively execute the set of configurations on one or more adjustable parameters of the LIDAR sensor as the AV approaches the future location of the AV on the current route of the AV.

2. The AV of claim 1, wherein the executed instruction set further causes the control system to:

store a set of sub-maps comprising recorded surface data of a given region upon which the AV operates;

wherein the current sub-map is included in the set of sub-maps.

3. The AV of claim 2, wherein each sub-map in the set of sub-maps comprises at least one of recorded LIDAR data or recorded image data.

4. The AV of claim 1, further comprising:

acceleration, braking, and steering systems;

wherein the executed instruction set further causes the control system to;

based on comparing the sensor data to the current sub-map, autonomously operate the acceleration, braking, and steering systems along the current route;

wherein the executed instruction set causes the control system

to predict the one or more imminent reflectance anomalies as the AV travels along the current route.

5. The AV of claim 1, wherein preemptively executing the set of configurations for the LIDAR sensor as the AV approaches the future location on the current route of the AV comprises adjusting at least one of a beam frequency, a laser power level, or a scan rate of the LIDAR sensor.

6. The AV of claim 1, wherein preemptively executing the set of configurations on the LIDAR sensor enables the control system to resolve the one or more imminent reflectance anomalies, and wherein the executed instruction set further causes the control system to:

based on resolving the one or more imminent reflectance anomalies, establish a mesh network with one or more rearward AVs; and

transmit data identifying the one or more imminent reflectance anomalies to the one or more rearward AVs.

7. The AV of claim 1, wherein the one or more imminent reflectance anomalies correspond to at least one of a dark object, a shiny object, an organic material, dust, smoke, fog, or precipitation.

8. The AV of claim 6, wherein the executed instruction set causes the control system to resolve the one or more imminent reflectance anomalies by positively identifying each of the one or more imminent reflectance anomalies.

9. The AV of claim 6, wherein the executed instruction set causes the control system to resolve each imminent reflectance anomaly of the one or more imminent reflectance anomalies by determining whether each imminent reflectance anomaly comprises a critical object or a neglectable object.

10. A non-transitory computer readable medium storing an instruction set that, when executed by one or more processors of a control system of an autonomous vehicle (AV), causes the control system to:

analyze a current sub-map comprising previously recorded surface data of a current route of the AV to predict one or more imminent reflectance anomalies for a future location of the AV on the current route of the AV;

store, in a database, a lookup table (LUT) comprising a plurality of sensor configurations for a LIDAR sensor;

based on the one or more predicted imminent reflectance anomalies, perform a lookup in the LUT to determine a set of configurations for the LIDAR sensor; and

preemptively execute the set of configurations on one or more adjustable parameters of the LIDAR sensor as the AV approaches the future location of the AV on the current route of the AV.

11. The non-transitory computer readable medium of claim 10, wherein the executed instruction set further causes the control system to:

store a set of sub-maps comprising recorded surface data of a given region upon which the AV operates;

wherein the current sub-map is included in the set of sub-maps.

12. The non-transitory computer readable medium of claim 11, wherein each sub-map in the set of sub-maps comprises at least one of recorded LIDAR data or recorded image data.

13. The non-transitory computer readable medium of claim 10, wherein the AV comprises acceleration, braking, and steering systems, and wherein the executed instruction set further causes the control system to:

based on comparing sensor data from the LIDAR sensor to the current sub-map, autonomously operate the acceleration, braking, and steering systems along the current route;

wherein the executed instruction set causes the control system to determine the one or more imminent reflectance anomalies as the AV travels along the current route.

14. The non-transitory computer readable medium of claim 10, wherein executing the set of configurations for the LIDAR sensor comprises adjusting at least one of a beam frequency, a laser power level, or a scan rate of the LIDAR sensor.

15. The non-transitory computer readable medium of claim 10, wherein executing the set of configurations on the LIDAR sensor enables the control system to resolve the one or more imminent reflectance anomalies, and wherein the executed instruction set further causes the control system to:

based on resolving the one or more imminent reflectance anomalies, establish a mesh network with one or more rearward AVs; and

transmit data identifying the one or more imminent reflectance anomalies to the one or more rearward AVs.

16. The non-transitory computer readable medium of claim 10, wherein the one or more imminent reflectance anomalies correspond to at least one of a dark object, a shiny object, an organic material, dust, smoke, fog, or precipitation.

17. The non-transitory computer readable medium of claim 15, wherein the executed instruction set causes the control system to resolve the one or more imminent reflectance anomalies by positively identifying each of the one or more imminent reflectance anomalies.

18. A computer-implemented method of resolving reflectance anomalies for a LIDAR sensor of an autonomous vehicle (AV), the method being performed by one or more processors of the AV and comprising:

analyzing, by a computing system comprising one or more computing devices, a current sub-map comprising previously recorded surface data of a current route of the AV to predict one or more imminent reflectance anomalies for a future location of the AV on the current route of the AV;

storing, by the computing system, in a database, a lookup table (LUT) comprising a plurality of sensor configurations for the LIDAR sensor;

based on the one or more predicted imminent reflectance anomalies, performing, by the computing system, a lookup in the LUT to determine a set of configurations for the LIDAR sensor; and

preemptively executing, by the computing system, the set of configurations on one or more adjustable parameters of the LIDAR sensor as the AV approaches the future location of the AV on the current route of the AV.