Annotated virtual track to inform autonomous vehicle control

Patent metadata

Field	Value
Publication number	US-9953535-B1
Application number	US-201615194385-A
Country	US
Kind code	B1
Filing date	Jun 27, 2016
Priority date	Jun 27, 2016
Publication date	Apr 24, 2018
Grant date	Apr 24, 2018

Abstract

Recent location and control information received from “lead” vehicles that traveled over a segment of land, sea, or air is captured to inform, via aggregated data, subsequent “trailing” vehicles that travel over that same segment of land, sea, or air. The aggregated data may provide the trailing vehicles with annotated road information that identifies obstacles. In some embodiments, at least some sensor control data may be provided to the subsequent vehicles to assist those vehicles in identifying the obstacles and/or performing other tasks. Besides, obstacles, the location and control information may enable determining areas traveled by vehicles that are not included in conventional maps, as well as vehicle actions associated with particular locations, such as places where vehicles park or make other maneuvers.

First claim

What is claimed is:

1. A method to generate control data for an autonomous vehicle, the method comprising:
receiving first location data and first control data from a first vehicle that travels through a segment of land, sea, or air;
aggregating the first location data with other location data to generate virtual track data that identifies locations where vehicles travel through the segment;
aggregating the first control data with other control data to generate aggregated control data associated with the virtual track data;
analyzing the virtual track data and the aggregated control data to determine at least one obstacle in the segment of land, sea, or air;
determining avoidance control data to avoid vehicle interaction with the obstacle based at least on the aggregated control data;
annotating the virtual track data with the obstacle and the avoidance control data to create annotated virtual track data; and
transmitting the annotated virtual track data to a second vehicle having second location data associated with the segment of land, sea, or air, the annotated virtual track data being an input of second control data processed by the second vehicle to traverse the segment of land, sea, or air.

2. The method as recited in claim 1 , further comprising generating a map of a road that specifies multiple lanes based on the virtual track data, wherein the virtual track data includes a first aggregated vehicle speed associated with a first lane that is different than a second aggregated vehicle speed associated with a second lane of the multiple lanes.

3. The method as recited in claim 1 , wherein the avoidance control data includes sensor control data used to augment operation of a sensor of the second vehicle to identify the obstacle or a vehicle near the obstacle.

4. The method as recited in claim 1 , further comprising determining vehicle use data associated with the segment of land, sea, or air based at least in part on the virtual track data and the aggregated control data, wherein the vehicle use data includes at least one of a parking location or a vehicle maneuver, and wherein the annotating includes annotating the virtual track data with the vehicle use data.

5. A system comprising,
one or more processors; and
memory to store computer-executable instructions that, when executed, cause the one or more processors to perform acts comprising:
receiving sensor data from a plurality of vehicles that travel through a segment;
aggregating the sensor data to generate virtual track data that identifies locations where vehicles travel through the segment, wherein the aggregating comprises applying a decay function to at least a portion of the sensor data, the decay function to apply a first weight to a first portion of the sensor data associated with a first time and to apply a second weight to a second portion of the sensor data associated with a second time that is different than the first time;
annotating the virtual track data with at least one of vehicle control parameters or hazard information to create annotated virtual track data; and
transmitting the annotated virtual track data to a vehicle expected to traverse the segment.

6. The system as recited in claim 5 , wherein the acts further comprise determining a weather condition associated with the annotated virtual track data, and classifying the annotate virtual track data as associated with the weather condition.

7. The system as recited in claim 5 , wherein the acts further comprise:
associating the annotated virtual track data with a first period of time; and
determining that the vehicle is expected to traverse the segment at a second period of time after the first period of time, and
wherein the transmitting is based at least in part on the second period of time being correlated with the first period of time.

8. The system as recited in claim 5 , wherein the acts further comprise:
analyzing the virtual track data to determine at least one hazard in the segment;
labeling the hazard as a temporary hazard;
receiving sensor data from a different vehicle that travels through a location associated with presence of the temporary hazard; and
removing an annotation of the temporary hazard from the annotated virtual track data in response to the receiving the sensor data from the different vehicle.

9. The system as recited in claim 5 , wherein the acts further comprise determining a spacing between adjacent vehicles moving through the segment.

10. The system as recited in claim 5 , wherein the acts further comprise:
receiving additional sensor data from a different vehicle traveling through the segment;
determining that the additional sensor data includes outlier data in comparison to the sensor data from the plurality of vehicles, and
refraining from including the additional sensor data associated with the different vehicle in the annotated virtual track data.

11. The system as recited in claim 5 , wherein the acts further comprise determining a vehicle parking location within the segment based at least in part on the virtual track data, and wherein the annotating includes annotating the virtual track data with the vehicle parking location.

12. The system as recited in claim 5 , wherein the acts further comprise generating a map of routes traveled by the plurality of vehicles through the segment during a period of time, the map including multiple lanes, wherein a first lane is associated with first attributes that are different than second attributes associated with a second lane of the multiple lanes.

13. The system as recited in claim 5 , wherein the avoidance control data includes sensor control data used to augment operation of a sensor of the vehicle to cause the sensor to generate signals associated with the hazard information.

14. The system as recited in claim 5 , wherein the acts further comprise determining vehicle maneuver data associated with the segment based at least in part on the virtual track data, and wherein the annotating includes annotating the annotated virtual track data with the vehicle maneuver data.

15. The system as recited in claim 5 , wherein the acts further comprise determining avoidance control data to avoid vehicle interaction with an obstacle denoted by the hazard information.

16. A method to operate an autonomous vehicle, the method comprising:
receiving annotated virtual track data that specifies routes available for use by the autonomous vehicle expected to traverse a segment, wherein the annotated virtual track data is generated, in part, by control data and location data from a prior vehicle that traversed the segment;
determining, from the annotated virtual track data, a location identified as having a hazard that influences behavior of other vehicles traveling the segment;
obtaining sensor data from onboard sensors that monitor the environment surrounding the autonomous vehicle; and
controlling the autonomous vehicle to traverse across the segment based at least in part on the sensor data from the onboard sensors and the annotated virtual track data.

17. The method as recited in claim 16 , further comprising:
receiving sensor control data associated with the annotated virtual track data; and
causing the onboard sensors to capture the sensor data based at least in part on the sensor control data associated with the annotated virtual track data.

18. The method as recited in claim 16 , further comprising:
accessing at least one of user preference data or vehicle performance data associated with the autonomous vehicle, and
wherein th

Assignees

• Amazon Tech Inc

Inventors

• Canavor Darren Ernest
• Cartwright Charles Edward
• Kimchi Gur
• Porter Brandon William

Classifications

• G08G1/096716

  where the received information does not generate an automatic action on the vehicle control · CPC title

• G08G1/0112

  from the vehicle, e.g. floating car data [FCD] · CPC title

• G08G1/165

  for passive traffic, e.g. including static obstacles, trees · CPC title

• G08G1/096775

  where the origin of the information is a central station · CPC title

• G08G1/166

  for active traffic, e.g. moving vehicles, pedestrians, bikes · CPC title