Road segment similarity determination

Patent metadata

Field	Value
Publication number	US-11091156-B2
Application number	US-201916681683-A
Country	US
Kind code	B2
Filing date	Nov 12, 2019
Priority date	Aug 17, 2018
Publication date	Aug 17, 2021
Grant date	Aug 17, 2021

Abstract

Systems, methods, and non-transitory computer-readable media can determine a road segment. A set of features associated with the road segment can be determined based at least in part on data captured by one or more sensors of a vehicle. A level of similarity between the road segment and each of a set of road segment types can be determined by comparing the set of features to features associated with each of the set of road segment types. The road segment can be classified as a road segment type based on the level of similarity. Scenario information associated with the road segment can be determined based on the classified road segment type.

First claim

What is claimed is:

1. A computer-implemented method comprising:
obtaining, by a computing system, sensor data captured by one or more sensors of one or more vehicles while navigating a plurality of road segments in a geographic region;
determining, by the computing system, features associated with the plurality of road segments in the geographic region based at least in part on the sensor data captured by the one or more sensors of the one or more vehicles;
generating, by the computing system, a value of an aggregate risk for at least one vehicle to operate in the geographic region based at least in part on the features associated with the plurality of road segments;
determining, by the computing system, that the value of the aggregate risk satisfies a threshold value for operating the at least one vehicle in the geographic region;
determining, by the computing system, a level of similarity between the geographic region and a particular geographic region by comparing the features associated with the plurality of road segments in the geographic region to features associated with a plurality of road segments in the particular geographic region; and
providing, by the computing system, an instruction associated with the operation of the at least one vehicle in the particular geographic region based at least in part on the level of similarity between the geographic region and the particular geographic region.

2. The computer-implemented method of claim 1 , wherein generating the value of the aggregate risk further comprises:
determining, by the computing system, a first value relating to the one or more vehicles being exposed to at least one scenario type in the geographic region;
determining, by the computing system, a second value relating to an efficacy of at least one driving system associated with the one or more vehicles in view of the at least one scenario type;
determining, by the computing system, a third value relating to a severity of an adverse outcome involving the one or more vehicles in the geographic region; and
determining, by the computing system, the value of the aggregate risk based at least in part on the first value relating to the one or more vehicles being exposed to the at least one scenario type in the geographic region, the second value relating to the efficacy of the at least one driving system associated with the one or more vehicles in view of the at least one scenario type, and the third value relating to the severity of an adverse outcome involving the one or more vehicles in the geographic region.

3. The computer-implemented method of claim 2 , wherein determining the first value relating to the one or more vehicles being exposed to the at least one scenario type further comprises:
determining, by the computing system, at least one aggregate scenario exposure rate for the plurality of road segments indicating a probability of the at least one scenario type occurring on the plurality of road segments.

4. The computer-implemented method of claim 2 , wherein the at least one driving system corresponds to an autonomous, semi-autonomous, or manually-driven system.

5. The computer-implemented method of claim 2 , wherein determining the second value relating to the efficacy of the at least one driving system associated with the one or more vehicles in view of the at least one scenario type further comprises:
determining, by the computing system, a probability of the one or more vehicles experiencing an interaction when exposed to the at least one scenario type in the geographic region.

6. The computer-implemented method of claim 5 , wherein determining the probability of the one or more vehicles experiencing the interaction when exposed to the at least one scenario type in the geographic region further comprises:
evaluating, by the computing system, at least one simulation involving a simulated vehicle with one or more real-world scenarios associated with the at least one scenario type that are encountered by the one or more vehicles while navigating the plurality of road segments in the geographic region.

7. The computer-implemented method of claim 5 , wherein determining the probability of the one or more vehicles experiencing the interaction when exposed to the at least one scenario type in the geographic region further comprises:
obtaining, by the computing system, logged sensor data associated with at least one real-world scenario corresponding to the at least one scenario type as encountered by a test vehicle operating in a test facility; and
evaluating, by the computing system, at least one simulation involving a simulated vehicle based at least in part on the logged sensor data.

8. The computer-implemented method of claim 5 , wherein determining the probability of the one or more vehicles experiencing the interaction when exposed to the at least one scenario type in the geographic region further comprises:
evaluating, by the computing system, a simulation of one or more simulated vehicles operating within a simulated world including one or more programmatically generated scenario instances.

9. The computer-implemented method of claim 2 , wherein the third value relating to a severity of an adverse outcome involving the one or more vehicles while navigating the plurality of road segments in the geographic region is based on one or more simulated collisions involving a simulated vehicle navigating the plurality of road segments in the geographic region.

10. The computer-implemented method of claim 9 , wherein the one or more simulated collisions are associated with a set of collision parameters that measure property damage or human injury.

11. A system comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
obtaining sensor data captured by one or more sensors of one or more vehicles while navigating a plurality of road segments in a geographic region;
determining features associated with the plurality of road segments in the geographic region based at least in part on the sensor data captured by the one or more sensors of the one or more vehicles;
generating a value of an aggregate risk for at least one vehicle to operate in the geographic region based at least in part on the features associated with the plurality of road segments;
determining that the value of the aggregate risk satisfies a threshold value for operating the at least one vehicle in the geographic region;
determining a level of similarity between the geographic region and a particular geographic region by comparing the features associated with the plurality of road segments in the geographic region to features associated with a plurality of road segments in the particular geographic region; and
providing an instruction associated with the operation of the at least one vehicle in the particular geographic region based at least in part on the level of similarity between the geographic region and the particular geographic region.

12. The system of claim 11 , wherein generating the value of the aggregate risk further comprises:
determining a first value relating to the one or more vehicles being exposed to at least one scenario type in the geographic region;
determining a second value relating to an efficacy of at least one driving system associated with the one or more vehicles in view of the at least one scenario type;
determining a third value relating to a severity of an adverse outcome involving the one or more vehicles in the geographic region; and
determining the value of the aggregate risk based at least in part on the first value relating to the one or mor

Assignees

• Lyft Inc

Inventors

• Haque Asif
• Huyler Mark Douglas
• Joyce Gerard
• Liu Ying
• Lu David Tse-Zhou
• Qureshi Sameer
• Shet Vinay

Classifications

• G01C21/28 Primary

  with correlation of data from several navigational instruments · CPC title

• B60Y2400/30

  Sensors · CPC title

• B60Y2300/14

  Cruise control · CPC title

• B60W2420/54

  Audio sensitive means, e.g. ultrasound · CPC title

• B60W2420/40

  Photo, light or radio wave sensitive means, e.g. infrared sensors · CPC title