Road segment similarity determination

Patent metadata

Field	Value
Publication number	US-11858503-B2
Application number	US-202117374654-A
Country	US
Kind code	B2
Filing date	Jul 13, 2021
Priority date	Aug 17, 2018
Publication date	Jan 2, 2024
Grant date	Jan 2, 2024

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:
determining, by a computing system, one or more scenarios associated with a road segment based on sensor data captured by one or more vehicles;
determining, by the computing system, a threshold similarity between the road segment and a road segment type based on the one or more scenarios associated with the road segment matching a threshold number of scenarios included in a scenario type associated with the road segment type, wherein the matching is determined based on a multi-level scenarios taxonomy that classifies a plurality of scenario types with respective scenarios, wherein a first level of the multi-level scenarios taxonomy includes a set of the scenarios included in the scenario type and a second level of the multi-level scenarios taxonomy includes a subset of the set of the scenarios;
classifying, by the computing system, the road segment as the road segment type based on the threshold similarity;
providing, by the computing system, information describing the classified road segment and the scenario type to a computing device of a vehicle; and
causing, by the computing system, control of an operation of the vehicle based on the information.

2. The computer-implemented method of claim 1 , wherein the first level of the multi-level scenarios taxonomy provides a higher level of generality than the second level of the multi-level scenarios taxonomy.

3. The computer-implemented method of claim 1 , wherein determining the one or more scenarios associated with the road segment based on sensor data captured by the one or more vehicles comprises:
determining, by the computing system, a set of features associated with the road segment based at least in part on the sensor data; and
determining, by the computing system, the one or more scenarios based on a comparison of the set of features associated with the road segment and respective features associated with the one or more scenarios.

4. The computer-implemented method of claim 1 , further comprising:
determining, by the computing system, a risk profile associated with the classified road segment based on the threshold similarity between the classified road segment and the road segment type, wherein the risk profile provides respective exposure rates for the scenarios included in the scenario type associated with the road segment type.

5. The computer-implemented method of claim 1 , wherein the information is provided to the computing device of the vehicle to navigate the classified road segment.

6. The computer-implemented method of claim 5 , wherein, when the vehicle is associated with the classified road segment, the computing device associated with the vehicle is configured to generate vehicle operation instructions based on the provided information to navigate the classified road segment.

7. The computer-implemented method of claim 1 , further comprising:
logging, by the computing system, an association between the classified road segment, the road segment type, and the scenario type in a scenario information database.

8. The computer-implemented method of claim 1 , further comprising:
determining, by the computing system, a geographic region that includes the classified road segment;
determining, by the computing system, a plurality of road segment types associated with the geographic region, the plurality of road segment types including the road segment type; and
determining, by the computing system, a threshold similarity between the geographic region and a different geographic region based on a comparison of the plurality of road segment types associated with the geographic region and a plurality of road segment types associated with the different geographic region.

9. The computer-implemented method of claim 8 , further comprising:
determining, by the computing system, scenario information associated with the geographic region based on the threshold similarity between the geographic region and the different geographic region.

10. The computer-implemented method of claim 8 , further comprising:
determining, by the computing system, a collective risk profile associated with the geographic region based on the threshold similarity between the geographic region and the different geographic region, wherein the collective risk profile provides respective exposure rates for scenarios associated with the different geographic region.

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:
determining one or more scenarios associated with a road segment based on sensor data captured by one or more vehicles;
determining a threshold similarity between the road segment and a road segment type based on the one or more scenarios associated with the road segment matching a threshold number of scenarios included in a scenario type associated with the road segment type, wherein the matching is determined based on a multi-level scenarios taxonomy that classifies a plurality of scenario types with respective scenarios, wherein a first level of the multi-level scenarios taxonomy includes a set of the scenarios included in the scenario type and a second level of the multi-level scenarios taxonomy includes a subset of the set of the scenarios;
classifying the road segment as the road segment type based on the threshold similarity;
providing information describing the classified road segment and the scenario type to a computing device of a vehicle; and
causing control of an operation of the vehicle based on the information.

12. The system of claim 11 , wherein the first level of the multi-level scenarios taxonomy provides a higher level of generality than the second level of the multi-level scenarios taxonomy.

13. The system of claim 11 , wherein determining the one or more scenarios associated with the road segment based on sensor data captured by the one or more vehicles causes the system to perform:
determining, by the computing system, a set of features associated with the road segment based at least in part on the sensor data; and
determining, by the computing system, the one or more scenarios based on a comparison of the set of features associated with the road segment and respective features associated with the one or more scenarios.

14. The system of claim 11 , wherein the instructions further cause the system to perform:
determining, by the computing system, a risk profile associated with the classified road segment based on the threshold similarity between the classified road segment and the road segment type, wherein the risk profile provides respective exposure rates for the scenarios included in the scenario type associated with the road segment type.

15. The system of claim 11 , wherein the information is provided to the computing device of the vehicle to navigate the classified road segment.

16. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:
determining one or more scenarios associated with a road segment based on sensor data captured by one or more vehicles;
determining a threshold similarity between the road segment and a road segment type based on the one or more scenarios associated with the road segment matching a threshold number of scenarios included in a scenario type associated with the road segment type, wherein the matching is determined based on a multi-level scenarios taxonomy that c

Assignees

• Lyft Inc

Inventors

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

Classifications

• B60W30/095 Primary

  Predicting travel path or likelihood of collision · CPC title

• B60W30/09

  Taking automatic action to avoid collision, e.g. braking and steering · CPC title

• B60W40/06 Primary

  Road conditions · CPC title

• B60W10/04

  including control of propulsion units · CPC title

• B60W10/18

  including control of braking systems · CPC title