Mapping and determining scenarios for geographic regions

Patent metadata

Field	Value
Publication number	US-11788846-B2
Application number	US-201916588729-A
Country	US
Kind code	B2
Filing date	Sep 30, 2019
Priority date	Sep 30, 2019
Publication date	Oct 17, 2023
Grant date	Oct 17, 2023

Abstract

Systems, methods, and non-transitory computer-readable media can determine sensor data captured by at least one sensor of a vehicle while navigating a road segment. A plurality of features describing the road segment can be extracted from the sensor data. A map representation of the road segment can be determined based at least in part on the sensor data and the plurality of features extracted from the sensor data, the map representation being determined as the vehicle navigates the road segment. While the map representation of the road segment is being determined, at least one scenario associated with the road segment can be determined based at least in part on the map representation and the plurality of features extracted from the sensor data.

First claim

What is claimed is:

1. A computer-implemented method comprising:
determining, by a computing system, sensor data captured by at least one sensor of a vehicle while navigating a road segment that is unmapped;
extracting, by the computing system, a plurality of features describing the road segment that is unmapped from the sensor data;
generating, by the computing system, a map of the road segment based at least in part on (i) the sensor data captured by the at least one sensor of the vehicle and (ii) the plurality of features describing the road segment extracted from the sensor data, wherein the generated map includes at least one label that identifies at least one of the plurality of features extracted from the sensor data captured by the at least one sensor of the vehicle while navigating the road segment;
determining, by the computing system, predetermined scenarios for the road segment based at least in part on the plurality of features describing the road segment;
subsequent to generating the map of the road segment, determining, by the computing system, a control of the vehicle using at least one scenario of the predetermined scenarios determined based at least in part on (i) the map being generated of the road segment and (ii) a determination that the plurality of features describing the road segment extracted from the sensor data that indicate a presence of a dynamic object, a static object, and an interaction between the dynamic object and the static object at the road segment satisfy a threshold number of features associated with the at least one scenario of the predetermined scenarios, wherein the control of the vehicle relative to the road segment is based at least in part on the plurality of features satisfying the threshold number of features; and
providing, by the computing system, the map of the road segment and the predetermined scenarios determined for the road segment for application to a fleet of vehicles.

2. The computer-implemented method of claim 1 , wherein extracting the plurality of features describing the road segment from the sensor data further comprises:
determining, by the computing system, map features describing the road segment from the sensor data;
determining, by the computing system, static objects detected on or along the road segment from the sensor data; and
determining, by the computing system, dynamic objects detected on or along the road segment from the sensor data.

3. The computer-implemented method of claim 2 , wherein the map features include at least one of: a road segment length, a road segment quality, a roadway type, information describing traffic lanes in the road segment, information describing a presence of one or more bike lanes, information describing a presence of one or more crosswalks, and a zone in which the road segment is geographically located.

4. The computer-implemented method of claim 1 , wherein the predetermined scenarios for the road segment are determined by a machine learning model.

5. The computer-implemented method of claim 1 , the method further comprising:
providing, by the computing system, information describing the map and the at least one scenario to a transportation management system, wherein the transportation management system applies the information when routing the fleet of vehicles that offer transportation services.

6. The computer-implemented method of claim 5 , wherein information describing the at least one scenario includes an identification code referencing the at least one scenario, and wherein the transportation management system interprets the identification code to recognize the at least one scenario.

7. The computer-implemented method of claim 1 , wherein the at least one sensor corresponds to an optical camera and the sensor data includes a set of images captured by the optical camera over a period of time during which the vehicle navigated the road segment.

8. The computer-implemented method of claim 1 , wherein the at least one sensor corresponds to an optical camera associated with a mobile device and the sensor data includes a set of images captured by the optical camera associated with the mobile device over a period of time during which the vehicle navigated the road segment.

9. The computer-implemented method of claim 1 , wherein the at least one sensor corresponds to a Light Detection And Ranging (LiDAR) system and the sensor data includes a set of point clouds captured by the LiDAR system over a period of time during which the vehicle navigated the road segment.

10. The computer-implemented method of claim 1 , wherein the at least one sensor corresponds to a radar system and the sensor data includes a set of radar data captured by the radar system over a period of time during which the vehicle navigated the road segment.

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 sensor data captured by at least one sensor of a vehicle while navigating a road segment that is unmapped;
extracting a plurality of features describing the road segment that is unmapped from the sensor data;
generating a map of the road segment based at least in part on (i) the sensor data captured by the at least one sensor of the vehicle and (ii) the plurality of features describing the road segment extracted from the sensor data, wherein the generated map includes at least one label that identifies at least one of the plurality of features extracted from the sensor data captured by the at least one sensor of the vehicle while navigating the road segment;
determining predetermined scenarios for the road segment based at least in part on the plurality of features describing the road segment;
subsequent to generating the map of the road segment, determining a control of the vehicle using at least one scenario of the predetermined scenarios determined based at least in part on (i) the map being generated of the road segment and (ii) a determination that the plurality of features describing the road segment extracted from the sensor data that a indicate presence of a dynamic object, a static object, and an interaction between the dynamic object and the static object at the road segment satisfy a threshold number of features associated with the at least one scenario of the predetermined scenarios, wherein the control of the vehicle relative to the road segment is based at least in part on the plurality of features satisfying the threshold number of features; and
providing the map of the road segment and the predetermined scenarios determined for the road segment for application to a fleet of vehicles.

12. The system of claim 11 , wherein extracting the plurality of features describing the road segment from the sensor data further causes the system to perform:
determining map features describing the road segment from the sensor data;
determining static objects detected on or along the road segment from the sensor data; and
determining dynamic objects detected on or along the road segment from the sensor data.

13. The system of claim 12 , wherein the map features include at least one of: a road segment length, a road segment quality, a roadway type, information describing traffic lanes in the road segment, information describing a presence of one or more bike lanes, information describing a presence of one or more crosswalks, and a zone in which the road segment is geographically located.

14. The system of claim 11 , wherein the predetermined scenarios for the road segment are determined by a machine learning model.

Assignees

• Lyft Inc

Inventors

• Lu David Tse-Zhou
• Haque Asif

Classifications

• G01C21/32 Primary

  Structuring or formatting of map data · CPC title

• G05D1/0231

  using optical position detecting means (position-fixing by using electromagnetic waves other than radio waves, e.g. optical position detecting means G01S5/16) · CPC title

• G05D1/0257

  using a radar (radar systems designed for anti-collision purposes between land vehicles or between land vehicle and fixed obstacles G01S13/931) · CPC title

• G05D1/0291

  Fleet control (monitoring fleets in traffic control systems for road vehicles G08G1/127, G08G1/127) · CPC title

• G06Q50/30

  Physics · mapped topic