Autonomous vehicle routing using annotated maps

Patent metadata

Field	Value
Publication number	US-10416677-B2
Application number	US-201715812606-A
Country	US
Kind code	B2
Filing date	Nov 14, 2017
Priority date	Nov 14, 2017
Publication date	Sep 17, 2019
Grant date	Sep 17, 2019

Abstract

A system and method for autonomous vehicle routing using annotated maps. For at least some path segments within a geographic region in which the vehicle is operating, values are determined for the path segments based at least on risk factors associated with autonomous operation of the vehicle along each path segment. Path segments are combined to generate a travel route, from a first location to a second location, based on the determined values, and the vehicle is controlled to navigate along the travel route.

First claim

What is claimed is:

1. A system for controlling navigation of a vehicle, comprising:
one or more processors; and
one or more memory resources storing instructions that, when executed by the one or more processors, cause the system to:
for a set of path segments within a geographic region in which the vehicle is operating, determine a risk value for each respective path segment of the set of path segments based on a plurality of risk factors associated with autonomous operation of the vehicle along the respective path segment;
based on the determined risk value for each respective path segment of the set of path segments, combine a plurality of path segments from the set of path segments to generate a travel route for the vehicle from a first location to a second location; and
autonomously control the vehicle to navigate along the travel route;
wherein the determined risk value for each respective path segment of the set of path segments represents a cost layer in a corresponding map utilized by the vehicle for autonomous operation along the respective path segment, and wherein the system generates the travel route based on a sum of the determined risk values for the plurality of path segments.

2. The system of claim 1 , wherein determination of the values for each respective path segment comprises using a weighted sum of (1) scores for each of the plurality of risk factors for the respective path segment, and (2) a travel time calculation for the respective path segment.

3. The system of claim 2 , wherein the scores for each of the plurality of risk factors represent probabilities that an undesirable event may occur during autonomous operation of the vehicle along the respective path segment.

4. The system of claim 2 , wherein the scores for each of the plurality of risk factors and the travel time calculation are determined by a statistical model.

5. The system of claim 4 , wherein the statistical model determines the scores for each of the plurality of risk factors based, at least in part, on sensor data collected from a plurality of sensors coupled to the vehicle and from other vehicles operating throughout the geographic region.

6. The system of claim 5 , wherein the executed instructions further cause the system to:
analyze the sensor data to identify events that impact one or more of the plurality of risk factors.

7. The system of claim 5 , wherein the executed instructions further cause the system to:
determine, from the sensor data, one or more road conditions for a current path segment that affect one or more of the plurality of risk factors; and
autonomously control the vehicle to navigate along an alternate path segment based on a determined risk value for the current path segment.

8. The system of claim 1 , wherein the executed instructions further cause the system to:
receive, over one or more networks, a transport request for a user, the transport request indicating a pick-up location and a destination; and
use the pick-up location as the first location and the destination as the second location.

9. The system of claim 1 , wherein the set of path segments correspond to lanes of roads identified in a set of localization maps for the geographic region.

10. The system of claim 1 , wherein the plurality of risk factors comprise an intervention risk, including when the vehicle is incapable of autonomous operation along a given path segment; a bad experience risk, including hard stops, jerking motions, and other events that impact a passenger experience; and a harmful event risk, including a collision involving the vehicle.

11. The system of claim 1 , wherein the system comprises a component of the vehicle.

12. A method of controlling navigation of a vehicle, the method being implemented by one or more processors and comprising:
for a set of path segments within a geographic region in which the vehicle is operating, determining a risk value for each respective path segment of the set of path segments based on a plurality of risk factors associated with autonomous operation of the vehicle along the respective path segment;
based on the determined risk value for each respective path segment of the set of path segments, combining a plurality of path segments from the set of path segments to generate a travel route for the vehicle from a first location to a second location; and
autonomously controlling the vehicle to navigate along the travel route;
wherein the determined risk value for each respective path segment of the set of path segments represents a cost layer in a corresponding map utilized by the vehicle for autonomous operation along the respective path segment, and wherein the one or more processors generate the travel route based on a sum of the determined risk values for the plurality of path segments.

13. The method of claim 12 , wherein the one or more processors determine the risk value for each respective path segment of the set of path segments using a weighted sum of (1) scores for each of the plurality of risk factors for the respective path segment and, (2) a travel time calculation for the respective path segment.

14. The method of claim 13 , wherein the scores for each of the plurality of risk factors represent probabilities that an undesirable event may occur during autonomous operation of the vehicle along the respective path segment.

15. The method of claim 13 , wherein the scores for each of the plurality of risk factors and the travel time calculation are determined by a statistical model.

16. The method of claim 15 , wherein the statistical model determines the scores for each of the plurality of risk factors based, at least in part, on sensor data collected from a plurality of sensors coupled to the vehicle and from other vehicles operating throughout the geographic region.

17. The method of claim 16 , further comprising:
analyzing the sensor data to identify events that impact one or more of the plurality of risk factors.

18. The method of claim 16 , further comprising:
determining, from the sensor data, one or more road conditions for a current path segment that affect one or more of the plurality of risk factors; and
autonomously controlling the vehicle to navigate along an alternate path segment based on a determined risk value for the current path segment.

19. A vehicle comprising:
a plurality of sensors that generate sensor data to determine a plurality of risk factors associated with autonomous operation of the vehicle;
one or more processors; and
one or more memory resources storing instructions that, when executed by the one or more processors, cause the vehicle to:
for a set of path segments within a geographic region in which the vehicle is operating, determine a risk value for each respective path segment of the set of path segments based on a plurality of risk factors associated with autonomous operation of the vehicle along the respective path segment;
based on the determined risk value for each respective path segment of the set of path segments, combine a plurality of the path segments to generate a travel route for the vehicle from a first location to a second location; and
autonomously control the vehicle to navigate along the travel route;
wherein the determined risk value for each respective path segment of the set of path segments represents a cost layer in a corresponding map utilized by the vehicle for autonomous operation along the respective path segment, and wherein the vehicle generates the travel route based on a sum of the determined risk values for

Assignees

• Uber Technologies Inc

Inventors

• Dean Robert
• Nagy Bryan
• Stentz Anthony
• Bavar Brett
• Zhang Xiaodong
• Panzica Adam

Classifications

• G01C21/3461 Primary

  Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types or segments such as motorways, toll roads or ferries · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N3/08

  Learning methods · CPC title

• G06N20/00

  Machine learning · CPC title

• G01C21/3492

  employing speed data or traffic data, e.g. real-time or historical (traffic control systems for road vehicles involving transmission of navigation instructions to the vehicle G08G1/0968) · CPC title