US-12623693-B2 - Determining dynamic route data

US12623693B2US 12623693 B2US12623693 B2US 12623693B2US-12623693-B2

Abstract

Techniques for enabling dynamic routing are described herein. A vehicle may receive a destination and generate a path to the destination. Further, the vehicle may generate a local graph that includes one or more driving lanes. The vehicle may use the path and the local graph to determine overlap data indicative of a distance that the path overlaps with the driving lane(s). The vehicle may utilize the overlap data to determine a color value(s) to associate with the driving lane(s) in a top-down image. Accordingly, based on determining the color value(s), the vehicle may generate colored top-down image(s) of the driving lane(s) and use such data to control the vehicle.

Inventors

Yan Chang
Philip Charles Dasler
Aaron Huang
Sutej Pramod KULGOD
Swapnil Vikas Mankar
Mark Jonathon McClelland
Arjun Sharma

Assignees

Zoox, Inc.

Dates

Publication Date: 20260512
Application Date: 20240329

Claims (20)

1 . A system comprising: one or more processors; and one or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause the system to perform operations comprising: receiving a destination associated with an environment; determining a path for an autonomous vehicle to follow to the destination; determining a plurality of road segments associated with a region of the environment within a threshold distance of the autonomous vehicle, wherein a road segment of the plurality of road segments includes a first driving lane; determining an amount of overlap between the path and the first driving lane; determining, based at least in part on data associated with the first driving lane, a cost associated with navigating the first driving lane to the destination; determining, based at least in part on the amount of overlap and the cost, a value to associate with a first top-down representation of the first driving lane; generating the first top-down representation of the first driving lane comprising the value along the first driving lane; determining a second top-down representation of a second driving lane, wherein the second top-down representation is independent from the first top-down representation; and controlling a steering system of the autonomous vehicle based at least in part on the first top-down representation of the first driving lane and the second top-down representation of the second driving lane.
2 . The system of claim 1 , wherein determining the second top-down representation is based at least in part on determining a second value to associate with the second driving lane; and determining, based at least in part on the second value, the second top-down representation of the second driving lane.
3 . The system of claim 1 , wherein the road segment comprises a third driving lane, the operations further comprising: determining a second value to associate with the third driving lane; determining, based at least in part on the second value, a third top-down representation of the third driving lane; combining the first top-down representation and the third top-down representation into a single top-down representation; and controlling the autonomous vehicle based at least in part on the single top-down representation.
4 . The system of claim 1 , the operations further comprising: determining, for a first type of metric, a first score; determining, for a second type of metric that is different than the first type, a second score; determining a second value associated with the first score and a third value associated with the second score; determining, based at least in part on the second value, a third top-down representation of the first driving lane associated with the first type of metric; determining, based at least in part on the third value, a fourth top-down representation of the first driving lane associated with the second type of metric, the third top-down representation being independent from the fourth top-down representation; and controlling the autonomous vehicle based at least in part on the third top-down representation and the fourth top-down representation.
5 . The system of claim 1 , wherein determining the amount of overlap is based at least in part on: determining a distance that the path and the first driving lane overlap; determining, based at least in part on a position of the autonomous vehicle, a modified distance; and causing the modified distance to be the amount of overlap.
6 . One or more non transitory computer readable media storing instructions executable by one or more processors, wherein the instructions, when executed, cause a system to perform operations comprising: determining a path for an autonomous vehicle to follow to a destination; determining a graph comprising a road segment that includes a first driving lane; determining a degree of overlap between the path and the first driving lane; determining, based at least in part on the degree of overlap, a value to associate with a first representation of the first driving lane; determining, based at least in part on the value, the first representation of the first driving lane; determining a second representation of a second driving lane, wherein the second representation is independent form the first representation; and controlling a steering system of the autonomous vehicle based at least in part on the first representation and the second representation.
7 . The one or more non transitory computer readable media of claim 6 , wherein determining the second representation is based at least in part on: determining a second value to associate with the second driving lane; and determining, based at least in part on the second value, the second representation of the second driving lane.
8 . The one or more non transitory computer readable media of claim 6 , the operations further comprising: determining a second value to associate with the second driving lane; determining, based at least in part on the second value, a third representation of the second driving lane; combining the first representation and the third representation into a single representation; and controlling the autonomous vehicle based at least in part on the single representation.
9 . The one or more non transitory computer readable media of claim 6 , the operations further comprising: determining, for a first type of metric, a first score; determining, for a second type of metric that is different than the first type, a second score; determining a second value associated with the first score and a third value associated with the second score; determining, based at least in part on the second value, a third representation of the first driving lane associated with the first type of metric; determining, based at least in part on the third value, a fourth representation of the first driving lane associated with the second type of metric, the third representation being independent from the fourth representation; and controlling the autonomous vehicle based at least in part on the third representation and the fourth representation.
10 . The one or more non transitory computer readable media of claim 6 , wherein determining the degree of overlap is based at least in part on: determining a distance that the path and the first driving lane overlap; determining, based at least in part on a position of the autonomous vehicle, a modified distance; and causing the modified distance to be the degree of overlap.
11 . The one or more non transitory computer readable media of claim 6 , wherein determining the value is based at least in part on: determining a cost associated with navigating the first driving lane to the destination, wherein the cost is determined based at least in part on at least one of: a speed limit associated with the first driving lane, or a distance between the autonomous vehicle and the destination.
12 . The one or more non transitory computer readable media of claim 6 , wherein the road segment includes multiple driving lanes, and wherein determining the value is based at least in part on: determining overlap values for the multiple driving lanes; determining, based at least in part on the overlap values, a ranking of the multiple driving lanes; determining, based at least in part on the ranking, a subset of the multiple driving lanes that meet or exceed a threshold; and determining, based at least in part on the first driving lane being in the subset, the value associated with the first driving lane.
13 . The system of claim 1 , wherein the road segment includes multiple driving lanes, and wherein determining the value is based at least in part on: determining overlap values for the multiple driving lanes; determining, based at least in part on the overlap values, a ranking of the multiple driving lanes; determining, based at least in part on the ranking, a subset of the multiple driving lanes that meet or exceed a threshold; and determining, based at least in part on the first driving lane being in the subset, the value associated with the first driving lane.
14 . A method comprising: determining a path for an autonomous vehicle to follow to a destination; determining a graph comprising a road segment that includes a first driving lane; determining a degree of overlap between the path and the first driving lane; determining, based at least in part on the degree of overlap, a value to associate with a first representation of the first driving lane; determining, based at least in part on the value, the first representation of the first driving lane; determining a second representation of a second driving lane, wherein the second representation is independent form the first representation; and controlling a steering system of the autonomous vehicle based at least in part on the first representation and the second representation.
15 . The method of claim 14 , wherein determining the second representation is based at least in part on: determining a second value to associate with the second driving lane; and determining, based at least in part on the second value, the second representation of the second driving lane.
16 . The method of claim 14 , further comprising: determining a second value to associate with the second driving lane; determining, based at least in part on the second value, a third representation of the second driving lane; combining the first representation and the third representation into a single representation; and controlling the autonomous vehicle based at least in part on the single representation.
17 . The method of claim 14 , further comprising: determining, for a first type of metric, a first score; determining, for a second type of metric that is different than the first type, a second score; determining a second value associated with the first score and a third value associated with the second score; determining, based at least in part on the second value, a third representation of the first driving lane associated with the first type of metric; determining, based at least in part on the third value, a fourth representation of the first driving lane associated with the second type of metric, the third representation being independent from the fourth representation; and controlling the autonomous vehicle based at least in part on the third representation and the fourth representation.
18 . The method of claim 14 , wherein determining the degree of overlap is based at least in part on: determining a distance that the path and the first driving lane overlap; determining, based at least in part on a position of the autonomous vehicle, a modified distance; and causing the modified distance to be the degree of overlap.
19 . The method of claim 14 , wherein determining the value is based at least in part on: determining a cost associated with navigating the first driving lane to the destination, wherein the cost is determined based at least in part on at least one of: a speed limit associated with the first driving lane, or a distance between the autonomous vehicle and the destination.
20 . The method of claim 14 , wherein the road segment includes multiple driving lanes, and wherein determining the value is based at least in part on: determining overlap values for the multiple driving lanes; determining, based at least in part on the overlap values, a ranking of the multiple driving lanes; determining, based at least in part on the ranking, a subset of the multiple driving lanes that meet or exceed a threshold; and determining, based at least in part on the first driving lane being in the subset, the value associated with the first driving lane.

Description

BACKGROUND Vehicles, such as autonomous vehicles, may navigate along a designated route. In some examples, autonomous vehicles may encounter various types of static and/or dynamic objects as well as traffic, construction zones, and the like. Upon detecting such occurrences, the vehicle may determine an updated route that leads the vehicle along different driving lanes and/or road segments that what was included in the original route. However, in certain circumstances, techniques for determining an updated route and/or controlling the vehicle based on the updated route may result in system failures or such systems outputting inaccurate or insufficient data. BRIEF DESCRIPTION OF THE DRAWINGS The detailed description is described with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The use of the same reference numbers in different figures indicates similar or identical components or features. FIG. 1 is a pictorial flow diagram illustrating an example technique for determining and/or utilizing routing data, in accordance with one or more examples of the disclosure. FIG. 2 illustrates an example computing system including a dynamic routing component configured to generate colored top-down representation(s) of candidate routes which may be used to control a vehicle, in accordance with one or more examples of the disclosure. FIG. 3 depicts an example environment that includes multiple driving lanes and/or a table with data representative of overlap and/or cost data associated with the multiple driving lanes, in accordance with one or more examples of the disclosure. FIG. 4 illustrates determining multiple top-down representations each of which being associated with a single driving lane, in accordance with one or more examples of the disclosure. FIG. 5 illustrates determining a single top-down representation that includes multiple driving lanes therein, in accordance with one or more examples of the disclosure. FIG. 6 illustrates determining multiple top-down representations each of which associated with a type of scoring metric and including multiple driving lanes, in accordance with one or more examples of the disclosure. FIG. 7 depicts a block diagram of an example system for implementing various techniques described herein. FIG. 8 is a flow diagram illustrating an example process for determining a path to a destination, determining a graph that includes a driving lane, determining an overlap between the path and the driving lane in the graph, determining a color based on the overlap, determining a colored top-down representation of the driving lane based on the color, and controlling the vehicle based on the colored top-down representation of the driving lane, in accordance with one or more examples of the disclosure. DETAILED DESCRIPTION Techniques for generating vehicle routing data are described herein. As discussed below, colored top-down representation(s) of driving lanes and/or candidate routes may be used in prediction and/or planning systems to control a vehicle. In some examples, a vehicle (such as an autonomous vehicle) may receive a destination representing a location to which the vehicle is to navigate. The vehicle may generate a path (e.g., a spatial representation of a route to the destination, covers one or more laterally adjacent driving lanes, etc.) to the destination. Additionally, the vehicle may generate a local graph (e.g., extends a portion of the distance from the vehicle to the destination) that includes one or more driving lanes. Based on generating the path and the local graph, the vehicle may determine overlap data indicative of a distance that the path overlaps with the driving lane(s) in the local graph. The vehicle may utilize the overlap data to determine value(s) to associate with the driving lane(s) which may, throughout the disclosure, be represented and discusses as a “color.” Accordingly, based on determining the color value(s), the vehicle may generate colored image(s) (which may, in some examples, include top-down perspective images) of the driving lane(s) and use such data to control the vehicle. As non-limiting examples, such images may be input into machine learned models to determine trajectories, perform reinforcement learning, determine costs (including learned costs), and the like for controlling a vehicle. As described in more detail below, the techniques described herein may improve vehicle safety and driving efficiency by enabling dynamic routing and increasing the ability to send the vehicle accurate representations of various candidate driving lanes and/or routes proximate the vehicle, thereby allowing the vehicle to perform safter and more efficient driving maneuvers. When instructing a vehicle through an environment, it may be beneficial to ensure that vehicle systems can receive, process, and/or output data consistent with dynamic routing.