Localizing vehicles using retroreflective surfaces

Patent metadata

Field	Value
Publication number	US-12566069-B2
Application number	US-202318448846-A
Country	US
Kind code	B2
Filing date	Aug 11, 2023
Priority date	Aug 11, 2023
Publication date	Mar 3, 2026
Grant date	Mar 3, 2026

Abstract

A method comprises receiving a first set of data associated with a plurality of retroreflective features from a vehicle; retrieving a digital map comprising vectorized data associated with the plurality of retroreflective features and a location associated with the plurality of retroreflective features, the map previously generated based on monitoring a second set of data retrieved from a sensor of a second vehicle where the second set of data is associated with the plurality of retroreflective features near a road being driven by the second vehicle; generating a score for each retroreflective feature indicating a match between each retroreflective feature as indicated within the digital map and a location of each retroreflective feature as identified within the first set of data; and localizing the vehicle.

First claim

What is claimed is:

1 . A method comprising:
receiving, by a processor, a first set of data associated with a plurality of retroreflective features from a first vehicle; retrieving, by the processor, a digital map comprising vectorized data associated with the plurality of retroreflective features and a location associated with the plurality of retroreflective features, the digital map previously generated based on monitoring a second set of data retrieved from a sensor of a second vehicle where the second set of data is associated with the plurality of retroreflective features near a road being driven by the second vehicle; iteratively forming, by the processor, a consensus of observations of the plurality of retroreflective features by determining a correction vector between the observations and corresponding estimation points of the observations; generating, by the processor, a score for each retroreflective feature indicating a match between a consensus of each retroreflective feature as indicated within the digital map and a location of each retroreflective feature as identified within the first set of data; localizing, by the processor, the first vehicle; and controlling, by the processor, operation of the first vehicle, based on localization of the first vehicle.

2 . The method of claim 1 , wherein the digital map corresponds to a location of the first vehicle.

3 . The method of claim 1 , wherein at least one score is weighted.

4 . The method of claim 3 , wherein the weight corresponds to a distance between a retroreflective object and the first vehicle.

5 . The method of claim 1 , further comprising:
transmitting, by the processor, a location of the first vehicle to an autonomous driving processor associated with the first vehicle.

6 . The method of claim 1 , wherein the retroreflective feature is represented as a cuboid within the digital map.

7 . The method of claim 1 , wherein generating the score further comprises generating the score based on a number of detections of the retroreflective feature compared to opportunities for detection of the retroreflective feature.

8 . A non-transitory machine-readable storage medium having computer-executable instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receive a first set of data associated with a plurality of retroreflective features from a first vehicle; retrieve a digital map comprising vectorized data associated with the plurality of retroreflective features and a location associated with the plurality of retroreflective features, the digital map previously generated based on monitoring a second set of data retrieved from a sensor of a second vehicle where the second set of data is associated with the plurality of retroreflective features near a road being driven by the second vehicle; iteratively forming, by the one or more processors, a consensus of observations of the plurality of retroreflective features; generate a score for each retroreflective feature indicating a match between a consensus of each retroreflective feature as indicated within the digital map and a location of each retroreflective feature as identified within the first set of data, generate the score further comprising:
generate the score based on a duration of detection of the retroreflective feature compared to a duration within a region of interest surrounding the retroreflective feature;
localize, by the one or more processors, the first vehicle; and control, by the one or more processors, operation of the first vehicle, based on localization of the first vehicle.

9 . The non-transitory machine-readable storage medium of claim 8 , wherein the digital map corresponds to a location of the first vehicle.

10 . The non-transitory machine-readable storage medium of claim 8 , wherein at least one score is weighted.

11 . The non-transitory machine-readable storage medium of claim 10 , wherein the weight corresponds to a distance between a retroreflective object and the first vehicle.

12 . The non-transitory machine-readable storage medium of claim 8 , wherein the instructions further cause the one or more processors to:
transmit a location of the first vehicle to an autonomous driving processor associated with the first vehicle.

13 . The non-transitory machine-readable storage medium of claim 8 , wherein the retroreflective feature is represented as a cuboid within the digital map.

14 . A system comprising a processor configured to:
receive a first set of data associated with a plurality of retroreflective features from a first vehicle; retrieve a digital map comprising vectorized data associated with the plurality of retroreflective features and a location associated with the plurality of retroreflective features, the digital map previously generated based on monitoring a second set of data retrieved from a sensor of a second vehicle where the second set of data is associated with the plurality of retroreflective features near a road being driven by the second vehicle; iteratively form, by the processor, a consensus of observations of the plurality of retroreflective features; generate a score for each retroreflective feature indicating a match between a consensus of each retroreflective feature as indicated within the digital map and a location of each retroreflective feature as identified within the first set of data, generate the score further comprising:
generate the score based on a duration of detection of the retroreflective feature compared to a duration within a region of interest surrounding the retroreflective feature;
localize, by the processor, the first vehicle; and control, by the processor, operation of the first vehicle, based on localization of the first vehicle.

15 . The system of claim 14 , wherein the digital map corresponds to a location of the first vehicle.

16 . The system of claim 14 , wherein at least one score is weighted.

17 . The system of claim 16 , wherein the weight corresponds to a distance between a retroreflective object and the first vehicle.

18 . The system of claim 14 , wherein the processor is further configured to transmit a location of the first vehicle to an autonomous driving processor associated with the first vehicle.

19 . The system of claim 14 , wherein the retroreflective feature is represented as a cuboid within the digital map.

Assignees

• Torc Robotics Inc

Inventors

• Foster Wade
• Chilton Ryan
• Bhargava Karan Vivek
• Pullagurla Harish
• Miller Zachary
• Udayakumar Gowtham Raj Gunaseela
• Harper Jason

Classifications

• B60W50/00

  Details of control systems for road vehicle drive control not related to the control of a particular sub-unit {, e.g. process diagnostic or vehicle driver interfaces} · CPC title

• B60W2556/65

  Data transmitted between vehicles · CPC title

• B60W2556/40

  High definition maps · CPC title

• B60W2050/0022

  Gains, weighting coefficients or weighting functions · CPC title

• B60W60/001

  Planning or execution of driving tasks · CPC title