Apparatus and methods for predicting a state of visibility for a road object based on a light source associated with the road object

Patent metadata

Field	Value
Publication number	US-2022410881-A1
Application number	US-202117362122-A
Country	US
Kind code	A1
Filing date	Jun 29, 2021
Priority date	Jun 29, 2021
Publication date	Dec 29, 2022
Grant date	—

Abstract

An apparatus, method and computer program product are provided for determining a state of visibility for a road object. In one example, the apparatus receives temporal data, calculates an orientation of a light source with respect to a road object using the temporal data, and predicts a state of visibility for the road object based on the orientation of the light source. In another example, the apparatus determines an artificial light source associated with a road object, receives attribute data associated with the artificial light source, determines a state of the artificial light source using the attribute data, and predicts a state of visibility for the road object based on the state of the artificial light source.

First claim

We (I) claim:

1 . A non-transitory computer-readable storage medium having computer program code instructions stored therein, the computer program code instructions, when executed by at least one processor, cause the at least one processor to:
receive temporal data; using the temporal data, calculate an orientation of a light source with respect to a road object; and based on the orientation of the light source, predict a state of visibility for the road object.

2 . The non-transitory computer-readable storage medium of claim 1 , wherein the temporal data indicates a time at which a vehicle is estimated to encounter the road object.

3 . The non-transitory computer-readable storage medium of claim 1 , wherein the computer program code instructions, when executed by at least one processor, cause the at least one processor to:
receive road object attribute data indicating an attribute of the road object; and predict the state of visibility based further on the road object attribute data.

4 . The non-transitory computer-readable storage medium of claim 3 , wherein the attribute of the road object indicates a location of road object, a type of road object, a shape of road object, a composition of road object, an orientation of road object, a color of road object, sign information displayed by road object, function associated with road object, a degree of difference or similarity between the road object and an object positioned at a peripheral of the road object, or a combination thereof.

5 . The non-transitory computer-readable storage medium of claim 1 , wherein the road object is a first road object, and wherein the computer program code instructions, when executed by at least one processor, cause the at least one processor to:
using map data and the orientation of the light source with respect to the road object, determine whether a static object proximate to the first road object exists, the static object being a second road object or a point-of-interest (POI); and responsive to the static object existing, predict the state of visibility for the road object based further on whether the static object affects light propagation from the light source to the road object at the orientation of the light source.

6 . The non-transitory computer-readable storage medium of claim 1 , wherein the computer program code instructions, when executed by at least one processor, cause the at least one processor to:
using location data and the orientation of the light source with respect to the road object, determine whether a vehicle proximate to the first road object exists; and responsive to the vehicle existing, predict the state of visibility for the road object based further on whether the vehicle affects light propagation from the light source to the road object at the orientation of the light source.

7 . The non-transitory computer-readable storage medium of claim 1 , wherein the computer program code instructions, when executed by at least one processor, cause the at least one processor to:
receive weather forecast data indicating a weather forecast of a location in which the road object is disposed; and predict the state of visibility based further on the weather forecast data.

8 . The non-transitory computer-readable storage medium of claim 7 , wherein the weather forecast data includes a forecasted precipitation type, a forecasted precipitation intensity, a forecasted air temperature, a forecasted precipitation rate, a forecasted cloud type, a forecasted wind direction, or a combination thereof.

9 . The non-transitory computer-readable storage medium of claim 1 , wherein the computer program code instructions, when executed by at least one processor, cause the at least one processor to:
determine an observation location, the observation location being a location at which the road object is estimated to be observed by a vehicle sensor, a vehicle operator, or a combination thereof; and predict the state of visibility based on a perspective of the observation location.

10 . The non-transitory computer-readable storage medium of claim 1 , wherein the computer program code instructions, when executed by at least one processor, cause the at least one processor to: (i) update a map to include information associated with the state of visibility; (ii) cause a transmitter to transmit a notification indicating the state of visibility to a user equipment; (iii) generate a visual indicator informing the state of visibility; (iv) generate a travel link that avoids the road object; (v) cause a vehicle that is estimated to encounter the road object at a time and date associated with temporal data to change usage of a first set of vehicle sensors to a second set of vehicle sensors; (vi) cause an autonomous or semi-autonomous vehicle to change from an autonomous mode to a manual mode; or (vii) a combination thereof.

11 . The non-transitory computer-readable storage medium of claim 1 , wherein the road object is a road marking.

12 . The non-transitory computer-readable storage medium of claim 1 , wherein, to predict the state of visibility for the road object, the computer program code instructions, when executed by at least one processor, cause the at least one processor to input the orientation of the light source to a machine learning model, wherein the machine learning model is trained using historical data, the historical data including, for each of at least one past time:
the orientation of the light source or other orientation of the light source with respect to the road object; and for the orientation of the light source or the other orientation of the light source, a ground truth data indicating a true state of visibility for the road object.

13 . An apparatus comprising at least one processor and at least one non-transitory memory including computer program code instructions, the computer program code instructions configured to, when executed, cause the apparatus to:
determine an artificial light source associated with a road object; receive attribute data associated with the artificial light source; using the attribute data, determine a state of the artificial light source; and predict a state of visibility for the road object based on the state of the artificial light source.

14 . The apparatus of claim 13 , wherein the attribute data indicates one or more timings at which the artificial light source generates light, one or more durations at which at which the artificial light source generates light at one or more levels of intensity, one or more durations at which the artificial light source generates light as one or more colors, or a combination thereof.

15 . The apparatus of claim 13 , wherein the instructions, when executed, further cause the apparatus to:
receive weather forecast data indicating a weather forecast of a location in which the road object is disposed; and predict the state of visibility based further on the weather forecast data.

16 . The apparatus of claim 13 , the artificial light source being a street light, a building light, or a combination thereof.

17 . A method of updating a map layer based on a state of visibility for a road object, the method comprising:
receiving sensor observation data; responsive to the sensor observation data indicating that the road object of a road segment was not observed by a sensor, determining attribute data associated with a light source affecting visibility of the road object; determining the state of visibility for the road object based on the attribute data; generating a data

Assignees

• Here Global Bv

Inventors

• Young Jeremy Michael
• Beaurepaire Jerome
• Stenneth Leon

Classifications

• G06V20/584

  of vehicle lights or traffic lights · CPC title

• B60W30/095 Primary

  Predicting travel path or likelihood of collision · CPC title

• B60W2554/404

  Characteristics · CPC title

• G06T2207/30261

  Obstacle · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title