Real-time traffic condition warning system

Patent metadata

Field	Value
Publication number	US-12437635-B2
Application number	US-202318385850-A
Country	US
Kind code	B2
Filing date	Oct 31, 2023
Priority date	Oct 31, 2023
Publication date	Oct 7, 2025
Grant date	Oct 7, 2025

Abstract

A system receives GPS data and on-board sensor data from several connected vehicles indicating locations of nearby vehicles and objects. The system processes the data to create a shared-world model that includes locations and velocities of the connected vehicles and nearby vehicles and objects, and the system determines whether driving hazards exist, such as potential collisions. The system may transmit an alert to at least one of the connected vehicles, to cause the connected vehicle or a mobile device to present a warning message to a driver, such as a visual, audio, or haptic message, or to cause the connected vehicle to implement an action to avoid the driving hazard, such as activating emergency braking or altering course. The system may create, and transmit to a connected vehicle or mobile device, a lane-level traffic model indicating traffic density, traffic speed, and traffic throughput.

First claim

What is claimed is:

1. A method, comprising:
receiving recurrently, from a first vehicle, first GPS data indicating an absolute location of the first vehicle and first on-board sensor data indicating a relative location of each object in a first set of nearby objects;
receiving recurrently, from at least one second vehicle, a second GPS data indicating an absolute location of the at least one second vehicle and a second on-board sensor data indicating a relative location of each object in a second set of nearby objects;
determining, based on the first GPS data and the first on-board sensor data, a velocity of the first vehicle and an absolute location and a velocity of one or more objects in the first set of nearby objects;
determining, based on the second GPS data and the second on-board sensor data, a velocity of the at least one second vehicle and an absolute location and a velocity of one or more objects in the second set of nearby objects;
generating a shared-world model of vehicles and objects comprising the absolute locations and velocities of the first vehicle, the at least one second vehicle, the one or more objects in the first set of nearby objects, and the one or more objects in the second set of nearby objects;
representing each plurality of vehicles and objects, selected from the first vehicle, the at least one second vehicle, the one or more objects of the first set of nearby objects, and the one or more objects in the second set of nearby objects, whose absolute locations are within a threshold distance of each other as a single vehicle or object in the shared-world model;
determining whether a collision hazard exists between the first vehicle and any other vehicle or object of the shared-world model based on determining whether the first vehicle is on a collision course with the other vehicle or object and whether a difference between the velocity of the first vehicle and the velocity of the other vehicle or object is greater than a threshold velocity; and
in response to the collision hazard existing, transmitting an alert to the first vehicle.

2. The method of claim 1 , wherein the first on-board sensor data and the second on-board sensor data each comprise at least one of:
lidar data;
camera data;
radar data; or
acoustic data.

3. The method of claim 1 , wherein the alert causes the first vehicle to produce a human-comprehendible message comprising at least one of:
a visual message presented via a graphical interface of an infotainment system, a head-up display, or a mobile device; or
an audio message presented via a speaker of an infotainment system or a mobile device.

4. The method of claim 1 , wherein the first vehicle is an autonomous vehicle and the alert causes the first vehicle to implement an action comprising at least one of:
modifying a speed of the first vehicle; or
modifying a trajectory of the first vehicle.

5. The method of claim 1 , further comprising:
determining a first confidence score for at least one object of the shared-world model based on a quantity of vehicles and objects that are represented by the at least one object;
wherein the transmitting of the alert is in further response to the first confidence score exceeding a first threshold value.

6. The method of claim 1 , further comprising:
determining an estimated absolute location and an estimated velocity for at least one object of the shared-world model that represents an object in the first set of nearby objects or an object in the second set of nearby objects for which no indication of a relative location has been received for at least a threshold duration.

7. The method of claim 1 , further comprising:
determining a second confidence score for at least one object of the shared-world model based on a time elapsed since receiving an indication of a relative location of the at least one object; wherein
the transmitting of the alert is in further response to the second confidence score exceeding a second threshold value.

8. A system, comprising:
one or more memories; and
one or more processors configured to execute instructions stored in the one or more memories to:
receive recurrently, from a first vehicle, first GPS data indicating an absolute location of the first vehicle and first on-board sensor data indicating a relative location of each object in a first set of nearby objects;
receive recurrently, from at least one second vehicle, a second GPS data indicating an absolute location of the at least one second vehicle and a second on-board sensor data indicating a relative location of each object in a second set of nearby objects;
determine, based on the first GPS data and the first on-board sensor data, a velocity of the first vehicle and an absolute location and a velocity of one or more objects in the first set of nearby objects;
determine, based on the second GPS data and the second on-board sensor data, a velocity of the at least one second vehicle and an absolute location and a velocity of one or more objects in the second set of nearby objects;
generate a shared-world model of vehicles and objects comprising the absolute locations and velocities of the first vehicle, the at least one second vehicle, the one or more objects in the first set of nearby objects, and the one or more objects in the second set of nearby objects;
represent each plurality of vehicles and objects, selected from the first vehicle, the at least one second vehicle, the one or more objects of the first set of nearby objects, and the one or more objects in the second set of nearby objects, whose absolute locations are within a threshold distance of each other as a single vehicle or object in the shared-world model;
determine whether a collision hazard exists between the first vehicle and any other vehicle or object of the shared-world model based on determining whether the first vehicle is on a collision course with the other vehicle or object and whether a difference between the velocity of the first vehicle and the velocity of the other vehicle or object is greater than a threshold velocity; and
in response to the collision hazard existing, transmit an alert to the first vehicle.

9. The system of claim 8 , wherein the first on-board sensor data and the second on-board sensor data each comprise at least one of:
lidar data;
camera data;
radar data; or
acoustic data.

10. The system of claim 8 , wherein the alert causes the first vehicle to produce a human-comprehendible message comprising at least one of:
a visual message presented via a graphical interface of an infotainment system, a head-up display, or a mobile device; or
an audio message presented via a speaker of an infotainment system or a mobile device.

11. The system of claim 8 , wherein the first vehicle is an autonomous vehicle and the alert causes the first vehicle to implement an action comprising at least one of:
modifying a speed of the first vehicle; or
modifying a trajectory of the first vehicle.

12. The system of claim 8 , wherein the instructions include instructions to:
determine a first confidence score for at least one object of the shared-world model based on a quantity of vehicles and objects that are represented by the at least one object; wherein
transmission of the alert is in further response to the first confidence score exceeding a first threshold value.

13. The system of claim 8 , wherein the instructions include instructions to:
determine an estimated absolute location and an estimated velocity for at least one object of the shared-world model that represents an object in the first set of nearby objects or an object in the second set of nearby

Assignees

• Nissan North America Inc

Inventors

• Chou Fang-Chieh
• Pedersen Liam
• Baig Najamuddin Mirza

Classifications

• B60W50/14

  Means for informing the driver, warning the driver or prompting a driver intervention · CPC title

• B60W2050/146

  Display means · CPC title

• B60W30/0956

  the prediction being responsive to traffic or environmental parameters · CPC title

• B60W30/085

  Taking automatic action to adjust vehicle attitude in preparation for collision, e.g. braking for nose dropping · CPC title

• B60W2554/80

  Spatial relation or speed relative to objects · CPC title