IP Library Granted Patent US 12676064
Granted Patent B2
US 12676064 · App. 17/707,394 · Granted Jul 7, 2026

Roadway congestion management

Inventors: Fang-Chieh Chou (Sunnyvale, CA); Viju James (Fremont, CA); Najamuddin Mirza Baig (San Jose, CA); Liam Pedersen (San Francisco, CA); Abdul Rahman Kreidieh (Oakland, CA)
Assignee: Nissan North America, Inc.
G08G1/096725B60W60/001G08G1/0112G08G1/0116G08G1/0129G08G1/052B60W2554/406B60W2554/802B60W2556/45B60W2720/10
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12676064
App. No.
17/707,394
Granted
Jul 7, 2026
Kind
B2
Abstract

A server accesses vehicle data from each connected vehicle (CV) of a subset of a plurality of CVs on a roadway portion, the vehicle data comprising at least one of: a position, a velocity, or a headway. The server generates, based on the accessed vehicle data, a long-term shared world model. The server generates, using the long-term shared world model, a data structure representing predicted future velocities on the roadway portion by position and time by applying a traffic flow model to the long-term shared world model. The server transmits, to a connected autonomous vehicle (CAV), a control signal for controlling operation of the CAV based on the generated data structure.

Claims (34)

1 . A method comprising:

receiving traffic state information from roadway sensors, connected vehicles (CVs), and connected automated vehicles (CAVs);

predicting, using at least one of artificial intelligence or machine learning, at least one of a future flow, a future average velocity, or a future density for at least one roadway segment;

in cases where a leading or following vehicle cannot be found in an adjacent lane, adjusting the at least one of the future flow, the future average velocity, or the future density for the at least one roadway segment using at least one of a velocity correction factor or a headway correction factor that is generated based on the received traffic state information; and

generating, using a multivehicle policy selector, one or more control signals to control one or more of the CAVs based on the at least one of the future flow, the future average velocity, or the future density that has been adjusted, wherein the one or more control signals control at least one of a velocity or a travel path of an associated CAV.

2 . The method of claim 1 , wherein the multivehicle policy selector uses a predictive optimization technique to reduce congestion on different roadway segments that comprises ensuring at least a minimum threshold following distance between each CAV and a vehicle in front of the CAV.

3 . The method of claim 1 , wherein the received traffic state information comprises at least one of a location of a vehicle, a speed of the vehicle, a following distance between the vehicle and another vehicle, or a number of vehicles on a different roadway segment.

4 . The method of claim 3 , wherein the vehicle comprises a CV or a CAV.

5 . The method of claim 3 , wherein the vehicle comprises a non-connected vehicle, wherein the traffic state information of the non-connected vehicle is determined using one or more of the roadway sensors.

6 . The method of claim 3 , wherein the vehicle comprises a non-connected vehicle, wherein the traffic state information of the non-connected vehicle is determined using at least one of the CVs or the CAVs.

7 . The method of claim 1 , wherein the CVs or the CAVs comprise at least one vehicle that is not on the at least one roadway segment.

8 . An apparatus comprising:

a memory storing instructions; and

a processor to execute the stored instructions to:

receive traffic state information from roadway sensors, connected vehicles (CVs), and connected automated vehicles (CAVs);

predict, using at least one of artificial intelligence or machine learning, at least one of a future flow, a future average velocity, or a future density for at least one roadway segment;

in cases where a leading or following vehicle cannot be found in an adjacent lane, adjust the at least one of the future flow, the future average velocity, or the future density for the at least one roadway segment using at least one of a velocity correction factor or a headway correction factor that is generated based on the received traffic state information; and

generate, using a multivehicle policy selector, one or more control signals to control one or more of the CAVs based on the at least one of the future flow, the future average velocity, or the future density that has been adjusted, wherein the one or more control signals control at least one of a velocity or a travel path of an associated CAV.

9 . The apparatus of claim 8 , wherein the multivehicle policy selector includes a predictive optimization technique to reduce congestion on the roadway comprises ensuring at least a minimum threshold following distance between each CAV and a vehicle in front of the CAV.

10 . The apparatus of claim 8 , wherein the traffic state information comprises at least one of a location of a vehicle, a speed of the vehicle, a following distance between the vehicle and another vehicle, or a number of vehicles on a roadway segment.

11 . The apparatus of claim 10 , wherein the vehicle comprises a CV or a CAV.

12 . The apparatus of claim 10 , wherein the vehicle comprises a non-connected vehicle, wherein the traffic state information of the non-connected vehicle is determined using one or more of the roadway sensors.

13 . The apparatus of claim 10 , wherein the vehicle comprises a non-connected vehicle, wherein the traffic state information of the non-connected vehicle is determined using at least one of the roadway sensors, the CVs, or the CAVs.

14 . The apparatus of claim 8 , wherein the CVs, the CAVs, and non-connected vehicles are traveling on the at least one roadway segment.

15 . The apparatus of claim 8 , wherein the CVs or the CAVs comprise at least one vehicle that is not on the at least one roadway segment.

16 . A non-transitory computer-readable medium storing instructions which, when executed by a processor, cause the processor to perform operations comprising:

receiving traffic state information from roadway sensors, connected vehicles (CVs), and connected automated vehicles (CAVs);

predicting, using at least one of artificial intelligence or machine learning, at least one of a future flow, a future average velocity, or a future density for at least one roadway segment;

in cases where a leading or following vehicle cannot be found in an adjacent lane, adjusting the at least one of the future flow, the future average velocity, or the future density for the least one roadway segment using at least one of a velocity correction factor or a headway correction factor that is generated based on the received traffic state information; and

generating, using a multivehicle policy selector, one or more control signals to control at least one of the CAVs based on the at least one of the future flow, the future average velocity, or the future density that has been adjusted, wherein the one or more control signals control at least one of a velocity or a travel path of an associated CAV.

17 . The computer-readable medium of claim 16 , wherein the multivehicle policy selector uses a predictive optimization technique to reduce congestion on the at least one roadway segment by ensuring at least a minimum threshold following distance between each CAV and a vehicle in front of the CAV.

18 . The computer-readable medium of claim 16 , wherein the traffic state information comprises at least one of a location of a vehicle, a speed of the vehicle, a following distance between the vehicle and another vehicle, or a number of vehicles on the at least one roadway segment.

19 . The computer-readable medium of claim 18 , wherein the vehicle comprises a CV or a CAV.

20 . The computer-readable medium of claim 16 , wherein predicting the at least one of the future flow, the future average velocity, and the future density comprises storing predicted values in a two-dimensional array that corresponds to roadway segments and discrete time slices.