IP Library › Granted Patent US 12682754
Granted Patent B2
US 12682754 · App. 17/534,259 · Granted Jul 14, 2026

Assisted traffic management

Inventors: Seyhan Ucar (Mountain View, CA); Takamasa Higuchi (Mountain View, CA); Onur Altintas (Mountain View, CA)
Assignee: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.
G08G1/096708G07C5/008G07C5/02G08G1/096741
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 12682754
App. No.
17/534,259
Granted
Jul 14, 2026
Kind
B2
Abstract

Systems and methods are provided for implementing traffic management techniques in connected, but not necessarily autonomous vehicles. In accordance with one embodiment, a method comprises determining a first vehicle instruction based on vehicle-related data; transmitting the first vehicle instruction to a first vehicle; when the first vehicle performs an action, inferring whether the action is in response to the first vehicle instruction; and based on the inference, transmitting a second vehicle instruction with a compensation action to a second vehicle.

Claims (42)

1 . A method comprising:

generating, via a trained machine learning (ML) model, a first vehicle instruction for a first vehicle based on vehicle-related data of the first vehicle;

determining, via the trained ML model, a value of inference that the first vehicle instruction will be executed by the first vehicle based on the vehicle-related data of the first vehicle;

transmitting the first vehicle instruction to the first vehicle;

when the first vehicle performs an action in response to the first vehicle instruction, determining whether the action performed by the first vehicle does or does not comply with the first vehicle instruction;

generating, via the trained ML model, a second vehicle instruction for a second vehicle based on the value of inference that the first vehicle instruction will be executed by the first vehicle and whether the action Performed by the first vehicle does or does not comply with the first vehicle instruction, wherein the second vehicle instruction includes a compensation action based on the value of inference that the first vehicle instruction will be executed by the first vehicle and whether the action performed by the first vehicle does or does not comply with the first vehicle instruction;

transmitting the second vehicle instruction to the second vehicle; and

causing the second vehicle to operate in accordance with the second vehicle instruction.

2 . The method of claim 1 , wherein the compensation action comprises an incentive offering to correct non-compliant actions performed by a vehicle.

3 . The method of claim 1 , wherein the first vehicle instruction is to slow a traveling speed, and when the action performed by the first vehicle does not comply with the first vehicle instruction, the compensation action is offering a monetary value to slow the traveling speed.

4 . The method of claim 1 , wherein the first vehicle instruction is to change lanes, and when the action performed by the first vehicle does not comply with the first vehicle instruction, the compensation action is offering a monetary value to change lanes.

5 . The method of claim 1 , wherein the first vehicle instruction is to enter a high-occupancy vehicle (HOV) lane, and when the action performed by the first vehicle does not comply with the first vehicle instruction, the compensation action is offering a monetary value to enter the HOV lane.

6 . The method of claim 1 , wherein generation, via the trained ML model, the second vehicle instruction for the second vehicle based on the value of inference that the first vehicle instruction will be executed by the first vehicle and whether the action performed by the first vehicle does or does not comply with the first vehicle instruction comprises:

responsive to the value of the inference exceeding a threshold value and the action performed by the first vehicle complying with the first vehicle instruction, the second vehicle instruction being generated to be same as the first vehicle instruction;

responsive to the value of the inference exceeding the threshold value and the action performed by the first vehicle not complying with the first vehicle instruction, the second vehicle instruction being generated to comprise (1) the first vehicle instruction and (2) the compensation action to perform the first vehicle instruction; and

responsive to the value of the inference not exceeding the threshold value and the action performed by the first vehicle complying or not complying with the first vehicle instruction, the second vehicle instruction being generated to comprise (1) the first vehicle instruction or a different vehicle instruction and (2) the compensation action to perform the first vehicle instruction or the different vehicle instruction.

7 . The method of claim 1 , wherein the second vehicle is a patrol officer and the second vehicle instruction is to abate traffic after the first vehicle.

8 . The method of claim 1 , wherein the vehicle-related data is determined by one of a network edge device, a cloud server, or an artificial intelligence analytics system resident on a vehicle associated with the vehicle-related data.

9 . The method of claim 1 , wherein the vehicle-related data originates from at least one of the first vehicle, another vehicle in communication with the first vehicle, and a third-party information source.

10 . A network edge device or cloud server comprising:

a memory; and

one or more processors that are configured to execute machine readable instructions stored in the memory for performing a method comprising:

generating, via a trained machine learning (ML) model, a first vehicle instruction for a first vehicle based on vehicle-related data of the first vehicle;

determining, via the trained ML model, a value of inference that the first vehicle instruction will be executed by the first vehicle based on the vehicle-related data of the first vehicle;

transmit the first vehicle instruction to the first vehicle;

when the first vehicle performs an action in response to the first vehicle instruction, determining whether the action performed by the first vehicle does or does not comply with the first vehicle instruction;

generating, via the trained ML model, a second vehicle instruction for a second vehicle based on the value of inference that the first vehicle instruction will be executed by the first vehicle and whether the action performed by the first vehicle does or does not comply with the first vehicle instruction, wherein the second vehicle instruction includes a compensation action based on the value of inference that the first vehicle instruction will be executed by the first vehicle and whether the action performed by the first vehicle does or does not comply with the first vehicle instruction;

transmitting the second vehicle instruction to the second vehicle; and

causing the second vehicle to operate in accordance with the second vehicle instruction.

11 . The network edge device or cloud server of claim 10 , wherein the compensation action comprises an incentive offering to correct non-compliant actions performed by a vehicle.

12 . The method of claim 1 , wherein the first vehicle and the second vehicle are identified to be part of a same cluster of vehicles responsive to prediction of the first vehicle and the second vehicle performing a similar action in response to an identical instruction.

13 . The network edge device or cloud server of claim 10 , wherein the first vehicle instruction is to slow a traveling speed, and when the action performed by the first vehicle does not comply with the first vehicle instruction, the compensation action is offering a monetary value to slow the traveling speed.

14 . The network edge device or cloud server of claim 10 , wherein the first vehicle instruction is to change lanes, and when the action performed by the first vehicle does not comply with the first vehicle instruction, the compensation action is offering a monetary value to change lanes.

15 . The network edge device or cloud server of claim 10 , wherein the first vehicle instruction is to enter a high-occupancy vehicle (HOV) lane, and when the action performed by the first vehicle does not comply with the first vehicle instruction, the compensation action is offering a monetary value to enter the HOV lane.

16 . The network edge device or cloud server of claim 10 , wherein generation, via the trained ML model, the second vehicle instruction for the second vehicle based on the value of inference that the first vehicle instruction will be executed by the first vehicle and whether the action performed by the first vehicle does or does not comply with the first vehicle instruction comprises:

responsive to the value of the inference exceeding a threshold value and the action performed by the first vehicle complying with the first vehicle instruction, the second vehicle instruction being generated to be same as the first vehicle instruction;

responsive to the value of the inference exceeding the threshold value and the action performed by the first vehicle not complying with the first vehicle instruction, the second vehicle instruction being generated to comprise (1) the first vehicle instruction and (2) the compensation action to perform the first vehicle instruction; and

responsive to the value of the inference not exceeding the threshold value and the action performed by the first vehicle complying or not complying with the first vehicle instruction, the second vehicle instruction being generated to comprise (1) the first vehicle instruction or a different vehicle instruction and (2) the compensation action to perform the first vehicle instruction or the different vehicle instruction.

17 . The network edge device or cloud server of claim 10 , wherein the second vehicle is a patrol officer and the second vehicle instruction is to abate traffic after the first vehicle.

18 . The network edge device or cloud server of claim 10 , wherein the vehicle-related data is determined by one of a network edge device, a cloud server, or an artificial intelligence analytics system resident on a vehicle associated with the vehicle-related data.

19 . The network edge device or cloud server of claim 10 , wherein the vehicle-related data originates from at least one of the first vehicle, another vehicle in communication with the first vehicle, and a third-party information source.

20 . The network edge device or cloud server of claim 10 , wherein the first vehicle and the second vehicle are identified to be part of a same cluster of vehicles responsive to prediction of the first vehicle and the second vehicle performing a similar action in response to an identical instruction.