Systems and methods involving features of adaptive and/or autonomous traffic control

• US 9,761,131 B2
• Filed: 09/01/2014
• Issued: 09/12/2017
• Est. Priority Date: 11/22/2011
• Status: Active Grant

• Current Assignee: Fastec International, LLC
• Original Assignee: Fastec International, LLC
• Inventors: Robinson, Kurt B.
• Primary Examiner(s): Khatib, Rami
• Application Number:
  US14/474,232
• Publication Number:
  US 20150134232A1
• Time in Patent Office: 1,107 Days
• Field of Search: None
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G08G 1/0116 from roadside infrastructure, e.g. beacons
• CPC Class Codes: G08G 1/0145 for active traffic flow control
• CPC Class Codes: G08G 1/042 using inductive or magnetic detectors

Abstract

Systems and method are disclosed for adaptive and/or autonomous traffic control. In one illustrative implementation, there is provided a method for processing traffic information. Moreover, the method may include receiving data regarding travel of vehicles associated with an intersection, using neural network technology to recognize types and/or states of traffic, and using the neural network technology to process/determine/memorize optimal traffic flow decisions as a function of experience information. Exemplary implementations may also include using the neural network technology to achieve efficient traffic flow via recognition of the optimal traffic flow decisions.

Claims

1. A method for processing traffic information, the method comprising:

at a computer with a processor and memory in communication with a data storage, to control automated traffic lights,

receiving data regarding travel of vehicles associated with an intersection;

processing the data using neural network technology to recognize traffic;

performing processing using the neural network technology to recognize states of the traffic;

processing the traffic and the states of traffic using the neural network technology to memorize optimal traffic flow decisions as a function of prior experience;

determining optimal traffic flow using the neural network technology to achieve efficient traffic flow via recognition of the optimal traffic flow decisions;

enhancing the traffic type recognition using an array having a plurality of sensor inputs beyond inputs from video sensors;

processing other sensor inputs including;

a traffic radar input providing enhanced capability from transmission of various data;

detailed radar signatures of detected traffic objects independent from adverse weather or light conditions for recognition of vehicle position and vehicle type of one or more of the vehicles associated with an intersection; and

radar measurement of velocities of incoming traffic vehicles;

wherein prediction of traffic flow is enhanced for traffic light control decisions at a higher level of the neural network array, including prioritization of incoming traffic and collision-avoidance traffic light hold.

2. The method of claim 1 wherein the traffic flow determination includes state information inputs from nearby traffic controllers comparable with intermediate level traffic state recognition at a local traffic controller which are combined at higher levels of the neural network to optimize traffic flow decision-making at a local traffic light.

3. The method of claim 1, further comprising recognizing driver intentions without use of communication or transmissions between a vehicle associated with the driver and the traffic lights.

4. The method of claim 3, wherein digital logic is included to provide an output or warning of current- and next-state information configured to be utilized by in-vehicle communication devices, as known, that transmit information to or from one or more of the traffic lights.

5. The method of claim 1, wherein digital logic is included to provide an output or warning of current- and next-state information configured to be utilized by in-vehicle communication devices, as known, that transmit information to or from one or more of the traffic lights.

6. The method of claim 1 wherein the other sensor inputs include an infrared traffic input providing enhanced capability from transmission of various types of data;

and

wherein the infrared traffic input comprises;

detailed infrared signatures of detected traffic objects independent from adverse weather or light conditions for recognition of the vehicle position and the vehicle type of at least one of the vehicles associated with an intersection; and

detection of the vehicle passenger occupancy which is used in traffic flow decision making at a higher level of the neural network array; and

wherein the method further comprises;

giving priority to passenger-weighted incoming traffic.

7. The method of claim 1, wherein neural network recognition is deployed to recognize various standardized signal types of at least one high-priority vehicle of the vehicles associated with an intersection, which, once recognized, is used to initiate required authentication and prioritize traffic flow decisions.

8. A method for processing traffic information, the method comprising:

at a computer with a processor and memory in communication with a data storage, to control automated traffic lights,

receiving data regarding travel of vehicles associated with an intersection;

processing the data using neural network technology to recognize traffic;

performing processing using the neural network technology to recognize states of the traffic;

processing the traffic and the states of traffic using the neural network technology to memorize optimal traffic flow decisions as a function of prior experience;

determining optimal traffic flow using the neural network technology to achieve efficient traffic flow via recognition of the optimal traffic flow decisions;

utilizing 2 or more layers of neural network neuron storage elements for unique recognition, classification, and traffic flow decision-making tasks

wherein the unique recognition includes feeding from the low level to the higher levels of the neural network array, wherein assigned neurons are;

trained to aggregate total numbers of incoming traffic vehicles; and

trained to recognize position over fixed time sequences resulting in recognition of relative velocity.

9. The method of claim 8 wherein the e traffic flow determination includes state information inputs from nearby traffic controllers comparable with intermediate level traffic state recognition at a local traffic controller which are combined at higher levels of the neural network array to optimize traffic flow decision- making at a local traffic light.

10. The method of claim 8, further comprising recognizing driver intentions without use of communication or transmissions between a vehicle associated with the driver and the traffic lights.

11. The method of claim 8, wherein digital logic is included to provide an output or warning of current- and next-state information configured to be utilized by in-vehicle communication devices, as known, that transmit information to or from one or more of the traffic lights.

12. The method of claim 8, wherein the other sensor inputs include an infrared traffic input providing enhanced capability from transmission of various types of data;

and

wherein the infrared traffic input comprises;

detailed infrared signatures of detected traffic objects independent from adverse weather or light conditions for recognition of vehicle position and vehicle type of one or more of the vehicles associated with an intersection; and

detection of the vehicle passenger occupancy which is used in traffic flow decision making at a higher level of the neural network array; and

wherein the method further comprises;

giving priority to passenger-weighted incoming traffic.

13. The method of claim 12, wherein digital logic is included to provide an output or warning of current- and next-state information configured to be utilized by in-vehicle communication devices, as known, that transmit information to or from one or more of the traffic lights.

14. The method of claim 8, wherein neural network recognition is deployed to recognize various standardized signal types of at least one high-priority vehicle of the vehicles associated with an intersection, which, once recognized, is used to initiate required authentication and prioritize traffic flow decisions.

15. A method for processing traffic information, the method comprising:

at a computer with a processor and memory in communication with a data storage, to control automated traffic lights,

receiving data regarding travel of vehicles associated with an intersection;

processing the data using neural network technology to recognize traffic;

performing processing using the neural network technology to recognize states of the traffic;

processing the traffic and the states of traffic using the neural network technology to memorize optimal traffic flow decisions as a function of prior experience;

determining optimal traffic flow using the neural network technology to achieve efficient traffic flow via recognition of the optimal traffic flow decisions;

utilizing 2 or more layers of neural network neuron storage elements for one or more of recognition, classification, and traffic flow decision-making tasks;

wherein the classification includes compiling aggregate traffic information as a function of neurons assigned to first-level data of the neural network array including one or more of;

processing weight of traffic within each zone;

processing data regarding vehicle occupancy; and

using composite weighting of all such inputs for higher level traffic flow decision-making.

16. The method of claim 15 wherein the traffic flow determination includes state information inputs from nearby traffic controllers comparable with intermediate level traffic state recognition at a local traffic controller which are combined at higher levels of the neural network array to optimize traffic flow decision-making at a local traffic light.

17. The method of claim 16, wherein digital logic is included to provide an output or warning of current- and next-state information configured to be utilized by in-vehicle communication devices, as known, that transmit information to or from one or more of the traffic lights.

18. The method of claim 15, further comprising recognizing driver intentions without use of communication or transmissions between a vehicle associated with the driver and the traffic light.

19. The method of claim 15, wherein digital logic is included to provide an output or warning of current- and next-state information configured to be utilized by in-vehicle communication devices, as known, that transmit information to or from one or more of the traffic lights.

20. The method of claim 15 wherein the other sensor inputs include an infrared traffic input providing enhanced capability from transmission of various types of data;

and

wherein the infrared traffic input comprises;

detailed infrared signatures of detected traffic objects independent from adverse weather or light conditions for recognition of vehicle position and vehicle type of one or more of the vehicles associated with an intersection; and

detection of the vehicle passenger occupancy which is used in traffic flow decision making at a higher level of the neural network array; and

wherein the method further comprises;

giving priority to passenger-weighted incoming traffic.