SYSTEMS AND METHODS INVOLVING FEATURES OF ADAPTIVE AND/OR AUTONOMOUS TRAFFIC CONTROL

• US 20150134232A1
• Filed: 09/01/2014
• Published: 05/14/2015
• Est. Priority Date: 11/22/2011
• Status: Active Grant

• Current Assignee: Fastec International, LLC
• Original Assignee: Kurt B. Robinson
• Inventors: ROBINSON, Kurt B.
• Granted Patent: US 9,761,131 B2
• Time in Patent Office: Days
• US Class Current: 701/117
• 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:

receiving data regarding travel of vehicles associated with an intersection;

using neural network technology to recognize types of traffic;

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

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

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

3. The method of claim 1 further comprising performing video image processing optimized for neural network recognition and/or control.

4. The method of claim 1, further comprising enhancing the traffic type recognition using existing infrastructure.

9. The method of claim 1, further comprising enhancing the traffic type recognition using an array having a plurality of sensor inputs beyond inputs from video sensors and traditional physical infrastructure.

10. The method of claim 9, wherein the system includes a sensor array that provides a plurality of input vectors in addition to inputs from basic video capture available at the intersection.

11. The method of claim 9 wherein the other sensor inputs include a traffic radar input providing enhanced capability from transmission of various data types.

12. The method of claim 11 wherein the traffic radar input comprises:

detailed radar signatures of detected traffic objects independent from adverse weather or light conditions for recognition of vehicle position and type; and

radar measurement of velocities of incoming traffic objects;

wherein prediction of traffic flow is enhanced for higher level signal light control decisions including prioritization of incoming traffic and collision-avoidance signal light hold.

13. The method of claim 9 wherein the other sensor inputs include an infrared traffic input providing enhanced capability from transmission of various data types.

15. The method of claim 1, further comprising:

processing new sensory inputs;

retraining previously deployed neurons to take advantage of the new sensors;

wherein recognition of the traffic types is enhanced via adapting their recognition to utilize the new inputs.

16. The method of claim 1, further comprising:

processing new sensory inputs;

utilizing additional, reserve neuron capacity that was initially included in the system, wherein the reserve neuron capacity is subsequently trained to utilize the new inputs.

17. The method of claim 16 further comprising:

improving recognition specificity through the combination of prior and newly added recognition from the new sensory input.

19. The method of claim 1, further comprising:

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

20. The method of claim 19 wherein the unique recognition includes feeding from the low level to the higher levels.

21. The method of claim 20 wherein, in the step of feeding from the low level to the high level, assigned neurons are:

trained to aggregate total numbers of incoming traffic objects; and

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

22. The method of claim 19 wherein the classification includes compiling aggregate traffic information as a function of neurons assigned to first-level data including one or more of:

processing weight/disparity of traffic within each zone;

processing data regarding vehicle occupancy; and

/or

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

23. The method of claim 19 wherein the traffic flow decision-making includes state information inputs from nearby similar traffic controllers comparable with intermediate level traffic state recognition at the local controller which are combined at higher levels to optimize traffic flow decision-making at the local traffic signal light.

28. The method of claim 1, wherein neural network recognition is deployed to recognize various standardized high-priority vehicle signal types which is used to initiate required authentication and prioritize traffic flow decisions.

46. The method of claim 1, wherein the system or method is capable of recognizing driver intentions without use of communication/transmissions between the vehicle and the signal light.

47. The method of claim 1, wherein digital logic and/or communication devices are included to provide an output of current- and next-state information for use by similar, nearby controllers

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

99. The method of claim 1 wherein the traffic comprises automobile traffic.

2. (canceled)

5-8. -8. (canceled)

14. (canceled)

18. (canceled)

24-27. -27. (canceled)

29-45. -45. (canceled)

49-69. -69. (canceled)

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

receiving data regarding travel of vehicles associated with an intersection;

using neural network technology to recognize types and/or states of traffic;

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

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

71-98. -98. (canceled)

100. A method for providing highly accurate visual recognition of all types of traffic, the method comprising:

receiving data regarding passage of vehicles through an intersection;

using neural network technology to recognize types of traffic;

using neural network technology to recognize states of the traffic;

using neural network technology to memorize sequences determined to be optimal traffic flow decisions as a function of prior experience; and

using neural network technology to achieve highest efficiency traffic flow via recognition of conditions associated with the memorized optimal traffic flow decisions.

101. The method of claim 100 wherein the intersection includes one or more traffic lanes involving different traffic types wherein traffic flow decisions and directives include optimization and/or safe operation for all of the different traffic types.

102. The method of claim 100 wherein certain traffic in the intersection is constrained to fixed lanes and lane change decisions, wherein traffic flow decisions and directives include optimization and safe operation for the certain traffic along with all other impending traffic types associated with one or more traffic intersections.

103. The method of claim 102 wherein traffic lanes comprise traffic routing given by conventions defined for each traffic type, with intersections at each location where traffic objects may transition from one traffic lane to another wherein traffic flow decisions and directives include optimization and safe operation for said traffic along with all other impending traffic types associated with one or more traffic intersections.

104. The method of claim 100 wherein the traffic comprises automobile traffic.