Real-time monitoring and diagnostic processing of traffic control data

• US 10,109,196 B2
• Filed: 12/13/2017
• Issued: 10/23/2018
• Est. Priority Date: 01/30/2015
• Status: Active Grant

• Current Assignee: Yunex LLC (Siemens AG)
• Original Assignee: Siemens AG, Siemens Industry Incorporated (Siemens AG)
• Inventors: Aparicio Ojea, Juan L., Collum, Brian, Valdez, Andrew, Wehrwein, Bradley
• Primary Examiner(s): Ghulamali, Qutbuddin
• Application Number:
  US15/840,010
• Publication Number:
  US 20180102052A1
• Time in Patent Office: 314 Days
• Field of Search: 340907
• 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 1/07 Controlling traffic signals
• CPC Class Codes: G08G 1/097 Supervising of traffic control systems, e.g. by giving an alarm if two crossing streets have green light simultaneously

Abstract

A traffic control monitoring and abnormality determination system and associated methods are disclosed for receiving and analyzing traffic controller input/output data during a learning phase to determine a model indicative of normal or healthy operation of the traffic controller in regulating traffic flow at an intersection and receiving and evaluating additional traffic controller input/output data against the model during an evaluation phase to determine whether an abnormality exists in operation of the traffic controller. If an abnormality is detected during the evaluation phase, the system may initiate a corrective action to resolve the abnormality such as sending an alarm signal to a traffic controller to cause the traffic controller to alter an operating state to resolve the abnormality.

Claims

1. A method for diagnostic processing of traffic controller data by a traffic control system, comprising:

during a training phase;

receiving traffic controller data from a traffic controller configured to control traffic flow at an intersection, wherein the traffic controller data is indicative of an input to the traffic controller or an output from the traffic controller;

extracting feature data based on the traffic controller data;

determining, based at least in part on the feature data, a model for the traffic flow at the intersection, wherein the model is indicative of a multi-dimensional view of expected traffic flow at the intersection over time;

during a real-time monitoring phase;

extracting current feature data from current traffic controller data;

determining presence of an abnormality in the traffic flow at the intersection based on a deviation between the current feature data and the model; and

initiating an action to resolve the abnormality.

2. The method of claim 1, wherein the initiating comprises causing an alarm signal to be transmitted to the traffic controller to cause the traffic controller to modify an internal operating state to resolve the abnormality, wherein the alarm signal includes an indication of the traffic controller data impacting the feature data as a root cause indicator.

3. The method of claim 1, wherein the determining presence of the abnormality comprises:

determining a metric indicative of the deviation between the current feature data and the model;

determining that the metric meets or exceeds a threshold value; and

determining that the abnormality is present based at least in part on determining that the metric meets or exceeds the threshold value.

4. The method of claim 1, wherein the feature data comprises at least one of a time domain statistical feature or a frequency domain statistical feature.

5. The method of claim 1, further comprising:

during the training phase;

receiving sensor data captured by one or more traffic sensors; and

determining, based at least in part on the sensor data, operating conditions of the traffic flow at the intersection,

calibrating the feature data by adjusting a respective coefficient to be applied to one or more model features based at least in part on a change in the operating conditions of the traffic flow at the intersection.

6. The method of claim 5, further comprising:

determining, based at least in part on the sensor data, first and second operating conditions of the traffic flow at the intersection, the second operating condition being different from the first operating condition.

7. The method of claim 1, further comprising:

aggregating multiple models corresponding to multiple traffic intersections to form a composite model associated with a larger travel area; and

determining, based in part on the composite model, a likelihood that a first abnormality detected at a first intersection will result in traffic conditions that cause a second different abnormality to occur at a second intersection.

8. A system for diagnostic processing of traffic controller data by a traffic control system, comprising:

at least one memory storing computer-executable instructions; and

at least one processor configured to access the at least one memory and execute the computer-executable instructions;

wherein the memory comprises;

a feature extraction engine configured to;

receive traffic controller data from a traffic controller configured to control traffic flow at an intersection, wherein the traffic controller data is indicative of an input to the traffic controller or an output from the traffic controller; and

extract feature data based on the traffic controller data;

a model determination engine configured to;

determine, based at least in part on the feature data, a model for the traffic flow at the intersection, wherein the model is indicative of a multi-dimensional view of expected traffic flow at the intersection over time;

the feature extraction engine further configured to;

extract, during a real-time monitoring phase, current feature data extracted from the traffic controller data;

a traffic abnormality evaluation engine configured to;

determine presence of an abnormality in the traffic flow at the intersection based on a deviation between the current feature data and the model; and

a traffic control engine configured to;

initiate an action to resolve the abnormality.

9. The system of claim 8, wherein the traffic control engine is further configured to initiate an alarm signal to be transmitted to the traffic controller to modify an internal operating state to resolve the abnormality.

10. The system of claim 8, wherein the traffic abnormality evaluation engine is further configured to:

determine a metric indicative of the deviation between the current feature data and the model;

determine that the metric meets or exceeds a threshold value; and

determine that the abnormality is present based at least in part on determining that the metric meets or exceeds the threshold value.

11. The system of claim 8, wherein the feature data comprises at least one of a time domain statistical feature or a frequency domain statistical feature.

12. The system of claim 8, wherein the memory further comprises a feature calibration engine configured to:

receive sensor data captured by one or more traffic sensors; and

determine, based at least in part on the sensor data, operating conditions of the traffic flow at the intersection, and

calibrate the feature data by adjusting a respective coefficient to be applied to at least one model feature of the one or more model features based at least in part on a change in the operating conditions of the traffic flow at the intersection.

13. The system of claim 12, wherein the model determination engine is further configured to:

determine, based at least in part on the sensor data, first and second operating conditions of the traffic flow at the intersection, the second operating condition being different from the first operating condition.

14. A computer program product comprising a non-transitory storage medium readable by a processing circuit, the storage medium storing instructions executable by the processing circuit to cause process steps to be performed, the process steps comprising:

receiving first traffic controller data from a traffic controller configured to control traffic flow at an intersection, wherein the first traffic controller data is indicative of an input to the traffic controller or an output from the traffic controller;

extracting feature data based on the traffic controller data;

determining, based at least in part on the feature data, a model for the traffic flow at the intersection, wherein the model is indicative of a multi-dimensional view of expected traffic flow at the intersection over time;

extracting current feature data from current traffic controller data;

determining presence of an abnormality in the traffic flow at the intersection based on a deviation between the current feature data and the model; and

initiating an action to resolve the abnormality.

15. The computer program product of claim 14, wherein the determining presence of the abnormality comprises:

determining, by the computer processor, a metric indicative of the deviation between the current feature data and the model;

determining, by the computer processor, that the metric meets or exceeds a threshold value; and

determining, by the computer processor, that the abnormality is present based at least in part on determining that the metric meets or exceeds the threshold value.

16. The computer program product of claim 15, the process steps further comprising:

determining, based at least in part on the sensor data, first and second operating conditions of the traffic flow at the intersection, the second operating condition being different from the first operating condition.

17. The computer program product of claim 14, wherein the initiating comprises causing an alarm signal to be transmitted to the traffic controller to cause the traffic controller to modify an internal operating state to resolve the abnormality, wherein the alarm signal includes an indication of the traffic controller data impacting the feature data as a root cause indicator.