Adaptive traffic control using vehicle trajectory data

• US 10,629,071 B1
• Filed: 12/12/2018
• Issued: 04/21/2020
• Est. Priority Date: 10/16/2018
• Status: Active Grant

• Current Assignee: Beijing Didi Infinity Technology And Development Co.Ltd.
• Original Assignee: Beijing Didi Infinity Technology And Development Co.Ltd.
• Inventors: Zheng, Jianfeng, Liu, Xianghong
• Primary Examiner(s): Khan, Omer S
• Application Number:
  US16/217,003
• Publication Number:
  US 20200118427A1
• Time in Patent Office: 496 Days
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/0145 for active traffic flow control
• CPC Class Codes: G08G 1/08 according to detected number or speed of vehicles
• CPC Class Codes: G08G 1/082 Controlling the time between beginning of the same phase of a cycle at adjacent intersections
• CPC Class Codes: G08G 1/083 Controlling the allocation of time between phases of a cycle
• CPC Class Codes: G08G 1/095 Traffic lights

Abstract

Embodiments of the disclosure provide traffic control systems and methods. The traffic control system may include a communication interface configured to receive vehicle trajectory data acquired by sensors and traffic control data from traffic signal controllers. The traffic control system may further include at least one processor. The at least one processor may be configured to detect an abnormal traffic condition. The at least one processor may be further configured to optimize an online traffic control scheme based on the vehicle trajectory data by adjusting green splits for a plurality of phases. The at least one processor may be also configured to provide, in real-time, the optimized online traffic control scheme to a traffic signal controller for generating traffic control signals.

Claims

1. A traffic control system, comprising:

a communication interface configured to;

receive vehicle trajectory data acquired by sensors and traffic control data from traffic signal controllers;

receive historical trajectory data; and

at least one processor configured to;

detect an abnormal traffic condition;

optimize an online traffic control scheme based on the vehicle trajectory data by adjusting green splits for a plurality of phases;

provide, in real-time, the optimized online traffic control scheme to a traffic signal controller for generating traffic control signals;

optimize an offline traffic control scheme based on the historical trajectory data by adjusting controlling periods in a time-of-day schedule and cycle lengths within each controlling period; and

periodically provide the optimized offline traffic control scheme to the traffic signal controller to replace an existing scheme used by the traffic signal controller.

2. The traffic control system of claim 1, wherein to optimize the traffic control scheme, the at least one processor is configured to:

determine a plurality of candidate traffic control schemes based on the vehicle trajectory data, each candidate traffic control associated with a different set of green splits;

calculate values indicative of effectiveness of the candidate traffic control schemes; and

select the candidate traffic control scheme corresponding to the highest value as the optimized online traffic control scheme.

3. The traffic control system of claim 1, wherein the abnormal traffic condition is an oversaturation condition, wherein the at least one processor is further configured to:

determine an oversaturation probability for each traffic flow direction based on the vehicle trajectory data; and

detect the oversaturation condition when the oversaturation probability exceeds a saturation threshold.

4. The traffic control system of claim 3, wherein the at least one processor is further configured to:

determine weights for respective traffic flow directions based on the oversaturation probability; and

optimize the online traffic control scheme using the weights to weigh conditions in the respective traffic flow directions.

5. The traffic control system of claim 1, wherein the abnormal traffic condition is a spillover condition, wherein the at least one processor is further configured to:

determine a queuing ratio for a road section based on the vehicle trajectory data; and

detect the spillover condition when the queuing ratio exceeds a spillover threshold.

6. The traffic control system of claim 5, wherein the at least one processor is further configured to:

identify traffic lights at intersections adjacent to the road section;

optimize the online traffic control scheme including a collection of sub-schemes for the respective identified traffic lights; and

provide, in real-time, the sub-scheme to traffic signal controllers of the respective identified traffic lights.

7. The traffic control system of claim 2, wherein the at least one processor is further configured to filter the plurality of candidate traffic control scheme using a predetermined range for green splits.

8. The traffic control system of claim 6, wherein at least one processor is further configured to optimize the online traffic control scheme by adjusting an offset between two of the identified traffic lights.

9. The traffic control system of claim 1, wherein the at least one processor is further configured to optimize the off line traffic control scheme by adjusting an offset between two traffic lights.

10. The traffic control system of claim 1, wherein the at least one processor is further configured to optimize the off line traffic control scheme by adjusting green splits for each phase within each controlling period.

11. A traffic control method, comprising:

receiving, by a communication interface, vehicle trajectory data acquired by sensors and traffic control data from traffic signal controllers;

receiving, by a communication interface, historical trajectory data;

detecting, by at least one processor, an abnormal traffic condition;

optimizing, by the at least one processor, an online traffic control scheme based on the vehicle trajectory data by adjusting green splits for a plurality of phases;

providing, in real-time, the optimized online traffic control scheme to a traffic signal controller for generating traffic control signals;

optimizing, by the at least one processor, an offline traffic control scheme based on the historical trajectory data by adjusting controlling periods in a time-of-day schedule and cycle lengths within each controlling period; and

periodically providing, by the at least one processor, the optimized off line traffic control scheme to the traffic signal controller to replace an existing scheme used by the traffic signal controller.

12. The traffic control method of claim 11, wherein optimizing the traffic control scheme further comprises:

determining a plurality of candidate traffic control schemes based on the vehicle trajectory data, each candidate traffic control associated with a different set of green splits;

calculating values indicative of effectiveness of the candidate traffic control schemes; and

selecting the candidate traffic control scheme corresponding to the highest value as the optimized online traffic control scheme.

13. The traffic control method of claim 11, wherein the abnormal traffic condition is an oversaturation condition, wherein detecting the abnormal traffic condition further comprises:

determining an oversaturation probability for each traffic flow direction based on the vehicle trajectory data; and

detecting the oversaturation condition when the oversaturation probability exceeds a saturation threshold.

14. The traffic control method of claim 11, wherein the abnormal traffic condition is a spillover condition, wherein detecting the abnormal traffic condition further comprises:

determining a queuing ratio for a road section based on the vehicle trajectory data; and

detecting the spillover condition when the queuing ratio exceeds a spillover threshold.

15. The traffic control method of claim 14, further comprising:

identifying traffic lights at intersections adjacent to the road section;

optimizing the online traffic control scheme including a collection of sub-schemes for the respective identified traffic lights; and

providing, in real-time, the sub-scheme to traffic signal controllers of the respective identified traffic lights.

16. The traffic control method of claim 15, wherein optimizing the online traffic control scheme further includes adjusting an offset between two of the identified traffic lights.

17. The traffic control method of claim 11, wherein optimizing the off line traffic control scheme is further by adjusting green splits for each phase within each controlling period.

18. A non-transitory computer-readable medium having instructions stored thereon, wherein the instructions, when executed by at least one processor, cause the at least one processor to perform a traffic control method, the traffic control method comprising:

receiving vehicle trajectory data acquired by sensors and traffic control data from traffic signal controllers;

receiving historical trajectory data;

detecting an abnormal traffic condition;

optimizing an online traffic control scheme based on the vehicle trajectory data by adjusting green splits for a plurality of phases;

providing, in real-time, the optimized online traffic control scheme to a traffic signal controller for generating traffic control signals;

optimizing an offline traffic control scheme based on the historical trajectory data by adjusting controlling periods in a time-of-day schedule and cycle lengths within each controlling period; and

periodically providing the optimized offline traffic control scheme to the traffic signal controller to replace an existing scheme used by the traffic signal controller.