WO2021097759A1

WO2021097759A1 - Systems and methods for traffic control based on vehicle trajectory data

Info

Publication number: WO2021097759A1
Application number: PCT/CN2019/119977
Authority: WO
Inventors: Jianfeng Zheng; Zihao Wang; Xianghong Liu; Yu Han
Original assignee: Beijing Didi Infinity Technology And Development Co., Ltd.
Priority date: 2019-11-21
Filing date: 2019-11-21
Publication date: 2021-05-27
Also published as: CN112492889A; CN112492889B

Abstract

A system (100) and a method (300) for traffic control based on vehicle trajectory data (203), the system (100) may include: a communication interface (202) configured to receive the vehicle trajectory data (203) associated with a traffic flow from at least one navigation device (110), at least one processor (204) configured to determine at least one bottleneck in the traffic flow based on the vehicle trajectory data (203) and estimate a traffic volume associated with the bottleneck based on the vehicle trajectory data (203). The at least one processor (204) may be further configured to predict a future traffic flow based on the estimated traffic volume and control traffic based on the predicted future traffic flow. And the system (100) may further include a storage (208) configured to store the trajectory data and the predicted future traffic flow.

Description

SYSTEMS AND METHODS FOR TRAFFIC CONTROL BASED ON VEHICLE TRAJECTORY DATA

TECHNICAL FIELD

The present disclosure relates to systems and methods for traffic control, and more particularly to, systems and methods for traffic control based on vehicle trajectory data.

BACKGROUND

Traffic management measures are widely used to improve the mobility and safety of freeway traffic because of the urbanization and the ever-growing transportation demands. For example, important traffic parameters such as traffic flow speed and efficiency may be improved based on proper traffic control. Inputs for a conventional freeway traffic control system usually come from fixed sensors (e.g., loop detectors, geomagnetic detectors, or video sensors that placed in strategic locations) . The performance of conventional freeway traffic control systems depends heavily on the data availability from the fixed detectors.

Although fixed sensors can provide a thorough time history of both speed and volume of traffic at the location where the sensor is located, installation and maintenance cost render the solution less preferable. Also, the ability of fixed sensors to provide sufficient traffic information is further limited due to its immobility. For example, insufficiency of detector coverage (e.g., in small cities or rural area where inadequate detectors are established) and damaged or malfunctioning detectors (e.g., due to deficient manpower for conducting routinely check) may reduce the quality and quantity of the data provided by fixed sensors. On the other hand, traffic information such as traffic flow can be obtained manually. However, the high cost of labor and required resource (e.g., for transporting investigators) would render the method not economical.

Embodiments of the disclosure address the above problems by improved methods and systems for traffic control based on vehicle trajectory data.

SUMMARY

Embodiments of the disclosure provide a method for traffic control based on vehicle trajectory data. The method may include receiving, by a communication interface, the vehicle trajectory data associated with a traffic flow from at least one navigation device. The method may further include determining, by at least one processor, at least one bottleneck in the traffic flow based on the vehicle trajectory data and estimating, a traffic volume associated with the bottleneck based on the vehicle trajectory data. The method may further include predicting, by the at least one processor, a future traffic flow based on the estimated traffic volume and controlling traffic based on the predicted future traffic flow.

Embodiments of the disclosure also provide a system for traffic control based on trajectory data. The system may include a communication interface configured to receive the vehicle trajectory data associated with a traffic flow from at least one navigation device. The system may also include at least one processor. The at least one processor may be configured to determine at least one bottleneck in the traffic flow based on the vehicle trajectory data and estimate a traffic volume associated with the bottleneck based on the vehicle trajectory data. The at least one processor may be further configured to predict a future traffic flow based on the estimated traffic volume and control traffic based on the predicted future traffic flow. The system may further include a storage configured to store the trajectory data and the predicted future traffic flow.

Embodiments of the disclosure further provide a non-transitory computer-readable medium having instructions stored thereon that, when executed by one or more processors, causes the one or more processors to perform a method for traffic control based on vehicle trajectory data. The method may include receiving the vehicle trajectory data associated with an intersection where the traffic light is located from at least one navigation device and determining at least one bottleneck in the traffic flow based on the vehicle trajectory data. The method may further include estimating a traffic volume associated with the bottleneck based on the vehicle trajectory data and predicting a future traffic flow based on the estimated traffic volume. The method may further include controlling traffic based on the predicted future traffic flow.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 illustrates a schematic diagram of an exemplary traffic control system, according to embodiments of the disclosure.

FIG. 2 illustrates a block diagram of an exemplary system for traffic control, according to embodiments of the disclosure.

FIG. 3 illustrates a flowchart of an exemplary method for traffic control, according to embodiments of the disclosure.

FIG. 4 illustrates an exemplary traffic diagnosis of the traffic control system, according to embodiments of the disclosure.

FIG. 5 illustrates an exemplary visualization rpovided by the traffic control system, according to embodiments of the disclosure.

DETAILED DESCRIPTION

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts.

FIG. 1 illustrates a schematic diagram of an exemplary traffic control system 100, according to embodiments of the disclosure. In some embodiments, traffic control system 100 may be configured to control freeway traffic by controlling traffic flows from the ramps merging onto the freeway. For example, traffic control system 100 may be configured to control traffic flow of a road section 130. Consistent with the present disclosure, road section 130 may include an entrance ramp (e.g., an on-ramp) that allows vehicles to enter a controlled-access highway (e.g., a freeway or a motorway) . Consistent with the disclosure, traffic control system 100 performs traffic control based on vehicle trajectory data acquired by a navigation device 110 onboard of each vehicle 101.

Consistent with some embodiments, a navigation device 110 may be a device configured to receive signals from a satellite navigation system (not shown) . Navigation device 110 may be a standalone device or integrated inside another device, e.g., a vehicle, a mobile phone, a wearable device, a camera, etc. It is contemplated that navigation device 110 may be any kind of movable device or equivalent structures equipped with any suitable satellite navigation module that enables navigation device 110 to obtain trajectory data.

It is contemplated that the satellite navigation system from which navigation device 110 receives signals may be a global navigation satellite system such as a Global Positioning System (GPS) , a Global Navigation Satellite System (GLONASS) , a BeiDou-2 Navigation Satellite System (BDS) or a European Union’s Galileo system. The satellite navigation system may also be a regional navigation satellite system such as a BeiDou-1 system, a NAVigation with Indian Constellation (NAVIC) system or a Quasi-Zenith Satellite System (QZSS) . Navigation device 110 may be a high sensitivity GPS receiver, a conventional GPS receiver, a hand-held receiver, an outdoor receiver, or a sport receiver. In some embodiments, navigation device 110 may be connected to the satellite directly, through Assisted or Augmented GPS, through an intermediary device (e.g., a cell tower or a station) , or via any other communication method that could transmit satellite signals (e.g., satellites broadcast microwave signals) or provide orbital data or almanac for the satellite (e.g., Mobile Station Based assistance) to navigation device 110.

In addition, navigation device 110 may be connected to traffic control system 100 via a network, such as a Wireless Local Area Network (WLAN) , a Wide Area Network (WAN) , wireless networks such as radio waves, a cellular network, a satellite communication network, and/or a local or short-range wireless network (e.g., Bluetooth ^TM) for transmitting vehicle navigation information.

Consistent with some embodiments, vehicle 101 may be a vehicle configured for traveling along the trajectory and allows navigation device 110 to acquire trajectory data. It is contemplated that vehicle 101 may be an electric vehicle, a fuel cell vehicle, a hybrid vehicle, or a conventional internal combustion engine vehicle. Vehicle 101 may have a body and at least one wheel. The body may be any body style, such as a sports vehicle, a coupe, a sedan, a pick-up truck, a station wagon, a sports utility vehicle (SUV) , a minivan, or a conversion van. In some embodiments, vehicle 101 may include a pair of front wheels and a pair of rear wheels, as illustrated in FIG. 1. However, it is contemplated that vehicle 101 may have more or less wheels or equivalent structures that enable vehicle 101 to move around. Vehicle 101 may be configured to be all-wheel drive (AWD) , front wheel drive (FWR) , or rear wheel drive (RWD) . In some embodiments, vehicle 101 may be configured to be operated by an operator occupying the vehicle, remotely controlled, and/or autonomous.

In some embodiments, navigation device 110 may be configured to capture trajectory data as vehicle 101 travels along a trajectory. Consistent with the present disclosure, navigation device 110 may be equipped with a GPS module configured to constantly receive location information of vehicle 101. In some embodiments, as vehicle 101 travels along the trajectory, a trace in geographical space associated with vehicle 101’s movement is generated (e.g., a trace represented by a series of chronologically ordered points, e.g. p1 → p2 → …→ pn, where each point consists of a geospatial coordinate set and a timestamp such as p = (x, y, t) ) . Navigation device 110 may also capture or construct road map data including map of areas along vehicle 101’s trajectory.

Consistent with the present disclosure, traffic control system 100 may include a server 120. In some embodiments, server 120 may be a local physical server, a cloud server (as illustrated in FIG. 1) , a virtual server, a distributed server, or any other suitable computing device. For example, server 120 may obtain data from navigation device 110. Consistent with the present disclosure, trajectory data may be transmitted to a server 120 in real-time (e.g., by streaming) , or collectively after a certain period of time (e.g., 1ms or 5ms) . Server 120 may communicate with navigation device 110, ramp meter 140 and/or other components internal or external to traffic control system 100 via a network, such as a Wireless Local Area Network (WLAN) , a Wide Area Network (WAN) , wireless networks such as radio waves, a cellular network, a satellite communication network, and/or a local or short-range wireless network (e.g., Bluetooth ^TM) . Consistent with the present disclosure, server 120 may store trajectory data acquired by navigation device 110.

In some embodiments, server 120 may be configured to determine at least one bottleneck in the traffic flow of road section 130 based on the vehicle trajectory data. For example, the bottleneck may be a standing queue bottleneck or a moving jam. In some embodiments, server 120 may determine various parameters associated with the bottleneck, such as location and range (e.g., length of the jam) . Server 120 may also estimate a traffic volume associated with the bottleneck based on the vehicle trajectory data. Server 120 may also be responsible for predicting a future traffic flow of road section 130 from time to time to provide optimized traffic control to ramp meter 140. Server 120 may use the acquired trajectory data to optimize a green-split time of ramp meter 140 to manage the traffic flow getting on the freeway.

Consistent with the present disclosure, server 120 may communicate the optimized green-split time to ramp meter 140. In some embodiments, ramp meter 140 can be a single aspects traffic light, a dual aspects traffic light, or a three or more aspects traffic lights. It is contemplated that ramp meter 140 may have one or more aspect or equivalent structures that enable ramp meter 140 to signal.

As illustrated in FIG. 1, ramp meter 140 may be mounted to supporting device 160 via a mounting structure 150. Mounting structure 150 may be an electro-mechanical device installed or otherwise attached to the supporting device 160. In some embodiments, mounting structure 150 may use screws, adhesives, or another mounting mechanism. Supporting device 160 may be a tripod, a jib, carne, a lamp stick or any other suitable structures for providing support to mounting structure 150 and ramp meter 140. It is contemplated that the manners in which ramp meter 140 is mounted are not limited by the example shown in FIG. 1 and may be modified depending on the types of ramp meter 140, mounting structure 150 and/or the supporting device 160 to achieve desirable detecting performance.

For example, FIG. 2 illustrates a block diagram of an exemplary server 120 for traffic control, according to embodiments of the disclosure. Consistent with the present disclosure, server 120 may receive road map data 201 and vehicle trajectory data 203 from navigation device 110 and may send green split time 205 to ramp meter 140. Based on vehicle trajectory data 203, server 120 may determine at least one bottleneck in a traffic flow and estimate traffic volume accordingly. Server 120 may then simulate a traffic speed based on the estimated traffic volume and calibrate the simulation with spatial and temporal speed data acquired from the trajectory data (e.g., minimizing the simulated traffic speed and the measured traffic speed) . Then server 120 may predict future traffic flow based on the simulation. Server 120 may then control the green-split time of ramp meter 140 for traffic management according to the future traffic flow prediction. In some embodiments, server 120 may further generate a visualization of traffic flow using road map data 201 to provides a visualized view of the freeway traffic flow in a map.

In some embodiments, as shown in FIG. 2, server 120 may include a communication interface 202, a processor 204, a memory 206, and a storage 208. In some embodiments, server 120 may have different modules in a single device, such as an integrated circuit (IC) chip (implemented as an application-specific integrated circuit (ASIC) or a field-programmable gate array (FPGA) ) , or separate devices with dedicated functions. In some embodiments, one or more components of server 120 may be located in a cloud or may be alternatively in a single location (such as inside navigation device 110) or distributed locations. Components of server 120 may be in an integrated device or distributed at different locations but communicate with each other through a network (not shown) .

Communication interface 202 may send data to and receive data from components such as navigation device 110 and ramp meter 140 via communication cables, a Wireless Local Area Network (WLAN) , a Wide Area Network (WAN) , wireless networks such as radio waves, a cellular network, and/or a local or short-range wireless network (e.g., Bluetooth ^TM) , or other communication methods. In some embodiments, communication interface 202 can be an integrated services digital network (ISDN) card, cable modem, satellite modem, or a modem to provide a data communication connection. As another example, communication interface 202 can be a local area network (LAN) card to provide a data communication connection to a compatible LAN. Wireless links can also be implemented by communication interface 202. In such an implementation, communication interface 202 can send and receive electrical, electromagnetic or optical signals that carry digital data streams representing various types of information via a network.

Consistent with some embodiments, communication interface 202 may receive data regarding the mobility of vehicle 101 that consists of vehicle trajectory data 203 and road map data 201 captured by navigation device 110. In some embodiments, vehicle trajectory data 203 includes GPS coordinates acquired by navigation device 110. Communication interface 202 may further provide the received data to storage 208 for storage or to processor 204 for processing. Communication interface 202 may also transmit control signals that consist of green-split time 205 to ramp meter 140 to control the traffic. In some embodiments, green-split time 205 is encoded into electronic signals that consists of traffic information (e.g., green-split time and/or cycle length) processed by processor 204.

Processor 204 may include any appropriate type of general-purpose or special-purpose microprocessor, digital signal processor, or microcontroller. Processor 204 may be configured as a separate processor module dedicated to determination of an optimized green-split time of a ramp meter. Alternatively, processor 204 may be configured as a shared processor module for performing other functions unrelated to optimizing green-split time of a ramp mete based on vehicle trajectory data.

As shown in FIG. 2, processor 204 may include multiple modules, such as a traffic diagnosis unit 210, a traffic volume estimation unit 212, a traffic simulation unit 214, a traffic control unit 216 and the like. These modules (and any corresponding sub-modules or sub-units) can be hardware units (e.g., portions of an integrated circuit) of processor 204 designed for use with other components or software units implemented by processor 204 through executing at least part of a program. The program may be stored on a computer-readable medium, and when executed by processor 204, it may perform one or more functions. Although FIG. 2 shows units 210-216 all within one processor 204, it is contemplated that these units may be distributed among multiple processors located near or remotely with each other.

Traffic diagnosis unit 210 may be configured to determine at least one bottleneck in a traffic flow based on vehicle trajectory data 203. For example, the bottleneck may be a standing queue bottleneck or a moving jam. In some embodiments, traffic diagnosis unit 210 may determine the bottleneck based on a spatial and temporal distribution of speed. For example, each and every speed within a range (e.g., 0-80 km/h) may be associated with a road section spatially and a time interval (e.g., set a duration of time interval as 5 minutes) temporally. The activation of a bottleneck is identified when the speed within a road section drops conspicuously while its downstream section still flows in free state. The place where the bottleneck is activated is determined as the location of the bottleneck. In some embodiments, traffic diagnosis unit 210 may further be configured to identify a congestion area triggered by the bottleneck. For example, traffic diagnosis unit 210 may apply a depth-first-search algorithm to identify the border of the traffic congestion that is triggered from the bottleneck.

For example, FIG. 4 illustrates an exemplary traffic diagnosis of the traffic control system, according to embodiments of the disclosure. A space-time diagram 400 is shown in FIG. 4. In diagram 400, each and every speed from 0-80 km/h corresponds to the road section spatially and to a time interval temporally. For example, the time interval in diagram 400 is 5 minutes. The bottleneck can be identified where the speed within a road section drops conspicuously while its downstream section still flows in free state (e.g., the two red-parts in the lower part of diagram 400) .

Return to FIG. 2, based on the determined bottleneck in the traffic flow, traffic volume estimation unit 212 may be configured to estimate a traffic volume associated with the bottleneck. In some embodiments, traffic volume estimation unit 212 may estimate a fundamental diagram (FD) of the road section and use the estimation to describe the relationship between traffic density and traffic flow. For example, traffic volume estimation unit 212 may use a triangular FD method to represent the relationship. For example, traffic estimation unit 212 may use a free-flow speed, capacity and jam density to represent the relationship. In some embodiments, the free-flow speed may be determined as the maximum speed limit of the freeway, capacity is the freeway-capacity before the jam occurs and the jam density may be assumed as a fixed value. In some embodiments, traffic volume estimation unit 212 may estimate the traffic volume based on the estimated FD and the measured speed contained in vehicle trajectory data 203.

Based on the estimated traffic volume, traffic simulation unit 214 may be configured to simulate the traffic speed. In some embodiments, traffic simulation unit 214 may apply a macroscopic first-order model (e.g., the cell transmission model or its variants) to simulate the traffic flow. Traffic simulation unit 214 may further be configured to calibrate the model parameters and traffic demand using optimization approaches. For example, the objective of the optimization approach is to minimize the difference between the simulated speed by traffic simulation unit 214 and the measured speed contained in vehicle trajectory data 203. In some embodiments, based on the calibrated simulation model, traffic simulation unit 214 may be configured to predict future traffic flow. For example, traffic simulation unit 214 may use the model to make short-term traffic flow predictions.

Based on the prediction, traffic control unit 216 may be configured to control the traffic. In some embodiments, traffic control unit 216 may use an adaptive ramp meter control approach to control the traffic. For example, traffic control unit 216 may use an ALINEA-type approach (e.g., applying a feedback regulator that is based on mainstream measurements of the downstream ramp occupancy) . In some embodiments, the feedback regulator is designed based on measurements of speed downstream of the ramp.

In another embodiment, traffic control unit 216 may use a fixed-time control strategy that is derived offline for particular time-of-day based on historical demands. For example, traffic control unit 216 may optimize green-split time for ramp meter 140 to maximize the capacity flows within a target area.

Memory 206 and storage 208 may include any appropriate type of mass storage provided to store any type of information that processor 204 may need to operate. Memory 206 and storage 208 may be a volatile or non-volatile, magnetic, semiconductor, tape, optical, removable, non-removable, or other type of storage device or tangible (i.e., non-transitory) computer-readable medium including, but not limited to, a ROM, a flash memory, a dynamic RAM, and a static RAM. Memory 206 and/or storage 208 may be configured to store one or more computer programs that may be executed by processor 204 to perform traffic control disclosed herein. For example, memory 206 and/or storage 208 may be configured to store program (s) that may be executed by processor 204 to control traffic based on vehicle trajectory data.

Memory 206 and/or storage 208 may be further configured to store information and data used by processor 204. For instance, memory 206 and/or storage 208 may be configured to store the various types of data (e.g., road map data, vehicle trajectory data, traffic information data etc. ) captured by navigation device 110. Memory 206 and/or storage 208 may also store intermediate data such as optimization models, bottleneck parameters, travel volumes, simulated traffic speed, and future traffic flows, etc. The various types of data may be stored permanently, removed periodically, or disregarded immediately after each frame of data is processed.

FIG. 3 illustrates a flowchart of an exemplary method 300 for traffic control, according to embodiments of the disclosure. In some embodiments, method 300 may be implemented by a traffic control system 100 that includes, among other things, server 120, and ramp meter 140. However, method 300 is not limited to that exemplary embodiment. Method 300 may include steps S302-S314 as described below. It is to be appreciated that some of the steps may be optional to perform the disclosure provided below. It is also to be appreciated that some of the steps may be optional to perform the disclosure provided herein. Further, some of the steps may be performed simultaneously, or in a different order than shown in FIG. 3.

In step S302, server 120 may receive vehicle trajectory data 203 and road map data 201 associated with a traffic flow acquired by navigation device 110. Navigation device 110 may collect vehicle 101’s position information at certain time intervals (e.g., 0.5s or 1s) in sequence to obtain vehicle trajectory data 203. In some embodiments, server 120 may calculate vehicle 101’s speed based on the time interval and the change of position meanwhile. For example, server 120 may divide the distance between a first position and a second position by the time interval between the time points information of the two positions was obtained. Server 120 may use the average speed between the two positions as the representation of the vehicle 101’s speed while vehicle 101 travels from the first position to the second position if the time interval is small enough (e.g., set the time interval as 0.5s) .

In step S304, server 120 may determine at least one bottleneck in the traffic flow based on vehicle trajectory data 203. In some embodiments, server 120 may determine the bottleneck based on a spatial and temporal distribution of speed where vehicles’ speed is distributed among both time and space. For example, server 120 may associate each and every speed within a range (e.g., 0-80 km/h, and can be colored to show different speed) to a road section (e.g., a portion of freeway within a target area) spatially and a time interval (e.g., set a duration of time interval as 1 minute or 5 minutes) temporally. The starting point of a bottleneck is identified on the time-space diagram where the speed within a road section drops conspicuously while its downstream section still flows in a free state. In some embodiments, server 120 may further identify a congestion area triggered by the determined bottleneck. For example, server 120 may apply the depth-first-search algorithm to identify the border of the traffic congestion that is triggered from the bottleneck according to Equation (1)

where s is the congestion area, i is a road section index (e.g., a target area include 5 road sections and the third road section’s index is 3) , and t is time index in the congestion (e.g., a total data collecting time of 3 hours with an interval of 5 minutes, the time index for data collected at the 30-minute time point is 6) , l _i is the length of section I, v _f is the free-flow speed and v _i (t) is the speed of road section i in time interval t.

In step S306, server 120 may estimate the traffic volume of the identified bottleneck based on vehicle trajectory data 203. In some embodiments, server 120 may estimate a fundamental diagram (FD) of the road section which may be used to describe the relationship between traffic density and traffic flow. For example, server 120 may use a triangular FD to represent the relationship. Server 120 may determine parameters characterizing the traffic volume, which include, e.g., the free-flow speed, the capacity and the jam density to the triangular FD. Typically, the free-flow speed and the critical speed in a triangular FD are the same, which is not realistic according to empirical findings. To differentiate the free-flow speed and critical speed, server 120 may assume a second-order function to represent the left part of the FD. Thus, the present FD is a piecewise function, in which server 120 assumes a second-order function for traffic density lower than the critical value and a first-order function for traffic density higher than the critical value. In some embodiments, the free-flow speed is determined as the maximum speed limit of the freeway. Critical speed corresponds to the average speed of traffic flow when traffic volume reaches the capacity and can be measured at the time point right before the traffic is broken down band the bottleneck. Also, critical speed can be calculated as the total travel distance over the total travel time of those trajectories.

In some embodiments, the jam density may be determined based on empirical evidence. Determination of the jam density may depend on the average length of vehicle bodies. For example, the jam density may be 135veh/h based on empirical evidence.

When the jam density and the critical speed are known, server 120 may derive the capacity based on the congestion wave speed. The congestion wave speed is indicative of the propagation speed of traffic jams. When traffic is in the car-following state, i.e., the right part of the FD, if the leading vehicle decelerates and changes his speed to a lower value, the new traffic state will propagate to the following vehicles. The backwards propagation speed of traffic state is known as the congestion wave speed. To determine the congestion wave speed, server 120 may identify conspicuous deceleration of two consecutive trajectories and calculate the wave speed. Server 120 may further filter unrealistic waves and determine the average of all remaining wave speeds to be the congestion wave speed.

In some embodiments, server 120 may estimate the traffic volume based on the estimated FD and the measured speed acquired contained in vehicle trajectory data 203 according to equation (2) :

where

is the space-mean flow, B is the area in the time-space diagram, d is the average distance driven by vehicle 101 in the target area, L is the total length of the target area, T is the total data collecting time.

In step S308, server 120 may simulate traffic speed based on the estimated traffic volume. In some embodiments, server 120 may apply a macroscopic first-order model to simulate the traffic flow. For example, server 120 may use the cell transmission model (CMT) or its variants in which the dynamics of variables (e.g., traffic density) may be captured to simulate traffic speed based on the estimated traffic flow.

In step S310, server 120 may be further configured to calibrate the model parameters and traffic demand using optimizations that minimize the difference between simulated speed and measured speed from vehicle trajectory data 203. For example, server 120 may calibrate the model based on comparing the estimated traffic speed with the measured traffic speed in real time. In some embodiments, based on the calibrated simulation model, server 120 may be configured to predict a future traffic flow. For example, server 120 may use the model to make short-term traffic flow predictions.

In step S312, server 120 may control traffic based on the predicted future traffic flow. In some embodiments, server 120 may use an adaptive ramp meter control approach to determine a green-split time for ramp meter 140. For example, server 120 may use an ALINEA-type approach (e.g., applying a feedback regulator that is based on mainstream measurements of the downstream ramp occupancy) . In some embodiments, the feedback regulator is designed based on measurements of speed downstream of the ramp.

In another embodiment, server 120 may use a fixed-time control strategy that is derived offline for a particular time-of-day based on constant historical demands to determine a green-split time for ramp meter 140. For example, traffic control unit 216 may optimize green-split time for ramp meters to maximize the capacity flows within a target area. Server 120 may send the determined green-split time 205 to ramp meter 140 to control the traffic within the target area.

In some embodiments, in step S314, server 120 may generate a visualization of traffic flow using road map data 201 to show the future traffic flow. For example, road map data 201 acquired by navigation device 110 may be used to construct the topology graph of the target area for visualization purposes. Server 120 may further associate the short-term traffic flow prediction to the constructed topology graph of the target area to provide a brief view of traffic status of the freeway. The visualization may be provided to vehicle 101 or a terminal device such as a mobile phone, which render the visualization for displaying to a user.

FIG. 5 illustrates an exemplary visualization 500 provided by traffic control system 100, according to embodiments of the disclosure. As shown in FIG. 5, short-term traffic flow prediction is superimposed or otherwise rendered into a topology graph constructed based on road map data 201 acquired by navigation device 110. For example, in visualization 500, the colored line on the graph is the part of a freeway where short-term traffic flow prediction is made. Different colors represent different traffic speeds. For example, in visualization 500, red indicates the congested area (e.g., a standing queue) , yellow indicates slow traffic (e.g., a moving jam) , and green indicates normal traffic (e.g., vehicles moving at a free-flow speed) . Additionally, visualization 500 may be used for presenting a brief view of traffic status of the freeway, for traffic management and/or for making individual travel plans.

Another aspect of the disclosure is directed to non-transitory computer-readable medium storing instructions which, when executed, cause one or more processors to perform the methods, as discussed above. The computer-readable medium may include volatile or non-volatile, magnetic, semiconductor, tape, optical, removable, non-removable, or other types of computer-readable medium or computer-readable storage devices. For example, the computer-readable medium may be the storage device or the memory module having the computer instructions stored thereon, as disclosed. In some embodiments, the computer-readable medium may be a disc or a flash drive having the computer instructions stored thereon.

It will be apparent to those skilled in the art that various modifications and variations can be made to the disclosed system and related methods. Other embodiments will be apparent to those skilled in the art from consideration of the specification and practice of the disclosed system and related methods.

It is intended that the specification and examples be considered as exemplary only, with a true scope being indicated by the following claims and their equivalents.

Claims

A method for traffic control based on vehicle trajectory data comprises:

receiving, by a communication interface, the vehicle trajectory data associated with a traffic flow from at least one navigation device;

determining, by at least one processor, at least one bottleneck in the traffic flow based on the vehicle trajectory data;

estimating, by the at least one processor, a traffic volume associated with the bottleneck based on the vehicle trajectory data;

predicting, by the at least one processor, a future traffic flow based on the estimated traffic volume; and

controlling traffic based on the predicted future traffic flow.
The method of claim 1, wherein controlling the traffic further comprises determining a green-split time for a ramp meter based on the predicted future traffic flow.
The method of claim 1, wherein determining the at least one bottleneck further comprises:

determining a spatial-temporal distribution of speed based on the vehicle trajectory data; and

identifying the at least one bottleneck using the spatial-temporal distribution of speed.
The method of claim 1, wherein determining the at least one bottleneck further comprises:

determining a location of the bottleneck; and

determining a congestion area triggered from the bottleneck.
The method of claim 4, wherein the congestion area is determined based on a depth-first-search algorithm.
The method of claim 1, wherein estimating the traffic volume further comprises determining at least one of a free-flow speed of the traffic flow, a road capacity, and a jam density associated with the traffic flow.
The method of claim 1, further comprising:

receiving, by a communication interface, road map data; and

generating, by the at least one processor, a visualization of the traffic flow based on the road map data and the future traffic flow.
The method of claim 1, wherein the at least one navigation device is associated with a vehicle traveling along a trajectory.
The method of claim 1, wherein the at least one bottleneck is a standing queue or a moving jam.
The method of claim 1, wherein estimating the traffic volume further comprises determining a congestion wave speed.
The method of claim 1, wherein predicting the future traffic flow further comprises:

simulating a traffic speed based on the estimated traffic volume using a macroscopic model; and

minimizing a difference between the simulated traffic speed and a measured traffic speed.
A system for traffic control based on vehicle trajectory data comprises:

a communication interface configured to receive the vehicle trajectory data associated with a traffic flow from at least one navigation device;

at least one processor configured to:

determine at least one bottleneck in the traffic flow based on the vehicle trajectory data;

estimate a traffic volume associated with the bottleneck based on the vehicle trajectory data;

predict a future traffic flow based on the estimated traffic volume; and

control traffic based on the predicted future traffic flow; and

a storage configured to store the trajectory data and the predicted future traffic flow.
The system of claim 12, wherein the at least one processor is further configured to determine a green-split time for a ramp meter based on the predicted future traffic flow.
The system of claim 12, wherein the at least one processor is further configured to:

determine a spatial-temporal distribution of speed based on the vehicle trajectory data; and

identify the at least one bottleneck using the spatial-temporal distribution of speed.
The system of claim 12, wherein to determine the at least one bottleneck the at least one processor is further configured to:

determine a location of the bottleneck; and

determining a congestion area triggered from the bottleneck.
The system of claim 15, wherein the congestion area is determined based on a depth-first-search algorithm.
The system of claim 12, wherein to estimate the traffic volume the at least one processor is further configured to determine at least one of a free-flow speed of the traffic flow, a road capacity, and a jam density associated with the traffic flow.
The system of claim 12, wherein the at least one processor is further configured to:

receive road map data; and

generate a visualization of the traffic flow based on the road map data and the future traffic flow.
The system of claim 12, wherein to predict the future traffic flow the at least one processor is further configured to:

simulate a traffic speed based on the estimated traffic volume using a macroscopic model; and

minimize a difference between the simulated traffic speed and a measured traffic speed.
A non-transitory computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by at least one processor, performs a method for traffic control based on vehicle trajectory data, the method comprising:

receiving the vehicle trajectory data associated with a traffic flow from at least one navigation device;

determining at least one bottleneck in the traffic flow based on the vehicle trajectory data;

estimating a traffic volume associated with the bottleneck based on the vehicle trajectory data;

predicting a future traffic flow based on the estimated traffic volume; and

controlling traffic based on the predicted future traffic flow.