Intersection signal priority method, system, device and medium based on intelligent networked vehicle trajectory prediction function

Abstract

The application provides a kind of intersection signal priority method based on intelligent network connection vehicle trajectory prediction function, the method comprises: obtaining the historical trajectory data of intersection motor vehicle and the real-time trajectory data of signal priority vehicle, the signal priority vehicle is the vehicle needing priority passage;According to the historical trajectory data, trajectory prediction model is trained, to obtain trained trajectory prediction model, the trained trajectory prediction model is used to predict the time required for vehicle to reach intersection stop line;According to the real-time trajectory data of signal priority vehicle and the trained trajectory prediction model, the time required for signal priority vehicle to reach intersection stop line is obtained;The signal timing scheme of intersection is obtained, and the signal timing scheme is dynamically adjusted according to the time required for signal priority vehicle to reach intersection stop line, to obtain signal priority timing scheme;Signal light timing control is carried out according to the signal priority timing scheme.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation, and in particular to a method, system, device, and readable medium for prioritizing intersection signals based on intelligent connected vehicle trajectory prediction. Background Technology

[0002] With the development of the automotive industry and the acceleration of urbanization, urban traffic congestion and traffic accidents have become increasingly prominent problems. Traffic signal control, as a common traffic management method, has become an important means to solve urban traffic congestion and traffic accidents.

[0003] In the field of intelligent transportation technology, with the continuous development of intelligent and automated technologies, the application of intelligent connected vehicles is becoming increasingly widespread. Intelligent connected vehicles have the ability to acquire real-time vehicle and road condition information and can communicate and coordinate with traffic facilities and other vehicles to achieve more efficient, safe, and intelligent transportation. However, at traffic bottlenecks such as intersections, the advantages of intelligent connected vehicles are not fully realized because intersection signal control systems are typically based on static timing schemes and cannot be dynamically adjusted according to real-time traffic conditions, making it difficult to support signal priority passage for intelligent connected vehicles. Summary of the Invention

[0004] One objective of this application is to provide an intersection signal priority algorithm, system, device, and readable medium based on intelligent connected vehicle trajectory prediction, at least to enable the method to dynamically predict vehicle trajectories, improve the passage efficiency of vehicles requiring priority, and alleviate traffic congestion.

[0005] To achieve the above objectives, this application provides a method for prioritizing traffic signals at intersections based on the trajectory prediction function of intelligent connected vehicles. The method includes: acquiring historical trajectory data of motor vehicles at the intersection and real-time trajectory data of vehicles with priority to traffic signals, wherein the vehicles with priority to traffic signals are those requiring priority passage; training a trajectory prediction model based on the historical trajectory data to obtain a trained trajectory prediction model, wherein the trained trajectory prediction model is used to predict the time required for a vehicle to reach the stop line at the intersection; obtaining the time required for the vehicles with priority to traffic signals to reach the stop line at the intersection based on the real-time trajectory data of the vehicles with priority to traffic signals and the trained trajectory prediction model; acquiring a traffic signal timing scheme for the intersection; dynamically adjusting the traffic signal timing scheme based on the time required for the vehicles with priority to traffic signals to reach the stop line at the intersection to obtain a priority traffic signal timing scheme; and performing traffic light timing control based on the priority traffic signal timing scheme.

[0006] Furthermore, the acquisition of historical trajectory data of motor vehicles at the intersection and real-time trajectory data of vehicles with priority to traffic signals includes: acquiring in real-time trajectory sequence data of vehicles within the traffic light intersection range uploaded by the roadside perception system through a cloud control platform in an intelligent connected environment.

[0007] Furthermore, training the trajectory prediction model based on the historical trajectory data includes: dividing the traffic light intersection area into several sub-segments; mapping the vehicle trajectory sequence data to the sub-segments; determining a probability function based on the number of trajectory positions within the sub-segments; calculating the trajectory similarity between the real-time trajectory data of the signal-priority vehicle and the trajectory prediction model based on the probability function; and determining the calculation result with the highest similarity among the trajectory similarity calculation results as the vehicle trajectory prediction set.

[0008] Furthermore, the step of determining the probability function based on the random variable and calculating the trajectory similarity includes: determining the probability function of the random variable through nonparametric fitting, and calculating the trajectory similarity between the real-time trajectory data of the signal-priority vehicle and the trajectory prediction model through similarity calculation.

[0009] Further, the step of dynamically adjusting the signal timing scheme based on the time required for the priority vehicle to reach the stop line at the intersection includes: obtaining the current remaining green light duration and the scheduled green light duration at the intersection according to the timing scheme; comparing the time required for the priority vehicle to reach the stop line at the intersection with the current remaining green light duration; if the time required for the priority vehicle to reach the stop line is less than the current remaining green light duration, maintaining the current signal timing scheme unchanged; if the time required for the priority vehicle to reach the stop line is greater than the current remaining green light duration, calculating the difference between the time required for the priority vehicle to reach the stop line and the current remaining green light duration, and adding the difference to the scheduled green light duration at the intersection to obtain a sum; if the sum is less than the maximum allowed green light duration at the intersection, extending the green light duration of the signal timing scheme; if the sum is greater than the maximum allowed green light duration at the intersection, maintaining the current signal timing scheme unchanged.

[0010] Further, the step of dynamically adjusting the signal timing scheme based on the time required for the priority vehicle to reach the stop line at the intersection includes: obtaining the remaining red light duration and the scheduled red light duration at the intersection according to the timing scheme; comparing the time required for the priority vehicle to reach the stop line at the intersection with the remaining red light duration; if the time required for the priority vehicle to reach the stop line is greater than the remaining red light duration, maintaining the current signal timing scheme unchanged; if the time required for the priority vehicle to reach the stop line is less than the remaining red light duration, calculating the difference between the time required for the priority vehicle to reach the stop line and the remaining red light duration, and subtracting the difference from the scheduled red light duration at the intersection to obtain the difference value; if the difference value is greater than the minimum allowed red light duration at the intersection, reducing the red light duration of the signal timing scheme; if the difference value is less than the minimum allowed red light duration at the intersection, maintaining the current signal timing scheme unchanged.

[0011] Furthermore, the traffic light timing control according to the signal priority timing scheme includes: sharing the signal priority timing scheme with the traffic signal control system of the transportation department through the cloud control platform, and performing the traffic light timing control.

[0012] Some embodiments of this application also provide an intersection signal priority system based on intelligent connected vehicle trajectory prediction function. The system includes: a prediction module, which acquires historical trajectory data of motor vehicles at the intersection and real-time trajectory data of signal priority vehicles, wherein the signal priority vehicles are vehicles that need to pass first; trains a trajectory prediction model based on the historical trajectory data to obtain a trained trajectory prediction model, wherein the trained trajectory prediction model is used to predict the time required for a vehicle to reach the stop line at the intersection; and obtains the time required for the signal priority vehicles to reach the stop line at the intersection based on the real-time trajectory data of the signal priority vehicles and the trained trajectory prediction model; a timing module, which acquires the signal timing scheme of the intersection, dynamically adjusts the signal timing scheme based on the time required for the signal priority vehicles to reach the stop line at the intersection to obtain a signal priority timing scheme; and performs traffic light timing control based on the signal priority timing scheme.

[0013] Some embodiments of this application also provide an intelligent traffic signal control device, the device comprising: one or more processors; and a memory storing computer program instructions, which, when executed, cause the processor to perform the method described above.

[0014] Some embodiments of this application also provide a computer-readable medium having computer program instructions stored thereon, which can be executed by a processor to implement the signal priority method described above.

[0015] Compared to existing technologies, the solution provided in this application, a method for prioritizing traffic signals at intersections based on intelligent connected vehicle trajectory prediction, involves acquiring historical trajectory data of motor vehicles at the intersection and real-time trajectory data of vehicles with priority to traffic signals (vehicles requiring priority passage); training a trajectory prediction model based on the historical trajectory data to obtain a trained trajectory prediction model, which predicts the time required for a vehicle to reach the stop line at the intersection; obtaining the time required for the vehicle to reach the stop line based on the real-time trajectory data of the vehicles with priority to traffic signals and the trained trajectory prediction model; acquiring a traffic signal timing scheme for the intersection; dynamically adjusting the traffic signal timing scheme based on the time required for the vehicles with priority to traffic signals to reach the stop line at the intersection to obtain a priority traffic signal timing scheme; and performing traffic light timing control based on the priority traffic signal timing scheme. This provides a feasible method for predicting the arrival time of intelligent connected vehicles at signalized intersections. The intersection signal priority algorithm based on intelligent connected vehicle trajectory prediction can scientifically determine whether to give the intersection signal priority based on the vehicle's arrival time at the intersection, avoiding the insufficient accuracy of calculating the vehicle's arrival time at the intersection using a kinematic model based solely on the vehicle's position. It also has strong adaptability, improving the traffic efficiency of intelligent connected vehicles passing through signalized intersections. Attached Figure Description

[0016] Figure 1 A flowchart of an intersection signal priority method based on intelligent connected vehicle trajectory prediction function provided in this application embodiment;

[0017] Figure 2 This is a structural diagram of an intelligent traffic signal control device provided in an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] This application provides a method for prioritizing intersection signals based on intelligent connected vehicle trajectory prediction, such as... Figure 1As shown, the method includes: acquiring historical trajectory data of motor vehicles at the intersection and real-time trajectory data of vehicles with priority to traffic signals, wherein the vehicles with priority to traffic signals are those that need to pass first; training a trajectory prediction model based on the historical trajectory data to obtain a trained trajectory prediction model, wherein the trained trajectory prediction model is used to predict the time required for a vehicle to reach the stop line at the intersection; obtaining the time required for the vehicles with priority to traffic signals to reach the stop line at the intersection based on the real-time trajectory data of the vehicles with priority to traffic signals and the trained trajectory prediction model; acquiring a signal timing scheme for the intersection; dynamically adjusting the signal timing scheme based on the time required for the vehicles with priority to traffic signals to reach the stop line at the intersection to obtain a signal priority timing scheme; and performing traffic light timing control based on the signal priority timing scheme.

[0020] In existing traffic signal control systems, signal timing schemes are often formulated based on historical traffic flow and time-period statistics. While they can control traffic flow according to different time periods, they are not very adaptable to actual traffic flow conditions. Furthermore, traditional traffic signal control systems often fail to proactively identify and respond to the needs of vehicles with priority, easily leading to excessively long waiting times for these vehicles at intersections, impacting traffic efficiency and public safety.

[0021] The intersection signal priority method based on intelligent connected vehicle trajectory prediction acquires historical and real-time trajectory data, uses a trajectory prediction model to predict the time required for vehicles to reach the intersection stop line, and dynamically adjusts the signal timing scheme to allow priority vehicles to pass through the intersection as quickly as possible, improving traffic efficiency and optimizing the traffic environment. Simultaneously, this method can adaptively adjust the signal timing scheme by monitoring intersection vehicles and traffic conditions in real time, making it more adaptable to the needs of priority vehicles in different traffic scenarios. This intersection signal priority method based on intelligent connected vehicles has advantages such as strong real-time performance, fast response speed, and high efficiency, effectively solving urban traffic congestion and safety problems, and improving traffic efficiency and service quality.

[0022] In some embodiments of this application, the acquisition of historical trajectory data of motor vehicles at intersections and real-time trajectory data of vehicles with priority to traffic signals includes: acquiring in real-time trajectory sequence data of vehicles within the traffic light intersection range uploaded by the roadside perception system through a cloud control platform in an intelligent connected environment.

[0023] In an intelligent connected vehicle environment, the cloud control platform can acquire real-time trajectory sequence data of all traffic participants within the signalized intersection area uploaded by roadside perception systems (such as millimeter-wave radar, radar-visual integrated machines, etc.), especially the continuous trajectory sequence set of all motor vehicles in any direction within the signalized intersection area at past historical moments. Taking a crossroads as an example, assuming the historical trajectory sequence set of all motor vehicles at the east entrance is T = [T1, T2, ..., T...] n], where T i (i∈[1,n]) represents the starting point x that the i-th vehicle can be detected by the roadside sensing system at the east entrance. O End point x at the eastern entrance D The trajectory sequence set of (i.e., the stop line at the eastern entrance). Where u i,j Let u be the trajectory location data of the i-th vehicle and the j-th vehicle. i,j ={x i,j ,y i,j}, x i,j y i,j Let be the latitude and longitude coordinates of the j-th trajectory position of the i-th motor vehicle.

[0024] Real-time vehicle trajectory data can be collected through various types of sensing devices, such as cameras, LiDAR, and millimeter-wave radar. In practical applications, the selection of appropriate sensing devices will affect data quality and real-time performance. Besides real-time vehicle trajectory data, historical trajectory data can also be obtained from different sources, such as road monitoring systems, vehicle-mounted sensors, and mobile devices. This data can improve the accuracy and generalization ability of trajectory prediction models. Trajectory sequence data can include multi-dimensional information, such as vehicle position, speed, acceleration, lane, and vehicle type. This information can be processed through data preprocessing and feature extraction to improve the accuracy and stability of trajectory prediction. In addition to acquiring vehicle trajectory sequence data uploaded by roadside sensing systems through cloud control platforms, other methods can be used to acquire historical and real-time trajectory data. For example, a data center can be built within an intelligent traffic management center or traffic control center to acquire historical trajectory data of motor vehicles at intersections and real-time trajectory data of vehicles with signal priority through vehicle-mounted communication technology, edge computing devices, or other data acquisition devices, and then upload this data to the cloud for processing and analysis. Furthermore, real-time trajectory data of vehicles can be acquired by equipping them with sensors and other devices, and then uploaded to the cloud for processing and analysis to enable trajectory prediction for intelligent connected vehicles. These methods can all be used to obtain historical trajectory data of motor vehicles at intersections and real-time trajectory data of vehicles with signal priority, in order to perform trajectory prediction and signal priority control.

[0025] In some embodiments of this application, training the trajectory prediction model based on the historical trajectory data includes: dividing the traffic light intersection area into several sub-segments; mapping the vehicle trajectory sequence data to the sub-segments, and determining a probability function based on the number of trajectory positions within the sub-segments; calculating the trajectory similarity between the real-time trajectory data of the signal-priority vehicle and the trajectory prediction model based on the probability function; and determining the calculation result with the highest similarity among the trajectory similarity calculation results as the vehicle trajectory prediction set.

[0026] Specifically, it includes the following sub-steps:

[0027] First, put all T i Substituting (i∈[1,n]) into T, we can obtain the historical dataset of trajectory sequences of all motor vehicles at the eastern entrance of the intersection. That is, to obtain the starting point x of all traffic participants at the east entrance of the intersection that can be perceived by the roadside perception system at the east entrance. O End point x at the eastern entrance D Historical dataset of trajectory sequences.

[0028] Sub-step 1 will determine the starting point x that the east entrance roadside sensing system can detect. O End point x at the eastern entrance D The road segment is divided into K equal parts, L=[l1,l2,…,l K ],

[0029] Sub-step 2 The trajectory sequence set of the i-th vehicle is used to geomap the corresponding trajectory points to the sub-road segments divided in sub-step 1 based on the latitude and longitude coordinates of the trajectory locations. Assume that for... There are m trajectory points falling into sub-segment l k ,Right now

[0030] Sub-step 3 considers the number of vehicle trajectory sequences falling within any sub-segment as a random variable ξ, and defines the probability function of the random variable ξ as p(ξ), F(ξ)=∑ ξ≤x p(ξ=x). For Using the trajectory sequence set of the i-th motor vehicle to analyze the random variable ξ i Nonparametric fitting is performed on the probability function to obtain n probability functions p(ξ). i (i∈[1,n]).

[0031] Sub-step 4 uses the real-time trajectory data T uploaded to the cloud control platform by the (n+1)th intelligent connected vehicle. n+1 Statistical T n+1 The number of trajectory positions falling into K sub-segments is used to obtain the probability function p(ξ) of the random variable ξ through nonparametric fitting. n+1 Then, p(ξ) is calculated using KL divergence. n+1 ) and p(ξ i The probability similarity of (i∈[1,n]) is used to identify the set of motor vehicle trajectory sequences most similar to the trajectory sequence of the (n+1)th intelligent connected vehicle, and the most similar motor vehicle arrives at the endpoint x at the east entrance. D The time required is taken as the time required for the (n+1)th intelligent connected vehicle to reach the stop line at the east entrance.

[0032] In some embodiments of this application, determining the probability function based on the random variable and calculating the trajectory similarity includes: determining the probability function of the random variable through nonparametric fitting, and calculating the trajectory similarity between the real-time trajectory data of the signal-priority vehicle and the trajectory prediction model through similarity calculation.

[0033] Training the trajectory prediction model involves dividing the intersection into multiple sub-segments based on historical trajectory data, each containing several historical trajectory points. For each sub-segment, the k closest historical trajectory points to the current prediction point are calculated, and the information from these k points is aggregated to obtain a probability function. This probability function describes the trajectory distribution of the k closest historical trajectory points to the current prediction point within that sub-segment. During real-time prediction, for each signal-priority vehicle, its real-time trajectory points are mapped to the corresponding sub-segment, and its similarity to historical trajectories is calculated based on the probability function within that sub-segment. Finally, for each sub-segment, the k historical trajectory points with the highest similarity are selected, and these points form the prediction set. For each prediction set, common regression algorithms, such as linear regression and multinomial regression, are used to train a trajectory prediction model to predict the arrival time of vehicles in that sub-segment. Combining the trajectory prediction models for all sub-segments yields the trajectory prediction model for the entire intersection.

[0034] In some embodiments of this application, the step of dynamically adjusting the signal timing scheme based on the time required for the signal-priority vehicle to reach the stop line at the intersection includes: obtaining the remaining green light duration and the scheduled green light duration at the intersection according to the timing scheme; comparing the time required for the signal-priority vehicle to reach the stop line at the intersection with the remaining green light duration; when the time required for the signal-priority vehicle to reach the stop line is less than the remaining green light duration, maintaining the current signal timing scheme unchanged; when the time required for the signal-priority vehicle to reach the stop line is greater than the remaining green light duration, calculating the difference between the time required for the signal-priority vehicle to reach the stop line and the remaining green light duration, and adding the difference to the scheduled green light duration at the intersection to obtain a sum; if the sum is less than the maximum allowed green light duration at the intersection, extending the green light duration of the signal timing scheme; if the sum is greater than the maximum allowed green light duration at the intersection, maintaining the current signal timing scheme unchanged.

[0035] The system compares the time required for a connected vehicle to reach the stop line at the intersection with the remaining time of the current green light. If the time required is less than the remaining time, the current green light duration remains unchanged. If the time is greater than the remaining time, the system calculates the difference between the time and the remaining time, and then sums the current green light duration with the difference. If the sum is less than the maximum allowed green light duration at the intersection, the green light duration is extended to allow the connected vehicle to pass through the intersection. If the sum is greater than the maximum allowed green light duration, the current timing scheme remains unchanged, and priority passage via the intersection signal cannot be supported.

[0036] The method dynamically adjusts the intersection signal timing scheme by comparing the time required for intelligent connected vehicles to reach the stop line at the intersection with the remaining time of the current green light. The technical effects of this method include: improved efficiency for intelligent connected vehicles passing through intersections: By comparing the time required for intelligent connected vehicles to reach the stop line at the intersection with the remaining time of the current green light, the signal timing scheme can be adjusted in a timely manner, extending the green light duration in advance, ensuring that intelligent connected vehicles have priority to pass through the intersection, thereby reducing traffic congestion and improving intersection throughput. Enhanced flexibility and intelligence of intersection signal control: This method can dynamically adjust the signal timing scheme based on real-time information from intelligent connected vehicles, making full use of intersection resources and improving the flexibility and intelligence of intersection signal control. Reduced risk of traffic accidents: By prioritizing the passage of intelligent connected vehicles, the risk of wasting time due to insufficient green light time for priority passage can be reduced.

[0037] In some embodiments of this application, the step of dynamically adjusting the signal timing scheme based on the time required for the signal-priority vehicle to reach the stop line at the intersection includes: obtaining the remaining red light duration and the scheduled red light duration at the intersection according to the timing scheme; comparing the time required for the signal-priority vehicle to reach the stop line at the intersection with the remaining red light duration at the intersection; when the time required for the signal-priority vehicle to reach the stop line at the intersection is greater than the remaining red light duration at the intersection, keeping the current signal timing scheme unchanged; when the time required for the signal-priority vehicle to reach the stop line at the intersection is less than the remaining red light duration at the intersection, calculating the difference between the time required for the signal-priority vehicle to reach the stop line at the intersection and the remaining red light duration at the intersection, and subtracting the difference from the scheduled red light duration at the intersection to obtain the difference value; if the difference value is greater than the minimum allowed red light duration at the intersection, reducing the red light duration of the signal timing scheme; if the difference value is less than the minimum allowed red light duration at the intersection, keeping the current signal timing scheme unchanged.

[0038] The system compares the time required for a connected vehicle to reach the stop line at the intersection with the remaining time of the current red light. If the time required is longer than the remaining time, the red light duration remains unchanged. If the time is shorter, the system calculates the difference between the time required and the remaining time, and then calculates the difference between the current red light duration and this difference. If the difference is greater than the minimum allowed red light duration at the intersection, the red light is ended earlier to ensure the connected vehicle has priority. If the difference is less than the minimum allowed red light duration, the current timing scheme remains unchanged, and priority passage cannot be supported.

[0039] The method dynamically adjusts the traffic signal timing scheme at intersections by comparing the time required for intelligent connected vehicles to reach the stop line with the remaining time of the current red light. The technical effects of this method include: improved efficiency for intelligent connected vehicles passing through intersections: By comparing the time required for intelligent connected vehicles to reach the stop line with the remaining time of the current red light, the traffic signal timing scheme can be adjusted in a timely manner, ending the red light earlier and ensuring priority passage for intelligent connected vehicles, thereby reducing traffic congestion and improving intersection throughput. Increased flexibility and intelligence of intersection signal control: This method can dynamically adjust the signal timing scheme based on real-time information from intelligent connected vehicles, making full use of intersection resources and improving the flexibility and intelligence of intersection signal control. Reduced risk of traffic accidents: By prioritizing the passage of intelligent connected vehicles, the risk of traffic violations and accidents caused by vehicles waiting too long at red lights can be reduced.

[0040] In some embodiments of this application, the traffic light timing control according to the signal priority timing scheme includes: sharing the signal priority timing scheme with the traffic signal control system of the transportation department through a cloud control platform, and performing the traffic light timing control.

[0041] In intelligent transportation systems, a signal priority method for intersections based on the trajectory prediction function of intelligent connected vehicles is proposed. This method involves acquiring the real-time timing scheme of the intersection's traffic signal control system through a vehicle-road cooperative system, constructing a trajectory prediction model for intelligent connected vehicles, inputting the trajectory sequence of the intelligent connected vehicles to predict the time when the vehicles arrive at the intersection stop line, comparing the trajectory prediction results with the intersection signal timing scheme to confirm whether intersection signal priority is supported and the corresponding strategy. The decision is fed back to the traffic control platform, which issues instructions to dynamically extend the green light time or start the red light time earlier, thereby improving the passage efficiency of vehicles with signal priority.

[0042] The signal priority timing scheme can be shared to the vehicle terminal, which then displays the traffic light timing information at the intersection to the driver, indicating whether the current traffic light supports priority passage for intelligent connected vehicles, thus helping drivers make better driving decisions. Technical effects: Improves the intelligence level of traffic intersections, enabling intelligent signal priority passage and reducing traffic congestion. Enhances road traffic safety and reduces the incidence of traffic accidents. Improves intersection throughput efficiency, shortens vehicle travel time, and reduces emissions pollution. Sharing the signal priority timing scheme through the cloud control platform improves the integration of traffic information and optimizes traffic dispatch management.

[0043] This application provides an intersection signal priority system based on intelligent connected vehicle trajectory prediction. The system includes: a prediction module, which acquires historical trajectory data of motor vehicles at the intersection and real-time trajectory data of signal priority vehicles, wherein the signal priority vehicles are vehicles that need to pass first; trains a trajectory prediction model based on the historical trajectory data to obtain a trained trajectory prediction model, which is used to predict the time required for a vehicle to reach the stop line at the intersection; and obtains the time required for the signal priority vehicle to reach the stop line at the intersection based on the real-time trajectory data of the signal priority vehicle and the trained trajectory prediction model; a timing module, which acquires the signal timing scheme of the intersection, dynamically adjusts the signal timing scheme based on the time required for the signal priority vehicle to reach the stop line at the intersection, and obtains a signal priority timing scheme; and performs traffic light timing control based on the signal priority timing scheme. The prediction module and the timing module are generalizations of the functions of the intersection signal priority method based on intelligent connected vehicle trajectory prediction. In practical applications, the system may not be limited to these two modules.

[0044] Furthermore, embodiments of this application provide an intelligent traffic signal control device, the structure of which is as follows: Figure 2 As shown, the device includes a memory 90 for storing computer-readable instructions and a processor 100 for executing the computer-readable instructions, wherein when the computer-readable instructions are executed by the processor, the processor is triggered to execute the signal priority method described above.

[0045] The methods and / or embodiments in this application can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. When the computer program is executed by a processing unit, it performs the functions defined in the methods of this application.

[0046] It should be noted that the computer-readable medium described in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0047] In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wireline, optical fiber, RF, etc., or any suitable combination thereof.

[0048] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0049] The flowcharts or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-specific system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0050] In another aspect, embodiments of this application also provide a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The aforementioned computer-readable medium carries one or more computer-readable instructions, which may be executed by a processor to implement the steps of the methods and / or technical solutions of the various embodiments of this application.

[0051] In a typical configuration of this application, the terminal and the service network devices each include one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0052] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0053] Computer-readable media include both permanent and non-permanent, removable and non-removable media, which can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only optical disc (CD-ROM), digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0054] It should be noted that this application can be implemented in software and / or a combination of software and hardware, for example, using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In some embodiments, the software program of this application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium, such as RAM memory, magnetic or optical drives, floppy disks, and similar devices. Furthermore, some steps or functions of this application can be implemented in hardware, for example, as circuitry that cooperates with a processor to perform the various steps or functions.

[0055] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in the apparatus claims may also be implemented by a single unit or device in software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

Claims

1. A method for prioritizing intersection signals based on intelligent connected vehicle trajectory prediction, characterized in that, The method includes: The historical trajectory data of motor vehicles at the intersection and the real-time trajectory data of vehicles with priority to traffic signals are obtained, wherein the vehicles with priority to traffic signals are those that need to pass first. The trajectory prediction model is trained based on the historical trajectory data to obtain a trained trajectory prediction model, which is used to predict the time required for a vehicle to reach the stop line at the intersection. Based on the real-time trajectory data of the signal-priority vehicle and the trained trajectory prediction model, the time required for the signal-priority vehicle to reach the stop line at the intersection is obtained. Obtain the signal timing scheme of the intersection, and dynamically adjust the signal timing scheme according to the time required for the signal priority vehicle to reach the stop line of the intersection to obtain the signal priority timing scheme; Traffic light timing control is performed according to the aforementioned signal priority timing scheme; The step of training the trajectory prediction model based on the historical trajectory data includes: The area of ​​the traffic light intersection is divided into several sub-segments; The trajectory sequence data of the vehicle is mapped to the sub-road segment, and a probability function is determined based on the number of trajectory positions within the sub-road segment; Based on the probability function, the trajectory similarity between the real-time trajectory data of the signal-priority vehicle and the trajectory prediction model is calculated. The calculation results with the highest similarity among the trajectory similarity calculation results are identified as the vehicle trajectory prediction set; Calculating trajectory similarity based on the probability function includes: The probability function is determined by nonparametric fitting, and the trajectory similarity between the real-time trajectory data of the signal-priority vehicle and the trajectory prediction model is calculated by similarity calculation. The time required to reach the destination corresponding to the vehicle trajectory prediction set is taken as the time required for the signal-priority vehicle to reach the stop line at the intersection.

2. The intersection signal priority method according to claim 1, characterized in that, The acquisition of historical trajectory data of motor vehicles at intersections and real-time trajectory data of vehicles with priority on traffic signals includes: The cloud control platform in the intelligent connected environment acquires real-time trajectory sequence data of vehicles within the signal light intersection range uploaded by the roadside perception system.

3. The intersection signal priority method according to claim 1, characterized in that, The method of dynamically adjusting the signal timing scheme based on the time required for the signal-priority vehicle to reach the stop line at the intersection includes: Based on the timing scheme, the remaining green light duration at the intersection and the timing green light duration at the intersection are obtained; Compare the time required for the signal-priority vehicle to reach the stop line at the intersection with the remaining time of the current green light at the intersection; When the time required for the signal-priority vehicle to reach the stop line at the intersection is less than the remaining duration of the current green light at the intersection, the current signal timing scheme remains unchanged. If the time required for the vehicle with priority to reach the stop line at the intersection is greater than the remaining duration of the current green light at the intersection, the difference between the time required for the vehicle with priority to reach the stop line at the intersection and the remaining duration of the current green light at the intersection is calculated. This difference is then added to the green light duration of the intersection to obtain a sum. If the sum is less than the maximum allowed green light duration at the intersection, the green light duration of the signal timing scheme is extended. If the sum is greater than the maximum allowed green light duration at the intersection, the current signal timing scheme remains unchanged.

4. The intersection signal priority method according to claim 1, characterized in that, The method of dynamically adjusting the signal timing scheme based on the time required for the signal-priority vehicle to reach the stop line at the intersection includes: Based on the timing scheme, the remaining duration of the current red light at the intersection and the duration of the red light at the intersection with the timing scheme are obtained; Compare the time required for the signal-priority vehicle to reach the stop line at the intersection with the remaining duration of the current red light at the intersection; If the time required for the signal-priority vehicle to reach the stop line at the intersection is greater than the remaining duration of the current red light at the intersection, the current signal timing scheme remains unchanged. If the time required for a vehicle with priority to reach the stop line at the intersection is less than the remaining duration of the current red light at the intersection, the difference between the time required for the vehicle with priority to reach the stop line and the remaining duration of the current red light at the intersection is calculated. This difference is then subtracted from the red light duration of the intersection. If the difference is greater than the minimum allowed red light duration at the intersection, the red light duration of the signal timing scheme is reduced. If the difference is less than the minimum allowed red light duration at the intersection, the current signal timing scheme remains unchanged.

5. The intersection signal priority method according to claim 1, characterized in that, The step of controlling traffic light timing according to the signal priority timing scheme includes: The signal priority timing scheme is shared with the traffic signal control system of the transportation department through the cloud control platform for signal timing control.

6. An intersection signal priority system based on intelligent connected vehicle trajectory prediction function, characterized in that, The system includes: The prediction module acquires historical trajectory data of motor vehicles at the intersection and real-time trajectory data of vehicles with priority to traffic signals, wherein the vehicles with priority to traffic signals are those that need to pass first; it trains a trajectory prediction model based on the historical trajectory data to obtain a trained trajectory prediction model, which is used to predict the time required for a vehicle to reach the stop line at the intersection; and it obtains the time required for the vehicles with priority to traffic signals to reach the stop line at the intersection based on the real-time trajectory data of the vehicles with priority to traffic signals and the trained trajectory prediction model. The timing module acquires the signal timing scheme of the intersection, dynamically adjusts the signal timing scheme according to the time required for the signal-priority vehicle to reach the stop line of the intersection, and obtains the signal priority timing scheme; and performs traffic light timing control according to the signal priority timing scheme. The step of training the trajectory prediction model based on the historical trajectory data includes: The area of ​​the traffic light intersection is divided into several sub-segments; The trajectory sequence data of the vehicle is mapped to the sub-road segment, and a probability function is determined based on the number of trajectory positions within the sub-road segment; Based on the probability function, the trajectory similarity between the real-time trajectory data of the signal-priority vehicle and the trajectory prediction model is calculated. The calculation results with the highest similarity among the trajectory similarity calculation results are identified as the vehicle trajectory prediction set; Calculating trajectory similarity based on the probability function includes: The probability function is determined by nonparametric fitting, and the trajectory similarity between the real-time trajectory data of the signal-priority vehicle and the trajectory prediction model is calculated by similarity calculation. The time required to reach the destination corresponding to the vehicle trajectory prediction set is taken as the time required for the signal-priority vehicle to reach the stop line at the intersection.

7. An intelligent traffic signal control device, characterized in that, The device includes: One or more processors; and a memory storing computer program instructions that, when executed, cause the processors to perform the method as described in any one of claims 1-5.

8. A computer-readable medium having stored thereon computer program instructions that can be executed by a processor to implement the method as claimed in any one of claims 1-5.

Images