A traffic condition early warning method and system for intelligent expressway

Abstract

The application discloses a traffic condition early warning method and system for intelligent expressway, relates to the technical field of expressway monitoring, and comprises the following steps: acquiring state information of a target vehicle, and constructing a driving state matrix of the target vehicle; constructing a road state matrix of a driving road section according to road state information of the driving road section; and based on the driving state matrix of the target vehicle and the road state matrix of the driving road section, acquiring risk variable information in real time, and calculating a traffic risk index of the target vehicle on the driving road section. The application constructs matrix features of vehicles and road sections in advance, so that relative conditions between the vehicles and the road sections can be understood, and effective reference can be provided for subsequent condition early warning. In addition, the application also interacts with the vehicles according to sudden conditions on the road sections to realize early warning of the sudden conditions on the road sections. That is, the application effectively solves the problem that the prior art cannot timely and accurately early warn real-time conditions of vehicles and roads.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of highway monitoring technology, and in particular to a traffic condition early warning method and system for intelligent highways. BACKGROUND

[0002] In the field of highway monitoring technology, as traffic flow increases and traffic conditions become more complex and variable, traditional traffic condition monitoring and early warning methods have been difficult to meet actual needs. Existing highway traffic monitoring methods mostly rely on single sensors or fixed-point monitoring equipment. These devices have obvious shortcomings in terms of the comprehensiveness, real-time nature, and accuracy of data collection. For example, some sensors can only obtain limited information such as vehicle speed and traffic volume at specific locations, and cannot comprehensively analyze and judge overall road conditions. Moreover, in the event of adverse weather, traffic accidents, and other sudden situations, existing monitoring systems often cannot timely and accurately issue early warnings, leading to increased traffic congestion and even secondary accidents, seriously affecting people's travel safety and traffic efficiency. SUMMARY

[0003] The present application relates to the field of highway monitoring technology, and in particular to a traffic condition early warning method and system for intelligent highways.

[0004] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0005] In a first aspect, the present application provides a traffic condition early warning method for intelligent highways, comprising:

[0006] Obtaining state information of a target vehicle and constructing a driving state matrix of the target vehicle;

[0007] Constructing a road state matrix of the driving route based on road state information of the driving route;

[0008] Based on the driving state matrix of the target vehicle and the road state matrix of the driving route, and real-time acquisition of risk variable information, calculating a traffic risk index of the target vehicle on the driving route;

[0009] Matching the traffic risk index of the target vehicle on the driving route with a preset risk threshold to generate traffic condition early warning information for the target vehicle;

[0010] Based on the traffic condition early warning information of the target vehicle, performing real-time early warning on the target vehicle.

[0011] In a feasible scheme, it further comprises:

[0012] Coordinate the driving route to obtain road condition coordinate information of the driving route;

[0013] Collecting multi-source state information of the target vehicle, and combining with the road condition coordinate information of the driving section, the lane deviation degree information of the target vehicle is determined;

[0014] Real-time collection of road state information of the driving section, and construction of road risk points;

[0015] According to the lane deviation degree information of the target vehicle, and combining with the road risk points, the evading control route of the target vehicle is determined.

[0016] In a feasible scheme, the method for calculating the traffic risk index of the target vehicle on the driving section comprises:

[0017] Let the driving state matrix risk factor be , the road state matrix risk factor be , and the emergency event risk factor be , then the traffic risk index is :

[0018] Formula 1;

[0019] In formula 1, is the driving section dynamic traffic density factor, , , , respectively are the weight coefficients of the driving state matrix, the road state matrix, the emergency event risk and the dynamic traffic density;

[0020] Specifically, the calculation method of the driving state matrix risk factor is as follows:

[0021] ;

[0022] Wherein, is the current speed of the target vehicle;

[0023] is the safety distance;

[0024] is the time when the vehicle and the front obstacle may collide;

[0025] is the collision threshold;

[0026] The calculation method of the road state matrix risk factor is as follows:

[0027] ;

[0028] Wherein, is the first Risk level of each road defect;

[0029] The number of road defects detected;

[0030] This is the distance attenuation factor;

[0031] For the target vehicle and the first The distance of each road defect;

[0032] It is a mathematical constant;

[0033] The dynamic traffic density factor The calculation method is as follows:

[0034] ;

[0035] in, This represents the current traffic density of the road segment.

[0036] This refers to the density of the road segment under unobstructed conditions.

[0037] This represents the density of a road segment under congested conditions.

[0038] In one feasible approach, the method further includes:

[0039] Traffic condition warnings for the target vehicle are distributed to the target vehicle via vehicle-to-everything (V2X) communication protocols.

[0040] Based on the traffic flow and road conditions of the travel segment, a traffic flow prediction model for the travel segment is constructed.

[0041] Based on the traffic flow prediction model for the travel segment, calculate the predicted traffic flow for the travel segment;

[0042] Based on the predicted traffic flow of the travel segment, the driving speed and driving lane of the target vehicle are dynamically optimized to generate recommended driving parameters.

[0043] In one feasible approach, the method for calculating the predicted traffic flow of a travel segment includes:

[0044] Based on historical information of the driving route, using The prediction is performed using a hybrid neural network, and the prediction formula is as follows:

[0045] Formula 2;

[0046] In Equation 2, To predict future traffic flow, This is the historical traffic flow sequence for the road segment. This is a historical sequence of vehicle speeds. For the historical road conditions series, for The model's output is a dynamic adjustment of the predicted flow rate based on short-term changes. for arrive The sequence of traffic flow changes, for arrive The sequence of vehicle speed changes.

[0047] In one feasible approach, the method includes:

[0048] Obtain the driving status information of the target vehicle and other related vehicles within the driving segment, and construct a multi-vehicle collaborative status matrix;

[0049] Based on the vehicle-to-everything (V2X) communication protocol, traffic condition warning information of the target vehicle and related vehicles is shared in real time, and multi-vehicle collaborative warning information is generated.

[0050] Calculate the multi-vehicle cooperative traffic risk index based on the multi-vehicle cooperative state matrix and the road state matrix of the driving segment;

[0051] Based on the multi-vehicle cooperative traffic risk index, it is matched with the preset cooperative risk threshold to generate multi-vehicle cooperative early warning information;

[0052] The multi-vehicle collaborative warning information is distributed to the target vehicle and associated vehicles through the vehicle-to-everything (V2X) communication protocol, and the driving parameters of the target vehicle and associated vehicles are dynamically adjusted according to the collaborative warning information.

[0053] One feasible approach to calculating the multi-vehicle cooperative traffic risk index includes:

[0054] Formula 3;

[0055] In Equation 3, For the first Risk factors in the driving status matrix of associated vehicles. For the number of associated vehicles, For road state matrix risk factors, As a risk factor for emergency events, For vehicle component interaction dynamic factors, , , , These are the weighting coefficients for multi-vehicle driving status, road conditions, emergency event risks, and inter-vehicle interaction dynamics, respectively.

[0056] In a feasible solution, the vehicle interaction dynamic factor is calculated as follows:

[0057] Formula 4;

[0058] In Formula 4, is the distance between the target vehicle and the first associated vehicle, is the speed of the target vehicle, is the speed of the first associated vehicle, is the included angle of the driving direction between the target vehicle and the first associated vehicle, is the direction difference attenuation factor, is a mathematical constant.

[0059] The present application provides, in a second aspect, a traffic condition early warning system for a smart expressway, which adopts a traffic condition early warning method for a smart expressway according to any one of the first aspect, and further comprises:

[0060] a data collection module, configured to collect state information of a target vehicle, driving road section road state information, and driving state information of associated vehicles in real time;

[0061] a data processing module, which is electrically connected with the data collection module, and is configured to construct a driving state matrix, a road state matrix, and a multi-vehicle cooperative state matrix according to the collected information, and to calculate a traffic risk index and a multi-vehicle cooperative traffic risk index;

[0062] a risk assessment module, which is electrically connected with the data processing module, and is configured to generate traffic condition early warning information and multi-vehicle cooperative early warning information;

[0063] an early warning distribution module, which is connected with the risk assessment module, and is configured to distribute the early warning information to the target vehicle and / or the associated vehicles;

[0064] a decision control module, which is connected with the early warning distribution module, and is configured to dynamically adjust driving parameters of the target vehicle and the associated vehicles according to the early warning information.

[0065] The present application has the following beneficial effects:

[0066] The present application constructs the matrix features of the vehicle and the road section in advance, so as to understand the relative situation between the vehicle and the road section, and provide effective reference for subsequent situation warning. In addition, the vehicle is interactively warned according to the sudden situation on the road section, so as to realize the early warning of the sudden situation on the road section. That is, the disadvantage that the real-time situation of the vehicle and the road cannot be timely and accurately warned in the prior art is effectively solved. BRIEF DESCRIPTION OF DRAWINGS

[0067] Figure 1 A whole flowchart of a traffic condition warning method of a smart expressway provided in an embodiment of the present application is shown in the figure.

[0068] Figure 2 A structure constitution diagram of a traffic condition warning method of a smart expressway provided in an embodiment of the present application is shown in the figure.

[0069] Figure 3 A multi-vehicle cooperative warning flowchart of a traffic condition warning method of a smart expressway provided in an embodiment of the present application is shown in the figure.

[0070] Figure 4 A multi-vehicle cooperative warning constitution diagram of a traffic condition warning method of a smart expressway provided in an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0071] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0072] In the present application, unless otherwise explicitly specified and limited, the terms "connection", "fixation" and the like should be understood in a broad sense, for example, "fixation" can be fixed connection, or detachable connection, or integral; can be mechanical connection, or electrical connection; can be direct connection, or indirect connection through intermediate medium, can be the internal communication of two elements or the interaction relationship between two elements, unless otherwise explicitly limited. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0073] In addition, if the description of "first", "second" and the like is involved in the embodiments of the present application, the description of "first", "second" and the like is only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can be explicitly or implicitly included at least one of the features. In addition, the meaning of "and / or" appearing throughout the text includes three parallel schemes. For example, "A and / or B" includes A scheme, or B scheme, or A and B simultaneously meet the scheme. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or cannot be realized, it should be considered that the combination of technical solutions does not exist, nor in the protection scope required by the present application.

[0074] With reference to Figures 1 to 4 In order to solve the problem that the real-time situation of the vehicle and the road cannot be timely and accurately warned in the prior art, the present application provides a traffic condition warning method of intelligent expressway. The warning method constructs the matrix features of the vehicle and the road section in advance, so as to understand the relative situation between the vehicle and the road section, and provide effective reference for subsequent situation warning. In addition, the sudden situation on the road section and the vehicle are interacted to realize the early warning of the sudden situation of the road section. That is, the problem that the real-time situation of the vehicle and the road cannot be timely and accurately warned in the prior art is effectively solved.

[0075] With reference to Figure 1 and Figure 2In a first aspect, the present application provides a traffic condition warning method for intelligent expressway, which comprises: obtaining state information of a target vehicle, and constructing a driving state matrix of the target vehicle; that is, constructing the driving state matrix of the target vehicle by collecting multi-source information (such as position, speed, acceleration, lane deviation and time to collision (TTC) of the target vehicle by multi-source sensors (such as GPS, IMU, LiDAR and V2X)) of the target vehicle, and then constructing the driving state matrix of the target vehicle. At the same time, a road state matrix of a driving road section can be constructed according to road state information of the driving road section (such as adding a coordinate system to the road to facilitate determination of the position where the road condition occurs). Then, based on the driving state matrix of the target vehicle and the road state matrix of the driving road section, and by obtaining risk variable information (such as road damage, landslides or traffic accidents and other emergency situations in front) in real time, the traffic risk index of the target vehicle on the driving road section can be calculated; then, according to the comparison result of the traffic risk index and the preset risk threshold, the traffic condition warning information of the target vehicle can be generated; so as to realize real-time warning of the target vehicle based on the traffic condition warning information of the target vehicle. That is, in this embodiment, by constructing the matrix features of the vehicle and the road section, the driving state of the vehicle and the condition of the road section can be mastered. That is, whether it is a pothole or a crack on the road surface, or an obstacle or a construction area around the road, it can be accurately positioned in the coordinate system. In this way, when analyzing the driving risk of the vehicle subsequently, the relative positional relationship between the vehicle and various road conditions can be clearly known, so that the influence of the road condition on the driving of the vehicle can be more accurately evaluated. In a feasible embodiment, in order to avoid and handle the risk as soon as possible, the traffic condition warning information can be sent to the target vehicle and / or the traffic management department simultaneously, so as to realize real-time warning and effective management of the traffic condition. Specifically, in order to facilitate understanding of how to extract the relative relationship between the target vehicle and the driving road section, the following is explained, the warning method further comprises: first, the driving road section can be coordinate (two-dimensional coordinate or spatial coordinate, etc.), and the road condition coordinate information of the driving road section can be obtained; then, the multi-source state information of the target vehicle can be collected by the multi-source sensor, and the lane deviation information of the target vehicle can be determined by combining the road condition coordinate information of the driving road section, that is, the relative position of the target vehicle on the driving road section is determined, and the road state information of the driving road section is collected in real time to construct the road risk point; then, the avoidance control route of the target vehicle is determined according to the lane deviation information of the target vehicle and in combination with the road risk point. That is, in this embodiment, by coordinate of the driving road section such as plane coordinate or three-dimensional coordinate, the accurate coordinate information of each position point of the driving road section can be obtained, which provides an effective reference for subsequent analysis.Meanwhile, by collecting multi-source state information of the target vehicle, covering vehicle speed, acceleration, steering angle and other data, and combining with road condition coordinate information of the driving section, lane deviation degree information of the target vehicle is accurately determined to determine whether the vehicle deviates from the normal driving lane. Then, by collecting road state information of the driving section in real time, including road flatness, whether there are obstacles, whether traffic signs and markings are clear, etc., road risk points are constructed to determine the areas that may have risks on the road. According to the lane deviation degree information of the target vehicle, when it is detected that the vehicle deviates from the normal lane and approaches the road risk point, the specific situation of the road risk point, such as the type and danger degree of the risk point, is combined to plan the avoidance control route of the target vehicle in advance, guide the vehicle to safely drive, and avoid traffic accidents. In another feasible embodiment, the method can further optimize the accuracy and practicality of the early warning. By introducing high-precision map data and real-time weather information, the driving state matrix and the road state matrix constructed above are deeply fused to realize comprehensive evaluation of traffic risks.

[0076] In the present embodiment, in order to facilitate understanding of how to calculate the traffic risk index of the target vehicle on the driving section, the following is exemplified, the method for calculating the traffic risk index of the target vehicle on the driving section comprising:

[0077] Let the driving state matrix risk factor be , the road state matrix risk factor be , and the emergency event risk factor be , then the traffic risk index is :

[0078] Formula 1;

[0079] In Formula 1, is the driving section dynamic traffic density factor, , , , respectively are the weight coefficients of the driving state matrix, the road state matrix, the emergency event risk and the dynamic traffic density, used to balance the contribution of each part to the overall risk. Among them, the weight coefficient value is dynamically adjusted by Bayesian optimization to adapt to different traffic scenarios;

[0080] Specifically, the calculation method of the driving state matrix risk factor is as follows:

[0081] ;

[0082] Among them, is the current speed of the target vehicle (unit: m / s);

[0083] is the safety distance (unit: m), which can be dynamically determined according to the actual road type and speed;

[0084] is the time for the vehicle to collide with the front obstacle;

[0085] is the collision threshold value, which is used for standardization , and can be set according to road conditions;

[0086] The road state matrix risk factor is calculated as follows:

[0087] ;

[0088] wherein, is the risk level of the th road defect;

[0089] is the number of detected road defects;

[0090] is the distance decay factor, which generally controls the decay rate of the distance on the risk (usually a positive value, such as 0.01);

[0091] is the distance (unit: m) between the target vehicle and the th road defect;

[0092] is a mathematical constant; that is, it can reflect the potential impact of the road environment on traffic safety through the risk factor calculated based on the road state (such as road defects, road conditions, weather, etc.);

[0093] The emergency event risk factor can be obtained by grading according to the severity of the event;

[0094] The dynamic traffic density factor is calculated as follows:

[0095] ;

[0096] wherein, is the current traffic density (unit: vehicle / km) of the driving section;

[0097] is the density (unit: vehicle / km) of the driving section in the smooth state;

[0098] Density of the driving section in the congestion state (unit: vehicle / km).

[0099] That is, in the present embodiment, the traffic risk index is evaluated and calculated by comprehensively considering the four dimensions of vehicle motion state, road environment, emergency and traffic flow by using weighted summation, ensuring the accuracy of subsequent warning. It should be noted that the weight coefficient value can be dynamically adjusted by Bayesian optimization to ensure that the formula adapts to different scenarios (such as peak hours and bad weather).

[0100] In a feasible implementation, in order to ensure that the target vehicle can pass through the driving section quickly, the method further comprises: the traffic condition warning information (including traffic condition warning information containing risk level, warning type and recommended driving strategy) of the target vehicle can be distributed to the target vehicle through the Internet of Vehicles communication protocol; at the same time, a traffic flow prediction model of the driving section can be constructed according to the traffic flow and road state of the driving section; then the predicted traffic flow of the driving section can be calculated according to the traffic flow prediction model of the driving section; and then the driving speed and driving lane of the target vehicle are dynamically optimized according to the predicted traffic flow of the driving section, and the recommended driving parameters are generated. That is, in the present embodiment, the warning information is distributed to the target vehicle in time through the Internet of Vehicles communication protocol, so that the driver can know the road conditions and potential risks in advance. At the same time, the traffic flow prediction model constructed can accurately predict the traffic flow changes of the driving section based on historical data and real-time information. According to the prediction result, the driving speed and lane selection of the target vehicle are dynamically adjusted, which helps to improve the road traffic efficiency and reduce the traffic congestion and accident risk. Specifically, the method for calculating the predicted traffic flow of the driving section comprises: based on the past historical information (including traffic flow, speed, road conditions, etc.) of the driving section, a hybrid neural network is used for prediction, and the prediction formula is:

[0101] Formula 2;

[0102] In formula 2, is the future predicted traffic flow, is the historical flow sequence of the driving section, is the historical driving speed sequence, is the historical road condition sequence, is the output of the model, the dynamic adjustment amount of the predicted flow based on short-term changes, is the traffic flow change amount sequence from t to t+1, is the speed change amount sequence from t to t+1; wherein, ​​​To represent a shorter time window, usually the last few time steps (e.g. the last 5 or 10 minutes), and reflect short-term fluctuations in traffic and short-term changes in vehicle speed. That is, in the present embodiment, the model captures long-term trends in traffic flow by capturing factors such as , and , outputs a base prediction value, and is suitable for processing patterns over a longer time span (e.g. the peak period in a day). Meanwhile, the model captures short-term dynamic changes by capturing and , and adjusts the prediction value of the model to adapt to sudden events (e.g. accidents or temporary construction). In addition, based on the future predicted traffic flow calculated above, the congestion probability of the driving route can be calculated:

[0103] ;

[0104] In the formula, is the congestion probability, ranging from ; is the function, which is used to map the input value to the interval, and calculate the probability is the maximum flow of the road in the non-congestion state, is the flow threshold when the road is completely congested (i.e. the flow when vehicles can hardly move). That is, the congestion probability of the driving route is calculated by the calculated future predicted traffic flow, and when the calculated congestion probability exceeds the preset congestion threshold, it is determined that there is a congestion risk in the driving route, and the corresponding congestion warning information is generated. These warning information will be sent to the target vehicle in real time through the vehicle network communication protocol, reminding the driver to adjust the driving route or speed in advance to avoid the congestion area. At the same time, according to the predicted traffic flow and the congestion probability, the traffic flow prediction model of the driving route can be dynamically updated, and the accuracy of subsequent prediction can be improved.

[0105] Referring to Figure 3 and Figure 4In one possible implementation, when multi-vehicle cooperation is performed, the method comprises: a multi-vehicle cooperation state matrix can be constructed by acquiring the driving state information of the target vehicle and the driving state information of other associated vehicles in the driving section; then, based on the Internet of Vehicles communication protocol, the traffic condition warning information of the target vehicle and the associated vehicles is shared in real time to generate multi-vehicle cooperation warning information; then, the multi-vehicle cooperation traffic risk index can be calculated according to the multi-vehicle cooperation state matrix and the road state matrix of the driving section; then, the multi-vehicle cooperation traffic risk index is matched with the preset cooperation risk threshold to generate the multi-vehicle cooperation warning information; finally, the multi-vehicle cooperation warning information can be distributed to the target vehicle and the associated vehicles through the Internet of Vehicles communication protocol, and the driving parameters (including driving speed, lane selection and evasive route) of the target vehicle and the associated vehicles are dynamically adjusted according to the cooperation warning information. In this embodiment, the driving state information of the target vehicle and the associated vehicles is acquired and integrated in real time to construct a multi-vehicle cooperation state matrix, which can comprehensively reflect the mutual relationship and state change of the multi-vehicles in the driving process. Then, based on the Internet of Vehicles communication protocol, the traffic condition warning information between the target vehicle and the associated vehicles is shared in real time to ensure that each vehicle can obtain the dynamic information of the surrounding vehicles in time. By combining the multi-vehicle cooperation state matrix and the road state matrix of the driving section, the multi-vehicle cooperation traffic risk index is calculated, the calculated multi-vehicle cooperation traffic risk index is matched with the preset cooperation risk threshold, and the multi-vehicle cooperation warning information is generated. When the risk index exceeds the threshold, the warning mechanism is triggered in time to remind the relevant vehicles to take measures. Finally, the multi-vehicle cooperation warning information is distributed to the target vehicle and the associated vehicles through the Internet of Vehicles communication protocol, and the driving parameters of each vehicle are dynamically adjusted according to the warning information, including driving speed, lane selection and evasive route, etc., to realize the cooperative driving between the multi-vehicles and improve the road traffic efficiency and safety. Specifically, the method for calculating the multi-vehicle cooperation traffic risk index comprises:

[0106] Formula 3;

[0107] In formula 3, is the driving state matrix risk factor of the nth associated vehicle, is the number of associated vehicles, is the road state matrix risk factor, is the emergency event risk factor, is the vehicle interaction dynamic factor, , , , , are the weight coefficients of multi-vehicle driving state, road state, emergency event risk and vehicle interaction dynamics, respectively. In equation 3, by considering the four key dimensions of multi-vehicle driving state, road state, emergency event risk and vehicle interaction dynamics, the multi-vehicle cooperative traffic risk is comprehensively evaluated by using the weighted summation method. Among them, each weight coefficient can be flexibly adjusted according to the actual traffic scene and demand to ensure the accuracy and applicability of the index. Among them, the calculation method of the vehicle interaction dynamic factor is as follows:

[0108] Equation 4

[0109] In equation 4, is the distance between the target vehicle and the first associated vehicle, is the speed of the target vehicle, is the speed of the first associated vehicle, is the driving direction angle between the target vehicle and the first associated vehicle, is the direction difference attenuation factor, is a mathematical constant. By calculating the vehicle interaction dynamic factor, the distance between the target vehicle and the associated vehicle, the speed difference and the driving direction angle can be considered comprehensively, so that the multi-vehicle cooperative traffic risk can be evaluated from multiple perspectives, providing strong support for subsequent warning and driving parameter adjustment. In practical applications, parameters such as the direction difference attenuation factor can be flexibly adjusted according to different traffic scenes and demands to optimize the calculation results of the vehicle interaction dynamic factor. At the same time, combined with the multi-vehicle cooperative state matrix and the road state matrix of the driving section, the multi-vehicle cooperative traffic risk index can be further calculated to provide more comprehensive and accurate warning information for multi-vehicle cooperative driving. Finally, the multi-vehicle cooperative warning information is distributed to the target vehicle and the associated vehicle through the Internet of Vehicles communication protocol, and the driving parameters of each vehicle are dynamically adjusted according to the warning information, including driving speed, lane selection and avoidance route, etc., to realize the cooperative driving between multiple vehicles and improve the road traffic efficiency and safety.

[0110] The application also provides a traffic condition early warning system of a smart expressway in a second aspect, which adopts the traffic condition early warning method of the smart expressway as described in any one of the first aspect, and the early warning system further comprises: a data acquisition module, a data processing module, a risk assessment module, an early warning distribution module, a decision control module, which are used to acquire the state information of a target vehicle, the road state information of a driving section and the driving state information of associated vehicles in real time; the data processing module is electrically connected with the data acquisition module, and is used to construct a driving state matrix, a road state matrix and a multi-vehicle cooperative state matrix according to the acquired information, and calculate a traffic risk index and a multi-vehicle cooperative traffic risk index; the risk assessment module is electrically connected with the data processing module, and is used to match the calculated traffic risk index and multi-vehicle cooperative traffic risk index with a preset risk threshold and a preset cooperative risk threshold respectively, and generate traffic condition early warning information and multi-vehicle cooperative early warning information; the early warning distribution module is connected with the risk assessment module, and is used to distribute the traffic condition early warning information and multi-vehicle cooperative early warning information to the target vehicle and associated vehicles through a vehicle networking communication protocol; the decision control module is connected with the early warning distribution module, and is used to dynamically adjust the driving parameters (including driving speed, lane selection and evasive route) of the target vehicle and associated vehicles according to the early warning information. In a feasible scheme, the early warning system further comprises: a storage module, which is electrically connected with the data acquisition module, the data processing module, the risk assessment module, the early warning distribution module and the decision control module respectively, and is used to store the acquired various types of information, intermediate data generated in the calculation process and finally generated early warning information and adjusted driving parameters.

[0111] In some embodiments, the early warning system can communicate using any currently known or future developed network protocol, such as HTTP (Hyper Text Transfer Protocol), and can be interconnected with digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

[0112] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0113] The third aspect of the present application provides a computer readable medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the traffic condition early warning method of the smart highway according to any one of the first aspect. The computer readable medium in the embodiments of the present application can be written in one or more programming languages or combinations of languages for executing operations of some embodiments of the present application, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" language or similar programming languages. The program code can be executed entirely on a user computer, partially on a user computer, as a separate software package, partially on a user computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet by using an Internet service provider).

[0114] The flowcharts and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in a different order than that noted in the figures. For example, two blocks noted in succession can actually be executed substantially concurrently, or they can sometimes be executed in reverse order, depending on the functionality 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 by dedicated hardware-based systems that perform the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0115] In particular, the processes described above with reference to the flowcharts can be implemented as computer software programs according to some embodiments of the present application. For example, some embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for executing the methods shown in the flowcharts.

[0116] In a fourth aspect, the present application provides an electronic device, comprising: one or more processors; a memory storing one or more programs; and the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the traffic condition early warning method of the intelligent expressway as described in the first aspect. The computer readable medium described above can be included in the electronic device; or can exist separately, i.e., not assembled into the electronic device. The computer readable medium described above carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device can implement the traffic condition early warning method of the intelligent expressway as described in the first aspect.

[0117] In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the traffic condition early warning method of the intelligent expressway as described in the first aspect.

[0118] The above description is merely some of the preferred embodiments of the present application and the explanation of the technical principles applied. Those skilled in the art should understand that the inventive scope of the embodiments of the present application is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combinations of the above technical features or equivalent features without departing from the inventive concept. For example, the above features can be replaced with the technical features disclosed in the embodiments of the present application (but not limited to) having similar functions to form technical solutions.

Claims

1. A traffic condition early warning method for intelligent highways, characterized in that, include: Obtain the status information of the target vehicle and construct the driving status matrix of the target vehicle; Construct a road state matrix for the driving route based on the road state information of the driving route; Based on the target vehicle's driving state matrix and the road state matrix of the driving segment, and by acquiring risk variable information in real time, the traffic risk index of the target vehicle on the driving segment is calculated. The traffic risk index of the target vehicle on the road segment is matched with a preset risk threshold to generate traffic condition warning information for the target vehicle. Based on traffic condition warning information of the target vehicle, real-time warnings are issued for the target vehicle. This also includes: The driving route is mapped to coordinates to obtain the road condition coordinate information of the driving route; Collect multi-source status information of the target vehicle and combine it with road condition coordinate information of the driving segment to determine the lane deviation information of the target vehicle. Real-time collection of road condition information for driving sections to identify road risk points; Based on the lane departure information of the target vehicle and in combination with the road risk points, determine the avoidance and control route of the target vehicle. Specifically, the method for calculating the traffic risk index of the target vehicle on the road segment includes: Let the risk factors of the driving state matrix be... The risk factors of the road state matrix are Emergency event risk factors are The traffic risk index : Formula 1; In Equation 1, This refers to the dynamic traffic density factor of the road segment. , , , These are the weighting coefficients for the driving state matrix, road state matrix, emergency event risk, and dynamic traffic density, respectively. Specifically, the driving state matrix risk factors The calculation method is as follows: ； in, The current speed of the target vehicle; To maintain a safe distance; The time at which the vehicle may collide with an obstacle ahead; The collision threshold; The road state matrix risk factors The calculation method is as follows: ； in, For the first Risk level of each road defect; The number of road defects detected; This is the distance attenuation factor; For the target vehicle and the first The distance of each road defect; It is a mathematical constant; The dynamic traffic density factor The calculation method is as follows: ； in, This represents the current traffic density of the road segment. This refers to the density of the road segment under unobstructed conditions. This represents the density of a road segment under congested conditions.

2. The traffic condition early warning method for intelligent highways according to claim 1, characterized in that, The method further includes: Traffic condition warnings for the target vehicle are distributed to the target vehicle via vehicle-to-everything (V2X) communication protocols. Based on the traffic flow and road conditions of the travel segment, a traffic flow prediction model for the travel segment is constructed. Based on the traffic flow prediction model for the travel segment, calculate the predicted traffic flow for the travel segment; Based on the predicted traffic flow of the travel segment, the driving speed and driving lane of the target vehicle are dynamically optimized to generate recommended driving parameters.

3. The traffic condition early warning method for intelligent highways according to claim 2, characterized in that, The method for calculating the predicted traffic flow of a travel segment includes: Based on historical information of the driving route, using The prediction is performed using a hybrid neural network, and the prediction formula is as follows: Formula 2; In Equation 2, To predict future traffic flow, This is the historical traffic flow sequence for the road segment. This is a historical sequence of vehicle speeds. For the historical road conditions series, for The model's output is a dynamic adjustment of the predicted flow rate based on short-term changes. for arrive The sequence of traffic flow changes, for arrive The sequence of vehicle speed changes.

4. A traffic condition early warning method for intelligent highways according to any one of claims 1 to 3, characterized in that, The method includes: Obtain the driving status information of the target vehicle and other related vehicles within the driving segment, and construct a multi-vehicle collaborative status matrix; Based on the vehicle-to-everything (V2X) communication protocol, traffic condition warning information of the target vehicle and related vehicles is shared in real time, and multi-vehicle collaborative warning information is generated. Calculate the multi-vehicle cooperative traffic risk index based on the multi-vehicle cooperative state matrix and the road state matrix of the driving segment; Based on the multi-vehicle cooperative traffic risk index, it is matched with the preset cooperative risk threshold to generate multi-vehicle cooperative early warning information; The multi-vehicle collaborative warning information is distributed to the target vehicle and associated vehicles through the vehicle-to-everything (V2X) communication protocol, and the driving parameters of the target vehicle and associated vehicles are dynamically adjusted according to the collaborative warning information.

5. The traffic condition early warning method for intelligent highways according to claim 4, characterized in that, Methods for calculating the multi-vehicle cooperative traffic risk index include: Formula 3; In Equation 3, For the first Risk factors in the driving status matrix of associated vehicles. For the number of associated vehicles, For road state matrix risk factors, As a risk factor for emergency events, For vehicle component interaction dynamic factors, , , , These are the weighting coefficients for multi-vehicle driving status, road conditions, emergency event risks, and inter-vehicle interaction dynamics, respectively.

6. The traffic condition early warning method for intelligent highways according to claim 5, characterized in that, The vehicle component interaction dynamic factor The calculation method is as follows: Equation 4; In Equation 4, For the target vehicle and the first The distance between the connected vehicles The speed of the target vehicle, For the first The speed of the associated vehicles For the target vehicle and the first The angle between the driving directions of the two related vehicles. As the directional difference attenuation factor, It is a mathematical constant.

7. A traffic condition early warning system for intelligent highways, characterized in that, The traffic condition early warning method for intelligent highways as described in any one of claims 1 to 6 is adopted, wherein the early warning system further includes: The data acquisition module is used to collect real-time status information of the target vehicle, road condition information of the driving segment, and driving status information of associated vehicles. The data processing module is electrically connected to the data acquisition module and is used to construct a driving state matrix, a road state matrix, and a multi-vehicle cooperative state matrix based on the acquired information, and to calculate the traffic risk index and the multi-vehicle cooperative traffic risk index. A risk assessment module, electrically connected to a data processing module, is used to generate traffic condition early warning information and multi-vehicle collaborative early warning information. The warning distribution module is connected to the risk assessment module and is used to distribute warning information to target vehicles and / or associated vehicles. The decision control module is connected to the early warning distribution module and is used to dynamically adjust the driving parameters of the target vehicle and related vehicles based on the early warning information.

Images