Expressway accident control scheme library generation method, platform, accident control scheme determination method, device and medium

Abstract

The embodiment of the application discloses a highway accident control scheme library generation method, a platform, an accident control scheme determination method, equipment and a medium. The accident control scheme library generation method determines a simulation accident from a historical traffic scene according to a preset rule, the simulation accident does not exist in the historical traffic scene, and micro-simulation of the simulation accident and a control scheme is performed, a control scheme meeting a prediction requirement is taken as an active control scheme, and corresponding information is added to an accident control scheme library; the accident control scheme determination method matches accident information in the accident control scheme library to obtain an accident control scheme, wherein the accident control scheme library is generated by the generation method. The application has the beneficial effect of expanding the accident control scheme library and taking into account the feasibility of the accident control scheme.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of highway active control, in particular to an accident control scheme library generation method and platform for expressway, an accident control scheme determination method, equipment and medium. BACKGROUND

[0002] With the rapid growth of the number of vehicles in China, the number of vehicles on the expressway is also increasing, and the number of expressway accidents occurring every year has been high. After the expressway accident occurs, it is easy to cause congestion or secondary accidents, which poses a great threat to the life and property safety of drivers and passengers.

[0003] Therefore, after the expressway accident occurs, the accident scene and the surrounding area need to be controlled in a timely manner to minimize the impact of the accident on road traffic. However, some control schemes need to be generated based on historical control schemes, but due to the small number of accidents on a particular road section, the number of corresponding historical control schemes is often small, making it difficult to generate control schemes that meet the requirements of the accident scene; some control schemes need to be formulated after obtaining the situation of the accident scene, which is slow and cannot meet the timeliness requirements of the control scheme. SUMMARY

[0004] The main purpose of the present application is to provide an accident control scheme library generation method and platform for expressway, an accident control scheme determination method, equipment and medium, which aims to solve the above-mentioned problems existing in the prior art.

[0005] To achieve the above-mentioned purpose, the present application provides an accident control scheme library generation method for expressway, characterized in that the method comprises:

[0006] reproducing a historical traffic scene based on historical traffic data, wherein the historical traffic scene at least includes a road network model, traffic flow data and weather data of a predetermined road section during a predetermined period;

[0007] determining simulation accident information from the historical traffic scene according to a preset rule, wherein the simulation accident information does not exist in the historical traffic scene;

[0008] determining a vehicle behavior model and a plurality of pending control schemes according to the historical traffic scene and the simulation accident information;

[0009] based on the simulation accident information and the vehicle behavior model, performing micro-simulation of the plurality of pending control schemes in the historical traffic scene and obtaining a plurality of corresponding simulation results;

[0010] evaluating the plurality of simulation results, and taking the pending control scheme corresponding to the simulation result meeting the preset evaluation requirement as an active control scheme;

[0011] adding all the active management schemes, the corresponding historical traffic scenes and the simulation accident information into the accident management scheme library.

[0012] In some embodiments,

[0013] determining an accident risk value of each interval road segment of the predetermined road segment within the predetermined period based on the historical traffic scene;

[0014] determining the simulation accident information, wherein the simulation accident information comprises a first interval road segment and a first time period in which a simulation accident occurs, and the first interval road segment and the first time period are respectively an interval road segment and a time period in which the accident risk value reaches a preset condition.

[0015] In some embodiments,

[0016] the simulation accident information further comprises lane closure information, wherein the lane closure information comprises lane position information closed due to the accident;

[0017] when the micro-simulation is performed to the first time period, closing the corresponding lane according to the lane closure information.

[0018] In some embodiments,

[0019] determining an influence range of the accident based on the traffic flow data and the weather data;

[0020] determining the lane closure information based on the influence range of the accident and the road network model.

[0021] In some embodiments,

[0022] adjusting vehicle behavior within a preset distance upstream of the closed lane based on the vehicle behavior model.

[0023] In some embodiments,

[0024] the predetermined road segment has a plurality of accident detection devices along the line;

[0025] determining an accident detection time based on the plurality of accident detection devices and the simulation accident information;

[0026] adding the pending management scheme into the micro-simulation after the accident detection time elapses from the first time period.

[0027] In addition, to achieve the above-mentioned purpose, the application further provides a method for determining an accident management scheme of an expressway, characterized in that the method comprises:

[0028] determining accident scene information, the accident scene information including a section of a road where the accident occurs, lane closure information, traffic flow data, and weather data;

[0029] According to the accident scene information, a first control scheme is matched in an accident control scheme library according to a preset rule, and the first control scheme is taken as an accident control scheme, wherein the accident control scheme library is established by the method for generating an accident control scheme library in any of the preceding embodiments.

[0030] In addition, to achieve the above-mentioned purpose, the application further provides a generation platform of an accident control scheme of an expressway, characterized in that the platform comprises:

[0031] a scene generation module, responsible for reproducing a historical traffic scene based on historical traffic data, the historical traffic scene including at least a road network model of a predetermined section of a road in a predetermined period, traffic flow data, and weather data;

[0032] an accident generation module, responsible for determining simulation accident information from the historical traffic scene according to a preset rule, wherein the simulation accident information does not exist in the historical traffic data;

[0033] a scheme generation module, responsible for determining a vehicle behavior model and a plurality of to-be-determined control schemes according to the historical traffic scene and the simulation accident information;

[0034] a simulation module, responsible for performing micro-simulation of the plurality of to-be-determined control schemes in the historical traffic scene based on the simulation accident information and the vehicle behavior model, and obtaining a plurality of simulation results corresponding thereto;

[0035] a determination module, responsible for evaluating the plurality of simulation results, taking the to-be-determined control scheme corresponding to the simulation result meeting a preset evaluation requirement as a proactive control scheme, and adding all proactive control schemes, corresponding historical traffic scenes, and simulation accident information into the accident control scheme library.

[0036] In addition, to achieve the above-mentioned purpose, the application further provides a computer device, characterized in that it comprises:

[0037] a memory, used for storing a computer program;

[0038] a processor, used for executing the computer program, so as to implement the method in any of the preceding embodiments.

[0039] In addition, to achieve the above-mentioned purpose, the application further provides a computer readable storage medium, characterized in that the computer readable storage medium stores a computer program, and the computer program is executed to implement the method in any of the preceding embodiments.

[0040] The expressway accident control scheme library generation method provided in the application reproduces a historical traffic scene through historical traffic data, and determines simulation accident information from the historical traffic scene according to a preset rule, wherein the simulation accident information does not exist in the historical traffic scene, but is generated according to the historical traffic scene. The simulation accident and a pending control scheme are added to the historical traffic scene for micro-simulation, and a required active control scheme is determined according to a simulation result and added to the accident control scheme library. The accident control scheme library of the application is not limited to historical accidents, but generates simulation accidents according to historical traffic scenes and performs active control deduction, thereby expanding the accident control scheme library. In addition, the expanded simulation accidents are generated based on historical traffic scenes, and the simulation accidents are closer to the real situation, so that the accident control scheme obtained based on the simulation accidents has high feasibility. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed to be used in the embodiments will be briefly introduced as follows. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0042] The methods, systems and / or programs in the drawings will be further described according to the exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, in which reference numerals represent similar mechanisms in each view of the drawings.

[0043] Figure 1 The flowchart of the expressway accident control scheme library generation method related to some of the embodiments of the application is shown in the following figure;

[0044] Figure 2 The flowchart of step S200 related to some of the embodiments of the application is shown in the following figure;

[0045] Figure 3 The flowchart of step S400 related to some of the embodiments of the application is shown in the following figure;

[0046] Figure 4 The flowchart of the expressway accident control scheme determination method related to some of the embodiments of the application is shown in the following figure;

[0047] Figure 5 The flowchart of the expressway accident control scheme determination method related to some of the embodiments of the application is shown in the following figure;

[0048] Figure 6A structural schematic diagram of a generation platform of an accident control scheme of a highway involved in some embodiment schemes of the present application.

[0049] Legend: 10 - scenario generation module, 20 - accident generation module, 30 - scheme generation module, 40 - simulation module, 50 - determination module. DETAILED DESCRIPTION

[0050] In order to better understand the above technical solutions, the technical solutions of the present application will be described in detail below through the drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application. In the case of no conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0051] In the following detailed description, many specific details are set forth in order to provide a thorough understanding of the relevant teachings. However, it will be apparent to one skilled in the art that the present application can be practiced without these details. In other instances, well-known methods, procedures, systems, components, and / or circuits have been described at a relatively high level, without detail, in order to avoid unnecessary obscurity of the aspects of the present application, thereby.

[0052] These and other characteristics, functions, methods, the functions of related elements in the structure, and the combination and production economy of components disclosed in the present application can become more apparent in the following description with reference to the accompanying drawings, all of which form a part of the present application. However, it should be clearly understood that the drawings are for illustrative and descriptive purposes only, and are not intended to limit the scope of the present application. It should be understood that these drawings are not drawn to scale. However, it should be clearly understood that the drawings are for illustrative and descriptive purposes only, and are not intended to limit the scope of the present application. It should be known that these drawings are not in proportion.

[0053] The flowcharts in the present application illustrate the execution processes performed by the system according to the embodiments of the present application. It should be clearly understood that the execution processes of the flowcharts can not be executed in sequence. On the contrary, these execution processes can be executed in reverse order or simultaneously. In addition, at least one other execution process can be added to the flowchart. One or more execution processes can be deleted from the flowchart.

[0054] Figure 1 is a flowchart of a generation method of an accident control scheme library of a highway according to some embodiments of the present application, which can specifically include the following steps S100-S600.

[0055] Step S100, reproduce a historical traffic scene based on historical traffic data, the historical traffic scene at least including a road network model, traffic flow data and weather data of a predetermined road section in a predetermined period.

[0056] In the embodiment, a plurality of data collection devices such as ETC gantry, camera, radar and the like can be arranged along the expressway to collect and calculate the number, vehicle type, position, speed, lane and the like of the vehicle in real time as traffic flow data and store them to obtain historical traffic flow data; the road network model is generated from an online map tool in real time or periodically and stored to obtain a historical road network model; the weather data is queried from a weather station in real time or periodically and stored to obtain historical weather data; and the above data are fused to obtain historical traffic data. It can be understood that the historical traffic data in the embodiment can also be obtained from other sources or directly obtained from existing historical traffic data, and the embodiment does not limit the manner of obtaining the historical traffic data.

[0057] In the embodiment, the historical traffic data is used for micro-simulation to reproduce the historical traffic scene. Due to the huge amount of historical traffic data, only the relevant historical traffic data of the predetermined road section and the predetermined period is selected for subsequent simulation in view of the need of deducing the control scheme, and the specific road section and period can be selected according to the size of simulation calculation and the actual control range.

[0058] Step S200, determine simulation accident information from the historical traffic scene according to a preset rule, wherein the simulation accident information does not exist in the historical traffic scene.

[0059] The simulation accident information in the embodiment does not exist in the historical traffic scene, that is, the simulation accident does not exist in the history, but is generated in the historical traffic scene according to the preset rule, for example, the simulation accident is generated according to the accident black point, traffic value, congestion index, specific road section of extreme weather and time information and the like. The simulation accident information includes the occurrence time and location of the accident and the influence range on the expressway and the like, so as to realize the simulation of the accident in the micro-simulation.

[0060] Step S300, determine a vehicle behavior model and a plurality of to-be-determined control schemes according to the historical traffic scene and the simulation accident information.

[0061] Step S400, perform micro-simulation of the plurality of to-be-determined control schemes in the historical traffic scene based on the simulation accident information and the vehicle behavior model to obtain a plurality of corresponding simulation results.

[0062] The embodiment is provided with an initial vehicle behavior model for micro-simulation, which includes a car-following model and a lane-changing model. Weather data in the historical traffic scene will affect the vehicle behavior model, so the embodiment adjusts the initial vehicle behavior model according to the weather data. In addition, since the embodiment inserts a simulated accident in the historical traffic scene, it can be understood that the simulated accident itself will affect the vehicle behavior, so the vehicle behavior in the accident influence area needs to be adjusted, including deceleration, lane changing, etc. The embodiment can generate a pending control scheme according to the characteristics of the historical traffic scene and the simulated accident information by artificial or deep learning, or directly use other existing control schemes as the pending control scheme, so as to configure multiple pending control schemes for each simulated accident. The control scheme can be sent by the control equipment arranged along the highway, which can be a display screen on a gantry, a directional sound device, or implemented by automatically or manually setting roadblocks or information boards to issue control measures for vehicles on different lanes. The control means include but are not limited to lane closure, lane-specific dynamic speed limit, temporary use of hard shoulder, dynamic truck management, lane-changing guidance, prohibition of overtaking, etc.

[0063] The micro-simulation of the embodiment uses parameters describing the micro-rules of traffic operation to design the model for simulation, simulates the condition of traffic flow from the details, generates different vehicles according to the traffic flow data in the historical traffic scene, and the vehicles drive on the designated lane; each vehicle is an individual and performs the behaviors of following and changing lanes under the predetermined conditions according to the vehicle behavior model, and adjusts its own behavior after entering the accident influence range, realizing lane-level simulation. The simulated accident is added in the historical traffic scene first, and then the corresponding pending control scheme is added, each time a pending control scheme is implemented and a simulation result is obtained, different pending control schemes are simulated for the same simulated accident, and multiple simulation results corresponding to the simulated accident are obtained.

[0064] Step S500, evaluating the multiple simulation results, and taking the pending control scheme corresponding to the simulation result meeting the preset evaluation requirement as the active control scheme.

[0065] Step S600, adding all active control schemes, corresponding historical traffic scenes and simulated accident information into the accident control scheme library.

[0066] After the active control micro-simulation of the accident, the simulation results of the traffic situation can be obtained. Specifically, the traffic situation includes one or a combination of more than one of the parameters such as average speed, average travel time, average waiting time, average vehicle density, average space occupancy, total number of vehicles, accident risk, congestion index, and the like. The evaluation results of the active control scheme are obtained based on the processing of each parameter of the traffic situation, and the specific way of evaluation is not limited in the embodiment. If the preset evaluation requirement is met, it means that the traffic situation after control meets the expectation, and the congestion caused by the accident can be effectively relieved or avoided, and the possibility of secondary accidents can be reduced.

[0067] The historical traffic scene and the simulation accident information are added to the accident control scheme library together with the active control scheme, so as to facilitate the acquisition of the corresponding active control scheme by approximately and / or completely matching the relevant information such as traffic flow data, weather data, and accident occurrence location when a real accident occurs later.

[0068] The embodiment establishes the accident control scheme library through steps S100 to S600. The control scheme is not limited to the historical accidents, but a simulation accident is generated according to the historical traffic scene, and the corresponding active control scheme is determined and deduced, which can effectively expand the number of accident control schemes. In addition, the simulation accident in the embodiment is generated based on the historical traffic scene, and the accident is closer to the real situation. At the same time, the micro-simulation is also established on the historical traffic scene, and the active control scheme obtained finally has high feasibility.

[0069] In some embodiments, as shown in Figure 2 S200 includes:

[0070] In step S210, the accident risk value of each interval road section of the predetermined road section in the predetermined period is determined based on the historical traffic scene.

[0071] In step S220, the simulation accident information is determined, wherein the simulation accident information includes a first interval road section and a first time period in which the simulation accident occurs, and the first interval road section and the first time period are respectively an interval road section and a time period in which the accident risk value reaches a preset condition.

[0072] In the historical traffic scene, the relevant road section or road network indicators including the average speed, the flow, the road congestion index, and the like are detected, and the accident risk value is calculated through a preset algorithm.

[0073] Further, when the SUMO is used for micro-simulation, the calculation method of the accident risk value is as follows:

[0074]

[0075] P = S * SD * VN * I, wherein, P is an accident risk value, S represents an average vehicle speed (km / h) of the road section, SD represents an absolute value of a difference between a first edge and a last edge of the road section (km / h), VN represents an average vehicle number (veh / min) of the road section, and I represents a length of the road section (km), and the edge is a minimum constituent unit of a road section level in SUMO.

[0076] After obtaining the accident risk value P through simulation, the P is compared with a preset condition (such as a preset value). If the P meets the preset condition, it indicates that the interval road section is likely to have an accident in the current simulation time period, and therefore the interval road section and the time period are taken as a first interval road section and a first time period of a simulation accident.

[0077] The embodiment assists in generating a simulation accident by calculating an accident risk value, so that the simulation accident is as close to a real scene as possible, improves simulation quality, and avoids a situation in which simulation calculation is increased but is not beneficial to actual accident control due to randomly setting a simulation accident.

[0078] In some embodiments, the simulation accident information further includes lane closure information, wherein the lane closure information includes lane position information closed due to the accident.

[0079] Step S400 further includes step S410: when the micro-simulation is performed to the first time period, closing a corresponding lane according to the lane closure information.

[0080] The embodiment determines an influence range of the accident according to a historical traffic scene, and further determines lane position information closed due to the accident. Specifically, a possible accident type can be determined according to traffic flow data such as average vehicle speed, vehicle type, and weather data when the simulation accident occurs, the influence range of the simulation accident is determined according to a preset rule such as matching other accidents of the same type, and the lane position information closed due to the simulation accident is determined in combination with a number of lanes of the road section in the road network model. When the micro-simulation is performed to the first time period, the corresponding lane is closed in the road network model, so as to realize simulation of the simulation accident.

[0081] The embodiment can accurately determine the influence of the simulation accident to a lane level by matching other accidents of the same type, so as to obtain more detailed and real simulation results.

[0082] In some embodiments, step S400 further includes step S420: adjusting vehicle behavior within a preset distance upstream of the closed lane on the basis of the vehicle behavior model.

[0083] The embodiment controls the behaviors of the vehicles upstream of the closed lane after the closed lane simulating the influence of the accident. The specific preset distance can be changed according to the weather data. When the visibility is high, such as sunny weather, the preset distance is appropriately increased, the vehicles within 50 meters upstream of the accident are braked, and the lane changing parameters or priorities are increased. When the visibility is low, such as rainy or snowy weather, the preset distance is appropriately reduced, the vehicles within 40 meters upstream of the accident are braked, and the lane changing parameters or priorities are increased. By adjusting the behaviors of the vehicles within the preset distance upstream of the closed lane, the influence of the accident on the vehicle traffic can be simulated relatively accurately before the active control scheme is implemented, and the effect of the active control scheme is more realistic.

[0084] In some embodiments, the predetermined road section has a plurality of accident detection devices along the line. As shown in the figure, step S400 further includes: Figure 3

[0085] Step S430, determining an accident detection time based on the plurality of accident detection devices and the simulation accident information.

[0086] Step S440, adding the pending control scheme to the micro-simulation after the accident detection time from the first time period.

[0087] In the embodiment, a plurality of accident detection devices are arranged along the expressway, and the accident detection devices include cameras, radars, vehicle detectors, microphones, night vision devices and other devices to detect collisions, anchors, reverse movements, spills and other accidents on the expressway. Due to the coverage range, cost and other objective factors, the embodiment will arrange the accident detection devices along the expressway at certain intervals. It takes a certain time from the occurrence of the accident to the detection of the accident, that is, the accident detection time. The distance between the simulation accident and the accident detection device will affect the detection time, in addition, the type of simulation accident and the type of corresponding accident detection device will also affect the detection time, and the specific detection time can be obtained by test, which is not limited in the embodiment. The embodiment adds the pending control scheme after the accident detection time from the first time period, that is, from the occurrence of the simulation accident, to analyze the influence effect of the active control scheme on the accident detection time, so that the result is closer to the real accident scene, and the usability of the active control scheme is improved.

[0088] Some embodiments relate to a method for determining an accident control scheme of an expressway, comprising:

[0089] Step S510, determining accident scene information, the accident scene information including an interval road section where the accident occurs, lane closure information, traffic flow data and weather data.

[0090] ​Step S520: Based on the accident scenario information, a first control scheme is obtained by matching the accident control scheme library according to preset rules, and the first control scheme is used as the accident control scheme.

[0091] The accident management scheme library is established by the accident management scheme library generation method described in any of the foregoing embodiments.

[0092] like Figure 4 As shown, in this embodiment, after a real accident occurs, accident scene information is collected. The accident scene information includes sub-information such as the section of road where the accident occurred, lane closure information, traffic flow data, and weather data. The above sub-information is matched in the accident control scheme database. Specifically, the similarity of each sub-information can be obtained, and the similarities are processed according to a certain weight to obtain a comprehensive similarity. The first control scheme with the highest comprehensive similarity is used as the accident control scheme. A minimum similarity threshold can also be set for each sub-information. This embodiment does not limit the specific matching rules.

[0093] Furthermore, the methods for determining accident control plans for highways also include:

[0094] Step S530: Determine real-time traffic flow data.

[0095] Step S540: Based on the real-time traffic flow data and the accident scenario information, a second control scheme is determined through deep learning.

[0096] Step S550: Adjust the first control scheme according to the second control scheme.

[0097] like Figure 5 As shown, the first control scheme in this embodiment is obtained by matching in the accident control scheme library, which is faster and can take effect immediately after an accident occurs, meeting the needs of immediate accident control. The second control scheme, on the other hand, needs to be obtained through deep learning using a neural network model, which is slower, but the control effect is relatively better. Therefore, this embodiment prioritizes the use of the first control scheme and adjusts the first control scheme after the second control scheme is generated. Specifically, the first control scheme can be replaced with the second control scheme, or the control effects of the first and second control schemes can be simulated and compared. Based on the differences in control effects and control methods, it is determined whether to continue using the first control scheme or gradually replace it with the second control scheme. For example, when the control methods of the first and second control schemes are significantly different, but the difference in control effects is not obvious, it is advisable to continue using the first control scheme to avoid the sudden change in control methods from adversely affecting traffic. When the control methods of the first and second control schemes are not significantly different, it is advisable to gradually replace the first control scheme with the second control scheme.

[0098] Some embodiments relate to a generation platform of an accident management scheme of a highway, as shown in Figure 6 The platform comprises:

[0099] a scenario generation module 10, responsible for reproducing a historical traffic scenario based on historical traffic data, the historical traffic scenario comprising at least a road network model, traffic flow data and weather data of a predetermined road section during a predetermined period.

[0100] an accident generation module 20, responsible for determining simulation accident information from the historical traffic scenario according to preset rules, wherein the simulation accident information does not exist in the historical traffic data.

[0101] a scheme generation module 30, responsible for determining a vehicle behavior model and a plurality of pending management schemes according to the historical traffic scenario and the simulation accident information.

[0102] a simulation module 40, responsible for performing micro-simulation of the plurality of pending management schemes in the historical traffic scenario based on the simulation accident information and the vehicle behavior model, and obtaining a corresponding plurality of simulation results.

[0103] a determination module 50, responsible for evaluating the plurality of simulation results, taking the pending management scheme corresponding to the simulation result meeting preset evaluation requirements as a proactive management scheme; adding all proactive management schemes, corresponding historical traffic scenarios and simulation accident information to the accident management scheme library.

[0104] Some embodiments relate to a computer device, comprising:

[0105] a memory for storing a computer program;

[0106] a processor for executing the computer program for implementing the method of any of the preceding embodiments.

[0107] Some embodiments relate to a computer readable storage medium storing a computer program, the computer program being executed to implement the method of any of the preceding embodiments.

[0108] It should be noted that, in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusions, so that processes, methods, articles or systems including a series of elements not only include those elements, but also include other elements not explicitly listed, or inherent to such processes, methods, articles or systems. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of another identical element in the process, method, article or system including the element.

[0109] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0110] Through the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and the necessary general hardware platform, of course, they can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk) as described above, and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0111] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent flow transformation made by using the content of the specification and drawings, or directly or indirectly applied to other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for generating a database of accident control schemes for highways, characterized in that, The method includes: Historical traffic scenarios are reproduced based on historical traffic data, and the historical traffic scenarios include at least the road network model, traffic flow data and weather data of the predetermined road segment within a predetermined period; Simulated accident information is determined from the historical traffic scenarios according to preset rules, wherein the simulated accident information does not exist in the historical traffic scenarios; Based on the historical traffic scenarios and the simulated accident information, a vehicle behavior model and multiple pending control schemes are determined. Based on the simulated accident information and the vehicle behavior model, microscopic simulations of the multiple undetermined control schemes are performed in the historical traffic scenario, and corresponding simulation results are obtained. The simulation results are evaluated, and the undetermined control scheme corresponding to the simulation results that meet the preset evaluation requirements is taken as the active control scheme. All proactive control schemes, the corresponding historical traffic scenarios, and the simulated accident information are added to the accident control scheme library; Based on the historical traffic scenarios, determine the accident risk value of each section of the predetermined road segment within the predetermined period; The simulated accident information is determined, wherein the simulated accident information includes a first road segment and a first time period in which the simulated accident occurred, and the first road segment and the first time period are respectively the road segment and the time period in which the accident risk value reaches the preset condition.

2. The method as described in claim 1, characterized in that, The simulated accident information also includes lane closure information, wherein the lane closure information includes the location information of the lanes closed due to the accident; When the micro-simulation reaches the first time period, the corresponding lane is closed according to the lane closure information.

3. The method as described in claim 2, characterized in that, The scope of the accident's impact is determined based on the traffic flow data and the weather data; Based on the impact range of the accident and the road network model, the lane closure information is determined.

4. The method as described in claim 2, characterized in that, Based on the vehicle behavior model, adjust the vehicle behavior within a preset upstream distance of the closed lane.

5. The method as described in claim 4, characterized in that, The predetermined road section is equipped with multiple accident detection devices. Based on the multiple accident detection devices and the simulated accident information, the accident detection time is determined; After the accident detection time has elapsed from the first time period, the pending control scheme is added to the microscopic simulation.

6. A method for determining an accident control scheme for highways, characterized in that, The method includes: Determine the accident scene information, which includes the section of road where the accident occurred, lane closure information, traffic flow data, and weather data; Based on the accident scenario information, a first control scheme is obtained by matching the accident control scheme library according to preset rules, and the first control scheme is used as the accident control scheme. The accident control scheme library is established by the method for generating the accident control scheme library according to any one of claims 1-5.

7. A platform for generating accident control schemes for highways, characterized in that, The platform includes: The scene generation module is responsible for reproducing historical traffic scenes based on historical traffic data. The historical traffic scenes include at least the road network model, traffic flow data and weather data of the predetermined road segment within a predetermined period. The accident generation module is responsible for determining simulated accident information from the historical traffic scenarios according to preset rules, wherein the simulated accident information does not exist in the historical traffic data; The scheme generation module is responsible for determining vehicle behavior models and multiple pending control schemes based on the historical traffic scenarios and the simulated accident information. The simulation module is responsible for performing microscopic simulations of the multiple pending control schemes in the historical traffic scenario based on the simulated accident information and the vehicle behavior model, and obtaining the corresponding multiple simulation results. The determination module is responsible for evaluating the multiple simulation results, and taking the pending control schemes corresponding to the simulation results that meet the preset evaluation requirements as active control schemes; adding all active control schemes, the corresponding historical traffic scenarios, and the simulation accident information to the accident control scheme library; The accident generation module is specifically used to determine the accident risk value of each section of the predetermined road segment within the predetermined period based on the historical traffic scenario. The simulated accident information is determined, wherein the simulated accident information includes a first road segment and a first time period in which the simulated accident occurred, and the first road segment and the first time period are respectively the road segment and the time period in which the accident risk value reaches the preset condition.

8. A computer device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the method as described in any one of claims 1-6.

Images