A highway lane-level guidance strategy optimization method, device and medium

Abstract

The embodiment of the present invention discloses a method, device and medium for optimizing lane-level induction strategy of a highway. The method includes: collecting traffic information of lanes before and after the induction equipment of the highway, screening out the target lanes that need to optimize the induction strategy; calibrating the traffic simulation model of the target lane; optimizing the induction strategy of the target lane by using a genetic algorithm with the minimum vehicle delay hours and congestion index as the optimization target, and importing the optimization strategy generated by each iteration into the traffic simulation model during the optimization process to determine whether the optimization target is achieved; placing the optimized induction strategy on the induction equipment of the target lane, and judging whether the optimized induction strategy is adapted to the real-time traffic status according to the improvement of the traffic status; if it is adapted, maintaining the optimized induction strategy; if it is not adapted, returning to the operation of collecting traffic information and re-optimizing the induction strategy.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of intelligent transportation technology, and in particular to a method, device and medium for optimizing a lane-level guidance strategy for a highway. Background Art

[0002] Expressways are an important part of the national transportation system. However, with the continuous increase in the number of motor vehicles, the congestion and safety issues of expressways have become increasingly prominent, hindering the normal operation of the expressway network. In order to improve the efficiency and safety of expressways, corresponding control and induction measures can be taken to achieve the purpose of optimizing traffic flow, alleviating congestion, and reducing accidents.

[0003] The existing highway guidance methods lack effective lane-level guidance. On the one hand, the existing lane-level guidance is greatly affected by human and unpredictable abnormal traffic conditions, and cannot make correct and effective guidance decisions; on the other hand, the existing lane-level guidance methods mostly adopt static or preset guidance strategies, which cannot adapt to the complex and changing traffic operation conditions on the highway in a timely manner, and cannot fully consider human factors such as the driver's acceptance of the guidance information and reaction time. Summary of the invention

[0004] The embodiments of the present invention provide a highway lane-level induction strategy optimization method, device and medium to solve the above technical problems.

[0005] In a first aspect, an embodiment of the present invention provides a method for optimizing a highway lane-level guidance strategy, comprising:

[0006] Collecting traffic information of each lane before and after the highway guidance device, wherein the traffic information includes traffic flow data and traffic event data;

[0007] According to the traffic information of each lane, select the target lane that needs to optimize the guidance strategy;

[0008] calibrating a traffic simulation model of the target lane according to the traffic information and the induced compliance rate of the target lane;

[0009] Taking the minimum vehicle delay hours and congestion index as optimization goals, the induction strategy of the target lane is optimized using a genetic algorithm, wherein the induction strategy includes lane recommended speed and lane change suggestions. During the optimization process, the optimization strategy generated by each iteration is introduced into the traffic simulation model to determine whether the optimization goal is achieved;

[0010] Delivering the optimized induction strategy to the induction equipment of the target lane to guide the driver to drive according to the optimized induction strategy;

[0011] According to the improvement of the traffic status, it is determined whether the optimized induction strategy is adapted to the real-time traffic status; if so, the optimized induction strategy is maintained; if not, the operation of collecting traffic information is returned to re-optimize the induction strategy.

[0012] In a second aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0013] one or more processors;

[0014] a memory for storing one or more programs,

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the highway lane-level induction strategy optimization method described in any embodiment.

[0016] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the highway lane-level induction strategy optimization method described in any embodiment.

[0017] Embodiments of the Invention In summary, embodiments of the present invention provide a method for optimizing lane-level induction strategies for highways, which formulates the best lane-level induction strategies according to the traffic conditions and driving behaviors of different lanes, implements differentiated induction measures at the lane level, and guides vehicles to be reasonably distributed to each lane, so as to solve traffic congestion under abnormal road conditions and improve the traffic capacity of the entire road section. Specifically, the method calibrates a traffic simulation model based on lane-level traffic flow data, traffic event data, and induction compliance rate, and applies the model to a genetic algorithm to optimize the induction strategy, checks the strategy performance and determines the optimization direction based on the model simulation results, and obtains the best induction strategy; finally, the best induction strategy is released to the simulation model or the actual road and runs for a period of time, and determines whether the induction strategy needs to be updated as the traffic flow data changes at any time. In this way, lane-level induction schemes can be dynamically generated and adjusted according to the real-time traffic conditions of the highway, thereby improving the traffic efficiency and safety of the highway; induction resources can also be reasonably allocated according to the induction needs of different areas or lanes to avoid excessive or insufficient induction; at the same time, the optimal lane change strategy can be generated based on the availability of the target lane and the induction schemes of adjacent or surrounding lane areas, taking into account the driving habits of different drivers and improving the driver's compliance rate with induction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 is a schematic diagram of a highway lane-level guidance scenario provided by an embodiment of the present invention;

[0020] Figure 2 It is a flow chart of a highway lane-level guidance strategy optimization method provided by an embodiment of the present invention;

[0021] Figure 3 A three-dimensional heat map of the lane-level density distribution of a road section of an existing induction scheme research provided by an embodiment of the present invention;

[0022] Figure 4 After the induction strategy optimized by the method provided by the embodiment of the present invention is released, a three-dimensional heat map of the lane-level density distribution of the research section is evaluated;

[0023] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0025] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0026] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0027] An embodiment of the present invention provides a method for optimizing a lane-level guidance strategy for a highway. To illustrate the method, an application scenario of the method is first introduced. Figure 1 is a schematic diagram of a highway lane-level guidance scenario provided by an embodiment of the present invention, such as Figure 1 As shown, the scenario is a multi-lane highway guidance section with existing guidance facilities, guidance strategies, and guidance systems.

[0028] Specifically, the highway needs to be equipped with intelligent traffic flow detection equipment that can collect traffic flow data and traffic event data with lane-level accuracy. Optionally, the detection equipment includes road test facilities, radars, cameras, coils, etc. The collected data will be transmitted to the guidance system.

[0029] The guidance system can collect driver characteristic behavior information based on traffic flow data and traffic event data, such as the driver's compliance rate with existing guidance strategies (called guidance compliance rate), and update lane-level guidance strategies based on driver characteristic behavior information, traffic event data and traffic flow data, including lane recommended speed and lane change suggestions, etc., wherein the lane recommended speed includes the maximum speed limit and minimum speed limit of the lane. Optionally, the guidance system can be an electronic device deployed in a highway traffic control center, or an electronic device independent of the traffic control center, which is not specifically limited in this embodiment.

[0030] The latest induction strategy can be transmitted to the induction device by wireless or optical fiber, and the induction device releases the latest induction strategy to the driver to induce the driver to drive according to the latest induction strategy. Optionally, the induction device includes an induction information board, a variable information board, a signal light, an arrow board, etc.

[0031] Based on the above application scenarios, Figure 2 This is a flow chart of a highway lane-level guidance strategy optimization method provided by an embodiment of the present invention. The method is executed by the above guidance system and specifically includes the following steps:

[0032] S110. Collect traffic information of each lane before and after the highway guidance device, wherein the traffic information includes traffic flow data and traffic event data.

[0033] This embodiment collects traffic flow data and traffic event data of each lane before and after the induction device through the traffic flow detection device, and combines road information such as the number of lanes, ramp entrances and exits, and toll station locations to construct a lane-level road state data set as the data source of the entire method. Optionally, data of each lane 5 km before and after the induction information board can be collected.

[0034] In a specific implementation, traffic flow data is detected by radar. The radar is arranged on the radar boom of the highway every 600m. The position, speed, acceleration and other parameters of the vehicle are measured in real time at a frequency of 1ms and sent to the traffic control center. The longitude and latitude are accurate to 7 decimal places, the distance is accurate to 0.1m, and the speed is accurate to 0.01m / s. The specific detection data is shown in Table 1:

[0035] Table 1

[0036]

[0037] At the same time, traffic event data is detected through video detectors (cameras). Video detectors are deployed on the cantilever gantry of the highway every 1 km, and real-time detection of traffic event information such as event status, event start and end time, event source, etc. is performed at a frequency of 1 second, and reported to the traffic control center. The specific detection information is shown in Table 2:

[0038] Table 2

[0039]

[0040]

[0041] After the data collection is completed, the collected data will be cleaned, verified, completed and normalized to ensure the integrity and accuracy of the data; at the same time, the data will be corrected in a targeted manner based on the existing layout of induction facilities and existing induction strategies.

[0042] S120. Filter out target lanes that require optimized guidance strategies based on traffic information of each lane.

[0043] This embodiment evaluates the congestion degree and service level of each lane based on the traffic flow data and traffic event data of each lane, and selects at least one lane that needs to be optimized, which is called at least one target lane.

[0044] In a specific implementation, first, at least one of the density, average speed, average delay and average flow of each lane is calculated based on the traffic information of each lane.

[0045] Then, the service level and traffic congestion degree of each lane are evaluated according to at least one of the density, average speed, average delay and average flow of each lane. Optionally, the lane service level grade and traffic congestion degree are evaluated according to the highway service level and traffic congestion degree standards. For example, when the vehicle density of the lane is greater than 7pc / (km·ln), the average speed is greater than 120km / h, the ratio of the maximum service traffic volume to the basic traffic capacity is less than 0.35, the service flow is less than 840pc / (h·ln), and the average delay is 0-55s, the congestion degree is smooth and the service level is A. The evaluation method of this embodiment can be applied to various traffic flows, including manually driven vehicles, intelligent networked vehicles and autonomous driving vehicles. The specific evaluation rules can be determined according to relevant standards or set according to experience, and this embodiment does not make specific restrictions.

[0046] Finally, according to the service level and traffic congestion of each lane, the target lanes that need to be optimized for the induction strategy are selected. For example, lanes other than "congestion level is smooth and service level is A" are taken as target lanes.

[0047] S130: Calibrate a traffic simulation model of the target lane according to the traffic information and the induced compliance rate of the target lane.

[0048] This embodiment takes into account the induced compliance rate in the traffic simulation model and calibrates the model based on actual traffic data. The calibrated model will be used in subsequent operations to simulate traffic flow under the induced strategy as a basis for judging the pros and cons of the induced strategy.

[0049] In a specific implementation, first, a combined model of an intelligent driving model and a lane changing model is constructed. The combined model can take into account the vehicle lane changing behavior and its impact on the traffic flow before and after the lane change. Optionally, the intelligent driving model adopts a 2D-IDM (2Dimensional Intelligent Driver Model) and the lane changing model adopts a MOBIL (Minimize Overall Braking Induced By Lane Change) model. In this embodiment, the combined model is recorded as 2D-IDM-MOBIL. The 2D-IDM-MOBIL combined model can calculate the acceleration and lane changing intention at each time step according to the traffic conditions of the current lane and adjacent / surrounding lanes to determine whether to perform the lane changing action.

[0050] Specifically, the 2D-IDM model is a microscopic driving model based on acceleration and following distance, which can describe the motion law and following behavior of a single vehicle on a two-dimensional plane. The MOBIL model is a lane-changing model based on incentive and inhibition factors, which can describe the lane-changing decision process of a single vehicle between different lanes. By combining the two models, the movement of vehicles with different driving characteristics on multi-lane highways can be simulated, and the impact of lane changing on the operating efficiency and safety of the vehicle itself and surrounding vehicles can be considered. The model theory is as follows:

[0051] Acceleration equation:

[0052]

[0053] Among them, a max,n is the maximum acceleration of lane n, v i,t,n is the speed of vehicle i in lane n at time t, v des,n is the expected speed of n lanes, δ n is the n-lane acceleration index, is the desired spacing of n lanes, Δx i is the distance between vehicle i and the vehicle in front, and ξ represents random factors such as noise in traffic flow.

[0054] Expected spacing equation:

[0055]

[0056] Where s0 is the minimum spacing, T is the expected time interval, and v lead,n is the speed of the preceding vehicle in lane n, and b is the maximum deceleration.

[0057] Lane change willingness equation:

[0058]

[0059] Among them, p is the courtesy coefficient, I th is the lane change threshold.

[0060] After the model is constructed, the induced compliance rate and the existing induced strategy are imported into the combined model. Optionally, in the combined model, a set proportion of vehicles is limited to comply with the maximum speed limit of the target lane. When the vehicle speed exceeds the maximum speed limit, the vehicle maintains the current speed value unchanged, wherein the set proportion is the value of the induced compliance rate.

[0061] Then, according to the traffic flow data of the target lane, the parameters of the lane-changing model are calibrated using the DE (Differential Evolution) algorithm, and the parameters of the intelligent driving model are calibrated using the global DIRECT (Dlvinding RECTangle) algorithm; the calibrated combined model is used to simulate the vehicle speed curve and the total number of lane changes and the average number of lane changes in the traffic flow, and the comparison is made with the actual traffic flow data. If the two are basically consistent, the calibration is completed. Among them, the parameters to be calibrated are the other position parameters in equations (1) to (3) except for the detectable data; the specific implementation methods of the DE algorithm and the global DIRECT algorithm are both existing technologies and will not be repeated here.

[0062] S140. Taking the minimum number of vehicle delay hours and congestion index as optimization goals, the induction strategy of the target lane is optimized using a genetic algorithm, wherein the induction strategy includes lane recommended speed and lane change suggestions. During the optimization process, the optimization strategy generated by each iteration is introduced into the traffic simulation model to determine whether the optimization goal is achieved.

[0063] This embodiment is based on optimization algorithms such as genetic algorithms to develop the optimal lane-level induction strategy, including the recommended speed and lane change suggestions for each lane. By setting different fitness functions and constraints, the optimal solution that maximizes or minimizes the objective function (objective functions related to traffic flow indicators such as total travel delay, total passing time, and total collision risk) is solved. The constraints are actual conditions such as speed limit regulations, lane change distance requirements, and lane change number restrictions. After the optimal solution is obtained through the optimization algorithm, it is converted into a specific induction strategy.

[0064] Optionally, the objective function can be constructed by using two indicators, VHD (Vehicle Hours of Delay) and CI (Congestion Index), and a multi-objective optimization function can be constructed by minimizing VHD and CI.

[0065]

[0066] Among them, T congestion is the time it takes for vehicles to pass through the road section when the traffic is congested, that is, the vehicle travel time measured by the radar, T free is the time to pass the road section when there is no congestion, that is, the time to pass the road section at the expected speed, and N is the total number of vehicles passing the road section during the study period.

[0067]

[0068] Among them, the expected vehicle speed V desireThe calculation is based on the value corresponding to the 85th percentile on the speed cumulative distribution curve under the free flow state of the road, combined with the road grade, design speed and expert score. i is the average speed of the i-th vehicle passing through the road section.

[0069] In a specific implementation, the process of optimizing the target lane guidance strategy using a genetic algorithm may include the following steps:

[0070] Step 1: Encode the target lane's induction strategy as the current solution to be optimized. The encoding process is a common step of the genetic algorithm and will not be described in detail.

[0071] Step 2: Import the traffic information and induction strategy of the target lane into the traffic simulation model, and simulate the future traffic state of the target lane according to the induction compliance rate. Optionally, based on the traffic event data and the induction compliance rate, issue the induction strategy to the traffic simulation model to simulate the future traffic flow state of the target lane. The induction compliance rate here can adopt the induction compliance rate obtained by actual statistics, or set an expected induction compliance rate. The former pays more attention to the driver's behavior habits obtained from actual data, while the latter takes into account the impact of the optimization of the induction strategy on the driver's behavior. In actual application, it can be flexibly selected according to needs.

[0072] Step 3: Calculate the objective function value consisting of vehicle delay hours and congestion index according to the future traffic status. Optionally, the weighted sum of VHD and CI can be used as the multi-objective function f:

[0073] f=α×VHD+β×CI (6)

[0074] After each simulation, the values ​​of VHD and CI are calculated according to the simulation results, and the objective function value is obtained.

[0075] Step 4: If the objective function value does not reach the set optimal condition, the current solution is cross-linked, selected and iterated to generate a new current solution; and the new current solution is decoded into a new induction strategy, and the operation of importing the traffic information and induction strategy of the target lane into the traffic simulation model is returned until the final objective function value reaches the optimal condition. Optionally, a non-dominated sorting genetic algorithm can be used for cross-linking, selection and iteration, and the process and decoding process are common steps of the genetic algorithm, which will not be repeated in this embodiment.

[0076] In general, the lane-level induction strategy obtained through the genetic algorithm will reduce the speed limit of the congested lane and provide reasonable lane-changing suggestions for vehicles in the congested lane, thereby improving the overall traffic conditions of the road section and each lane.

[0077] S150: Deliver the optimized induction strategy to the induction equipment of the target lane to guide the driver to drive according to the optimized induction strategy.

[0078] After obtaining the optimized induction strategy, the strategy can be deployed to the target lane and run for a period of time to verify the effectiveness and adaptability of the induction strategy. Optionally, the strategy can be deployed in the above-mentioned traffic simulation model to simulate the traffic conditions in the future through the model; it can also be deployed in an actual highway and verified through actual traffic data for a period of time. When deployed in the traffic simulation model, the induced compliance rate can be selected from the actual induced compliance rate or the expected induced compliance rate, or the actual induced compliance rate can be selected first to simulate for a period of time and then the expected induced compliance rate can be selected to simulate for a period of time. This embodiment does not make specific restrictions.

[0079] S160. According to the improvement of the traffic status, determine whether the optimized induction strategy is suitable for the real-time traffic status; if so, maintain the optimized induction strategy; if not, return to the operation of collecting traffic information and re-optimize the induction strategy.

[0080] This embodiment determines whether the optimized induction strategy is adapted to the real-time traffic status based on the improvement of the overall traffic status of the road section and the improvement of the traffic status of each lane. Optionally, the cycle duration of evaluating the induction scheme and updating the induction strategy is set, and at least one of the density distribution, average speed and traffic capacity of the lanes in the road section is regularly measured to evaluate the road congestion, the reduction of the total passing time and the reduction of the total travel delay, so as to test the effectiveness and adaptability of the induction scheme, and predict whether the induction algorithm still needs to be optimized as the traffic flow status is updated.

[0081] In a specific implementation, by comparing traffic flow parameters and indicators before and after induction, the influence of the induction scheme on the traffic flow conditions of different lanes is analyzed to determine whether the induction scheme has achieved the expected effect. In the case of verification on actual roads, the driving behavior data before and after induction can also be compared to analyze the influence of the induction scheme on the lane changing behavior and speed limit compliance rate of vehicles with different driving characteristics to determine whether the induction scheme meets the driver's expectations and habits. Based on the evaluation results, it is determined whether the induction scheme needs to be adjusted or updated to adapt to the real-time changing traffic flow status.

[0082] The effectiveness of this method is illustrated below by comparing the results of an application example. In this example, a 2500m long section of the Beijing-Harbin Expressway in the Shenyang direction is selected as the research section. The section has six lanes in both directions and is designed according to the six-level service level. The section contains external monitoring facilities such as variable information boards and cantilever screens, and dividing and merging areas such as ramp checkpoints and toll stations. According to statistical data in recent years, the average daily flow rate of this section during peak hours, especially during peak traffic hours on holidays, is much higher than the designed traffic capacity. At the same time, traffic accidents on this section account for a high proportion of the total number of accidents in the jurisdiction, and it has become a section prone to congestion during peak traffic hours, and it also seriously affects the safety of people's travel. The main traffic is small and medium-sized passenger cars and extra-large trucks, mixed with other vehicles such as container trucks, small trucks and large trucks, and the vehicle types are complex.

[0083] In this embodiment, radar data of 13 minutes during a peak period is selected as research data, with a data length accuracy of 1m and a time accuracy of 1ms. After data processing, a three-dimensional heat map of the density distribution of the entire lane and each lane is drawn. Figure 3 This is a three-dimensional heat map of the lane-level density distribution of the existing induction scheme research section, where the lane numbers are from the inner side of the road to the outer side of the road, and lane 4 is the emergency lane; the 0 point and 2500 point of the 2500m section correspond to the starting point and end point of the road driving direction. Figure 3 It can be seen that the density of the entire section reached nearly 70veh / km / lane, and at the same time, vehicles merged into the merging area of ​​the front ramp, causing the density to continue to increase; among them, congestion occurred at the front end of lane 1. According to the traffic event data, a pedestrian intrusion occurred at the front end of the section. The event lasted for 15 minutes, resulting in a congestion belt at the location of the event and spreading backward; the density of lane 2 was relatively low, and a small amount of congestion occurred in the middle of the section. Due to the congestion in lane 1, some vehicles changed lanes to lane 2, which led to an increase in density in the middle section of lane 2; the density of lane 3 was between lanes 1 and 2, and it was mainly used for large trucks, extra-large trucks and other large vehicles with slower speeds, so the density was higher; lane 4 was an emergency lane, and the reason for the density was that social vehicles illegally occupied the emergency lane and traffic police vehicles parked.

[0084] Figure 4It is a three-dimensional heat map of the lane-level density distribution of the research section evaluated after the induction strategy optimized by the method provided in the embodiment of the present invention is released. This figure is simulated by a traffic simulation model. It is assumed that after the induction strategy is released, the induced compliance rate is 75% (the expected compliance rate), and all vehicles entering the section are induced and simulated. The density distribution of the entire lane and each lane after simulation is used to observe the induction effect. The density of the section is reduced as a whole, and the congestion belt is controlled in the middle part of the target section, and both ends are maintained at a low congestion level; since lane 1 has a lower speed and acceleration than lane 2, the 2D-IDM combined model will guide vehicles in lane 1 to change lanes to lane 2, so that the density of lane 1 gradually decreases; at the same time, according to the speed limit value interval obtained by the genetic algorithm, the speed limit value of lane 2 is increased, and the speed limit value of lane 1 is reduced. Vehicles in lane 1 pass at a low speed, while vehicles with faster driving styles such as passenger cars merge into lane 2 and pass quickly. Therefore, the density of the lane change area in lane 2 increases slightly, and the density at the front and rear ends of the induced road section decreases. Lane 3 is mainly a lane for slow vehicles, and its speed limit is appropriately increased so that vehicles in the congested section of lane 2 can merge into lane 3 and pass quickly.

[0085] In summary, the embodiment of the present invention provides a method for optimizing lane-level induction strategy for highways. According to the traffic conditions and driving behaviors of different lanes, an optimal lane-level induction strategy is formulated, and differentiated induction measures at the lane level are implemented to guide vehicles to be reasonably distributed to each lane, so as to solve traffic congestion under abnormal road conditions and improve the traffic capacity of the entire road section.

[0086] Specifically, the method calibrates the traffic simulation model according to lane-level traffic flow data, traffic event data, and induced compliance rate, and applies the model to the genetic algorithm to optimize the induced strategy. By setting the objective function and constraints matching the traffic state, the induced compliance rate is used to simulate the driving behavior characteristics, and the strategy performance is tested and the optimization direction is determined according to the model simulation results to obtain the optimal induced strategy. Finally, the optimal induced strategy is released to the simulation model or the actual road and runs for a period of time to determine whether the induced strategy needs to be updated as the traffic flow data changes at any time. In this way, the lane-level induced scheme can be dynamically generated and adjusted according to the real-time traffic conditions of the highway to improve the traffic efficiency and safety of the highway; the induced resources can also be reasonably allocated according to the induced needs of different areas or lanes to avoid excessive or insufficient induced; at the same time, the optimal lane change strategy can be generated according to the availability of the target lane and the induced scheme of the adjacent or surrounding lane area, taking into account the driving habits of different drivers to improve the induced compliance rate of the driver.

[0087] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention is shown in FIG. Figure 5As shown, the device includes a processor 60, a memory 61, an input device 62 and an output device 63; the number of processors 60 in the device can be one or more. Figure 5 A processor 60 is taken as an example; the processor 60, the memory 61, the input device 62 and the output device 63 in the device can be connected by a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0088] The memory 61 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the highway lane-level induction strategy optimization method in the embodiment of the present invention. The processor 60 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 61, that is, realizing the above-mentioned highway lane-level induction strategy optimization method.

[0089] The memory 61 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 61 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 61 may further include a memory remotely arranged relative to the processor 60, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0090] The input device 62 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 63 may include a display device such as a display screen.

[0091] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the highway lane-level induction strategy optimization method of any embodiment.

[0092] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0093] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0094] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0095] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's 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 may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A highway lane-level guidance strategy optimization method, characterized in that: include: Collecting traffic information of each lane before and after the highway guidance device, wherein the traffic information includes traffic flow data and traffic event data; According to the traffic information of each lane, select the target lane that needs to optimize the guidance strategy; According to the traffic information and induced compliance rate of the target lane, the traffic simulation model of the target lane is calibrated; specifically, first, a combined model of an intelligent driving model and a lane changing model is constructed, wherein the intelligent driving model adopts a two-dimensional intelligent driving model, and the lane changing model adopts a total braking model that minimizes the lane changing. After the model is constructed, the induced compliance rate and the existing induced strategy are introduced into the combined model, wherein a set proportion of vehicles is limited to comply with the maximum speed limit of the target lane in the combined model, and when the vehicle speed exceeds the maximum speed limit, the vehicle maintains the current speed value unchanged, wherein the set proportion takes the value of the induced compliance rate; then, according to the traffic flow data of the target lane, the parameters of the lane changing model are calibrated using a differential evolution algorithm, and the parameters of the intelligent driving model are calibrated using a global DIRECT algorithm; the calibrated combined model is used to simulate the vehicle speed curve and the total number of lane changes and the average number of lane changes of the traffic flow, and the comparison is performed with the actual traffic flow data, and the calibration is completed if the two are basically consistent; Taking the minimum vehicle delay hours and congestion index as the optimization objectives, the induction strategy of the target lane is optimized by using a genetic algorithm, wherein the induction strategy includes the lane recommended speed and lane change recommendation. During the optimization process, the optimization strategy generated by each iteration is imported into the traffic simulation model to determine whether the optimization objective is achieved; specifically, the induction strategy of the target lane is encoded as a current solution to be optimized; the traffic information and the induction strategy of the target lane are imported into the traffic simulation model, and the future traffic state of the target lane is simulated according to the induction compliance rate; according to the future traffic state, the objective function value composed of the vehicle delay hours and the congestion index is calculated; if the set optimal condition is not reached according to the objective function value, the current solution is cross-cut, selected and iterated to generate a new current solution; and the new current solution is decoded into a new induction strategy, and the operation of importing the traffic information and the induction strategy of the target lane into the traffic simulation model is returned until the final objective function value reaches the optimal condition, wherein the weighted sum of VHD and CI is used as the multi-objective function f: f=α×VHD+β×CI Among them, VHD represents the number of vehicle delay hours, CI represents the congestion index, and α and β are the weight coefficients of weighted summation; Among them, T congestion is the time it takes for vehicles to pass through the road section when the traffic is congested, that is, the vehicle travel time measured by the radar, T free is the time to pass the road section when there is no congestion, N is the total number of vehicles passing the road section during the study period, and i represents a natural number; Among them, the expected vehicle speed V desire The calculation is based on the value corresponding to the 85th percentile on the speed cumulative distribution curve under the free flow state of the road, combined with the road grade, design speed and expert score. i is the average speed of the i-th vehicle passing through the road section; Delivering the optimized induction strategy to the induction equipment of the target lane to guide the driver to drive according to the optimized induction strategy; According to the improvement of traffic conditions, determine whether the optimized induction strategy is suitable for the real-time traffic conditions; if it is suitable, maintain the optimized induction strategy; if it is not suitable, return to the operation of collecting traffic information and re-optimize the induction strategy.

2. The method according to claim 1, characterized in that The target lanes that need to be optimized for the guidance strategy are selected based on the traffic information of each lane, including: Calculate at least one of an average speed, an average delay, and an average flow rate of each lane according to the traffic information of each lane; Evaluate the service level and traffic congestion degree of each lane according to at least one of the average speed, average delay and average flow of each lane; According to the service level and traffic congestion of each lane, the target lanes that need to be optimized for guidance strategy are selected.

3. The method according to claim 1, characterized in that The step of importing the traffic information and the induction strategy of the target lane into the traffic simulation model and simulating the future traffic state of the target lane according to the induction compliance rate includes: According to the traffic event data and the induced compliance rate, an induced strategy is issued to the traffic simulation model to simulate the future traffic flow state of the target lane.

4. The method according to claim 1, characterized in that The crossover, selection and iteration of the current solution comprises: A non-dominated sorting genetic algorithm is used to perform crossover, selection and iteration on the current solution.

5. The method according to claim 1, characterized in that The step of judging whether the optimized induction strategy is adapted to the real-time traffic status according to the improvement of the traffic status includes: According to the improvement of the overall traffic condition of the road section and the traffic condition of each lane, it is judged whether the optimized induction strategy is suitable for the implemented traffic conditions.

6. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the highway lane-level induction strategy optimization method described in any one of claims 1-5.

7. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the highway lane-level induction strategy optimization method described in any one of claims 1-5 is implemented.

Images