Intelligent network connection automobile control method and system based on vehicle-road cooperation

Abstract

The invention provides an intelligent network connection automobile control method and system based on vehicle-road cooperation, and relates to the technical field of intelligent traffic. Calculating a dynamic pheromone concentration in an inverse proportion relation with the congestion degree of the alternative road section based on the traffic state data; broadcasting the dynamic pheromone concentration to a second automobile through a roadside data broadcasting module, wherein the spacing distance between the second automobile and the starting point of the alternative road section is smaller than a preset spacing distance; acquiring an original navigation route of the second automobile from the current node to the target node; selecting a target road section from each alternative road section, and updating the original navigation route; controlling the second automobile to run according to the updated original navigation route until the second automobile leaves the target road section; and updating the dynamic pheromone concentration based on the traffic state information about the target road section acquired by the second automobile, and updating the current node of the second automobile until the second automobile arrives at the target node. And the road smoothness is improved, and meanwhile, the operation efficiency of the intelligent network connection automobile is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a control method and system for an intelligent networked vehicle based on vehicle-road collaboration. Background Art

[0002] Vehicle-road collaboration refers to the exchange of information between vehicles and roads, which enables vehicles and infrastructure (such as traffic signals and roadside equipment) to work together to improve traffic efficiency and driving safety. Intelligent connected vehicles are intelligent vehicles that can exchange data through network connections, have automated driving and decision-making functions, and can communicate with other vehicles and roadside infrastructure in real time.

[0003] The necessity of controlling intelligent connected vehicles is that they have the ability to drive and communicate, but in complex traffic environments, external scheduling is required to ensure safe and efficient operation. Effective control can avoid conflicts between vehicles, optimize driving paths, reduce energy consumption and traffic congestion, and thus improve the reliability and stability of the overall transportation system.

[0004] However, existing intelligent connected vehicle control solutions often rely too much on third-party navigation programs, are easily affected by network conditions, lack sensitivity in identifying congested sections, and lack fault tolerance, which can easily lead to road congestion and delay the journey of intelligent connected vehicles. Summary of the invention

[0005] In order to solve the technical problems that existing intelligent connected vehicle control solutions often rely too much on third-party navigation programs, are easily affected by network status, lack sensitivity in identifying congested road sections, lack fault tolerance, and easily cause road congestion and delay the travel of intelligent connected vehicles, the present invention provides an intelligent connected vehicle control method and system based on vehicle-road collaboration.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect:

[0008] An embodiment of the present invention provides a control method for an intelligent connected vehicle based on vehicle-road collaboration, which is applied to an intelligent connected vehicle control platform. The intelligent connected vehicle control platform includes a driving status acquisition module located at the vehicle end and a roadside data acquisition module and a roadside data broadcast module located at the road end. The vehicle end and the road segment can perform data interaction. The method includes:

[0009] S1: Collecting traffic status data through a driving status collection module and a roadside data collection module, wherein the traffic status data includes an average speed and a total waiting time of the first vehicle on the alternative road section, and a vehicle density and a traffic flow on the alternative road section;

[0010] S2: Based on the traffic status data, the dynamic pheromone concentration inversely proportional to the congestion degree of the candidate road section is calculated in combination with the heat diffusion process, and the dynamic pheromone concentration is stored in the roadside data broadcast module;

[0011] S3: broadcasting the dynamic pheromone concentration to a second vehicle whose interval distance from the starting point of the alternative road section is less than a preset interval distance through a roadside data broadcasting module;

[0012] S4: Obtaining the original navigation route of the second car from the current node to the target node;

[0013] S5: based on vehicle density, traffic flow and dynamic pheromone concentration, selecting a target road segment from various candidate road segments under constraints to update the original navigation route, wherein the constraints include that the average vehicle speed is greater than a preset average vehicle speed, the total waiting time is the shortest, and the mileage of the updated original navigation route is less than a preset mileage;

[0014] S6: Controlling the second vehicle to travel according to the updated original navigation route until it leaves the target road section;

[0015] S7: Based on the traffic status information about the target road section acquired by the second car, the dynamic pheromone concentration is updated, the current node of the second car is updated, and the process returns to step S4 until the second car reaches the target node.

[0016] Second aspect:

[0017] An embodiment of the present invention provides an intelligent connected vehicle control system based on vehicle-road collaboration, including:

[0018] processor;

[0019] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the intelligent connected vehicle control method based on vehicle-road collaboration as described in the first aspect is implemented.

[0020] The third aspect:

[0021] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method for controlling an intelligent connected vehicle based on vehicle-road collaboration as described in the first aspect is implemented.

[0022] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0023] In the present invention, in the process of controlling the intelligent networked vehicle, the data collection module based on the vehicle end and the road section collects the traffic status data shared by the historical vehicle, i.e., the first vehicle, in real time, and then combines the thermal diffusion process to determine the dynamic pheromone concentration that is inversely proportional to the congestion degree of the candidate road section, simulates the diffusion characteristics of congestion, and makes the pheromone concentration change with the congestion degree, so as to achieve more accurate congestion warning. By dynamically adjusting the pheromone concentration, the intelligent networked vehicle can obtain the congestion conditions of different road sections in time, flexibly avoid congestion, and improve traffic fluency and driving efficiency. Then, it is stored in the roadside data broadcast module to broadcast to other vehicles, i.e., the second vehicle that may travel to the road section. This vehicle-road collaborative control scheme is highly sensitive to road conditions and has high fault tolerance, and can effectively divert traffic flow and avoid road congestion. During the control process of the intelligent networked vehicle, the dynamic pheromone concentration is also combined to select a suitable target section from various alternative sections, that is, the average vehicle speed is greater than the preset average vehicle speed, the total waiting time is the shortest, and the mileage of the updated original navigation route is less than the preset mileage, and recommended to the second vehicle. It has the full-trip navigation capability of route warning recommendation, and can be combined with the existing navigation software to realize the rapid trip processing capability of the intelligent networked vehicle without increasing the mileage, which greatly improves the operating efficiency of the networked vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A flowchart of a method for controlling an intelligent connected vehicle based on vehicle-road collaboration provided by an embodiment of the present invention;

[0026] Figure 2 A schematic diagram of the structure of an intelligent connected vehicle control platform provided by an embodiment of the present invention;

[0027] Figure 3 A schematic diagram of the structure of an intelligent connected vehicle control system based on vehicle-road collaboration provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0029] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0030] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0031] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0032] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0033] Reference Manual Attached Figure 1 , showing a flow chart of a method for controlling an intelligent connected vehicle based on vehicle-road collaboration provided by an embodiment of the present invention.

[0034] Reference Manual Attached Figure 2 , showing a schematic structural diagram of an intelligent connected vehicle control platform provided by an embodiment of the present invention.

[0035] An embodiment of the present invention provides a method for controlling an intelligent connected vehicle based on vehicle-road collaboration, which is applied to an intelligent connected vehicle control platform. The intelligent connected vehicle control platform includes a driving status acquisition module located at the vehicle end and a roadside data acquisition module and a roadside data broadcasting module located at the road end. The vehicle end and the road segment can interact with each other.

[0036] It is understandable that the intelligent connected vehicle control platform integrates data collection and broadcasting modules on the vehicle side and the road side. The driving status collection module monitors the vehicle's driving status in real time, and the roadside data collection module obtains the road's traffic status information. The two share information through data interaction to achieve coordinated linkage between the vehicle and the road. This design ensures real-time synchronization of vehicle and road information, which helps optimize route planning and improve driving safety.

[0037] The processing flow of the intelligent connected vehicle control method based on vehicle-road collaboration may include the following steps:

[0038] S1: Collect traffic status data through the driving status collection module and the roadside data collection module.

[0039] The traffic status data include the average speed and total waiting time of the first automobile on the alternative road section, as well as the vehicle density and traffic flow of the alternative road section.

[0040] Among them, the candidate road section refers to one or more candidate driving sections that the current vehicle may choose during the route planning process. These sections will be analyzed and compared during route planning to determine whether they are suitable as a pass path. Through the driving status collection module and the roadside data collection module, the system obtains key traffic data of vehicles and sections, including the average speed, waiting time, vehicle density and traffic flow of the first vehicle on the candidate road section. This process ensures that the intelligent connected vehicle can understand the driving conditions of the candidate road section in real time and provide data support for the subsequent route optimization.

[0041] In a possible implementation, S1 specifically includes:

[0042] S101: Collecting the average speed and total waiting time of the first vehicle on the candidate road section through a driving status collection module.

[0043] S102: Collect vehicle density and traffic flow of the candidate road section through a roadside data collection module.

[0044] It is understandable that the average speed and waiting time of the first car on the candidate road section are obtained through the driving state collection module, and the vehicle density and traffic flow of the road section are collected through the roadside data collection module. These data provide detailed traffic state information for subsequent path optimization, which helps the intelligent connected car to choose a smoother driving path.

[0045] S2: Based on the traffic status data, the dynamic pheromone concentration inversely proportional to the congestion level of the candidate road section is calculated in combination with the heat diffusion process, and the dynamic pheromone concentration is stored in the roadside data broadcast module.

[0046] Among them, congestion information is diffused from high-density areas to surrounding sections in a manner similar to heat diffusion to simulate the propagation characteristics of congestion. Pheromone concentration is an indicator that reflects the degree of smoothness or congestion of a road section. The concentration value is inversely proportional to the degree of congestion, that is, the smoother the road section, the higher the pheromone concentration, and vehicles are more inclined to choose this road section.

[0047] It should be noted that the determination of dynamic pheromone concentrations in combination with the heat diffusion process can dynamically and continuously reflect the diffusion of congestion between road sections, rather than simply treating the road sections as isolated. In this way, the pheromone concentration not only indicates the smoothness of the current road section, but also predicts how congestion affects adjacent road sections, allowing the system to respond more sensitively to changes in traffic flow as a whole. Through this diffusion simulation, vehicles can avoid areas that may be congested earlier, thereby achieving more optimized traffic flow distribution and improving the overall traffic efficiency of the road. Based on traffic status data, the dynamic pheromone concentration that is inversely proportional to the congestion level of the road section is calculated using the heat diffusion process, and an indicator reflecting the smoothness of the road section is generated. The data is stored in the roadside data broadcast module for real-time reference by other vehicles to help vehicles avoid congestion.

[0048] In a possible implementation, S2 specifically includes:

[0049] S201: Calculate the instantaneous traffic density of the candidate road section based on the traffic flow:

[0050]

[0051] Among them, Q ij (t) represents the instantaneous flow density of the candidate road section ij, n ij (t) represents the traffic flow of the candidate road section at time t, i.e., the number of vehicles, L ij Indicates the total length of the alternative road segments.

[0052] S202: Establishing a congestion diffusion function for the candidate road segments based on the heat diffusion process:

[0053]

[0054] D=W·V avg，ij

[0055] Among them, ψ ij (t) represents the congestion diffusion function of the candidate road section ij associated with time t, Indicates partial derivative, D represents the average speed V of the alternative road section width W and the alternative road section ij avg，ij The related congestion diffusion coefficient, k represents the natural attenuation coefficient of the congestion state, x represents the position coordinates on the alternative road section, Represents the congestion diffusion rate associated with the location coordinates of the candidate road segment.

[0056] It should be noted that wider roads generally have higher traffic capacity, so congestion will spread faster and affect a wider area. The average speed directly affects the speed at which vehicles move on the road. The higher the speed, the easier it is for vehicles to spread congestion information (such as deceleration and parking information on congested roads) to farther places.

[0057] S203: Solve the steady-state solution of the congestion diffusion function reflecting the termination of congestion diffusion:

[0058]

[0059] in, represents the steady-state solution of the alternative road section ij, Indicates the maximum vehicle capacity of the alternative road segment.

[0060] S204: Determine the dynamic pheromone concentration in the steady state by combining the steady-state solution, the average vehicle speed, and the total waiting time:

[0061]

[0062] Among them, T ij (t) represents the dynamic pheromone concentration of the candidate road section ij at time t, represents the reference pheromone concentration constant, f1(t) and f2(t) represent the average vehicle speed factor and the total waiting time attenuation factor at time t, respectively, V avg,ij (t) represents the average speed of the first vehicle at time t on the candidate road section ij, V desired represents the expected average vehicle speed, e represents the natural constant, δ represents the influence coefficient of the total waiting time, T wait Indicates the total waiting time of the first car.

[0063] S205: Storing the dynamic pheromone concentration in the roadside data broadcast module.

[0064] It should be noted that by considering the congestion diffusion process and solving the dynamic pheromone concentration in steady state, the dynamic pheromone concentration obtained is more accurate, which in turn provides more accurate guidance data for the selection of subsequent vehicles. By combining the heat diffusion process and the steady-state solution, the system can more accurately reflect the spread and stability of congestion between road sections. Based on factors such as vehicle density, average speed, and waiting time, the dynamic pheromone concentration automatically adjusts with congestion changes at different times. It can not only accurately characterize the smoothness of the current road section, but also predict the potential impact of congestion on adjacent road sections, thereby providing real-time and accurate path selection basis for subsequent vehicles, effectively improving overall traffic flow and driving efficiency.

[0065] S3: Broadcasting the dynamic pheromone concentration to a second vehicle whose interval distance from the starting point of the alternative road section is less than a preset interval distance through a roadside data broadcasting module.

[0066] It should be noted that the system uses the roadside data broadcast module to send the dynamic pheromone concentration in real time to the vehicle (i.e., the second vehicle) that is close to the starting point of the alternative road section and whose distance is less than the set interval. This allows the vehicle that is about to enter the road section to know in advance whether the road section is smooth or congested, thereby helping the vehicle to adjust the driving route in time and optimize travel decisions.

[0067] It should be noted that those skilled in the art can set the size of the preset spacing distance according to actual needs, and the present invention is not limited thereto.

[0068] S4: Obtain the original navigation route of the second car from the current node to the target node.

[0069] Among them, the current node is the current location of the second car, and the target node is the location that the second car wants to reach. The original navigation route refers to the path preliminarily planned by the navigation system for the second car without considering the real-time traffic status (such as congestion pheromone concentration). This route is calculated based on normal road conditions and does not include dynamic road condition adjustments. The system obtains the initial navigation route of the second car from the current node to the target node, that is, the path that is not affected by real-time road conditions. This route provides a basis for optimization based on dynamic pheromone concentrations in subsequent steps, enabling the system to flexibly adjust on the basis of the original path and select a smoother section of the road.

[0070] In a possible implementation manner, S4 is specifically:

[0071] The original navigation route of the second car from the current node to the target node is obtained through the navigation software.

[0072] S5: Based on vehicle density, traffic flow, and dynamic pheromone concentration, a target segment is selected from various candidate segments under constraints to update the original navigation route.

[0073] The constraints include that the average vehicle speed is greater than a preset average vehicle speed, the total waiting time is the shortest, and the mileage of the updated original navigation route is less than a preset mileage.

[0074] The target road section is the optimal road section selected from the candidate roads after multiple indicators are evaluated. This road section is relatively smoother and takes less time, which helps to optimize the entire driving route. Constraints are the standards that need to be met when selecting the target road section.

[0075] It should be noted that the system selects the optimal target section from each candidate section based on the vehicle density, traffic flow and dynamic pheromone concentration, subject to certain constraints, to update the original navigation route. Constraints include: the average vehicle speed must be higher than the set value, the total waiting time must be the shortest, and the total mileage of the updated route must not exceed the preset maximum mileage. This process ensures that path planning minimizes mileage and waiting time while taking into account traffic efficiency, thereby helping vehicles choose smoother and more efficient driving routes and improving the overall travel experience.

[0076] In a possible implementation, S5 specifically includes:

[0077] S501: Constructing a travel cost function for alternative road segments:

[0078]

[0079] Among them, F ij (t) represents the travel cost function value of the candidate road section ij at time t, ρ ij (t), Q ij (t), T ij (t) represent the vehicle density, traffic flow and dynamic pheromone concentration of the alternative road section ij at time t respectively.

[0080] Among them, the vehicle density term It indicates the degree of congestion on the road. When the density is high and the flow is low, the value increases, indicating that the road section is congested. It indicates the smoothness of the road. The lower the pheromone concentration, the higher the value, which means the road section is not ideal, otherwise it is smooth.

[0081] In a possible implementation, before S502, the process further includes: calculating a travel cost function value by combining a gradient strategy algorithm and a reinforcement learning algorithm.

[0082] Among them, the gradient strategy algorithm is a policy-based optimization algorithm, which is mainly used in reinforcement learning. By calculating the gradient of the strategy (that is, the direction and magnitude of the change in the policy parameters under the current strategy), the gradient strategy algorithm continuously adjusts the strategy to make it closer to the optimal in each step. Its core is to find the policy parameters that can maximize the reward through gradient ascent or descent. The reinforcement learning algorithm is a machine learning method that aims to allow the agent to continuously learn through interaction with the environment to obtain the maximum cumulative reward. The agent observes the state of the environment and chooses an action. The environment returns the corresponding reward and new state. The agent finds the optimal strategy through multiple attempts, so as to obtain more rewards in future decisions.

[0083] In one possible implementation, a pass cost function is established by combining a gradient strategy algorithm and a reinforcement learning algorithm, specifically including:

[0084] S502A: Define the states, actions, and rewards of the reinforcement learning algorithm:

[0085] S t =[V avg,ij (t),ρ ij (t),Q ij (t),T ij (t)]

[0086] A t =[w1,w2,w3]

[0087]

[0088] Among them, S t represents the state vector at time t including different states, w1, w2, w3 represent the vehicle density weight, traffic flow weight and dynamic pheromone concentration weight as actions, respectively, A t represents the action vector at time t including different actions, R t Represents the reward function value at time t regarding the travel cost function value of different alternative road sections ij.

[0089] S502B: Establishing the travel cost function:

[0090]

[0091] S502C: Optimize the policy parameters of the gradient strategy algorithm with the goal of maximizing the reward function value:

[0092]

[0093] Among them, θ represents the policy parameter of the gradient strategy algorithm, T represents the total time, represents the gradient of the objective function J(θ) with respect to the policy parameter θ, For all S t and A t Take the average value, represents the value of θ that maximizes J(θ). * represents the optimal policy parameter, α represents the learning rate of the update step of the control policy parameter θ, and π(A t |S t ; θ) represents the given state S t Next, select action A according to the policy parameter θ t The probability distribution of , log represents the logarithmic function, It represents the gradient of the probability distribution after taking the logarithm, and ← represents the assignment.

[0094] in, is the gradient of the logarithmic probability, indicating that under the current parameter θ, if the strategy is changed to select action A t The probability of how the expected reward will change is used to calculate the direction and magnitude of the policy update.

[0095] S502D: Substitute the optimized strategy parameters into the gradient strategy algorithm to obtain an optimized gradient strategy algorithm.

[0096] S502E: Input the current state vector into the optimization gradient strategy algorithm, and output the current vehicle density weight, the current traffic flow weight, and the current dynamic pheromone concentration weight.

[0097] S502F: Substitute the current vehicle density weight, the current traffic flow weight and the current dynamic pheromone concentration weight into the traffic cost function to complete the establishment of the traffic cost function.

[0098] It should be noted that the combination of the gradient strategy algorithm and the reinforcement learning algorithm to calculate the traffic cost function value can adaptively adjust the weights, make full use of real-time traffic data, and enable the algorithm to gradually learn the optimal traffic strategy in a complex environment. This approach can not only effectively respond to changing traffic conditions, but also optimize the accuracy of target road section selection, ensuring that each decision is optimal, thereby improving the efficiency of traffic flow and the smoothness of traffic.

[0099] S502: Taking the minimum value of the travel cost function as the goal, determine the target road section from the candidate road sections in combination with the constraint conditions:

[0100]

[0101] V avg,ij (t)≥V preset

[0102] T avg,ij ≤T min

[0103] D ij -D≤ε

[0104]

[0105] Among them, min means taking the minimum value, D ij represents the updated original navigation route, i.e., the mileage of the alternative route ij, D represents the mileage of the original navigation route, ε represents the mileage deviation threshold, V avg,ij represents the average speed of the candidate road section ij, V preset Indicates the preset average vehicle speed, T avg,ij represents the average waiting time of the alternative road section ij, T min represents the preset waiting time, and λ1, λ2, and λ3 represent the Lagrange multipliers of different constraints respectively.

[0106] In a possible implementation, each Lagrange multiplier is calculated based on the KKT condition, and the calculation method of each Lagrange multiplier is specifically as follows:

[0107]

[0108] in, It means partial derivative.

[0109] Among them, KKT conditions (Karush-Kuhn-Tucker conditions) are a set of necessary conditions for solving constrained optimization problems.

[0110] It should be noted that the main benefit of using KKT conditions to calculate Lagrange multipliers is that it provides a systematic and rigorous method to consider constraints in optimization problems. In this way, it can be ensured that the solution is not only the extreme point of the objective function, but also satisfies all given constraints. This is especially important for complex engineering and management problems that require finding the optimal solution under multiple constraints, ensuring the feasibility and effectiveness of the solution. In addition, it makes the solution of the problem more direct and efficient because it is directly related to the case where the gradient is equal to zero, which is convenient for solving using numerical methods. Determining the Lagrange multiplier by this method helps to more accurately determine the target section, avoid driving into congested sections without increasing mileage, and make the intelligent connected vehicle more efficient throughout the navigation process.

[0111] S503: Update the original navigation route based on the target segment.

[0112] Specifically, we first construct a traffic cost function, which reflects the vehicle density and flow rate as the degree of congestion. High density and low flow rate will increase the cost, while the pheromone concentration indicates the smoothness of the road section. The higher the concentration, the smoother the road section. On this basis, we select the best target road section by minimizing the traffic cost and combining constraints (such as vehicle speed greater than the preset value, short waiting time, and limited mileage). We ensure that the route with the lowest cost is selected while meeting the traffic efficiency and smoothness, and optimize the overall travel experience.

[0113] S6: Control the second vehicle to travel according to the updated original navigation route until it leaves the target road section.

[0114] It should be noted that the system guides the second car to travel according to the optimized and updated navigation route. The vehicle will travel along the optimized target section until it exits the section, thereby achieving path optimization under real-time traffic conditions and ensuring driving efficiency and safety.

[0115] S7: Based on the traffic status information about the target road section acquired by the second car, the dynamic pheromone concentration is updated, the current node of the second car is updated, and the process returns to step S4 until the second car reaches the target node.

[0116] It should be noted that the dynamic pheromone concentration of the road section is updated based on the real-time traffic status information fed back by the second car, and the current node of the vehicle is updated synchronously. Then, the process returns to step S4, and the path is optimized and adjusted again, and this process is repeated until the vehicle reaches the predetermined target node. This step ensures that the path planning is always based on the latest road condition information, improving driving efficiency and accuracy.

[0117] In a possible implementation manner, after S7, the method further includes:

[0118] The dynamic pheromone concentration in the roadside data broadcast module is reset at preset intervals.

[0119] It should be noted that those skilled in the art can set the preset duration according to actual needs, and the present invention does not limit it here. It is understandable that regularly resetting the dynamic pheromone concentration in the roadside data broadcast module can ensure the freshness and accuracy of the information, avoid interference from old information, improve the response speed and efficiency of the traffic management system, and promote diversified information dissemination.

[0120] In actual application, the traffic status is acquired in real time through the data acquisition modules on the vehicle side and the road side, and the concentration of congestion pheromones on the road section is dynamically calculated in combination with the heat diffusion process, and stored in the roadside broadcast module for dissemination. Based on data such as vehicle density, traffic flow and pheromone concentration, the system plans the optimal driving path for the vehicle under multiple constraints. The vehicle drives according to the real-time updated path and feedback road condition information, and replans the path when necessary to ensure the efficiency and safety of driving, thereby realizing the dynamic optimization and coordinated control of intelligent connected vehicles in complex road conditions. While improving the smoothness of the road, it also improves the operating efficiency of intelligent connected vehicles.

[0121] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0122] In the present invention, in the process of controlling the intelligent networked vehicle, the data collection module based on the vehicle end and the road section collects the traffic status data shared by the historical vehicle, i.e., the first vehicle, in real time, and then combines the thermal diffusion process to determine the dynamic pheromone concentration that is inversely proportional to the congestion degree of the candidate road section, simulates the diffusion characteristics of congestion, and makes the pheromone concentration change with the congestion degree, so as to achieve more accurate congestion warning. By dynamically adjusting the pheromone concentration, the intelligent networked vehicle can obtain the congestion conditions of different road sections in time, flexibly avoid congestion, and improve traffic fluency and driving efficiency. Then, it is stored in the roadside data broadcast module to broadcast to other vehicles, i.e., the second vehicle that may travel to the road section. This vehicle-road collaborative control scheme is highly sensitive to road conditions and has high fault tolerance, and can effectively divert traffic flow and avoid road congestion. During the control process of intelligent connected vehicles, the dynamic pheromone concentration is also combined to select a suitable target section from various alternative sections, where the average vehicle speed is greater than the preset average vehicle speed, the total waiting time is the shortest, and the mileage of the updated original navigation route is less than the preset mileage, and recommend it to the second car. It has the full-trip navigation capability of route warning recommendation, and can be combined with existing navigation software to achieve the rapid trip processing capability of intelligent network vehicles without increasing the mileage, greatly improving the operating efficiency of connected vehicles.

[0123] Reference Manual Attached Figure 3 , showing a structural schematic diagram of an intelligent connected vehicle control system based on vehicle-road collaboration provided by the present invention.

[0124] The present invention further provides an intelligent networked vehicle control system 20 based on vehicle-road collaboration, which is applied to the above-mentioned intelligent networked vehicle control method based on vehicle-road collaboration, comprising:

[0125] Processor 201.

[0126] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the intelligent connected vehicle control method based on vehicle-road collaboration as in the method embodiment is implemented.

[0127] The intelligent connected vehicle control system 20 based on vehicle-road collaboration provided by the present invention can execute the above-mentioned intelligent connected vehicle control method based on vehicle-road collaboration and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0128] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0129] In the present invention, in the process of controlling the intelligent networked vehicle, the data collection module based on the vehicle end and the road section collects the traffic status data shared by the historical vehicle, i.e., the first vehicle, in real time, and then combines the thermal diffusion process to determine the dynamic pheromone concentration that is inversely proportional to the congestion degree of the candidate road section, simulates the diffusion characteristics of congestion, and makes the pheromone concentration change with the congestion degree, so as to achieve more accurate congestion warning. By dynamically adjusting the pheromone concentration, the intelligent networked vehicle can obtain the congestion conditions of different road sections in time, flexibly avoid congestion, and improve traffic fluency and driving efficiency. Then, it is stored in the roadside data broadcast module to broadcast to other vehicles, i.e., the second vehicle that may travel to the road section. This vehicle-road collaborative control scheme is highly sensitive to road conditions and has high fault tolerance, and can effectively divert traffic flow and avoid road congestion. During the control process of the intelligent networked vehicle, the dynamic pheromone concentration is also combined to select a suitable target section from various alternative sections, that is, the average vehicle speed is greater than the preset average vehicle speed, the total waiting time is the shortest, and the mileage of the updated original navigation route is less than the preset mileage, and recommended to the second vehicle. It has the full-trip navigation capability of route warning recommendation, and can be combined with the existing navigation software to realize the rapid trip processing capability of the intelligent networked vehicle without increasing the mileage, which greatly improves the operating efficiency of the networked vehicle.

[0130] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0131] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).

[0132] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0133] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0134] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0135] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0136] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0137] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0138] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0139] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0140] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0141] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc., various media that can store program codes.

[0142] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the program implements the intelligent connected vehicle control method based on vehicle-road collaboration as described in the method embodiment.

[0143] A computer-readable storage medium provided by the present invention can implement the steps and effects of the intelligent connected vehicle control method based on vehicle-road collaboration of the above-mentioned method embodiment. To avoid repetition, the present invention will not go into details.

[0144] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0145] In the present invention, in the process of controlling the intelligent networked vehicle, the data collection module based on the vehicle end and the road section collects the traffic status data shared by the historical vehicle, i.e., the first vehicle, in real time, and then combines the thermal diffusion process to determine the dynamic pheromone concentration that is inversely proportional to the congestion degree of the candidate road section, simulates the diffusion characteristics of congestion, and makes the pheromone concentration change with the congestion degree, so as to achieve more accurate congestion warning. By dynamically adjusting the pheromone concentration, the intelligent networked vehicle can obtain the congestion conditions of different road sections in time, flexibly avoid congestion, and improve traffic fluency and driving efficiency. Then, it is stored in the roadside data broadcast module to broadcast to other vehicles, i.e., the second vehicle that may travel to the road section. This vehicle-road collaborative control scheme is highly sensitive to road conditions and has high fault tolerance, and can effectively divert traffic flow and avoid road congestion. During the control process of the intelligent networked vehicle, the dynamic pheromone concentration is also combined to select a suitable target section from various alternative sections, that is, the average vehicle speed is greater than the preset average vehicle speed, the total waiting time is the shortest, and the mileage of the updated original navigation route is less than the preset mileage, and recommended to the second vehicle. It has the full-trip navigation capability of route warning recommendation, and can be combined with the existing navigation software to realize the rapid trip processing capability of the intelligent networked vehicle without increasing the mileage, which greatly improves the operating efficiency of the networked vehicle.

[0146] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0147] There are a few points to note:

[0148] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0149] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0150] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0151] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A control method for an intelligent connected vehicle based on vehicle-road collaboration, characterized in that: Applied to an intelligent networked vehicle control platform, the intelligent networked vehicle control platform includes a driving status acquisition module located at the vehicle end and a roadside data acquisition module and a roadside data broadcasting module located at the road end, the vehicle end and the road segment can perform data interaction; the method includes: S1: collecting traffic status data through the driving status collection module and the roadside data collection module, wherein the traffic status data includes the average speed and total waiting time of the first vehicle on the alternative road section and the vehicle density and traffic flow of the alternative road section; S2: Based on the traffic status data, a dynamic pheromone concentration inversely proportional to the congestion degree of the candidate road section is calculated in combination with a heat diffusion process, and the dynamic pheromone concentration is stored in the roadside data broadcast module; S3: broadcasting the dynamic pheromone concentration to a second vehicle whose interval distance from the starting point of the candidate road section is less than a preset interval distance through the roadside data broadcasting module; S4: Acquire the original navigation route of the second car from the current node to the target node; S5: Based on the vehicle density, the traffic flow and the dynamic pheromone concentration, a target road section is selected from each candidate road section under a constraint condition to update the original navigation route, wherein the constraint condition includes that the average vehicle speed is greater than a preset average vehicle speed, the total waiting time is the shortest, and the mileage of the updated original navigation route is less than a preset mileage; S6: Controlling the second vehicle to travel according to the updated original navigation route until leaving the target road section; S7: Based on the traffic status information about the target road section acquired by the second car, the dynamic pheromone concentration is updated, the current node of the second car is updated, and the process returns to step S4 until the second car reaches the target node.

2. The intelligent connected vehicle control method based on vehicle-road collaboration according to claim 1 is characterized in that: The S1 specifically includes: S101: collecting the average speed and total waiting time of the first vehicle on the candidate road section through the driving status collection module; S102: Collecting the vehicle density and traffic flow of the candidate road section through the roadside data collection module.

3. The intelligent connected vehicle control method based on vehicle-road collaboration according to claim 1 is characterized in that: The S2 specifically includes: S201: Calculate the instantaneous traffic density of the candidate road section based on the traffic flow: Among them, Q ij (t) represents the instantaneous flow density of the candidate road section ij, n ij (t) represents the traffic flow of the candidate road section at time t, i.e., the number of vehicles, L ij Indicates the total length of the alternative road segments; S202: Establishing a congestion diffusion function for the candidate road segment based on a heat diffusion process: D=W·V avg，ij Among them, ψ ij (t) represents the congestion diffusion function of the candidate road section ij associated with time t, Indicates partial derivative, D represents the average speed V of the alternative road section width W and the alternative road section ij avg，ij The related congestion diffusion coefficient, k represents the natural attenuation coefficient of the congestion state, x represents the position coordinates on the alternative road section, represents the congestion diffusion rate associated with the location coordinates of the alternative road segment; S203: Solving the steady-state solution of the congestion diffusion function reflecting the termination of congestion diffusion: in, represents the steady-state solution of the alternative road section ij, Indicates the maximum vehicle capacity of the alternative road section; S204: Determine the dynamic pheromone concentration in the steady state by combining the steady-state solution, the average vehicle speed and the total waiting time: Among them, T ij (t) represents the dynamic pheromone concentration of the candidate road section ij at time t, represents the reference pheromone concentration constant, f1(t) and f2(t) represent the average vehicle speed factor and the total waiting time attenuation factor at time t, respectively, V avg,ij (t) represents the average speed of the first vehicle at time t on the candidate road section ij, V desired represents the expected average vehicle speed, e represents the natural constant, δ represents the influence coefficient of the total waiting time, T wait Indicates the total waiting time of the first car; S205: Storing the dynamic pheromone concentration in the roadside data broadcasting module.

4. The intelligent connected vehicle control method based on vehicle-road collaboration according to claim 1, characterized in that: The S4 is specifically: The original navigation route of the second automobile from the current node to the target node is obtained through navigation software.

5. The intelligent connected vehicle control method based on vehicle-road collaboration according to claim 1 is characterized in that: The S5 specifically includes: S501: Constructing a travel cost function for the candidate road segment: Among them, F ij (t) represents the travel cost function value of the candidate road section ij at time t, ρ ij (t), Q ij (t), T ij (t) respectively represent the vehicle density, traffic flow and dynamic pheromone concentration of the candidate road section ij at time t; S502: Taking the minimum value of the traffic cost function as the goal, determine the target road section from the candidate road sections in combination with the constraint conditions: V avg,ij (t)≥V preset T avg,ij ≤T min D ij -D≤ε Among them, min means taking the minimum value, D ij represents the updated original navigation route, i.e., the mileage of the alternative route ij, D represents the mileage of the original navigation route, ε represents the mileage deviation threshold, V avg,ij represents the average speed of the candidate road section ij, V preset Indicates the preset average vehicle speed, T avg,ij represents the average waiting time of the alternative road section ij, T min represents the preset waiting time, λ1, λ2, and λ3 represent the Lagrange multipliers of different constraints respectively; S503: Update the original navigation route based on the target segment.

6. The intelligent connected vehicle control method based on vehicle-road collaboration according to claim 5 is characterized in that: Before S502, the method further includes: calculating the passing cost function value by combining a gradient strategy algorithm and a reinforcement learning algorithm.

7. The intelligent connected vehicle control method based on vehicle-road collaboration according to claim 6 is characterized in that: The combination of the gradient strategy algorithm and the reinforcement learning algorithm to establish the pass cost function specifically includes: S502A: Define the state, action and reward of the reinforcement learning algorithm: S t =[V avg,ij (t),ρ ij (t),Q ij (t),T ij (t)] A t =[w1,w2,w3] Among them, S t represents the state vector at time t including different states, w1, w2, w3 represent the vehicle density weight, traffic flow weight and dynamic pheromone concentration weight as actions, respectively, A t represents the action vector at time t including different actions, R t represents the reward function value at time t for the travel cost function value of different alternative road sections ij; S502B: Establish the travel cost function: S502C: Optimizing the policy parameters of the gradient policy algorithm with the goal of maximizing the reward function value: Among them, θ represents the policy parameter of the gradient strategy algorithm, T represents the total time, represents the gradient of the objective function J(θ) with respect to the policy parameter θ, For all S t and A t Take the average value, represents the θ that maximizes J(θ), θ* represents the optimal policy parameter, α represents the learning rate of the update step of the control policy parameter θ, π(A t |S t ; θ) represents the given state S t Next, select action A according to the policy parameter θ t The probability distribution of , log represents the logarithmic function, represents the gradient of the probability distribution after taking the logarithm, ← represents the assignment; S502D: Substituting the optimized strategy parameters into the gradient strategy algorithm to obtain an optimized gradient strategy algorithm; S502E: Input the current state vector into the optimization gradient strategy algorithm, and output the current vehicle density weight, the current traffic flow weight, and the current dynamic pheromone concentration weight; S502F: Substitute the current vehicle density weight, the current traffic flow weight and the current dynamic pheromone concentration weight into the traffic cost function to complete the establishment of the traffic cost function.

8. The intelligent connected vehicle control method based on vehicle-road collaboration according to claim 5 is characterized in that: Based on the KKT condition, each Lagrange multiplier is calculated as follows: in, It means partial derivative.

9. The intelligent connected vehicle control method based on vehicle-road collaboration according to claim 1, characterized in that: After S7, the method further includes: The dynamic pheromone concentration in the roadside data broadcast module is reset at intervals of a preset time.

10. An intelligent connected vehicle control system based on vehicle-road collaboration, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the intelligent connected vehicle control method based on vehicle-road collaboration as described in any one of claims 1 to 9 is implemented.

Images