Intelligent connected vehicle dynamic path planning method and device, terminal and medium

Abstract

The application provides a kind of intelligent network connection car dynamic path planning method, device, terminal and medium, the method includes: in the path planning of vehicle in current iteration based on ant algorithm, obtain current pheromone concentration, traffic operation information, traffic network information, vehicle starting position and vehicle target position;According to traffic network information and traffic operation information, determine the heuristic information of vehicle;According to current pheromone concentration, vehicle heuristic information and traffic operation information, determine the path selection probability of vehicle in current iteration;After generating the planning path of vehicle in current iteration and determining the optimal path of current iteration, obtain the latest pheromone concentration on path;Generate the planning path of vehicle in next iteration and determine the optimal path of next iteration, and obtain the optimal path of vehicle after vehicle path planning meets end iteration condition.Improves the real-time, accuracy and adaptability of intelligent network connection car path planning.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, specifically to a method, device, terminal, and medium for dynamic path planning of intelligent connected vehicles. Background Technology

[0002] With the rapid development of intelligent connected vehicle technology, information interaction between vehicles (V2V), vehicles and infrastructure (V2I), and vehicles and cloud platforms (V2N) has become increasingly frequent and efficient. This makes it possible to achieve more intelligent and efficient traffic management and route planning. Route planning, as one of the core technologies of intelligent connected vehicles, aims to find an optimal or suboptimal path from origin to destination for vehicles in complex and ever-changing traffic environments to meet the needs of fast, safe, and energy-efficient driving. Traditional route planning algorithms, such as Dijkstra's algorithm and A* algorithm, show good performance when dealing with static road networks, but they often cannot adjust route planning in a timely and effective manner when facing dynamically changing traffic environments, such as real-time traffic congestion and sudden events, resulting in poor timeliness and adaptability of the planned routes. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention proposes a dynamic path planning method, device, terminal, and medium for intelligent connected vehicles, aiming to improve the real-time performance, accuracy, and adaptability of path planning for intelligent connected vehicles.

[0004] In a first aspect, embodiments of this application provide a dynamic path planning method for intelligent connected vehicles, including:

[0005] In the current iteration of the ant colony algorithm, when planning the vehicle's path, the current pheromone concentration on the path updated in the previous iteration, the traffic operation information on the path updated in the previous iteration, the traffic network information, the vehicle's starting position, and the vehicle's target position are obtained.

[0006] The vehicle heuristic information is determined based on the traffic network information and traffic operation information;

[0007] Based on the current pheromone concentration, the vehicle heuristic information, and the traffic operation information, determine the path selection probability of the vehicle in the current iteration;

[0008] After generating the planned path for the vehicle in the current iteration and determining the optimal path for the current iteration based on the path selection probability, the vehicle's starting position, and the vehicle's target position, the current pheromone concentration is updated using the traffic operation information to obtain the latest pheromone concentration on the path.

[0009] Based on the latest pheromone concentration, the traffic network information, and the latest traffic operation information, the path selection probability of the vehicle in the next iteration is determined. Based on the path selection probability of the next iteration, the starting position of the vehicle, and the target position of the vehicle, the planned path of the vehicle in the next iteration is generated, and the optimal path of the next iteration is determined. The optimal path of the vehicle is obtained after the vehicle path planning meets the end iteration condition.

[0010] Optionally, the traffic operation information includes traffic flow and average vehicle speed; determining the path selection probability of vehicles in the current iteration based on the current pheromone concentration, the vehicle heuristic information, and the traffic operation information includes:

[0011] Based on the traffic flow and the average vehicle speed, real-time traffic information factors are obtained;

[0012] The path selection probability of the vehicle in the current iteration is determined based on the current pheromone concentration, the vehicle heuristic information, and the real-time traffic information factor.

[0013] Optionally, the path selection probability of a vehicle in the current iteration is determined based on the current pheromone concentration, the vehicle heuristic information, and the real-time traffic information factor, including:

[0014] ;

[0015] in, For at any time The k-th ant starts from node Transfer to node The probability of; For at any time ,node To the node The current pheromone concentration along the path; Heuristic information about the path from node i to node j at time t; At any moment ,node To the node Real-time traffic information factors of the route; Pheromones are the inductive factor; As a desired heuristic factor; For real-time traffic factor weights; For the k-th ant at node The set of next nodes that can be selected at that time.

[0016] Optionally, obtaining the real-time traffic information factor based on the traffic flow and the average vehicle speed includes:

[0017] ;

[0018] For at any time ,node To the node Real-time traffic information factors of the route; For at any time ,node To the node Traffic flow along the route; For at any time ,node To the node Average vehicle speed along the path.

[0019] Optionally, the traffic operation information includes: accident status and road congestion index; after generating the planned path of the vehicle in the current iteration and determining the optimal path for the current iteration based on the path selection probability, the vehicle's starting position, and the vehicle's target position, the current pheromone concentration is updated using the traffic operation information to obtain the latest pheromone concentration on the path, including:

[0020] Based on the path selection probability, the vehicle's starting position, and the vehicle's target position, the planned path for the vehicle in the current iteration is generated, and the ant path length is obtained.

[0021] Based on the ant path length and the road congestion index, an ant path score is obtained, and the path with the highest ant path score is taken as the optimal path for the current iteration.

[0022] Based on the ant path length and the incident status, the pheromone increment is obtained;

[0023] The latest pheromone concentration on the path is obtained based on the pheromone increment and the current pheromone concentration.

[0024] Optionally, obtaining the pheromone increment based on the ant path length and the incident state includes:

[0025] ;

[0026] for For nodes To the node The pheromone increment along the path; The pheromone intensity index; Ant Path length; For nodes To the node Accident status of the path;

[0027] Optionally, obtaining the latest pheromone concentration on the path based on the pheromone increment and the current pheromone concentration includes:

[0028] ;

[0029] The latest pheromone concentration along the path; The pheromone evaporation coefficient; The current pheromone concentration; for For nodes To the node The pheromone increment along the path; This represents the number of ants.

[0030] Optionally, obtaining the ant path score based on the ant path length and the road congestion index includes:

[0031] ;

[0032] in, Scoring ant paths; This represents the length of the ant's path. Indicates the first The total congestion index of all road segments in the route; This refers to the path scoring weighting coefficient.

[0033] Optionally, the traffic network information includes road segment length, and the traffic operation information includes a road congestion index; determining the vehicle heuristic information based on the traffic network information and the traffic operation information includes:

[0034] ;

[0035] in, This provides heuristic information about the path from node i to node j at time t; Let be the length of the path segment from node i to node j; Let be the road congestion index for the path from node i to node j.

[0036] Optionally, the path planning for the vehicle in the current iteration based on the ant colony algorithm previously included:

[0037] Obtain the number of ants, pheromone evaporation coefficient, initial pheromone value, pheromone intensity index, convergence threshold, and maximum number of iterations.

[0038] Optionally, the termination iteration condition is any one of the following: maximum iteration count condition, iteration path stability condition, or pheromone distribution stability condition.

[0039] The maximum iteration count condition includes: if the vehicle path planning iteration count reaches the maximum iteration count, then the maximum iteration count condition is satisfied.

[0040] The stable conditions for pheromone distribution include:

[0041] ;

[0042] in, The total number of road segments. This is the convergence threshold;

[0043] The iterative path is stable, including:

[0044] If the optimal path is the same in each iteration after a predetermined number of stable iterations, then the iterative path stability condition is satisfied.

[0045] Secondly, embodiments of this application provide a dynamic path planning device for intelligent connected vehicles, comprising:

[0046] The parameter acquisition module is used to acquire the current pheromone concentration, traffic operation information, traffic network information, vehicle starting position, and vehicle target position on the path updated in the previous iteration of the ant algorithm during the current iteration of vehicle path planning.

[0047] The information determination module is used to determine the vehicle heuristic information based on the traffic network information and traffic operation information;

[0048] The probability determination module is used to determine the path selection probability of a vehicle in the current iteration based on the current pheromone concentration, the vehicle heuristic information, and the traffic operation information.

[0049] The pheromone update module is used to update the current pheromone concentration through the traffic operation information after generating the planned path of the vehicle in the current iteration and determining the optimal path of the current iteration based on the path selection probability, the vehicle starting position and the vehicle target position, so as to obtain the latest pheromone concentration on the path.

[0050] The optimal path determination module is used to determine the path selection probability of the vehicle in the next iteration based on the latest pheromone concentration, the traffic network information, and the latest traffic operation information; generate the planned path of the vehicle in the next iteration based on the path selection probability of the next iteration, the starting position of the vehicle, and the target position of the vehicle; determine the optimal path of the next iteration; and obtain the optimal path of the vehicle after the vehicle path planning meets the end iteration condition.

[0051] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the intelligent connected vehicle dynamic path planning method as described in any one of the first aspects above.

[0052] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the intelligent connected vehicle dynamic path planning method as described in any one of the first aspects above.

[0053] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute the intelligent connected vehicle dynamic path planning method described in any one of the first aspects.

[0054] In this embodiment, during the current iteration of vehicle path planning based on the ant colony algorithm, the following are obtained: the current pheromone concentration on the path updated in the previous iteration, traffic operation information, traffic network information, vehicle starting position, and vehicle target position. The vehicle heuristic information is determined based on the traffic network information and traffic operation information. The path selection probability of the vehicle in the current iteration is determined based on the current pheromone concentration, the vehicle heuristic information, and the traffic operation information. After generating the planned path for the vehicle in the current iteration and determining the optimal path for the current iteration based on the path selection probability, the vehicle starting position, and the vehicle target position, the current pheromone concentration is updated using the traffic operation information to obtain the latest pheromone concentration on the path. Based on the latest pheromone concentration, the traffic network information, and the latest traffic operation information, the path selection probability of the vehicle in the next iteration is determined. The planned path for the vehicle in the next iteration and the optimal path for the next iteration are generated based on the path selection probability of the next iteration, the vehicle starting position, and the vehicle target position. The optimal path for the vehicle is obtained after the vehicle path planning meets the iteration termination condition. It improves the real-time performance, accuracy, and adaptability of route planning for intelligent connected vehicles.

[0055] This application integrates dynamic traffic information into the path planning algorithm through real-time collection and processing of traffic information. This enables rapid response to changes in the traffic environment and timely planning of optimal routes for vehicles, meeting the real-time path planning requirements of intelligent connected vehicles. The improved ant colony algorithm, by introducing real-time traffic information factors and comprehensively considering pheromone concentration, heuristic information, and real-time traffic operation information along the path, can more accurately evaluate the merits of paths, avoid getting trapped in local optima, and improve the accuracy and reliability of path planning. By providing vehicles with reasonable path guidance, it guides them to avoid congested sections, balances traffic flow, and effectively alleviates traffic congestion, thereby improving the overall operational efficiency of the transportation system. It can provide intelligent connected vehicle users with efficient and accurate path planning services, reducing vehicle travel time and fuel consumption, and enhancing the user's travel experience. Attached Figure Description

[0056] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0057] Figure 1 This is a flowchart illustrating a dynamic path planning method for intelligent connected vehicles provided in an embodiment of this application.

[0058] Figure 2 This is a flowchart illustrating the second embodiment of the dynamic path planning method for intelligent connected vehicles provided in this application;

[0059] Figure 3 This is an iterative schematic diagram of the dynamic path planning method for intelligent connected vehicles provided in this application;

[0060] Figure 4 This is a schematic diagram of the urban road network for the intelligent connected vehicle dynamic path planning method provided in this application;

[0061] Figure 5 This is a schematic diagram of the optimal path for the dynamic path planning method for intelligent connected vehicles provided in this application;

[0062] Figure 6 This is a schematic diagram of the structure of the intelligent connected vehicle dynamic path planning device provided in the embodiments of this application;

[0063] Figure 7 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. Detailed Implementation

[0064] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0065] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0066] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0067] The execution entity of the intelligent connected vehicle dynamic path planning method provided in this application embodiment can be an intelligent connected vehicle dynamic path planning device. When planning the vehicle's path in the current iteration based on the ant colony algorithm, the intelligent connected vehicle dynamic path planning device can obtain the current pheromone concentration on the path updated in the previous iteration, traffic operation information on the path updated in the previous iteration, traffic network information, the vehicle's starting position, and the vehicle's target position; determine the vehicle's heuristic information based on the traffic network information and traffic operation information; determine the path selection probability of the vehicle in the current iteration based on the current pheromone concentration, the vehicle's heuristic information, and the traffic operation information; and further determine the path selection probability of the vehicle in the current iteration based on the ant colony algorithm. After generating the planned path for the vehicle in the current iteration and determining the optimal path for the current iteration based on the path selection probability, the vehicle's starting position, and the vehicle's target position, the current pheromone concentration is updated using the traffic operation information to obtain the latest pheromone concentration on the path. Based on the latest pheromone concentration, the traffic network information, and the latest traffic operation information, the path selection probability for the vehicle in the next iteration is determined. Based on the path selection probability for the next iteration, the vehicle's starting position, and the vehicle's target position, the planned path for the vehicle in the next iteration is generated, and the optimal path for the next iteration is determined. The optimal path for the vehicle is obtained after the vehicle path planning meets the iteration termination condition.

[0068] Figure 1 This illustration shows a schematic flowchart of dynamic path planning for intelligent connected vehicles according to an embodiment of this application. It is provided as an example and not as a limitation; the method can be applied to the aforementioned dynamic path planning device for intelligent connected vehicles. Figure 1 As shown, the method may include:

[0069] S10, In the current iteration of the ant colony algorithm, when planning the vehicle's path, the intelligent connected vehicle dynamic path planning device obtains the current pheromone concentration on the path updated in the previous iteration, the traffic operation information on the path updated in the previous iteration, the traffic network information, the vehicle's starting position, and the vehicle's target position.

[0070] To improve the intelligent network's path planning for vehicles in the current iteration based on the ant colony algorithm, it is necessary to obtain the current pheromone concentration on the path updated in the previous iteration, traffic operation information on the path updated in the previous iteration, traffic network information, vehicle starting position, and vehicle target position.

[0071] Wherein, the current pheromone concentration is the pheromone concentration during the iteration; the initial pheromone value... Traffic network information is a grid formed by several nodes in a traffic network. This information includes the segment lengths of paths between two adjacent nodes. To simplify the representation of the network, intersections of roads can be abstracted as nodes, and a node-arc model can be used to describe the network. Let G(V, E) be a directed connected graph of a directed connected network system, where V = {V1, V2, ..., V...} n Let} be the set of nodes of G, and E = {e} ij | e ij To connect V i With V j The directed arc segment (road segment), V i Starting from V j The set of arc segments (road segments) with endpoint G. The vehicle's starting position is its current coordinates, which is its position within the traffic network. The vehicle's target position is its desired location coordinates, which is the location of its destination within the traffic network.

[0072] Traffic operation information includes road congestion index, accident status, traffic flow, and average vehicle speed between two adjacent nodes in the traffic network. Intelligent connected vehicle dynamic path planning devices can collect real-time traffic information around the vehicle, including traffic flow Q and average vehicle speed, through onboard sensors, roadside radar, high-definition cameras, and V2V, V2I, and V2N communication modules. Road congestion Accident status ( Indicates an accident. (Indicates normal), and preprocesses the collected information, such as data cleaning, filtering, and fusion, to improve the accuracy and reliability of the data.

[0073] The dynamic path planning device for intelligent connected vehicles may include a data acquisition and processing module, an ant colony algorithm optimization module, a path planning module, and a user interaction module.

[0074] The data acquisition and processing module is used to support data input from sensors, GPS, and traffic monitoring systems via hardware interfaces; it also filters invalid data and standardizes the format.

[0075] The ant colony algorithm optimization module is used to support the dynamic adjustment of parameters such as parameter configuration unit; it implements parallel ant search based on multithreading to improve computational efficiency; and it executes global and local pheromone update strategies.

[0076] The route planning module is used to generate visualized routes based on the route data output by the ant colony algorithm and combined with GIS maps; it triggers route replanning and calculates detour schemes by detecting traffic data in real time.

[0077] The user interaction module is used to receive the user's starting point, destination, and preference settings (such as avoiding congestion and shortest distance) through the input interface; the output interface displays the dynamic route through the APP / vehicle terminal, and supports voice navigation and real-time traffic prompts.

[0078] As one implementation, the path planning of the vehicle in the current iteration based on the ant colony algorithm includes, prior to: obtaining the number of ants, the pheromone evaporation coefficient, the initial value of the pheromone, the pheromone intensity index, the convergence threshold, and the maximum number of iterations.

[0079] In other words, before calculating the optimal path for the vehicle using the ant colony algorithm, the dynamic path planning device for intelligent connected vehicles needs to set the number of ants. Maximum number of iterations pheromone volatility coefficient Pheromones as heuristic factors Expected heuristic factors Parameters such as the number of ants. Based on the size of the transportation network (usually) ); initial pheromone value pheromone volatility coefficient , The larger the value, the faster the pheromone evaporates, the weaker the influence of historical paths, and the more the algorithm tends to explore new paths. The smaller the value, the more pheromones are retained, and the more the algorithm relies on historically optimal paths. (Pheromone heuristic factor) This reflects the degree to which pheromone concentration influences path selection. Expected heuristic factor. It reflects the degree to which heuristic information influences path selection.

[0080] S20, determine the vehicle heuristic information based on the traffic network information and traffic operation information;

[0081] After acquiring the current pheromone concentration on the path updated in the previous iteration, traffic operation information on the path updated in the previous iteration, traffic network information, vehicle starting position, and the current pheromone concentration on the path updated in the previous iteration, traffic operation information on the path updated in the previous iteration, and traffic network information, the intelligent connected vehicle dynamic path planning device determines the vehicle heuristic information based on the traffic network information and traffic operation information.

[0082] As one implementation method, the traffic network information is a grid formed by several nodes of the traffic network. The traffic network information includes the segment length of the path between two adjacent nodes in the traffic network, and the traffic operation information includes the road congestion index between two adjacent nodes in the traffic network. Determining the vehicle heuristic information based on the traffic network information and the traffic operation information includes:

[0083] ;

[0084] in, This provides heuristic information about the path from node i to node j at time t; Let be the length of the path segment from node i to node j; Let be the road congestion index for the path from node i to node j.

[0085] S30, determine the path selection probability of the vehicle in the current iteration based on the current pheromone concentration, the vehicle heuristic information, and the traffic operation information;

[0086] After acquiring the current pheromone concentration and traffic operation information, as well as the vehicle heuristic information, the intelligent connected vehicle dynamic path planning device determines the path selection probability of the vehicle in the current iteration based on the current pheromone concentration, the vehicle heuristic information, and the traffic operation information.

[0087] The traffic operation information includes traffic flow and average vehicle speed; determining the path selection probability of vehicles in the current iteration based on the current pheromone concentration, the vehicle heuristic information, and the traffic operation information specifically includes:

[0088] A1. Based on the traffic flow and the average vehicle speed, obtain the real-time traffic information factor;

[0089] After acquiring traffic flow and average vehicle speed, the intelligent connected vehicle dynamic path planning device obtains real-time traffic information factors based on the traffic flow and average vehicle speed.

[0090] As one implementation method, obtaining real-time traffic information factors based on the traffic flow and the average vehicle speed includes:

[0091] ;

[0092] For at any time ,node To the node Real-time traffic information factors of the route; For at any time ,node To the node Traffic flow along the route; For at any time ,node To the node Average vehicle speed along the path.

[0093] A2, based on the current pheromone concentration, the vehicle heuristic information, and the real-time traffic information factor, determine the path selection probability of the vehicle in the current iteration;

[0094] After acquiring the current pheromone concentration, vehicle heuristic information, and real-time traffic information factors, the intelligent connected vehicle dynamic path planning device determines the path selection probability of the vehicle in the current iteration based on the current pheromone concentration, the vehicle heuristic information, and the real-time traffic information factors.

[0095] As one implementation method, determining the path selection probability of a vehicle in the current iteration based on the current pheromone concentration, the vehicle heuristic information, and the real-time traffic information factor includes:

[0096] ;

[0097] in, For at any time The k-th ant starts from node Transfer to node The probability of; For at any time ,node To the node The current pheromone concentration along the path; Heuristic information about the path from node i to node j at time t; At any moment ,node To the node Real-time traffic information factors of the route; Pheromones are the inductive factor; As a desired heuristic factor; This refers to the weights of real-time traffic factors (i.e., the weights of real-time traffic information factors). For the k-th ant at node The set of next nodes that can be selected at that time.

[0098] S40, after generating the planned path of the vehicle in the current iteration and determining the optimal path of the current iteration based on the path selection probability, the vehicle starting position and the vehicle target position, the current pheromone concentration is updated by the traffic operation information to obtain the latest pheromone concentration on the path.

[0099] After acquiring the vehicle's starting position and target position, and obtaining the path selection probability, the intelligent connected vehicle dynamic path planning device generates the planned path for the vehicle in the current iteration and determines the optimal path for the current iteration based on the path selection probability, the vehicle's starting position, and the vehicle's target position. Then, it updates the current pheromone concentration through the traffic operation information to obtain the latest pheromone concentration on the path.

[0100] Furthermore, referring to Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the intelligent connected vehicle dynamic path planning method of the present invention. Based on the above... Figure 2 In the illustrated embodiment, the traffic operation information includes: accident status and road congestion index between two adjacent nodes in the traffic network; after generating the planned path of the vehicle in the current iteration and determining the optimal path for the current iteration based on the path selection probability, the vehicle's starting position, and the vehicle's target position, the current pheromone concentration is updated using the traffic operation information to obtain the latest pheromone concentration on the path, specifically including:

[0101] S41, Based on the path selection probability, the vehicle's starting position, and the vehicle's target position, generate the planned path for the vehicle in the current iteration, and obtain the ant path length;

[0102] After obtaining the vehicle's starting position and target position, as well as the path selection probability, the intelligent connected vehicle dynamic path planning device generates the planned path of the vehicle in the current iteration based on the path selection probability, the vehicle's starting position, and the vehicle's target position, and obtains the ant path length.

[0103] S42, Based on the ant path length and the road congestion index, obtain the ant path score, and take the path with the highest ant path score as the optimal path for the current iteration;

[0104] After obtaining the road congestion index and the length of the ant paths, the intelligent connected vehicle dynamic path planning device calculates an ant path score based on the ant path length and the road congestion index, and selects the path with the highest ant path score as the optimal path for the current iteration. In other words, the intelligent connected vehicle dynamic path planning device selects the path with the highest comprehensive score from the iteratively optimized path set as the optimal solution.

[0105] As one implementation method, obtaining the ant path score based on the ant path length and the road congestion index includes:

[0106] ;

[0107] in, Scoring ant paths, that is, ant paths Path scoring; This is the length of the ant's path, which is also the length of the ant's path. Path length; Indicates the first The total congestion index of all road segments in the route; This refers to the path scoring weighting coefficient.

[0108] S43, Based on the ant path length and the incident status, obtain the pheromone increment;

[0109] After acquiring the accident status and obtaining the ant path length, the intelligent connected vehicle dynamic path planning device obtains the pheromone increment based on the ant path length and the accident status.

[0110] As one implementation method, obtaining the pheromone increment based on the ant path length and the incident state includes:

[0111] ;

[0112] for For nodes To the node The pheromone increment along the path, that is... For ants For path ( The pheromone increment; The pheromone intensity index, where It can be 100 or 90; Ant Path length; For nodes To the node The accident status of the path, that is, For the edge ( The accident status (when an accident exists) =1, otherwise 0), and when When =1, the pheromone level of this road segment is forcibly set to the minimum value. This avoids the ants making subsequent choices.

[0113] S44, Based on the pheromone increment and the current pheromone concentration, obtain the latest pheromone concentration on the path;

[0114] After acquiring the current pheromone concentration, as well as vehicle heuristic information and real-time traffic information factors, the intelligent connected vehicle dynamic path planning device obtains the latest pheromone concentration on the path based on the pheromone increment, the current pheromone concentration, and the pheromone evaporation coefficient.

[0115] As one implementation, obtaining the latest pheromone concentration on the path based on the pheromone increment and the current pheromone concentration includes:

[0116] ;

[0117] The latest pheromone concentration along the path; The pheromone evaporation coefficient; The current pheromone concentration; for For nodes To the node The pheromone increment along the path; This represents the number of ants.

[0118] S50, based on the latest pheromone concentration, the traffic network information, and the latest traffic operation information, determine the path selection probability of the vehicle in the next iteration, generate the planned path of the vehicle in the next iteration based on the path selection probability of the next iteration, the starting position of the vehicle, and the target position of the vehicle, and determine the optimal path of the next iteration, and obtain the optimal path of the vehicle after the vehicle path planning meets the end iteration condition.

[0119] After acquiring traffic network information, the latest traffic operation information, and the latest pheromone concentration, the intelligent connected vehicle dynamic path planning device determines the path selection probability of the vehicle in the next iteration based on the latest pheromone concentration, traffic network information, and the latest traffic operation information. Based on the path selection probability of the next iteration, the vehicle's starting position, and the vehicle's target position, it generates the planned path of the vehicle in the next iteration and determines the optimal path for the next iteration. The optimal path of the vehicle is obtained after the vehicle path planning meets the end-of-iteration condition.

[0120] As one implementation method, the latest traffic operation information includes: the latest road congestion index, the latest traffic flow, and the latest average vehicle speed; based on the latest pheromone concentration, the traffic network information, and the latest traffic operation information, the path selection probability of vehicles in the next iteration is determined, including:

[0121] B1. Determine the latest vehicle heuristic information based on the traffic network information and the latest road congestion index;

[0122] After acquiring the latest road congestion index and traffic network information, the intelligent connected vehicle dynamic path planning device determines the vehicle heuristic information based on the traffic network information and the latest road congestion index.

[0123] The traffic network information includes the segment length of the path between two adjacent nodes in the traffic network, and the latest traffic operation information includes the latest road congestion index between two adjacent nodes in the traffic network; the determination of the latest vehicle heuristic information based on the traffic network information and the latest road congestion index includes:

[0124] ;

[0125] in, This provides heuristic information about the path from node i to node j at time t; Let be the length of the path segment from node i to node j; Let be the road congestion index for the path from node i to node j.

[0126] B2, based on the latest traffic flow and the latest average vehicle speed, obtains the latest real-time traffic information factors;

[0127] After acquiring the latest traffic flow and the latest average vehicle speed, the intelligent connected vehicle dynamic path planning device obtains the latest real-time traffic information factors based on the latest traffic flow and the latest average vehicle speed.

[0128] The step of obtaining the latest real-time traffic information factors based on the latest traffic flow and the latest average vehicle speed includes:

[0129] ;

[0130] For at any time ,node To the node Real-time traffic information factors of the route; For at any time ,node To the node Traffic flow along the route; For at any time ,node To the node Average vehicle speed along the path.

[0131] B3. Based on the latest pheromone concentration, the latest vehicle heuristic information, and the latest real-time traffic information factors, determine the path selection probability of the vehicle in the next iteration.

[0132] After obtaining the latest pheromone concentration, the latest vehicle heuristic information, and the latest real-time traffic information factors, the intelligent connected vehicle dynamic path planning device determines the path selection probability of the vehicle in the next iteration based on the latest pheromone concentration, the latest vehicle heuristic information, and the latest real-time traffic information factors.

[0133] Specifically, the path selection probability of vehicles in the next iteration is determined based on the latest pheromone concentration, the latest vehicle heuristic information, and the latest real-time traffic information factors, including:

[0134] ;

[0135] in, For at any time The k-th ant starts from node Transfer to node The probability of; For at any time ,node To the node The current pheromone concentration along the path; Heuristic information about the path from node i to node j at time t; At any moment ,node To the node Real-time traffic information factors of the route; Pheromones are the inductive factor; As a desired heuristic factor; This refers to the weights of real-time traffic factors (i.e., the weights of real-time traffic information factors). For the k-th ant at node The set of next nodes that can be selected at that time.

[0136] As one implementation method, the latest traffic operation information includes: the road congestion index between two adjacent nodes in the traffic network; generating the planned path for the vehicle in the next iteration based on the path selection probability of the next iteration, the vehicle's starting position, and the vehicle's destination position, and determining the optimal path for the next iteration, specifically including:

[0137] C1, based on the path selection probability of the next iteration, the starting position of the vehicle and the target position of the vehicle, generate the planned path of the vehicle in the current iteration, and obtain the ant path length of the next iteration;

[0138] After obtaining the vehicle's starting position and target position, as well as the path selection probability for the next iteration, the intelligent connected vehicle dynamic path planning device generates the planned path for the vehicle in the current iteration based on the path selection probability for the next iteration, the vehicle's starting position, and the vehicle's target position, and obtains the ant path length for the next iteration.

[0139] C2, based on the ant path length of the next iteration and the latest road congestion index, obtain the ant path score for the next iteration, and take the path with the highest ant path score for the next iteration as the optimal path for the next iteration.

[0140] After obtaining the latest road congestion index and the ant path length for the next iteration, the intelligent connected vehicle dynamic path planning device calculates the ant path score for the next iteration based on the ant path length and the latest road congestion index. The path with the highest ant path score for the next iteration is then selected as the optimal path for that iteration. In other words, the intelligent connected vehicle dynamic path planning device selects the path with the highest overall score from the iteratively optimized path set as the optimal solution.

[0141] The step of obtaining the ant path score for the next iteration based on the ant path length of the next iteration and the latest road congestion index includes:

[0142] ;

[0143] in, Scoring ant paths, that is, ant paths Path scoring; This is the length of the ant's path, which is also the length of the ant's path. Path length; Indicates the first The total congestion index of all road segments in the route; This refers to the path scoring weighting coefficient.

[0144] In one implementation, the termination iteration condition is any one of the following: maximum iteration count condition, iteration path stability condition, or pheromone distribution stability condition.

[0145] The maximum iteration count condition includes: if the vehicle path planning iteration count reaches the maximum iteration count, then the maximum iteration count condition is satisfied.

[0146] The stable conditions for pheromone distribution include:

[0147] ;

[0148] in, The total number of road segments. This is the convergence threshold;

[0149] The stability of the iterative path includes the following: if the optimal path is the same in each iteration of a predetermined number of consecutive stable iterations, then the iterative path stability condition is met.

[0150] That is to say, such as Figure 3 As shown, when the maximum number of iterations is reached... (generally =100) or path convergence, yielding the optimal path for the vehicle. Where, when the maximum number of iterations is reached... (generally When the value is 100, the optimal path obtained in the last iteration is taken as the optimal path for the vehicle.

[0151] The path convergence condition satisfies any one of the following:

[0152] Path stability: If the optimal output path is completely consistent in N consecutive iterations (N=10), it is determined to be converged;

[0153] When the path convergence condition satisfies the path stability, the optimal path output in N consecutive iterations (N=10) is completely consistent, and the completely consistent optimal path obtained in N consecutive iterations is taken as the optimal path of the vehicle.

[0154] Pheromone distribution stability: Calculate the average relative rate of change of pheromone concentration across the entire road network. Convergence is determined if the following conditions are met:

[0155] ;

[0156] in The total number of road segments. This is the convergence threshold.

[0157] When the path convergence condition satisfies the pheromone distribution stability condition, the optimal path obtained in the last iteration when the path convergence condition satisfies the pheromone distribution stability condition is taken as the optimal path for the vehicle.

[0158] For example, when the dynamic path planning device of an intelligent connected vehicle needs to perform a rescue mission in a 4x4 urban grid, such as Figure 4As shown, this is a simplified map of a city's road network. An ambulance (our intelligent connected vehicle) needs to urgently travel from point A1 (the starting point, i.e., the vehicle's originating location) in the upper left corner to point D4 (the destination, i.e., the vehicle's target location) in the lower right corner. The intelligent connected vehicle's dynamic path planning method finds the shortest route with the best overall road conditions for this ambulance.

[0159] Step 1, that is, executing step S10, such as Figure 4 As shown, in a 4x4 grid, the intelligent connected vehicle dynamic path planning device first obtains real-time information of each road segment (such as A1 to A2, A1 to B1) through various sensors.

[0160] Section (B2)-(C2): Located in the city center, with high traffic volume Q and low average vehicle speed V, the congestion index C is very high.

[0161] Section (A3)-(A4): Located on the edge of the city, with low traffic volume (Q), high vehicle speed (V), and very low congestion index (C).

[0162] Road network construction: We abstract the 16 intersections (A1 to D4) as nodes (V) and the 24 bidirectional road segments connecting them as edges (E). The physical map of the traffic road network is then transformed into a G(V, E) data structure that the algorithm can understand.

[0163] Step 2: Before starting the search, set the parameters. Set the number of ants m: 50 virtual ants will be deployed. Set the maximum number of iterations Tmax: the ants will explore for a total of 100 rounds. Set the pheromone evaporation coefficient ρ: set to 0.3, meaning that 30% of the pheromones on the path will evaporate after each round. Set the initial pheromone τ; before the first round begins, the pheromone concentration on all 24 road segments is set to the same initial value, for example... This means that, without any prior knowledge, every path is equally attractive to the ant.

[0164] Step 3, as follows Figure 4 As shown, during path search and selection, which involves executing steps S20, S20, and S40 (path planning), 50 ants simultaneously start from point A1. The decision-making process for tracking one of the ants, "Ant A," is as follows:

[0165] Ant A starts at point A1:

[0166] It has two choices: go right to A2, or go down to B1.

[0167] How does Ant A choose? Ant A calculates the probability of going to A2 and B1 using a probability formula. In the first round, since all road segments have the same pheromone τ, the decision is mainly influenced by heuristic information η (distance and congestion) and real-time traffic information φ.

[0168] Assuming both A1-A2 and A1-B1 have excellent road conditions (very low congestion index C), then both... The values ​​of φ and φ are both high and similar. Therefore, the probability that ant A chooses A2 and B1 is almost 50 / 50. We assume that it randomly chose to go down and reached B1.

[0169] Ant A is at node B2:

[0170] Suppose ant A's path is A1 -> B1 -> B2. It is now at B2 and faces a choice: go up to A2, go right to B3, or go down to C2. (It has a memory list and will not backtrack to B1).

[0171] We previously defined B2 to C2 as a congested section of the city center.

[0172] For path B2 -> C2: Because the congestion index C is very high, according to the formula... Its heuristic information The value will be very low. At the same time, the real-time traffic factor φ will also be very low.

[0173] For the path B2 -> B3: the road conditions are normal, the C value is low, therefore the η and φ values ​​are relatively high.

[0174] Why did ant A choose this path? Although B2-C2 is closer to the destination D4 in terms of direction, the congestion penalty mechanism in the algorithm greatly reduces the probability of choosing it. Therefore, ant A has a very high probability of choosing to go to B3, thus actively avoiding congestion.

[0175] Completed Path: Ant A continues making decisions in a similar manner, potentially eventually forging a path such as A1 -> B1 -> B2 -> B3 -> C3 -> D3 -> D4. The intelligent connected vehicle's dynamic path planning device records the total length L of this path. Meanwhile, the other 49 ants are exploring their own paths; some may take longer routes, while others may unfortunately enter congested areas.

[0176] Step 4, the pheromone update step (that is, at the end of the first iteration), is the step of executing step S40 to obtain the latest pheromone concentration.

[0177] Once all 50 ants have reached the destination D4, the intelligent connected vehicle dynamic path planning device begins to reward those who have made contributions.

[0178] Ant A's contribution: The path it took, A1 -> B1 -> ... -> D4, was 6 units long (L_A = 6) and did not pass through the accident section (S=0). According to the formula... It will increase the amount of pheromones by 100 / 6 ≈ 16.7 on each of the 6 road segments it passes through.

[0179] Lesson from Ant B: Suppose another "ant B" unfortunately takes the congested route A1 -> B1 -> B2 -> C2 -> C3 -> D3 -> D4. Due to congestion, we can assume its equivalent path length is... If it's longer, say 8, then the pheromone it gains along its path is only 100 / 8 = 12.5.

[0180] Results: After the first update, the pheromone concentration on road segments B2-B3 will be higher than that on B2-C2. Meanwhile, the pheromone levels on all road segments will be adjusted accordingly. A portion of it evaporated.

[0181] Step 5: Iterative optimization (rounds 2 to N), which is to execute step S50.

[0182] Second iteration:

[0183] A new batch of 50 ants sets off from A1. When one ant arrives at B2 again, the choices it faces are different from before.

[0184] The probability of choosing B2 -> B3: Due to the enhancement in the previous round, the pheromone τ of this path has become higher, so its attractiveness has become stronger in the probability formula.

[0185] The probability of choosing B2 -> C2: The pheromone τ increases less along this path, so its relative attractiveness is weaker.

[0186] Result: In the second round, more ants tend to choose B2->B3, thus reinforcing this superior path. This positive feedback process is the core of the dynamic path planning method for intelligent connected vehicles.

[0187] 50th Iteration: Emergency Response

[0188] After dozens of iterations, one or several optimal paths (such as paths that bypass the central congestion area) have formed a very strong pheromone "highway".

[0189] Emergency: At this moment, the system learns through V2I (vehicle-to-infrastructure) communication that a traffic accident has occurred on the C3 to D3 section!

[0190] Algorithm response:

[0191] The intelligent connected vehicle dynamic path planning device immediately updates the accident status S of road segment (C3)-(D3) to 1.

[0192] When S=1, the pheromone level of this road segment will be forced to the minimum value. .

[0193] In the new round (51st round) of ant exploration, when an ant reaches C3, the probability of choosing it becomes negligible because the pheromone level of C3->D3 is extremely low.

[0194] The ants were forced to abandon this former "highway" and instead explore new paths, such as C3 -> C4 -> D4.

[0195] After several rounds of iteration, a new optimal path that bypasses the accident site will quickly form, and pheromones will gather on the new path.

[0196] Step 6: Dynamically output the optimal path

[0197] like Figure 5 As shown, the algorithm converges when the number of iterations reaches 100, or when the optimal path remains unchanged for 10 consecutive iterations. The intelligent connected vehicle dynamic path planning device outputs the path with the highest current pheromone concentration and the best overall score, such as A1 -> B1 -> B2 -> B3 -> C3 -> C4 -> D4, and presents it to the driver through the in-vehicle navigation system, thus perfectly completing the dynamic and intelligent path planning task.

[0198] The reason the optimal path can be determined is not because the algorithm knew it was the shortest from the beginning, but because it evolved through a competitive mechanism based on "path length." Shorter paths receive more pheromone rewards, which are amplified exponentially through positive feedback, ultimately making them stand out among many possible paths.

[0199] The improved algorithm in the dynamic path planning method for intelligent connected vehicles not only considers the length L, but also incorporates factors such as the congestion index C and real-time accidents S. Therefore, the algorithm ultimately finds not only the shortest path in terms of geometric distance, but the optimal path with the lowest "comprehensive cost" that takes into account factors such as time, efficiency, and safety.

[0200] In summary, during the current iteration of the ant colony algorithm for vehicle path planning, the following steps are taken: First, the current pheromone concentration, traffic operation information, traffic network information, vehicle starting position, and vehicle target position on the path updated in the previous iteration are obtained. Second, the vehicle's heuristic information is determined based on the traffic network information and traffic operation information. Third, the path selection probability of the vehicle in the current iteration is determined based on the current pheromone concentration, the vehicle's heuristic information, and the traffic operation information. Fourth, after generating the planned path and determining the optimal path for the current iteration based on the path selection probability, the vehicle's starting position, and the vehicle target position, the current pheromone concentration is updated using the traffic operation information to obtain the latest pheromone concentration on the path. Fifth, the path selection probability for the vehicle in the next iteration is determined based on the latest pheromone concentration, the traffic network information, and the latest traffic operation information. Sixth, the planned path and the optimal path for the next iteration are generated based on the path selection probability, the vehicle's starting position, and the vehicle target position. Finally, the optimal path for the vehicle is obtained after the path planning meets the iteration termination condition. It improves the real-time performance, accuracy, and adaptability of route planning for intelligent connected vehicles.

[0201] This application integrates dynamic traffic information into the path planning algorithm through real-time collection and processing of traffic information. This enables rapid response to changes in the traffic environment and timely planning of optimal routes for vehicles, meeting the real-time path planning requirements of intelligent connected vehicles. The improved ant colony algorithm, by introducing real-time traffic information factors and comprehensively considering pheromone concentration, heuristic information, and real-time traffic operation information along the path, can more accurately evaluate the merits of paths, avoid getting trapped in local optima, and improve the accuracy and reliability of path planning. By providing vehicles with reasonable path guidance, it guides them to avoid congested sections, balances traffic flow, and effectively alleviates traffic congestion, thereby improving the overall operational efficiency of the transportation system. It can provide intelligent connected vehicle users with efficient and accurate path planning services, reducing vehicle travel time and fuel consumption, and enhancing the user's travel experience.

[0202] For those consistent with the above, please refer to Figure 6 , Figure 6 This application provides a schematic diagram of the structure of a dynamic path planning device for intelligent connected vehicles. For example... Figure 6 As shown, the device includes:

[0203] The parameter acquisition module 601 is used to acquire the current pheromone concentration on the path updated in the previous iteration, traffic operation information on the path updated in the previous iteration, traffic network information, vehicle starting position and vehicle target position when planning the vehicle's path in the current iteration based on the ant algorithm.

[0204] The information determination module 602 is used to determine the vehicle heuristic information based on the traffic network information and traffic operation information;

[0205] The probability determination module 603 is used to determine the path selection probability of a vehicle in the current iteration based on the current pheromone concentration, the vehicle heuristic information, and the traffic operation information.

[0206] The pheromone update module 604 is used to update the current pheromone concentration through the traffic operation information after generating the planned path of the vehicle in the current iteration and determining the optimal path of the current iteration based on the path selection probability, the vehicle starting position and the vehicle target position, to obtain the latest pheromone concentration on the path.

[0207] The optimal path determination module 605 is used to determine the path selection probability of the vehicle in the next iteration based on the latest pheromone concentration, the traffic network information, and the latest traffic operation information; generate the planned path of the vehicle in the next iteration based on the path selection probability of the next iteration, the starting position of the vehicle, and the target position of the vehicle; determine the optimal path of the vehicle in the next iteration; and obtain the optimal path of the vehicle after the vehicle path planning meets the end iteration condition.

[0208] This application also provides a terminal device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor. When the processor executes the computer program, it implements the steps in the embodiment of the intelligent connected vehicle dynamic path planning method.

[0209] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the intelligent connected vehicle dynamic path planning methods described in the above method embodiments.

[0210] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps of any of the intelligent connected vehicle dynamic path planning methods described in the above method embodiments.

[0211] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable storage medium can include at least: any entity or device capable of carrying computer program code to a device / terminal equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable storage media cannot be electrical carrier signals or telecommunication signals.

[0212] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0213] Those skilled in the art will recognize that the units and algorithm steps of the various examples 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 implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0214] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0215] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

Claims

1. A dynamic path planning method for intelligent connected vehicles, characterized in that, include: In the current iteration of the ant colony algorithm, when planning the vehicle's path, the current pheromone concentration on the path updated in the previous iteration, the traffic operation information on the path updated in the previous iteration, the traffic network information, the vehicle's starting position, and the vehicle's target position are obtained. The vehicle heuristic information is determined based on the traffic network information and traffic operation information; the traffic network information includes road segment length, and the traffic operation information includes road congestion index. Based on the current pheromone concentration, the vehicle heuristic information, and the traffic operation information, the path selection probability of the vehicle in the current iteration is determined; the traffic operation information includes traffic flow and average vehicle speed. After generating the planned path for the vehicle in the current iteration and determining the optimal path for the current iteration based on the path selection probability, the vehicle's starting position, and the vehicle's target position, the current pheromone concentration is updated using the traffic operation information to obtain the latest pheromone concentration on the path; the traffic operation information includes: accident status and road congestion index; Based on the latest pheromone concentration, the traffic network information, and the latest traffic operation information, the path selection probability of the vehicle in the next iteration is determined. Based on the path selection probability of the next iteration, the starting position of the vehicle, and the target position of the vehicle, the planned path of the vehicle in the next iteration is generated, and the optimal path of the next iteration is determined. The optimal path of the vehicle is obtained after the vehicle path planning meets the end iteration condition.

2. The dynamic path planning method for intelligent connected vehicles according to claim 1, characterized in that, The step of determining the path selection probability of a vehicle in the current iteration based on the current pheromone concentration, the vehicle heuristic information, and the traffic operation information includes: Based on the traffic flow and the average vehicle speed, real-time traffic information factors are obtained; The path selection probability of the vehicle in the current iteration is determined based on the current pheromone concentration, the vehicle heuristic information, and the real-time traffic information factor.

3. The dynamic path planning method for intelligent connected vehicles according to claim 2, characterized in that, Based on the current pheromone concentration, the vehicle heuristic information, and the real-time traffic information factor, the path selection probability of the vehicle in the current iteration is determined, including: ； in, For at any time The k-th ant starts from node Transfer to node The probability of; For at any time ,node To the node The current pheromone concentration along the path; Heuristic information about the path from node i to node j at time t; At any moment ,node To the node Real-time traffic information factors of the route; Pheromones are the inductive factor; As a desired heuristic factor; For real-time traffic factor weights; For the k-th ant at node The set of next nodes that can be selected at that time.

4. The dynamic path planning method for intelligent connected vehicles according to any one of claims 1 to 3, characterized in that, After generating the planned path for the vehicle in the current iteration and determining the optimal path for the current iteration based on the path selection probability, the vehicle's starting position, and the vehicle's target position, the current pheromone concentration is updated using the traffic operation information to obtain the latest pheromone concentration on the path, including: Based on the path selection probability, the vehicle's starting position, and the vehicle's target position, the planned path for the vehicle in the current iteration is generated, and the ant path length is obtained. Based on the ant path length and the road congestion index, an ant path score is obtained, and the path with the highest ant path score is taken as the optimal path for the current iteration. Based on the ant path length and the incident status, the pheromone increment is obtained; The latest pheromone concentration on the path is obtained based on the pheromone increment and the current pheromone concentration.

5. The dynamic path planning method for intelligent connected vehicles according to claim 4, characterized in that, The step of obtaining the pheromone increment based on the ant path length and the incident state includes: ； for For nodes To the node The pheromone increment along the path; The pheromone intensity index; Ant Path length; For nodes To the node Accident status of the path; Alternatively, obtaining the latest pheromone concentration on the path based on the pheromone increment and the current pheromone concentration includes: ； The latest pheromone concentration along the path; The pheromone evaporation coefficient; The current pheromone concentration; for For nodes To the node The pheromone increment along the path; This represents the number of ants.

6. The dynamic path planning method for intelligent connected vehicles according to claim 4, characterized in that, The ant path score is obtained based on the ant path length and the road congestion index, including: ； in, Scoring ant paths; This represents the length of the ant's path. Indicates the first The total congestion index of all road segments in the route; This refers to the path scoring weighting coefficient.

7. The dynamic path planning method for intelligent connected vehicles according to any one of claims 1 to 3, characterized in that, The step of determining the vehicle heuristic information based on the traffic network information and traffic operation information includes: ； in, This provides heuristic information about the path from node i to node j at time t; Let be the length of the path segment from node i to node j; Let be the road congestion index for the path from node i to node j.

8. A dynamic path planning device for intelligent connected vehicles, characterized in that, include: The parameter acquisition module is used to acquire the current pheromone concentration, traffic operation information, traffic network information, vehicle starting position, and vehicle target position on the path updated in the previous iteration of the ant algorithm during the current iteration of vehicle path planning. The information determination module is used to determine the vehicle heuristic information based on the traffic network information and traffic operation information; the traffic network information includes road segment length, and the traffic operation information includes road congestion index; The probability determination module is used to determine the path selection probability of a vehicle in the current iteration based on the current pheromone concentration, the vehicle heuristic information, and the traffic operation information; the traffic operation information includes traffic flow and average vehicle speed. The pheromone update module is used to update the current pheromone concentration through the traffic operation information after generating the planned path of the vehicle in the current iteration and determining the optimal path of the current iteration based on the path selection probability, the vehicle's starting position and the vehicle's target position, to obtain the latest pheromone concentration on the path; the traffic operation information includes: accident status and road congestion index; The optimal path determination module is used to determine the path selection probability of the vehicle in the next iteration based on the latest pheromone concentration, the traffic network information, and the latest traffic operation information; generate the planned path of the vehicle in the next iteration based on the path selection probability of the next iteration, the starting position of the vehicle, and the target position of the vehicle; determine the optimal path of the next iteration; and obtain the optimal path of the vehicle after the vehicle path planning meets the end iteration condition.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the dynamic path planning method for intelligent connected vehicles as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the dynamic path planning method for intelligent connected vehicles as described in any one of claims 1 to 7.

Images