Path generation method, path planning method and path system

Abstract

The embodiment of the invention provides a path generation method, a path planning method and a path system. The method comprises the following steps: acquiring static data and dynamic data of a road where a vehicle is located; the static data is used for representing fixed attribute information of a road where the vehicle is located, and the dynamic data is used for representing real-time state information of the road and the vehicle; and generating a target path of the vehicle according to the static data and the dynamic data. According to the embodiment of the invention, the static data and the dynamic data in the road can be fused in real time to reasonably plan the path of the vehicle, the vehicle passing efficiency is improved, and high-quality path planning service is provided for users.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer technology, and in particular to a path generation and planning method and a path system. Background Art

[0002] In specific implementation, path planning of urban roads is related to the safe travel and traffic efficiency of every traffic participant, and is also closely related to the city's sustainable development, energy consumption and environmental protection.

[0003] However, the current path planning for vehicles on urban roads is not perfect, resulting in low vehicle traffic efficiency and an inability to provide high-quality path planning services for traffic participants. Summary of the Invention

[0004] In view of the above problems, a path generation, path planning method and path system are proposed to overcome or at least partially solve the above problems. The specific technical solution is as follows:

[0005] In a first aspect of the present invention, a path generation method is provided, the method comprising:

[0006] Obtaining static data and dynamic data of the road on which the vehicle is located; the static data is used to represent fixed attribute information of the road on which the vehicle is located, and the dynamic data is used to represent real-time status information of the road and the vehicle;

[0007] A target path of the vehicle is generated based on the static data and the dynamic data.

[0008] In a second aspect of the present invention, a path planning method is provided, comprising:

[0009] Obtaining static data and dynamic data of the road on which the vehicle is located in the cloud to generate a target path; the static data is used to represent fixed attribute information of the road on which the vehicle is located, and the dynamic data is used to represent real-time status information of the road and the vehicle;

[0010] The driving path of the vehicle is dynamically adjusted based on the target path.

[0011] In a third aspect of the present invention, a routing system is provided, comprising a cloud control platform, a vehicle-mounted platform, and a road-side platform;

[0012] The vehicle-mounted platform and the road-side platform are used to collect static data and dynamic data of the road where the vehicle is located;

[0013] A cloud control platform is used to obtain static data and dynamic data of the road where the vehicle is located; the static data is used to represent fixed attribute information of the road where the vehicle is located, and the dynamic data is used to represent real-time status information of the road and the vehicle; and a target path for the vehicle is generated based on the static data and the dynamic data.

[0014] In another aspect of the present invention, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium. When the computer-readable storage medium is run on a computer, the computer executes any of the above-mentioned path generation methods and / or implements the above-mentioned path planning method.

[0015] In another aspect of the implementation of the present invention, a vehicle is provided, which implements any of the above-mentioned path generation methods and / or the above-mentioned path planning methods.

[0016] In another aspect of the present invention, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute any of the above-mentioned path generation methods and / or implement the above-mentioned path planning method.

[0017] Compared with the related art, the embodiments of the present invention have at least the following advantages:

[0018] In embodiments of the present invention, when planning a vehicle's route, static and dynamic data about the road on which the vehicle is located is acquired. The static data represents fixed attributes of the road, while the dynamic data represents real-time status information about the road and vehicle. The target vehicle route is generated based on these static and dynamic data. This embodiment of the present invention integrates static and dynamic road data in real time to rationally plan vehicle routes, improving vehicle traffic efficiency and providing high-quality route planning services for traffic participants. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for describing the embodiments or the prior art.

[0020] Figure 1 A flowchart of a path generation method provided in an embodiment of the present invention;

[0021] Figure 2 A schematic diagram of the architecture of a vehicle-road-cloud integrated system provided in an embodiment of the present invention;

[0022] Figure 3 A flow chart of a path planning provided in an embodiment of the present invention;

[0023] Figure 4A schematic diagram of a global optimal path generation process provided in an embodiment of the present invention;

[0024] Figure 5 A flowchart of the steps of a path planning method provided in an embodiment of the present invention;

[0025] Figure 6 A structural block diagram of a path system provided in an embodiment of the present invention;

[0026] Figure 7 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.

[0028] Currently, the path planning method for vehicles can rely on single vehicle perception, static map and dynamic map. Figure 3 Method to achieve.

[0029] Bicycle perception: Bicycle perception has a short distance and limited computing power, which affects its overall effect in practical applications.

[0030] Static maps: Static maps contain data such as road network structure, classification, landmarks, points of interest, and fixed infrastructure. The data in these static maps does not fully consider the impact of traffic light status on urban roads, dynamic changes in traffic flow, etc. on route planning.

[0031] Dynamic map: The dynamic map contains traffic light information installed by some intelligent transportation systems, as well as dynamic information on traffic flow, such as road congestion information, etc. However, traffic participants need to plan their routes based on the dynamic map.

[0032] However, although the current path planning method can dynamically adjust the path according to the traffic light cycle, it cannot integrate real-time traffic light information, nor can it dynamically adjust the path according to the traffic light cycle, resulting in vehicles frequently encountering red lights, increasing waiting time and reducing vehicle traffic efficiency.

[0033] On the other hand, current route planning methods mainly rely on historical or limited real-time data on traffic flow. Although they can predict traffic congestion, the real-time prediction is poor, especially during peak hours when traffic flow changes rapidly. The predictions and planned routes of traditional navigation systems often lag behind the actual situation. When planning routes, they usually only consider the current congestion situation and lack the ability to predict future traffic flow. As a result, vehicles choose congested roads, further exacerbating the congestion problem.

[0034] On the other hand, current path planning methods typically prioritize minimizing time or distance. However, with the increasing penetration of new energy vehicles, path planning methods must not only improve traffic efficiency but also consider vehicle energy consumption and remaining range. Existing path planning methods often overlook numerous factors that influence vehicle energy consumption, such as road grade, acceleration and deceleration times, wait times at traffic lights, and traffic congestion. This results in frequent acceleration and deceleration on high-energy-consuming roads, significantly increasing vehicle energy consumption.

[0035] In response to the above problems, an embodiment of the present invention proposes an integrated vehicle-road-cloud architecture, in which the cloud (cloud control platform) can obtain more accurate real-time static data and dynamic data (dynamic and static data / dynamic and static information) from the roadside platform and the vehicle-side platform. Dynamic data can include information such as traffic light status and real-time traffic flow. The depth of dynamic and static data is integrated to achieve vehicle path planning, which not only makes up for the shortcomings of current path planning methods in integrating real-time traffic lights and traffic flow, but also can dynamically optimize path recommendations for vehicles, effectively improve vehicle traffic efficiency, and provide high-quality path planning services for traffic participants. In addition, an embodiment of the present invention also proposes a multi-objective optimization algorithm, which improves the overall path planning efficiency by integrating factors such as time, distance, and energy consumption, and provides traffic participants with better path planning services.

[0036] Reference Figure 1 , is a flow chart of the steps of a path generation method provided in an embodiment of the present invention, such as Figure 1 As shown, the method may specifically include the following steps:

[0037] Step 101: Obtain static data and dynamic data of the road where the vehicle is located; the static data is used to represent fixed attribute information of the road where the vehicle is located, and the dynamic data is used to represent real-time status information of the road and the vehicle.

[0038] Step 102: Generate a target path for the vehicle based on the static data and the dynamic data.

[0039] In a specific implementation, the path generation method of the embodiment of the present invention is implemented based on a vehicle-road-cloud integrated system, where the vehicle-road-cloud refers to the vehicle-side platform (vehicle-mounted terminal / vehicle), the road test platform, and the cloud control platform. Among them, the roadside platform can obtain data collected by road infrastructure deployed on urban roads (such as smart sensors and traffic lights, etc.). The embodiment of the present invention realizes real-time data interaction between vehicles, road infrastructure and the cloud control platform, thereby optimizing the path planning effect of a single vehicle based on the interactive real-time data. Among them, the path generation method of the embodiment of the present invention can be implemented on the vehicle-side platform, or on the cloud control platform, or in combination with the vehicle-side platform and the cloud control platform. The embodiment of the present invention does not need to be limited to this. In view of the fact that the computing power of the cloud control platform is better than that of the vehicle-side platform, when both the vehicle-side platform and the cloud control platform can be implemented, it can be preferably implemented through the cloud control platform.

[0040] For example, referring to Figure 2 , a schematic diagram of the architecture of a vehicle-road-cloud integrated system provided in an embodiment of the present invention. Specifically, the roadside platform can utilize on-road intelligent sensors, traffic lights, and other road infrastructure to collect dynamic data on the road in real time. An information sharing mechanism is established via a wireless communication network. The vehicle-side platform's T-Box (Telematics Box, a telematics processor / on-board terminal) enables vehicles to obtain dynamic data on surrounding road infrastructure through the roadside platform in a timely manner. Furthermore, the cloud control platform can also obtain static road data from Open Street Map (OSM). Static data represents fixed attribute information about the road the vehicle is on, while dynamic data represents real-time status information about the road and vehicle. Static and dynamic data can then be integrated to implement route planning.

[0041] Static data can include road geometry, topology, and traffic sign information. First, the geometric characteristics of roads are crucial and can include detailed geometric features such as width, curvature, slope, and lane lines. These data determine the basic conditions for vehicle travel. Second, the road topology fully reflects the connection relationships between different roads, such as intersections, roundabouts, and ramps, ensuring that urban road environment modeling constructed based on static data can accurately describe the layout of the road network. In addition, traffic sign information, such as speed limit signs, traffic light locations, stop signs, and road markings, is also an important part of traffic regulations and directly affects vehicle driving behavior.

[0042] In some embodiments, static data can be represented by nodes (such as road intersections, road starting points, or road end points) and edges (road segments connecting nodes) in a graph model (edges table). Each node not only represents a physical location but can also contain additional information such as traffic lights and signs. Edges can represent attributes such as road length, speed limit, and number of lanes.

[0043] Dynamic data can include real-time traffic flow (traffic density), changes in traffic light cycles, and temporary road closures and construction information in urban transportation systems. These data reflect the real-time status of roads, and dynamic data reflects the changes in urban transportation systems that keep pace with the times. The real-time nature of dynamic data is crucial for autonomous driving systems and intelligent traffic management, and directly affects the effectiveness of path planning and traffic optimization. In order to ensure the timeliness and effectiveness of dynamic data, the embodiments of the present invention use multiple tables in the database design to store different types of dynamic data respectively, and keep the dynamic data up to date through efficient query and update mechanisms.

[0044] In some embodiments, the dynamic data acquisition system will regularly obtain the latest dynamic data from road infrastructure such as sensors, traffic management systems, or Internet data sources according to preset time intervals, and write it into the corresponding dynamic data table of the database. For example, the traffic light status table can be connected to the traffic management system in real time to update the traffic light status every second. In an embodiment of the present invention, in order to improve query efficiency, spatial indexes and time indexes are also set in the dynamic data table to ensure that the system can quickly find data at a specific location or time period. In addition, the database can also use triggers or monitoring mechanisms to immediately update the information in the relevant dynamic data table when important dynamic data changes (such as sudden accidents or road closures), triggering the path planning module to recalculate.

[0045] In an embodiment of the present invention, the cloud control platform integrates massive, comprehensive, and accurate static and dynamic data, and leverages its powerful computing capabilities to perform complex calculations and intelligent analysis, providing personalized route planning and optimization for each vehicle, ultimately determining the vehicle's target path. For example, the cloud control platform can monitor each vehicle's specific location and driving status in real time. Combined with dynamic data provided by road infrastructure, it analyzes and predicts overall traffic flow, providing optimal route recommendations for each vehicle, generating a target path, and providing it to traffic participants. This allows them to navigate the road with assistance or autonomously, avoiding congested sections and improving traffic efficiency.

[0046] In embodiments of the present invention, when planning a vehicle's route, static and dynamic data about the road on which the vehicle is located is acquired. The static data represents fixed attributes of the road, while the dynamic data represents real-time status information about the road and vehicle. The target vehicle route is generated based on these static and dynamic data. This embodiment of the present invention integrates static and dynamic road data in real time to rationally plan vehicle routes, improving vehicle traffic efficiency and providing high-quality route planning services for traffic participants.

[0047] In one embodiment of the present invention, step 102, generating the target path of the vehicle according to the static data and the dynamic data, includes:

[0048] generating an initial path of the vehicle based on the static data and the dynamic data;

[0049] The initial path is adjusted according to a preset target to obtain a target path for the vehicle.

[0050] In some embodiments, the preset target may include at least energy consumption and time, wherein the energy consumption and time may be generated based on static data and dynamic data.

[0051] In an embodiment of the present invention, the cloud control platform can generate an initial path for the vehicle based on the acquired static data and dynamic data, and then optimize the initial path according to the preset goals to obtain a target path. That is, the target path is a set of optimal or near-optimal paths obtained after weighing the preset goals. Therefore, based on the target path, a better path planning service can be provided to traffic participants.

[0052] Among them, since there are usually multiple preset goals, such as optimizing energy consumption and time at the same time, it can also be called multi-objective optimization. Multi-objective optimization requires specific goals and constraints to collect, calculate and adjust information to achieve optimization effects such as efficient energy saving and path selection. For example, the optimization goal can be to minimize the energy consumption or total travel time during vehicle driving, while ensuring a certain driving comfort. The constraints mainly include path legitimacy, that is, the path of the vehicle must comply with the topological structure of the road, traffic regulations and actual feasibility. For example, a vehicle cannot pass directly between intersection A and intersection B where there is no road section, or a vehicle cannot drive on a closed road C.

[0053] In one embodiment of the present invention, generating the initial path of the vehicle according to the static data and the dynamic data includes:

[0054] Obtaining a target starting point, a target end point, and a road graph model of the vehicle; the road graph model is used to characterize connectivity between the roads;

[0055] An initial path of the vehicle is generated according to the static data, the dynamic data, the target starting point, the target end point, and a road graph theory model.

[0056] In some embodiments, static data can be stored based on a graph theory model / road graph theory model (edges table). Of course, other storage methods can also be used, and the embodiments of the present invention are not limited to this. Specifically, the road graph theory model can determine the connectivity between roads, that is, whether a vehicle can pass from one road to another.

[0057] In an embodiment of the present invention, when performing vehicle path planning, the cloud control platform obtains the target starting point and target end point of the vehicle, where the target starting point and target end point can be any two locations in the area where the vehicle is located. The positions of the target starting point and target end point are determined based on the road graph model. Then, static data and dynamic data can be integrated to determine the travel distance (travel time / distance) between the target starting point and the target end point in the road graph model, and then an initial path can be generated based on the travel distance, for example, a path with the shortest total travel distance can be generated.

[0058] In one embodiment of the present invention, the road graph model may include nodes and edges of roads; the nodes are waypoints on the roads; the edges are roads between the waypoints; the waypoints include intersections of the roads, starting points of the roads, or end points of the roads;

[0059] Generating an initial path of the vehicle according to the static data, the dynamic data, the target starting point, the target end point, and a road graph theory model includes:

[0060] Determine the travel distance between the nodes where the edges exist in the road graph model according to the dynamic data and the static data;

[0061] Taking the node corresponding to the target starting point in the road graph model as the starting node;

[0062] Using the node corresponding to the target end point in the road graph model as the end point node;

[0063] An initial path of the vehicle is generated according to the travel distance, the starting node, and the ending node.

[0064] In an embodiment of the present invention, static data can be stored based on a road graph model. Specifically, the road graph model derived from the static data includes nodes and edges representing roads in a region (e.g., a province or city). Nodes represent waypoints on a road, and edges represent roads (road segments) between waypoints. Waypoints can include intersections, road starting points, or road end points. Each node in the road graph model can not only represent a physical location in a city but also include additional information such as traffic lights and signs. Each edge in the road graph model can also represent attributes of the corresponding road, such as road length, speed limit, and number of lanes.

[0065] In an embodiment of the present invention, when performing vehicle path planning, the cloud control platform obtains the target starting point and target end point of the vehicle, wherein the target starting point and target end point can be any two locations in the area where the vehicle is located. The node corresponding to the target starting point in the road graph model can be used as the starting node, and the node corresponding to the target end point can be used as the end node. Then, static data and dynamic data can be integrated to determine the travel distance between nodes with edges, and then an initial path can be generated based on the travel distance, for example, a path with the shortest total travel distance can be generated.

[0066] In one embodiment of the present invention, determining the travel distance between the nodes having the edges in the road graph model based on the dynamic data and the static data includes:

[0067] The travel distance between the nodes where the edge exists is determined based on the road length corresponding to the road between the nodes where the edge exists, the average vehicle speed, the traffic flow density and / or the preset maximum traffic flow density.

[0068] In an embodiment of the present invention, the fusion of dynamic and static data, that is, the fusion of static data and dynamic data, is the core of the vehicle-road-cloud integrated system. One of the core points is that the travel distance of each road in the static data, that is, the travel distance between each node, can be dynamically adjusted according to the dynamic data. Therefore, the travel distance of a certain road not only depends on the road length of the road itself (static data), but also depends on one or more combinations of dynamic data of the road such as traffic flow, temporary road closures, construction conditions, vehicle speed, etc. In this way, the initial path generated based on the travel distance is more adapted to the real-time status of the road, thereby avoiding congestion and improving vehicle travel efficiency.

[0069] Specifically, when traffic volume on a particular road segment increases, the system adjusts the distance field in the road graph model, representing the travel time for that segment, based on changes in vehicle density and average vehicle speed. Generally, the weight increases with increasing vehicle density and longer travel distances. Conversely, if vehicle density decreases and travel distances shorten, the weight decreases.

[0070] In some embodiments, the travel distance between nodes with edges (i.e., roads in a city) can be determined using the travel distance formula:

[0071]

[0072] Where Distance represents the travel distance; L represents the road length corresponding to each road; v represents the average vehicle speed corresponding to each road; ρ represents the traffic flow density corresponding to each road; T max Indicates the preset maximum traffic flow density; wherein, the average vehicle speed corresponding to each road is adjusted according to the traffic flow density corresponding to the road.

[0073] Of course, travel distance is affected not only by road length, traffic density, and / or average vehicle speed, but also by other dynamic data. For example, at intersections that rely on traffic lights, the travel distance is also affected by the traffic light cycle. For example, if the red light at a certain intersection is prolonged, the travel delay increases, and the travel distance corresponding to the corresponding distance field should also increase. Traffic light status not only affects a single road segment but may also affect the coordination between multiple intersections. The system needs to dynamically adjust the travel distance between different roads. Therefore, in practical applications, road-related dynamic data can be incorporated into the process of determining travel distance based on the actual state of the road, so that the travel distance can better reflect the situation of the vehicle when driving on the road.

[0074] In one embodiment of the present invention, after determining the travel distance between the nodes where the edge exists based on the road length corresponding to the road between the nodes where the edge exists, the average vehicle speed, the traffic flow density, and / or a preset maximum traffic flow density, the method further includes:

[0075] When the traffic flow density corresponding to the road between the nodes where the edge exists is greater than a preset traffic flow density, the travel distance is adjusted according to a preset coefficient.

[0076] In practice, traffic density significantly impacts road traffic. In particular, when traffic density exceeds a preset value, it not only takes longer to navigate the road but also makes driving more difficult, resulting in a poor driving experience for road users. Therefore, in this embodiment of the present invention, after calculating the travel distance, the travel distance can be further adjusted based on the road's traffic density.

[0077] Specifically, if the traffic density corresponding to a road is greater than a preset traffic density, for example, a traffic density exceeding 50, the determined travel distance will be multiplied by a preset coefficient, such as 1.5 or another value greater than 1, to reflect the impact of the higher traffic density on travel time. The probability of the road being planned as the initial route will be reduced accordingly. Of course, if the traffic density corresponding to a road is less than or equal to the preset traffic density, for example, a traffic density less than or equal to 50, there is no need to adjust the determined travel distance.

[0078] In one embodiment of the present invention, determining the travel distance between the nodes having the edges in the road graph model based on the dynamic data and the static data may include:

[0079] When it is determined according to the road closure information that the road between the nodes where the edge exists is in a road closure state, the travel distance between the nodes where the edge exists is marked as infinite or impassable.

[0080] In an embodiment of the present invention, when dynamic data is updated, for example, when the traffic density of a road is updated, the system determines the new travel distance of the road using a predefined travel distance formula and updates the travel distance corresponding to the distance field of the road in the edges table (road graph model). If a road closure event occurs, such as a temporary road closure or a road closure determined based on construction conditions, the system sets the travel distance corresponding to the distance field in the edges table to a very large value (e.g., infinity) or directly marks it as impassable. In this case, the road will not be used to generate the initial path, ensuring the legitimacy and feasibility of the initial path.

[0081] In one embodiment of the present invention, generating the initial path of the vehicle according to the travel distance, the starting node, and the ending node includes:

[0082] When the sum of the travel distances between consecutive nodes from the starting node to the end node meets a preset distance condition, an initial path of the vehicle is generated based on the consecutive nodes between the starting node and the end node, and the starting node and the end node.

[0083] Among them, when the sum of the travel distances between the consecutive nodes from the starting node to the end node meets the preset distance condition, the initial path of the vehicle is generated according to the consecutive nodes between the starting node and the end node, and the starting node and the end node, which may include: when the sum of the travel distances between the consecutive nodes from the starting node to the end node is the shortest, the initial path of the vehicle is generated according to the consecutive nodes between the starting node and the end node, and the starting node and the end node.

[0084] In a specific implementation, the path with the shortest travel distance from the starting node to the end node is usually used as the initial path to ensure the travel efficiency of the vehicle.

[0085] In an embodiment of the present invention, a variety of different algorithms can be used to generate an initial path based on continuous nodes from the start node to the end node. For example, the initial path can be generated based on the Dijkstra algorithm or the A* algorithm, and the embodiment of the present invention does not need to be limited to this.

[0086] In a specific example, the Dijkstra algorithm can be used to generate the initial path for the vehicle, ensuring that the initial particle is the shortest path based on the network structure of the road graph theory model. Specifically, the Dijkstra algorithm is a classic algorithm for solving the single-source shortest path problem, applicable to graphs with non-negative weights, such as road graph theory models. Its principle is to gradually expand the neighboring nodes of the known shortest path node and update the shortest distance of these neighboring nodes until all nodes are processed.

[0087] In the specific implementation, first initialize the nodes and edges of all roads in the area. For the starting node s, its initial distance is set to 0, and d(s) means that the distance from the starting node to the starting node is 0:

[0088] d(s)=0

[0089] At this point, the initial distances of all other nodes v in the road graph model are set to infinity∞, and d(v) indicates that the distance from the starting node to other nodes v is infinite:

[0090] d(v)=∞

[0091] Create a set of visited nodes. When preparing to generate the initial path, the nodes in the road graph model are unvisited nodes and are not in the visited node set. In each iteration, select the node u with the minimum current travel distance from the unvisited nodes.

[0092] In some embodiments, the formula for selecting node u may be as follows:

[0093]

[0094] Where u represents the currently selected node (the unvisited node closest to the starting node); argmin returns the variable value that minimizes the expression (i.e., node v); Unvisited represents the set of unvisited nodes; and d(v) represents the currently known shortest distance (i.e., cumulative distance) from the starting node to node v.

[0095] Add the visited node u to the visited node set. For the neighbor node v of node u, if the path to v through node u is shorter than the currently recorded shortest path, update the shortest distance of the neighbor node v:

[0096] In some embodiments, the formula for selecting node u may be as follows:

[0097] d(v)=min(d(v),d(u)+w(u,v))

[0098] Among them, w(u,v) represents the weight of the edge from node u to node v, such as the travel distance; d(u) represents the shortest distance from the starting point s to node u; d(v) represents the cumulative distance of the currently known shortest path from the starting point node s to node u, and d(v) is dynamically updated according to d(u); min means retaining the smaller value.

[0099] Finally, when the end node is processed, the path from the start node to the end node is recorded as the initial path.

[0100] In another specific example, the A* algorithm can also be used to generate the vehicle's initial path. Specifically, in order to be closer to actual urban traffic conditions, in addition to the shortest path generated based on static data, the A* algorithm can be further used in combination with dynamic data (such as traffic flow, signal light status, etc.) to perform heuristic adjustments to the initial path. Specifically, the A* algorithm is a heuristic search algorithm that combines shortest path search and heuristic information, that is, by considering both the cost of the current path and the estimated cost of reaching the destination in the future during the path search, the optimal initial path can be found more efficiently.

[0101] In some embodiments, the core formula of the A* algorithm is:

[0102] f(n)=g(n)+h(n)

[0103] Where g(n) is the actual cost (e.g., travel time or distance) from the starting node to node n. g(n) can be expressed by the following formula:

[0104] g(n)=g(parent(n))+w(parent(n),n)

[0105] Here, g(parent(n)) represents the cumulative cost from the starting node to node n's parent node parent(n), and w(parent(n),n) is the edge weight from parent node parent(n) to node n, typically based on factors such as road length or travel time. h(n) represents a heuristic estimate of the distance from node n to the end node, typically using Euclidean distance to estimate future costs.

[0106] In some embodiments, the formula for Euclidean distance may be:

[0107]

[0108] Among them, x goal and y goal Indicates the two-dimensional coordinates of the end node; x n and y n Represents the two-dimensional coordinates of the current node n.

[0109] The heuristic estimate provides the A* algorithm with an estimate of future travel through heuristic information, allowing the algorithm to more effectively select nodes for expansion. f(n) is the combined actual cost g(n) and estimated cost h(n), representing the total cost of reaching the destination node via node n. Each time, the A* algorithm expands the node with the smallest f(n). That is, it selects the node n with the smallest f(n) from the open list (which stores nodes explored from the starting node but whose neighbors have not yet been calculated). This is the node most likely to be on the optimal path after combining the actual cost g(n) and estimated cost h(n). The initial path can then be generated based on these nodes.

[0110] During the path planning process of the embodiment of the present invention, the weight of the edge is adjusted or heuristically estimated through dynamic data to adapt to the current traffic conditions. For example, when the traffic flow is large, the weight of the edge is increased to simulate a delay, or the travel time is adjusted according to the status of the traffic light, and even the weight of certain edges is set to infinity when a road is closed or an accident occurs. In addition, each time a node is expanded, in addition to considering g(n), it is also necessary to estimate the cost of future travel through the heuristic function h(n), making the path planning closer to reality. Finally, after using the A* algorithm to search for a path, an adjusted path that meets the current traffic conditions is generated and used as the adjusted initial particle.

[0111] Of course, the above-mentioned calculation process of the initial path is only used as an example. In actual applications, other algorithms besides the Dijkstra algorithm or the A* algorithm can also be used, or the initial path can be generated by integrating algorithms such as the Dijkstra algorithm or the A* algorithm. The embodiment of the present invention does not need to be limited to this.

[0112] In an embodiment of the present invention, after the initial path is obtained, the initial path may be used as an initial particle, and then a particle swarm optimization (PSO) algorithm is used to perform multi-objective optimization to obtain a final target path.

[0113] In one embodiment of the present invention, the method may further include:

[0114] Randomly replacing at least one node in the initial path with another node in the road graph model to obtain a replacement path;

[0115] When it is determined according to the road graph theory model that there are edges between consecutive nodes in the replacement path, the replacement path is used as the initial path.

[0116] In the specific implementation, in order to prevent all initial particles from concentrating near the local optimal solution, it is necessary to generate some exploratory initial particles through random perturbations. Particles generated through random perturbations can increase the diversity of the search space and prevent the particle swarm algorithm (PSO) from falling into the local optimal solution.

[0117] In some embodiments, random perturbation can be implemented in the following ways: First, during the generation of initial particles (initial paths) for the shortest path, random perturbations can be introduced to generate some alternative paths that are slightly different from the shortest path. The specific steps include randomly selecting one or more nodes from the road graph model to replace the nodes in the initial path generated based on the Dijkstra algorithm or the A* algorithm based on the road graph model and dynamic and static data, thereby obtaining an alternative path. In some embodiments, the formula for random perturbation is as follows:

[0118] P ′ =P+ΔP

[0119] Among them, P is the original initial path, ΔP is the random perturbation, P ′ is the replacement node after random perturbation.

[0120] During the random perturbation process, the replacement nodes used to replace the original initial nodes can be selected within a relatively close range to the nodes of the original initial path to ensure that the subsequently generated replacement path remains reasonable. The replacement path obtained after replacement can then be verified to ensure its feasibility (for example, the absence of impassable roads). Specifically, the verification method can be to determine whether there are edges (roads) between consecutive nodes (waypoints) in the replacement path based on the road graph theory model. If so, it indicates that the edges between the nodes in the replacement path are passable, and the verification passes. Conversely, if not, it indicates that the edges between the nodes in the replacement path are impassable, and the verification fails. After passing the verification, the replacement path will be used as the new initial path and used together with the original initial path to determine the final target path, preserving diversity. The generated diverse initial particles can effectively improve the global search capability of the particle swarm algorithm (PSO) and avoid falling into local optimality.

[0121] In one embodiment of the present invention, adjusting the initial path according to a preset target to obtain the target path of the vehicle includes:

[0122] updating at least one of the initial paths according to a preset speed update formula and a preset position update formula to obtain an updated path; wherein the speed update formula is used to control the initial path to determine a node corresponding to a target position in a road graph model according to an update trend and an update step size, and the position update formula is used to determine an updated path based on the node corresponding to the target position according to the speed update formula and the initial path;

[0123] The initial path and the updated path are adjusted according to a preset target to obtain a target path for the vehicle.

[0124] In an embodiment of the present invention, a preset speed update formula and a preset position update formula set based on a particle swarm algorithm (PSO) can be used to update at least one initial path to obtain an updated path, wherein the speed update formula is used to control how the initial path evolves and adjusts. Specifically, the speed update formula can determine the update trend and update step of the initial path in the road graph model, wherein the update trend determines the update direction of the initial path in the road graph model, such as avoiding congested roads and reducing turns, etc. The update step determines the update amplitude of the initial path in the road graph model, such as how many edges or nodes can be updated each time. The position update formula generates one or more updated paths based on the result of the speed update formula, that is, the node corresponding to the target position in the road graph model output by the speed update formula.

[0125] In one embodiment of the present invention, adjusting the initial path and the updated path according to a preset target to obtain the target path of the vehicle includes:

[0126] Creating a multi-objective fitness function; the multi-objective fitness function is used to balance multiple preset objectives;

[0127] Calculating the fitness of the initial path and the updated path corresponding to the initial path according to the multi-objective fitness function;

[0128] Filtering a preferred path from the initial path and the updated path according to the fitness;

[0129] Taking the preferred path as the initial path, and returning to the step of updating at least one of the initial paths according to the speed update formula and the position update formula to obtain an updated path;

[0130] When a preset convergence condition is met, the preferred path whose fitness meets a preset screening condition is used as the target path of the vehicle.

[0131] In a specific implementation, based on the obtained initial path (initial particles), the embodiment of the present invention uses a particle swarm algorithm (PSO) to perform multi-objective optimization to obtain the final target path. The multi-objective optimization may include at least the optimization of preset objectives such as energy consumption and time. The particle swarm algorithm (PSO) can achieve the optimization of preset objectives such as energy consumption and time through a multi-objective fitness function.

[0132] Energy consumption is a measure of the total energy consumption of a vehicle on a specific route and is affected by many factors. The speed of the vehicle is crucial to energy consumption. A higher speed will increase air resistance, resulting in increased fuel or battery consumption, while a lower speed may prolong the engine's inefficient operation time and reduce efficiency. Acceleration is also a key factor in determining energy consumption. Frequent acceleration and deceleration, especially violent acceleration or prolonged deceleration, will significantly increase energy consumption. The length of the road is proportional to the total energy consumption. The longer the distance traveled, the greater the energy consumption. The slope and road conditions are also not to be ignored. When going uphill, the vehicle needs to consume more energy to overcome gravity, while when going downhill, it may save some energy with the help of gravity. Different road conditions (such as wet or rugged) will also affect the vehicle's energy consumption performance, causing it to vary.

[0133] In some embodiments of the present invention, the energy consumption calculation formula is as follows:

[0134]

[0135] Among them, E represents energy consumption, C1, C2, C3, and C4 are energy consumption coefficients of different factors respectively; v i represents the speed of the vehicle on the i-th section of road; a i represents the acceleration of the vehicle on the i-th section of road; d i represents the length of the road in section i; R irepresents the road condition coefficient of the i-th section of road; θ i represents the slope angle of the road in section i; C idling Indicates idle energy consumption; t redlight,i is the waiting time of the traffic light on the i-th road segment.

[0136] It should be noted that energy consumption coefficients C1, C2, C3, and C4 can be determined through vehicle performance experiments, road testing, model fitting, and literature data. They reflect the impact of speed, acceleration, slope, road conditions, and other factors on energy consumption. For example, speed-related energy consumption coefficients can be derived by fitting the vehicle's speed-energy consumption curve. Energy consumption at idle is relatively fixed and can be measured by the vehicle's fuel or electricity consumption rate at rest. The ability to dynamically adjust coefficients such as C1, C2, C3, and C4 can improve system adaptability and accuracy.

[0137] Time is intended to measure the total time required for a vehicle to travel on a route and is one of the key factors affecting route selection, especially when balancing energy conservation and traffic efficiency. The driving time of a vehicle is mainly determined by the length of the road and the driving speed. Of course, other factors can also significantly affect the total time. For example, on some sections of road, waiting at traffic lights may extend the journey, which not only increases the vehicle's driving time, but also may cause additional energy consumption due to start-stop operations. In the case of traffic congestion, the vehicle may be traveling at a low speed or stagnant, which not only increases the travel time, but also may increase the energy consumption during idling. For this reason, the traffic flow correction factor C is introduced when determining the time. traffic,i To correct the actual speed of the vehicle, so as to more accurately reflect the impact of congestion on time. In addition, in complex urban traffic scenarios, temporary stops, such as traffic police directing or pedestrians passing, will also cause additional waiting time. This waiting time can be calculated using the constant t stop,i This helps to better quantify the impact of these unexpected factors on the total journey time.

[0138] In some embodiments of the present invention, the time calculation formula is as follows:

[0139]

[0140] Where T represents time; v i represents the speed of the vehicle on the i-th section of road; d i represents the length of the road in section i; t stop,i Represents a constant; C traffic,i represents the traffic flow correction coefficient; t redlight,i is the waiting time of the traffic light on the i-th road segment.

[0141] It should be added that the traffic flow correction factor C traffic,iIt can be determined through traffic data analysis, traffic simulation models and empirical formulas to show the impact of different traffic conditions on vehicle speed. Based on the traffic flow correction coefficient C traffic,i The dynamic adjustment capability of equal coefficients can improve the adaptability and accuracy of the system.

[0142] In a specific implementation, to make the path planning algorithm more intelligent and adaptable to complex traffic environments, the particle swarm optimization (PSO) algorithm in an embodiment of the present invention introduces a dynamic weight coefficient into the multi-objective fitness function it creates. This aims to dynamically adjust the weight of the path planning based on real-time traffic conditions, thereby ensuring that the planned path has both high traffic efficiency and low energy consumption. The dynamic weight coefficient can include dynamic weight coefficients corresponding to different preset goals, for example, a dynamic weight coefficient corresponding to energy consumption (energy consumption weight) and a dynamic weight coefficient corresponding to time (time weight).

[0143] Among them, the dynamic weight coefficient adjustment is based on real-time traffic data (dynamic data), including but not limited to one or a combination of traffic flow, traffic light status, vehicle acceleration and deceleration times, etc. Specifically, when it is detected that the real-time traffic density (traffic flow) of a certain road increases, the dynamic weight coefficient corresponding to the time of the road will increase accordingly to reflect the importance of the increase in the time required to pass the road; conversely, if the traffic density decreases, the dynamic weight coefficient corresponding to the time of the road will decrease accordingly. Similarly, frequent acceleration and deceleration will lead to increased energy consumption. Therefore, when determining frequent acceleration and deceleration, the weight coefficient corresponding to energy consumption should also be increased accordingly.

[0144] In some embodiments, the dynamic adjustment formula of the time weight ωt in the multi-objective fitness function can be as follows:

[0145]

[0146] Among them, ω t_base Indicates the basic time weight; α indicates the adjustment factor; traffic_density indicates the current traffic flow density; traffic_density max represents the maximum flow density;

[0147] In some embodiments, the dynamic adjustment formula of the energy consumption weight ωe in the multi-objective fitness function can be as follows:

[0148]

[0149] Among them, ω e_base represents the basic energy consumption weight; β represents the adjustment factor; peed_changes represents the number of speed changes; speed_changes max Indicates the maximum number of speed changes.

[0150] The embodiment of the present invention combines the two preset goals of energy consumption and time to define a multi-objective fitness function. For example, a linear weighting method can be used to weight energy consumption and time to form a comprehensive evaluation index.

[0151] In some embodiments, the formula of the multi-objective fitness function can be as follows:

[0152] F=ω e ·E+ω t ·T

[0153] Among them, ω e is the dynamic weight coefficient corresponding to energy consumption E, ω t is the dynamic weight coefficient corresponding to time T, indicating the relative importance of energy consumption and time. The multi-objective fitness function of the embodiment of the present invention can comprehensively evaluate the pros and cons of paths under multiple constraints, providing a clear basis for updating the particle (path) group.

[0154] The core of the Particle Swarm Optimization (PSO) algorithm is that particles update their speed and position during each iteration based on their individual optimal solution and the global optimal solution. In path optimization problems, position updates mean making fine-tuning adjustments to the current path, such as replacing sections, selecting new nodes, or adjusting through different roads, to explore a more optimal path.

[0155] Dynamic data acquisition and adaptive adjustment are key to the application of the particle swarm algorithm (PSO) in the vehicle-road-cloud integrated system. In each iteration, particles need to obtain the latest dynamic data such as traffic flow, traffic light status, and road conditions from the vehicle-road-cloud integrated system. This dynamic data is stored in the database and can be retrieved through real-time queries. Based on dynamic data, the particle swarm algorithm (PSO) can adaptively adjust the path: if the traffic flow on a certain road is too high, the particle swarm algorithm (PSO) can increase the adjustment force, prompting particles to explore other, smoother paths; and in response to changes in traffic light status, the particle swarm algorithm (PSO) can dynamically adjust the path's transit time to avoid long waits, thereby improving overall traffic efficiency.

[0156] In some embodiments, the particle velocity update formula may be as follows:

[0157]

[0158] in, represents the velocity of the i-th particle at the k+1-th iteration; represents the position of the i-th particle at the k-th iteration (i.e., the current path); represents the historical optimal path of the i-th particle; g bestrepresents the global optimal path; ω represents the inertia weight, which controls the stability of speed update; c1 and c2 represent learning factors, which control the influence of individual optimality and global optimality respectively; r1 and r2 represent random numbers, which increase the randomness of exploration.

[0159] In some embodiments, the particle position update formula may be as follows:

[0160]

[0161] The PSO algorithm typically stops iterations when one of the following conditions is met: the number of iterations reaches a set upper limit, or the global optimal solution of the particles stabilizes after multiple iterations and no longer changes. Ultimately, the PSO algorithm outputs an optimal path (target path), which can be updated and optimized in real time using dynamic data provided by the vehicle-road-cloud system to minimize energy consumption and travel time. In practical applications, such path planning can be continuously adjusted as real-time traffic conditions change, ensuring energy efficiency and traffic efficiency.

[0162] In addition, the particle swarm optimization (PSO) algorithm can also integrate other preset objectives (such as comfort and safety) to further improve the effectiveness of route selection through multi-objective optimization. The route optimization model of the embodiment of the present invention can not only adapt to complex road environments, but also achieve an optimal balance between energy conservation and traffic efficiency while ensuring safety and comfort.

[0163] An embodiment of the present invention relates to a path planning method, which aims to solve various problems in current path planning technology. Specifically, the cloud control platform in the vehicle-road-cloud integrated system uses open source maps to complete the extraction of static map basic data (static data), build a complete high-precision map and complete a static environmental model; in order to cope with the complex and changeable urban traffic environment, the necessary dynamic data such as traffic lights and traffic flow are also added to the environmental model to complete the superposition of dynamic and static layers, so that the vehicle-road-cloud integrated system can be dynamically adjusted according to the actual situation of the road. In the vehicle-road-cloud integrated system, the application of the particle swarm optimization algorithm (PSO) can also improve traffic efficiency and optimize energy consumption.

[0164] In order to make those skilled in the art better understand, a specific example is used below to illustrate. Figure 3 , which is a flow chart of a path planning provided in an embodiment of the present invention, the process of generating the global optimal path (target path) may mainly include the following steps:

[0165] 301. Urban road environment modeling;

[0166] 302. Dynamic and static data fusion; initial path generation and multi-objective optimization (multi-objective fitness function) to obtain the global optimal path.

[0167] Reference Figure 4 , which is a schematic diagram of a global optimal path generation process provided in an embodiment of the present invention. Based on the vehicle-road-cloud integrated system, the global optimal path generation process may include:

[0168] In some embodiments of the present invention, 301, urban road environment modeling includes:

[0169] Obtain static and dynamic data collected through OSM (Open Source Map), RTK (Real-time Kinematic, real-time differential positioning) and roadside sensing equipment; static data may include but is not limited to the basic geometry (geometric features) and topology of the road, and then preprocess the static and dynamic data to remove unnecessary data or correct the data.

[0170] By integrating static and dynamic data, a dynamically adjustable urban road environment model is constructed, enabling intelligent and refined path planning. Specifically, open source maps and RTK technology are used to integrate high-precision open source maps (static data) and dynamic data to construct a high-precision urban road environment model (urban road environment model). The data stream processing framework of distributed data storage (Apache Kafka) is used to achieve real-time updating and storage of dynamic data, ensuring that the vehicle-road-cloud integrated system can obtain the latest dynamic data in real time. Dynamic and static data are stored in the PostgreSQL database, and the PostGIS plug-in can also be used to process geographic spatial information to ensure efficient data management and real-time access.

[0171] In some embodiments of the present invention, 302, fusion of dynamic and static data includes:

[0172] Initial path generation: Use the Dijkstra algorithm or the A* algorithm to generate an initial path by fusing static data (data in the static data table) and dynamic data (data in the dynamic data table). After the initial path is generated, you can also generate a variety of other initial paths based on the initial path through random perturbations.

[0173] Multi-Objective Optimization: Utilizing multi-objective optimization and the particle swarm optimization (MOPSO) algorithm, a multi-objective fitness function is constructed, combining preset objectives such as time and energy consumption. This achieves dual optimization of traffic efficiency and energy conservation. A multi-objective fitness function combining time and energy consumption is defined, assigning different dynamic weights to time and energy optimization to comprehensively evaluate the performance of routes. The MOPSO algorithm is used for route optimization, comprehensively considering dynamic data such as traffic flow, traffic light cycles, road events, and road conditions, which are key factors influencing efficiency and energy conservation. Routes are adjusted accordingly to avoid congested sections and improve traffic efficiency.

[0174] The global optimal path ultimately output by the embodiment of the present invention can be dynamically updated and optimized based on real-time dynamic data to achieve minimum energy consumption and shortest travel time, thereby providing high-quality path planning services for traffic participants.

[0175] Reference Figure 5 , is a flowchart of the steps of a path planning method provided in an embodiment of the present invention, such as Figure 5 As shown, the method may specifically include the following steps:

[0176] Step 501: Obtain static data and dynamic data of the road on which the vehicle is located in the cloud to generate a target path; the static data is used to represent fixed attribute information of the road on which the vehicle is located, and the dynamic data is used to represent real-time status information of the road and the vehicle;

[0177] Step 502: Dynamically adjust the vehicle's driving path based on the target path.

[0178] In a specific implementation, the path planning method of an embodiment of the present invention is implemented based on a vehicle-road-cloud integrated system. Specifically, the vehicle-side platform (vehicle-side) in the vehicle-road-cloud integrated system can obtain from the cloud (cloud control platform) the static data and dynamic data of the road on which the vehicle is located, and generate a target path based on the cloud control platform. The static data is used to characterize the fixed attribute information of the road on which the vehicle is located, and the dynamic data is used to characterize the real-time status information of the road and the vehicle. The cloud control platform can fuse the static data and the dynamic data to generate a target path and send it to the vehicle-side platform, so that the vehicle-side platform can plan the vehicle's driving path according to the target path to realize intelligent driving of the vehicle.

[0179] The embodiments of the present invention can integrate static data and dynamic data in the road in real time to generate a target path, and plan the vehicle's driving path according to the target path, thereby improving vehicle traffic efficiency and providing high-quality path planning services for traffic participants.

[0180] As for the above-mentioned path planning method embodiment, since it is basically similar to the path generation method embodiment, the description is relatively simple. For relevant details, please refer to the partial description of the path generation method embodiment.

[0181] It should be noted that for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required for the embodiments of the present invention.

[0182] Reference Figure 6 , is a structural block diagram of a path system provided in an embodiment of the present invention, such as Figure 6 As shown, the system may include a module cloud control platform 601, a vehicle-mounted platform 602, and a road-side platform 603. Specifically:

[0183] The vehicle-mounted platform and the road-side platform are used to collect static and dynamic data of the road where the vehicle is located.

[0184] A cloud control platform is used to obtain static data and dynamic data of the road where the vehicle is located; the static data is used to represent fixed attribute information of the road where the vehicle is located, and the dynamic data is used to represent real-time status information of the road and the vehicle; and a target path for the vehicle is generated based on the static data and the dynamic data.

[0185] In one embodiment of the present invention, the cloud control platform 601 is used to:

[0186] generating an initial path of the vehicle based on the static data and the dynamic data;

[0187] The initial path is adjusted according to a preset target to obtain a target path for the vehicle.

[0188] In one embodiment of the present invention, the cloud control platform 601 is used to:

[0189] Obtaining a target starting point, a target end point, and a road graph model of the vehicle; the road graph model is used to characterize connectivity between the roads;

[0190] Generate the initial path of the vehicle according to the static data, the dynamic data, the target starting point, the target end point and the road graph model

[0191] In one embodiment of the present invention, the road graph model includes nodes and edges of roads; the nodes are waypoints on the roads; the edges are roads between the waypoints; the waypoints include intersections of the roads, starting points of the roads, or end points of the roads; the cloud control platform 601 is used to:

[0192] Generating an initial path of the vehicle according to the static data, the dynamic data, the target starting point, the target end point, and a road graph theory model includes:

[0193] Determine the travel distance between the nodes where the edges exist in the road graph model according to the dynamic data and the static data;

[0194] Taking the node corresponding to the target starting point in the road graph model as the starting node;

[0195] Using the node corresponding to the target end point in the road graph model as the end point node;

[0196] An initial path of the vehicle is generated according to the travel distance, the starting node, and the ending node.

[0197] In one embodiment of the present invention, the static data includes at least the road length, and the dynamic data includes at least the average vehicle speed corresponding to each road, the traffic flow density corresponding to each road and / or the road section closure information corresponding to each road; the average vehicle speed corresponding to each road is adjusted according to the traffic flow density corresponding to the road.

[0198] In one embodiment of the present invention, the cloud control platform 601 is used to:

[0199] The travel distance between the nodes where the edge exists is determined based on the road length corresponding to the road between the nodes where the edge exists, the average vehicle speed, the traffic flow density and / or the preset maximum traffic flow density.

[0200] In one embodiment of the present invention, the cloud control platform 601 is used to:

[0201] When the traffic flow density corresponding to the road between the nodes where the edge exists is greater than a preset traffic flow density, the travel distance is adjusted according to a preset coefficient.

[0202] In one embodiment of the present invention, the cloud control platform 601 is used to:

[0203] When it is determined according to the road closure information that the road between the nodes where the edge exists is in a road closure state, the travel distance between the nodes where the edge exists is marked as infinite or impassable.

[0204] In one embodiment of the present invention, the cloud control platform 601 is used to:

[0205] When the sum of the travel distances between consecutive nodes from the starting node to the end node meets a preset distance condition, an initial path of the vehicle is generated based on the consecutive nodes between the starting node and the end node, and the starting node and the end node.

[0206] In one embodiment of the present invention, the cloud control platform 601 is used to:

[0207] When the sum of travel distances between consecutive nodes from the starting node to the ending node is shortest, an initial path of the vehicle is generated based on the consecutive nodes from the starting node to the ending node, and the starting node and the ending node.

[0208] In one embodiment of the present invention, the cloud control platform 601 is used to:

[0209] Randomly replacing at least one node in the initial path with another node in the road graph model to obtain a replacement path;

[0210] When it is determined according to the road graph theory model that there are edges between consecutive nodes in the replacement path, the replacement path is used as the initial path.

[0211] In one embodiment of the present invention, the cloud control platform 601 is used to:

[0212] updating at least one of the initial paths according to a preset speed update formula and a preset position update formula to obtain an updated path; wherein the speed update formula is used to control the initial path to determine a node corresponding to a target position in a road graph model according to an update trend and an update step size, and the position update formula is used to determine an updated path based on the node corresponding to the target position according to the speed update formula and the initial path;

[0213] The initial path and the updated path are adjusted according to a preset target to obtain a target path for the vehicle.

[0214] In one embodiment of the present invention, the cloud control platform 601 is used to:

[0215] Creating a multi-objective fitness function; the multi-objective fitness function is used to balance multiple preset objectives;

[0216] Calculating the fitness of the initial path and the updated path corresponding to the initial path according to the multi-objective fitness function;

[0217] Filtering a preferred path from the initial path and the updated path according to the fitness;

[0218] Taking the preferred path as the initial path, and returning to the step of updating at least one of the initial paths according to the speed update formula and the position update formula to obtain an updated path;

[0219] When a preset convergence condition is met, the preferred path whose fitness meets a preset screening condition is used as the target path of the vehicle.

[0220] In an embodiment of the present invention, the preset target includes at least energy consumption and time; the energy consumption and the time are generated according to the static data and the dynamic data.

[0221] In one embodiment of the present invention, the multi-objective fitness function includes the energy consumption and the dynamic weight coefficient corresponding to the energy consumption, as well as the time and the dynamic weight coefficient corresponding to the time; the dynamic weight coefficient is generated based on the dynamic data.

[0222] In embodiments of the present invention, when planning a vehicle's route, static and dynamic data about the road on which the vehicle is located is acquired. The static data represents fixed attributes of the road, while the dynamic data represents real-time status information about the road and vehicle. The target vehicle route is generated based on these static and dynamic data. This embodiment of the present invention integrates static and dynamic road data in real time to rationally plan vehicle routes, improving vehicle traffic efficiency and providing high-quality route planning services for traffic participants.

[0223] As for the above-mentioned system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0224] It should be noted that the embodiments of the present invention may involve the use of user data. In actual applications, user-specific personal data may be used in the scheme described herein within the scope permitted by applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0225] The embodiment of the present invention further provides an electronic device, such as Figure 7 As shown, it includes a processor 701, a communication interface 702, a memory 703 and a communication bus 704, wherein the processor 701, the communication interface 702, and the memory 703 communicate with each other through the communication bus 704.

[0226] Memory 703, used for storing computer programs;

[0227] The processor 701 is configured to implement any one of the path generation methods and / or path planning methods described in the above embodiments when executing the program stored in the memory 703 .

[0228] The communication bus mentioned in the terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0229] The communication interface is used for communication between the above terminal and other devices.

[0230] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0231] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0232] In another embodiment provided by the present invention, a computer-readable storage medium is also provided, which stores instructions. When the computer-readable storage medium is run on a computer, it enables the computer to execute the path generation method described in any of the above embodiments and / or execute the path planning method described in any of the above embodiments.

[0233] In another embodiment provided by the present invention, a computer program product containing instructions is also provided. When the computer is run on a computer, the computer executes the path generation method described in any one of the above embodiments, and / or executes the path planning method described in any one of the above embodiments.

[0234] In another embodiment of the present invention, a vehicle is provided, which implements any of the above-mentioned path generation methods and / or the above-mentioned path planning methods.

[0235] In the above embodiments, they can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, they 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. When the computer program instructions are loaded and executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are 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. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. 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 includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0236] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0237] Each embodiment in this specification is described in a related manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are described briefly because they are generally similar to the method embodiments. For related portions, reference can be made to the description of the method embodiments.

[0238] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the scope of protection of the present invention.

Claims

1. A path generation method, characterized in that: The method comprises: Obtaining static data and dynamic data of the road on which the vehicle is located; the static data is used to represent fixed attribute information of the road on which the vehicle is located, and the dynamic data is used to represent real-time status information of the road and the vehicle; A target path of the vehicle is generated based on the static data and the dynamic data.

2. The method according to claim 1, characterized in that Generating a target path of the vehicle according to the static data and the dynamic data includes: generating an initial path of the vehicle based on the static data and the dynamic data; The initial path is adjusted according to a preset target to obtain a target path for the vehicle.

3. The method according to claim 2, characterized in that Generating an initial path of the vehicle according to the static data and the dynamic data, comprising: Obtaining a target starting point, a target end point, and a road graph model of the vehicle; the road graph model is used to characterize connectivity between the roads; An initial path of the vehicle is generated according to the static data, the dynamic data, the target starting point, the target end point, and a road graph theory model.

4. The method according to claim 3, characterized in that The road graph model includes nodes and edges of roads; the nodes are waypoints on the roads; the edges are roads between the waypoints; the waypoints include intersections of the roads, starting points of the roads, or end points of the roads; Generating an initial path of the vehicle according to the static data, the dynamic data, the target starting point, the target end point, and a road graph theory model includes: Determine the travel distance between the nodes where the edges exist in the road graph model according to the dynamic data and the static data; Taking the node corresponding to the target starting point in the road graph model as the starting node; Using the node corresponding to the target end point in the road graph model as the end point node; An initial path of the vehicle is generated according to the travel distance, the starting node, and the ending node.

5. The method according to claim 4, characterized in that The static data includes at least the road length, and the dynamic data includes at least the average vehicle speed corresponding to each road, the traffic flow density corresponding to each road and / or the road section closure information corresponding to each road; the average vehicle speed corresponding to each road is adjusted according to the traffic flow density corresponding to the road.

6. The method according to claim 5, characterized in that Determining the travel distance between the nodes having the edges in the road graph model according to the dynamic data and the static data includes: The travel distance between the nodes where the edge exists is determined based on the road length corresponding to the road between the nodes where the edge exists, the average vehicle speed, the traffic flow density and / or the preset maximum traffic flow density.

7. The method according to claim 6, characterized in that The method further comprises: When the traffic flow density corresponding to the road between the nodes where the edge exists is greater than a preset traffic flow density, the travel distance is adjusted according to a preset coefficient.

8. The method according to any one of claims 4 to 7, characterized in that: Determining the travel distance between the nodes having the edges in the road graph model according to the dynamic data and the static data includes: When it is determined according to the road closure information that the road between the nodes where the edge exists is in a road closure state, the travel distance between the nodes where the edge exists is marked as infinite or impassable.

9. The method according to claim 4, characterized in that Generating an initial path of the vehicle according to the travel distance, the starting node, and the ending node includes: When the travel distance between the consecutive nodes from the starting node to the end node meets the preset distance condition, the initial path of the vehicle is generated according to the consecutive nodes between the starting node and the end node, and the starting node and the end node.

10. The method according to claim 9, characterized in that When the sum of travel distances between consecutive nodes from the starting node to the ending node meets a preset distance condition, generating an initial path for the vehicle based on the consecutive nodes between the starting node and the ending node, and the starting node and the ending node, includes: When the sum of travel distances between consecutive nodes from the starting node to the ending node is shortest, an initial path of the vehicle is generated based on the consecutive nodes from the starting node to the ending node, and the starting node and the ending node.

11. The method according to claim 3, characterized in that The method further comprises: Randomly replacing at least one node in the initial path with another node in the road graph model to obtain a replacement path; When it is determined according to the road graph theory model that there are edges between consecutive nodes in the replacement path, the replacement path is used as the initial path.

12. The method according to claim 2 or 11, characterized in that Adjusting the initial path according to a preset target to obtain a target path for the vehicle includes: updating at least one of the initial paths according to a preset speed update formula and a preset position update formula to obtain an updated path; wherein the speed update formula is used to control the initial path to determine a node corresponding to a target position in a road graph model according to an update trend and an update step size, and the position update formula is used to determine an updated path based on the node corresponding to the target position in the speed update formula and the initial path; The initial path and the updated path are adjusted according to a preset target to obtain a target path for the vehicle.

13. The method according to claim 12, characterized in that Adjusting the initial path and the updated path according to a preset target to obtain a target path for the vehicle includes: Creating a multi-objective fitness function; the multi-objective fitness function is used to balance multiple preset objectives; Calculating the fitness of the initial path and the updated path corresponding to the initial path according to the multi-objective fitness function; Filtering a preferred path from the initial path and the updated path according to the fitness; Taking the preferred path as the initial path, and returning to the step of updating at least one of the initial paths according to the speed update formula and the position update formula to obtain an updated path; When a preset convergence condition is met, the preferred path whose fitness meets a preset screening condition is used as the target path of the vehicle.

14. The method according to any one of claims 2 to 13, characterized in that: The preset target includes at least energy consumption and time; The energy consumption and the time are generated according to the static data and the dynamic data.

15. The method according to claim 14, characterized in that The multi-objective fitness function includes the energy consumption and the dynamic weight coefficient corresponding to the energy consumption, and the time and the dynamic weight coefficient corresponding to the time; The dynamic weight coefficient is generated according to the dynamic data.

16. A path planning method, characterized in that: The method comprises: Obtaining static data and dynamic data of the road on which the vehicle is located in the cloud to generate a target path; the static data is used to represent fixed attribute information of the road on which the vehicle is located, and the dynamic data is used to represent real-time status information of the road and the vehicle; The driving path of the vehicle is dynamically adjusted based on the target path.

17. A path system, characterized in that: The system includes a cloud control platform, a vehicle-mounted platform and a road-side platform; The vehicle-mounted platform and the road-side platform are used to collect static data and dynamic data of the road where the vehicle is located; A cloud control platform is used to obtain static data and dynamic data of the road where the vehicle is located; the static data is used to represent fixed attribute information of the road where the vehicle is located, and the dynamic data is used to represent real-time status information of the road and the vehicle; and a target path for the vehicle is generated based on the static data and the dynamic data.

18. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; A processor, configured to implement the method steps of any one of claims 1 to 15 and / or the method steps of claim 16 when executing a program stored in a memory.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 15 is implemented, and / or the method steps according to claim 16 are implemented.

20. A vehicle, characterized in that: The vehicle implements the method according to any one of claims 1 to 15 and / or implements the method steps according to claim 16.

21. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 15 is implemented, and / or the method steps according to claim 16 are implemented.

Images