Path planning method and device, computing equipment and storage medium
Through the historical travel trajectory and clustering algorithm of terminal equipment, path planning is carried out independently of road network information, solving the problem of unreasonable path planning in navigation technology, improving the efficiency and rationality of path planning, and reducing costs.
Patent Information
- Application Number
- CN202411341952.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-24
- Publication Date
- 2024-12-13
AI Technical Summary
In the existing navigation technology, path planning relies heavily on road network information, resulting in unreasonable path planning when road conditions change, and data collection costs and low efficiency completed by multiple companies.
By obtaining the historical travel trajectory of the terminal device, using the clustering algorithm to cluster to form a reference travel trajectory cluster and representative path, path planning is performed independently of the road network information, and device identification is sent to determine the target planning path.
It reduces the dependence of path planning on road network information, improves the rationality and efficiency of path planning, reduces communication costs, and ensures that reasonable paths can still be planned when road network information is not updated.
Smart Images
Figure CN119124206A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of navigation technology, and in particular to a path planning method, device, computing equipment and storage medium. Background Art
[0002] With the popularization of vehicles and the development of navigation technology, navigation has become an indispensable part of travel planning. Navigation is the way to guide a terminal device from one point of the planned path to another point, so path planning is the top priority of navigation. Among them, terminal devices include smartphones, smart watches and in-vehicle devices.
[0003] In the related art, a route is planned for a terminal device by combining the starting point, end point and road network information sent by the terminal device. However, the update cycle of the road network information is relatively long and requires cooperation among multiple companies. Therefore, when the road conditions change (such as newly developed roads or abandoned roads) and the road network information has not been updated, the planned route does not match the actual road conditions, which reduces the rationality of the route. Summary of the invention
[0004] Based on the above problems, the present application provides a path planning method, apparatus, computing device and storage medium to get rid of the dependence on road network information in the path planning process and improve the rationality of path planning.
[0005] The embodiments of the present application disclose the following technical solutions:
[0006] In a first aspect, an embodiment of the present application provides a path planning method, including:
[0007] Acquire path planning requirement information of the terminal device; wherein the path planning requirement information includes a target starting point area corresponding to the target starting point, a target end point area corresponding to the target path end point, and a device identifier of the terminal device;
[0008] Determine a target planning path according to the target starting area, the target end area and the historical travel trajectory of each of the terminal devices;
[0009] The target planned path is sent according to the device identification.
[0010] Optionally, determining the target planning path according to the target starting area, the target end area and the historical travel trajectory of each of the terminal devices specifically includes:
[0011] Determining a reference travel trajectory from the historical travel trajectory of each of the terminal devices according to the target starting area and the target end area;
[0012] Clustering the reference travel trajectories according to a clustering algorithm to obtain a plurality of reference travel trajectory clusters and a reference path representing each of the reference travel trajectory clusters; wherein each of the reference travel trajectory clusters includes a plurality of the reference travel trajectories;
[0013] The target planning path is determined from the reference path.
[0014] Optionally, clustering the reference travel trajectory according to a clustering algorithm to obtain a plurality of reference travel trajectory clusters and a reference path representing each of the reference travel trajectory clusters specifically includes:
[0015] Acquiring the track distance between the reference travel tracks;
[0016] Clustering the reference travel trajectories according to the trajectory distances according to a first clustering algorithm, and dividing the reference travel trajectories whose difference between the trajectory distances is less than or equal to a first preset threshold into one of the reference travel trajectory clusters;
[0017] The reference travel trajectory clusters are clustered according to a second clustering algorithm to obtain reference paths representing the reference travel trajectory clusters.
[0018] Optionally, the determining the target planning path from the reference path specifically includes:
[0019] Obtaining a reference starting point and a reference end point of each reference path;
[0020] When the distance between the reference starting point and the target starting point is less than or equal to a preset second threshold, and the distance between the reference end point and the target end point is less than or equal to the preset second threshold, the corresponding reference path is used as the target planning path.
[0021] Optionally, the distance between the reference starting point and the target starting point of the plurality of reference paths is less than or equal to a preset second threshold, and the distance between the corresponding reference end point and the target end point is less than or equal to the preset second threshold, and the method further includes:
[0022] The target planning path is determined according to the number of travel times and the time taken to travel corresponding to the multiple reference paths.
[0023] Optionally, the method further comprises:
[0024] When the terminal device identified by the device moves along the target planned path, the positioning information of the terminal device is obtained at regular intervals to form the historical moving trajectory.
[0025] Optionally, the planned path requirement information further includes the type of the terminal device, and determining the reference travel trajectory from the historical travel trajectory of each of the terminal devices according to the target starting area and the target end area specifically includes:
[0026] According to the target starting area, the target ending area and the type of the terminal device, a reference travel trajectory is determined from the historical travel trajectory of each of the terminal devices.
[0027] In a second aspect, an embodiment of the present application provides a path planning device, the device comprising: an acquisition module, a determination module and a sending module;
[0028] The acquisition module is used to acquire the path planning requirement information of the terminal device; wherein the path planning requirement information includes a target starting point area corresponding to the target starting point, a target end point area corresponding to the target end point, and a device identifier of the terminal device;
[0029] The determination module is used to determine the target planning path according to the target starting area, the target end area and the historical travel trajectory of each of the terminal devices;
[0030] The sending module is used to send the target planned path according to the device identifier.
[0031] Optionally, the determination module includes a first determination unit, an obtaining unit and a second determination unit;
[0032] The first determining unit is used to determine a reference travel trajectory from the historical travel trajectory of each of the terminal devices according to the target starting area and the target end area;
[0033] The obtaining unit is used to cluster the reference travel trajectories according to a clustering algorithm to obtain a plurality of reference travel trajectory clusters and a reference path representing each of the reference travel trajectory clusters; wherein each of the reference travel trajectory clusters includes a plurality of the reference travel trajectories;
[0034] The second determining unit is used to determine the target planning path from the reference path.
[0035] Optionally, the obtaining unit is specifically used to obtain the trajectory distance between each of the reference travel trajectories; cluster each of the reference travel trajectories according to the trajectory distance according to a first clustering algorithm, and divide the reference travel trajectories whose difference between the trajectory distances is less than or equal to a first preset threshold into a reference travel trajectory cluster; cluster each of the reference travel trajectory clusters according to a second clustering algorithm to obtain a reference path representing each of the reference travel trajectory clusters.
[0036] Optionally, the second determination unit is specifically used to obtain a reference starting point and a reference end point of each of the reference paths; when the distance between the reference starting point and the target starting point is less than or equal to a preset second threshold, and the distance between the reference end point and the target end point is less than or equal to the preset second threshold, the corresponding reference path is used as the target planning path.
[0037] Optionally, the second determination unit is further used to determine the target planned path according to the number of travels and the time taken to travel each of the reference paths.
[0038] Optionally, the acquisition module is further used to periodically acquire the positioning information of the terminal device when the terminal device identified by the device moves along the target planned path, so as to form the historical travel trajectory.
[0039] Optionally, the first determining unit is specifically configured to determine a reference travel trajectory from historical travel trajectories of each of the terminal devices according to the target starting area, the target ending area and the type of the terminal device.
[0040] In a third aspect, an embodiment of the present application provides a computing device, including:
[0041] at least one memory for storing a program;
[0042] At least one processor is used to execute the program stored in the memory; wherein, when the program stored in the memory is executed, the processor is used to execute the path planning method as described in any of the aforementioned embodiments.
[0043] In a fourth aspect, an embodiment of the present application provides a storage medium, in which instructions are stored. When the instructions are executed on a computing device, the computing device executes the path planning method as described in any of the aforementioned embodiments.
[0044] Compared with the prior art, this application has the following beneficial effects:
[0045] The path planning method described in the embodiment of the present application first obtains the path planning requirement information of the terminal device; wherein the path planning requirement information includes the target starting point area corresponding to the target starting point, the target end point area corresponding to the target path end point, and the device identification of the terminal device; then, the target planning path is determined according to the target starting point area, the target end point area, and the historical travel trajectory of each terminal device; finally, the target planning path is sent according to the device identification. In the embodiment of the present application, the path is planned using the historical travel trajectory of the terminal device, that is, the path of the current terminal device is planned using its own previous travel trajectory and the past travel trajectory of others, thereby reducing the dependence of the path planning on the road network information, and even if the road network information is not updated, a reasonable path can be planned. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0047] Figure 1 A schematic diagram of an application scenario of path planning provided in an embodiment of the present application;
[0048] Figure 2 A flow chart of a path planning method provided in an embodiment of the present application;
[0049] Figure 3 A schematic diagram of a path provided in an embodiment of the present application;
[0050] Figure 4 A flowchart of another path planning method provided in an embodiment of the present application;
[0051] Figure 5 A schematic diagram of determining a reference travel trajectory cluster provided in an embodiment of the present application;
[0052] Figure 6 A schematic diagram of determining a reference path provided in an embodiment of the present application;
[0053] Figure 7 A schematic diagram of determining a target planning path provided in an embodiment of the present application;
[0054] Figure 8 A schematic diagram of the structure of a path planning device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0055] As described above, current route planning is heavily dependent on road network information. When road conditions change (such as newly developed roads or abandoned roads) and the road network information has not been updated, the planned route does not match the actual road conditions, resulting in an unreasonable planned route.
[0056] In order to solve the above technical problems, the present application embodiment provides a path planning method. When the terminal device is a vehicle-mounted device, its application scenario diagram is as follows: Figure 1 As shown. Figure 1 In the example, the computing device 101 receives a route planning request sent by the terminal device 102, where the starting point is A and the end point is B; the computing device 101 determines the final route LINE2, which is more reasonable, from the historical travel trajectory (including the route LINE1 included in the road network and the route LINE2 not included in the road network but traveled by the vehicle 1) according to the starting point A and the end point B, and sends LINE2 to the terminal device 102. Therefore, the embodiment of the present application can plan a reasonable route for the terminal device when the road network information is not updated in time.
[0057] The embodiment of the present application plans the route based on the route traveled by the driver (the driver of the vehicle and the driver of other vehicles), which improves the driver's recognition of the planned route. In addition, compared with the related art in which data collection, DB compilation, route planning and route description are completed by multiple companies in a collaborative manner, which is costly and relatively inefficient, the embodiment of the present application can reduce communication costs and improve efficiency.
[0058] It is understandable that the computing device 101 can be a personal computer (PC), a physical server, a cloud server, or a virtual device (such as a virtual machine), etc., but is not limited thereto.
[0059] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0060] See also Figure 2 , which is a flow chart of a path planning method provided in an embodiment of the present application.
[0061] like Figure 2 As shown, the method includes:
[0062] S201: Acquire path planning requirement information of a terminal device; wherein the path planning requirement information includes a target starting point area corresponding to a target starting point, a target end point area corresponding to a target path end point, and a device identifier of the terminal device.
[0063] It should be understood that the terminal device described in the embodiments of the present application may be a vehicle-mounted device, or a mobile terminal device such as a smart phone or a smart watch.
[0064] As an example, when the terminal device is a vehicle-mounted device, the device identifier may be a vehicle identification number (VIN). The VIN code includes letters and numbers corresponding to information such as the manufacturer, year, model, body type and code, engine code, and assembly location of the vehicle, and is the key to identifying specific vehicle information.
[0065] As an example, when the terminal device is a mobile terminal such as a smart phone or a smart watch, the device identifier may be any one of an International Mobile Equipment Identity (IMEI), a Mobile Equipment Identifier (MEID), a Unique Device Identifier (UDID), and a Universally Unique Identifier (UUID). It should be understood that the aforementioned device identifiers are merely exemplary, and the embodiments of the present application do not specifically limit the device identifiers.
[0066] The target starting point and target end point in the embodiment of the present application can be obtained by inputting the terminal device, or by positioning. The starting point area can be a circular area with the coordinates of the target starting point as the center and a radius of m, and the end point area can be a circular area with the coordinates of the target end point as the center and a radius of n. It should be understood that the circular area described in the embodiment of the present application is only exemplary, and the embodiment of the present application does not limit other area division methods, such as rectangles and ellipses.
[0067] It should be understood that the method described in the embodiments of the present application does not rely on road network information, so the use of starting point areas and end point areas can provide more path options, thereby making the planned route more reasonable.
[0068] S202: Determine a target planning path according to a target starting area, a target end area, and a historical travel trajectory of each terminal device; the historical travel trajectory includes the historical travel trajectory of all terminal devices.
[0069] The target starting point area may be a surrounding area including the target starting point coordinates, and the target ending point area may be a surrounding area including the ending point coordinates.
[0070] For example, if the target starting point coordinate is P, the target starting point area is a circular area with P as the center and r as the radius; if the target starting point coordinate is Q, the target starting point area is a circular area with Q as the center and r as the radius. It should be understood that the radius r described in the embodiment of the present application can be set or changed according to the needs of the user.
[0071] It should be understood that the historical travel trajectory is a set of coordinate points. When the set includes the coordinates of the target starting area and the coordinates of the target end area, the corresponding historical travel trajectory can be regarded as an available path and the target planning path can be determined from the available paths.
[0072] The historical trajectory can be stored in a corresponding storage area or database according to different terminal devices. For example, the historical trajectory of the vehicle is stored in database A, and the historical trajectory of a mobile terminal such as a mobile phone or a watch is stored in database B. When the corresponding historical trajectory needs to be used, the data is directly obtained from the corresponding database, thereby improving the efficiency of determining the target planning path with data.
[0073] In a possible implementation, when the terminal device is a vehicle-mounted device, the historical travel trajectory includes the historical travel trajectory of the vehicle and the historical travel trajectory of other vehicles (other vehicles that use the same path planning software or system as the vehicle described in the embodiment of the present application), that is, the trajectory that the vehicle has traveled. During the driving process, the vehicle uploads the positioning information of the vehicle to the computing device for storage at intervals of a first preset time. After the vehicle has traveled a section of the path, the set of positioning information stored by the computing device can constitute the historical travel trajectory.
[0074] As an example, Figure 3 As shown, region X plans and builds Line 2. After Line 2 is built, it is not included in the road network, that is, Line 2 does not exist for the road network, and vehicles must pass through Line 1 to get from point A to point B. It should be understood that local vehicles in region X are familiar with the local road conditions and know that Line 2 is drivable. They go from point A to point B via Line 2, and upload the vehicle's location information to the computing device during the vehicle's driving process, so that Line 2 can be planned for subsequent vehicles when they need to go from point A to point B.
[0075] In a possible implementation, when the terminal device is a mobile terminal, the historical movement trajectory includes the historical movement trajectory of the terminal and the historical movement trajectory of other mobile devices. During the movement of the terminal device, the terminal device uploads the positioning information of the terminal device to the computing device for storage at intervals of a second preset time. After the terminal device moves a certain distance, the positioning information stored by the computing device can constitute the historical movement trajectory. It should be understood that in actual applications, the second preset time is greater than the first preset time.
[0076] In the embodiment of the present application, full use is made of the historical travel trajectory of the vehicle or mobile terminal, and a path is planned for the vehicle or mobile terminal based on this, thereby reducing the dependence of current navigation technology on road network information. Even when the road network information is not updated in a timely manner, a reasonable route can still be planned for the terminal device.
[0077] In addition, it should be understood that the historical travel trajectory described in the embodiments of the present application can be refreshed regularly to ensure the reliability of the historical travel trajectory in terms of timeliness and further improve the rationality of the planned path.
[0078] S203: Send the target planning path according to the device identification.
[0079] In an embodiment of the present application, the path is planned using the historical travel trajectory of the terminal device, that is, using one's own previous historical travel trajectory and referring to the historical travel trajectory of others, the dependence of path planning on road network information is reduced, and a reasonable path can be planned even if the road network information is not updated.
[0080] Since the embodiment of the present application plans the route based on the route traveled by the driver (the driver of the vehicle and the driver of other vehicles), the driver's recognition of the planned route is improved. In addition, compared with the related art in which data collection, DB compilation, route planning and route description are completed by multiple companies in a collaborative manner, which is costly and relatively inefficient, the embodiment of the present application can reduce communication costs and improve efficiency.
[0081] Since multiple available paths can be determined based on the target starting area, the target terminal area, and the historical travel trajectory, the following embodiments of the present application will focus on describing how to determine the target planning path from the multiple available paths.
[0082] See also Figure 4 , which is a flow chart of another path planning method provided in an embodiment of the present application.
[0083] like Figure 4 As shown, the method includes:
[0084] S401: Acquire path planning requirement information of a terminal device; wherein the path planning requirement information includes a target starting point area corresponding to a target starting point, a target end point area corresponding to a target path end point, and a device identifier of the terminal device.
[0085] S402: Determine a reference travel trajectory from the historical travel trajectory of each terminal device according to the target starting area and the target end area.
[0086] According to the above, the historical travel trajectories corresponding to different terminal devices are stored in different storage areas or databases. For example, the historical travel trajectories corresponding to the vehicle-mounted terminal are stored in database A, and the historical travel trajectories corresponding to the mobile terminal are stored in database B.
[0087] In an optional embodiment, when the terminal device is a vehicle-mounted terminal, the computing device determines the historical travel trajectory that satisfies the target starting area and target terminal area from database A based on the target starting area and target terminal area sent by the vehicle-mounted terminal, and uses it as a reference travel trajectory.
[0088] S403: Clustering the reference travel trajectories according to a clustering algorithm to obtain a plurality of reference travel trajectory clusters and a reference path representing each reference travel trajectory cluster; wherein each reference travel trajectory cluster includes a plurality of reference travel trajectories.
[0089] The present application embodiment will describe S403 through the following two steps:
[0090] Step 1: cluster the reference travel trajectories to obtain multiple reference travel trajectory clusters.
[0091] The essence of the trajectory is a sequence composed of a number of discretely sampled GPS points, so the density-based clustering algorithm is used to cluster the trajectory in the embodiment of this solution.
[0092] For example, the embodiment of the present application adopts a density-based spatial clustering of applications with noise (DBSCAN), and clusters the trajectories by replacing the point-to-point distance in DBSCAN with the trajectory distance.
[0093] As an example, two reference trajectories A = {a1, a2, ..., an} and reference trajectories B = {b1, b2, ..., bn}, both of length n, then the distance between the reference trajectories (the minimum point-by-point Euclidean distance of the two reference trajectories in positive and reverse order) can be defined as:
[0094]
[0095] The distance between every two reference travel trajectories can be determined by the above formula, and two reference travel trajectories whose distance is less than a preset first threshold value are divided into the same reference travel trajectory cluster.
[0096] As an example, the reference travel trajectory includes a reference travel trajectory A, a reference travel trajectory B, a reference travel trajectory C, a reference travel trajectory D, a reference travel trajectory E, a reference travel trajectory F, a reference travel trajectory G, a reference travel trajectory H, and a reference travel trajectory I. Among them, if the distance between the reference travel trajectory A and the reference travel trajectory B is less than the preset threshold, and the distance between the reference travel trajectory A and the reference travel trajectory C is less than the preset threshold, then the reference travel trajectory A, the reference travel trajectory B and the reference travel trajectory C are divided into a reference travel trajectory cluster A; if the distance between the reference travel trajectory D and the reference travel trajectory E is less than the preset threshold, and the distance between the reference travel trajectory D and the reference travel trajectory F is less than the preset threshold, then the reference travel trajectory D, the reference travel trajectory E and the reference travel trajectory F are divided into a reference travel trajectory cluster B; if the distance between the reference travel trajectory G and the reference travel trajectory H is less than the preset threshold, and the distance between the reference travel trajectory G and the reference travel trajectory I is less than the preset threshold, then the reference travel trajectory G, the reference travel trajectory H and the reference travel trajectory I are divided into a reference travel trajectory cluster C, as shown in the following example. Figure 5 shown.
[0097] Step 2: determining a reference path representing the reference trajectory cluster from among the reference trajectory clusters.
[0098] In the embodiment of the present application, the reference path representing the reference travel cluster may be determined by clustering. The clustering method may be any one of the following clustering methods:
[0099] (1) K-means clustering algorithm (K-Means), in which the representative data of the reference trajectory cluster is usually the centroid of the cluster, that is, the average value of all points in the cluster. In the K-means algorithm, first, k initial centroids are randomly selected as cluster centers; then, the centroids are iteratively assigned and updated according to the distance from each data point to the cluster center until the centroid no longer changes significantly and the final centroid is used as the representative point.
[0100] Exemplarily, for each reference trajectory cluster, the center of the reference trajectory cluster or the trajectory closest to the center of the reference trajectory cluster may be regarded as a representative path of the cluster.
[0101] (2) Hierarchical clustering: Hierarchical clustering does not directly specify the representative data of the cluster, but builds a hierarchical structure between data points. In the bottom-up agglomerative method, the centroid or median of the reference trajectory cluster after each layer is merged can be selected as the representative data; in the top-down splitting method, the data points are usually split into different clusters based on a certain splitting criterion, but the representative data is also not directly specified.
[0102] Exemplarily, for each reference trajectory cluster, a certain central trajectory of the most common trajectories in the reference trajectory cluster is selected as the representative path of the reference trajectory cluster, for example, the mean trajectory or the median trajectory of all trajectories.
[0103] (3) DBSCAN clustering,In DBSCAN, core points (i.e., points with enough neighbors in their neighborhood) can be regarded as,representative data of the reference trajectory cluster, because the core points define the,boundaries and shapes of the clusters.
[0104] Exemplarily, for each reference traveling trajectory cluster, any one of the trajectories with the highest density, the median trajectory, and the average trajectory in the reference traveling trajectory cluster may be selected as the representative trajectory of the reference traveling trajectory cluster.
[0105] (4) Spectral clustering: Spectral clustering uses the similarity matrix of data for clustering and is usually applicable to data sets with complex shapes. The representative data of the reference trajectory cluster may be determined based on the eigenvector or cluster center obtained by the spectral clustering algorithm, but the specific method of selecting representative data may vary depending on the algorithm implementation.
[0106] For example, for each reference travel trajectory cluster, the representative trajectory of the reference travel trajectory cluster can be generated by calculating the mean trajectory, median trajectory of the trajectories within the cluster, or by performing some form of averaging or merging on the trajectories within the cluster. (5) Gaussian Mixture Model (GMM): GMM is a clustering method based on a probability model, which assumes that the data is a mixture of multiple Gaussian distributions. In GMM, the center (mean) of each Gaussian distribution can be regarded as the representative data of the reference travel trajectory cluster because it describes the distribution center of the data.
[0107] Exemplarily, for each reference travel trajectory cluster, a mean trajectory or a median trajectory of all trajectories in the cluster may be calculated as a representative trajectory of the reference travel trajectory cluster.
[0108] (6) Fuzzy C-means Algorithm (FCMA): FCMA is similar to K-means clustering, but allows data points to belong to multiple clusters, each with a certain degree of membership or probability. In FCMA, the representative data of the reference trajectory cluster may be a weighted centroid, where the weight is determined by the degree of membership of the data point to each reference trajectory cluster.
[0109] Exemplarily, for each reference travel trajectory cluster, FCMA provides the membership of each trajectory point to the reference travel trajectory cluster, and the trajectory with the highest membership can be selected as the representative trajectory of the cluster; or, a weighted trajectory is calculated based on the membership of the trajectory point to the reference travel trajectory cluster; or, the trajectory with the highest total membership in the reference travel trajectory cluster is selected as the representative path.
[0110] It should be understood that the aforementioned clustering method is merely exemplary, and the embodiments of the present application do not limit the specific clustering method to obtain the representative trajectory of the reference travel trajectory cluster, that is, the reference path.
[0111] For ease of understanding, the present application embodiment provides a schematic diagram of a reference path, such as Figure 6 As shown. Figure 6 , the representative trajectory of the reference trajectory cluster A is Line1, the representative trajectory of the reference trajectory cluster B is Line2, and the representative trajectory of the reference trajectory cluster is Line3.
[0112] S404: Determine a target planning path from the reference path.
[0113] In a possible implementation, the target planning path is determined according to the distance between the starting point of the reference path and the starting point of the target, and the distance between the end point of the reference path and the end point of the target.
[0114] As an example, the present application embodiment provides a schematic diagram for determining a target planning path, such as Figure 7 As shown. Figure 7 In the example, the distances of Line2 and Line3 from the target starting point meet the requirements, that is, they are less than or equal to the preset second threshold; the distances of Line2 and Line3 from the target end point meet the requirements, that is, they are less than or equal to the preset second threshold. Therefore, Line2 can be sent to the terminal device as the target planning path.
[0115] It should be understood that the target planning path may not be uniquely determined based on the distance between the reference path starting point and the target starting point, and the distance between the reference path end point and the target end point. Therefore, when multiple target planning paths are determined based on the distance between the reference path starting point and the target starting point, and the distance between the reference path end point and the target end point, they can be determined based on factors such as the number of walks or the time taken.
[0116] As an example, when the distances between Line1, Line2 and Line3 and the target starting point meet the requirements, and the distances between Line1, Line2 and Line3 and the target end point also meet the requirements, if Line2 has the largest number of walks and the shortest time, Line2 will be used as the final target planning path.
[0117] In addition, factors such as the number of walks and the duration can be used to determine the unique target planning path through weighted averaging.
[0118] Since the reference travel trajectories are clustered according to the clustering algorithm, multiple reference travel trajectory clusters and reference paths representing the reference travel trajectory clusters are obtained, which have the following advantages: First, from the perspective of data compression and simplification, the representative data is usually a concise expression of the data in the cluster. It uses less information to represent the characteristics of the entire cluster, which helps to reduce data storage requirements and computational complexity; second, from the perspective of data processing and analysis, the entire cluster can be more conveniently analyzed and operated without processing every data point in the cluster; third, from the perspective of data interpretability, representative data usually have higher interpretability because they represent the "center" or "average" state of the entire cluster, which makes it easier to understand the characteristics of the cluster and data distribution.
[0119] In addition, the embodiment of the present application further provides a path planning device, which includes: an acquisition module 801, a determination module 802 and a sending module 803;
[0120] The acquisition module 801 is used to acquire the path planning requirement information of the terminal device; wherein the path planning requirement information includes the target starting point area corresponding to the target starting point, the target end point area corresponding to the target end point, and the device identification of the terminal device;
[0121] The determination module 802 is used to determine the target planning path according to the target starting area, the target end area and the historical travel trajectory; the historical travel trajectory includes the historical travel trajectory of all terminal devices;
[0122] The sending module 803 is used to send the target planned path according to the device identification.
[0123] Optionally, the determination module 802 includes a first determination unit, an obtaining unit, and a second determination unit;
[0124] A first determining unit is used to determine a reference travel trajectory from historical travel trajectories according to a target starting area and a target end area;
[0125] An obtaining unit, used for clustering the reference travel trajectory according to a clustering algorithm to obtain a plurality of reference travel trajectory clusters and a reference path representing each reference travel trajectory cluster;
[0126] The second determining unit is used to determine the target planning path from the reference path.
[0127] Optionally, the obtaining unit is specifically used to obtain the trajectory distance between each reference travel trajectory; cluster the trajectory distances according to a first clustering algorithm, and take the reference travel trajectories whose trajectory distance differences are less than or equal to a first preset threshold as a reference travel trajectory cluster; cluster the reference travel trajectory clusters according to a second clustering algorithm to obtain reference paths representing each reference travel trajectory cluster.
[0128] Optionally, the second determination unit is specifically used to obtain the reference starting point and reference end point of each reference path; the distance between the reference starting point and the target starting point is less than or equal to a preset second threshold, and the distance between the reference end point and the target end point is less than or equal to the preset second threshold, and the corresponding reference path is used as the target planning path.
[0129] Optionally, the second determination unit is further used to determine the target planned path according to the number of travels and / or the time taken for each reference path.
[0130] Optionally, the acquisition module 801 is further used to periodically acquire the positioning information of the terminal device to form a historical travel trajectory when the terminal device identified by the device moves along the target planned path.
[0131] Optionally, the first determining unit is specifically configured to determine a reference travel trajectory from historical travel trajectories according to a target starting area, a target ending area, and a type of terminal device.
[0132] In addition, an embodiment of the present application provides a computing device and a storage medium, wherein the computing device includes:
[0133] at least one memory for storing a program;
[0134] At least one processor, configured to execute a program stored in the memory; wherein, when the program stored in the memory is executed, the processor is configured to execute the path planning method according to any of the foregoing embodiments;
[0135] The storage medium stores instructions, and when the instructions are executed on the computing device, the computing device executes the path planning method as described in any of the aforementioned embodiments.
[0136] In an embodiment of the present application, the path is planned using the historical travel trajectory of the terminal device, that is, using one's own previous historical travel trajectory and referring to the historical travel trajectory of others, the dependence of path planning on road network information is reduced, and a reasonable path can be planned even if the road network information is not updated.
[0137] It should be noted that each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and equipment embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments. The device and equipment embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components indicated as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. A person of ordinary skill in the art can understand and implement it without paying creative labor.
[0138] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A path planning method, characterized in that: The method comprises: Acquire path planning requirement information of the terminal device; wherein the path planning requirement information includes a target starting point area corresponding to the target starting point, a target end point area corresponding to the target end point, and a device identifier of the terminal device; Determine a target planning path according to the target starting area, the target end area and the historical travel trajectory of each of the terminal devices; The target planned path is sent according to the device identification.
2. The method according to claim 1, characterized in that: The determining of the target planning path according to the target starting area, the target end area and the historical travel trajectory of each of the terminal devices specifically includes: Determining a reference travel trajectory from the historical travel trajectory of each of the terminal devices according to the target starting area and the target end area; Clustering the reference travel trajectories according to a clustering algorithm to obtain a plurality of reference travel trajectory clusters and a reference path representing each of the reference travel trajectory clusters; wherein each of the reference travel trajectory clusters includes a plurality of the reference travel trajectories; The target planning path is determined from the reference path.
3. The method according to claim 2, characterized in that The clustering of the reference trajectory according to the clustering algorithm to obtain a plurality of reference trajectory clusters and a reference path representing each of the reference trajectory clusters specifically includes: Acquiring the track distance between the reference travel tracks; Clustering the reference travel trajectories according to the trajectory distances according to a first clustering algorithm, and dividing the reference travel trajectories whose difference between the trajectory distances is less than or equal to a first preset threshold into one of the reference travel trajectory clusters; The reference travel trajectory clusters are clustered according to a second clustering algorithm to obtain reference paths representing the reference travel trajectory clusters.
4. The method according to claim 2, characterized in that: Determining the target planning path from the reference path specifically includes: Obtaining a reference starting point and a reference end point of each reference path; When the distance between the reference starting point and the target starting point is less than or equal to a preset second threshold, and the distance between the reference end point and the target end point is less than or equal to the preset second threshold, the corresponding reference path is used as the target planning path.
5. The method according to claim 4, characterized in that The distance between the reference starting point and the target starting point of the plurality of reference paths is less than or equal to a preset second threshold, and the distance between the corresponding reference end point and the target end point is less than or equal to the preset second threshold, the method further comprising: The target planning path is determined according to the number of travel times and the time taken to travel corresponding to the multiple reference paths.
6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: When the terminal device identified by the device moves along the target planned path, the positioning information of the terminal device is obtained at regular intervals to form the historical moving trajectory.
7. The method according to claim 6, characterized in that The planned path requirement information also includes the type of the terminal device, and determining the reference travel trajectory from the historical travel trajectory of each of the terminal devices according to the target starting area and the target end area specifically includes: According to the target starting area, the target ending area and the type of the terminal device, a reference travel trajectory is determined from the historical travel trajectory of each of the terminal devices.
8. A path planning device, characterized in that: The device comprises: an acquisition module, a determination module and a sending module; The acquisition module is used to acquire the path planning requirement information of the terminal device; wherein the path planning requirement information includes a target starting point area corresponding to the target starting point, a target end point area corresponding to the target end point, and a device identifier of the terminal device; The determination module is used to determine the target planning path according to the target starting area, the target end area and the historical travel trajectory of each of the terminal devices; The sending module is used to send the target planned path according to the device identifier.
9. A computing device, characterized in that include: at least one memory for storing a program; At least one processor, used to execute the program stored in the memory; wherein, when the program stored in the memory is executed, the processor is used to execute the path planning method as described in any one of claims 1-7.
10. A storage medium, characterized in that: The storage medium stores instructions, and when the instructions are executed on a computing device, the computing device executes the path planning method according to any one of claims 1 to 7.