Traveling path acquisition method and device, electronic equipment and storage medium

Abstract

The invention discloses a traveling path acquisition method and device, electronic equipment and a storage medium. The method comprises the following steps: determining whether a historical navigation route associated with the current position of a user exists in historical data or not according to an image of the current environment of the user; under the condition that the historical navigation route does not exist in the historical data, obtaining the contour of each object in the image; determining that the type of each object is a preset type object or a non-preset type object; obtaining a first gradient corresponding to each non-preset type of object according to a preset potential field model, each preset type of object and the contour of each object; and according to the first gradient corresponding to each non-preset type of object, obtaining a travel path. According to the marching path acquisition method provided by the embodiment of the invention, a better marching path can be acquired, higher navigation accuracy can be achieved, and particularly, the navigation accuracy is higher in a scene with a smaller space and a more complex space structure, and the application range is wider.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular, to a method for obtaining a traveling path, an obtaining device, an electronic device, and a storage medium. Background Art

[0002] With the rapid development of satellite navigation technology, its application scenarios in daily life are becoming more and more extensive. For example, vehicle satellite navigation technology has been widely applied in fields such as public transportation, providing services such as vehicle positioning and driving path planning, and bringing great convenience to people's daily transportation. However, the navigation technology solutions of related technologies have a low navigation accuracy in scenarios with a small space and a complex space structure, resulting in a large limitation in their applicability.

[0003] The above statements are only used to provide background technical information related to the present application, and do not necessarily constitute prior art. Summary of the Invention

[0004] The purpose of the present application is to provide a method for obtaining a traveling path, an obtaining device, an electronic device, and a storage medium. To have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary part is not a general review, nor is it intended to identify key / important constituent elements or delineate the protection scope of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the subsequent detailed description.

[0005] According to one aspect of the embodiments of the present application, a method for obtaining a traveling path is provided, including:

[0006] Determine whether a historical navigation route associated with the user's current position exists in historical data according to an image of the user's current environment;

[0007] In the case where the historical navigation route does not exist in historical data, obtain the contours of each object in the image;

[0008] Determine that the type of each object is a preset type object or a non-preset type object;

[0009] According to a preset potential field model, each of the preset type objects, and the contours of each object, obtain a first gradient corresponding to each non-preset type object; the first gradient is the resultant force gradient of the resultant force exerted on the non-preset type object by each of the preset type objects at a first pixel point; the first pixel point is a pixel point within a preset area outside the contour of the non-preset type object;

[0010] Obtain a traveling path according to the first gradient corresponding to each non-preset type object.

[0011] In some embodiments of the present application, the preset potential field model includes an improved Lennard-Jones potential field model; the step of obtaining the first gradient corresponding to each non-preset type object according to the preset potential field model, each of the preset type objects, and the contours of each object includes:

[0012] According to the improved Lennard-Jones potential field model, for each non-preset type object, obtain the resultant force exerted on the non-preset type object by each of the preset type objects;

[0013] For each non-preset type object, calculate the rate of change of the resultant force exerted on the non-preset type object with respect to each first distance to obtain the first gradient; the first distance is the distance between the non-preset type object and any one of the preset type objects.

[0014] In some embodiments of the present application, the step of, according to the improved Lennard-Jones potential field model, for each non-preset type object, obtaining the resultant force exerted on the non-preset type object by each of the preset type objects includes:

[0015] According to the gravitation conversion coefficient obtained through pre-training and the spatial distance between the first pixel point and the second pixel point, obtain the attraction force of the first pixel point on the second pixel point; the first pixel point is any pixel point on the boundary line of any one of the preset type objects; the second pixel point is any pixel point in the image;

[0016] According to the repulsion coefficient and the potential field balance distance obtained through pre-training and the spatial distance between the first pixel point and the second pixel point, obtain the repulsion force of the first pixel point on the second pixel point;

[0017] For the contour, the attraction force, and the repulsion force of each non-preset type object, obtain the resultant force exerted on all pixel points in the non-preset type object by each of the preset type objects.

[0018] In some embodiments of the present application, the step of, for each non-preset type object, calculating the rate of change of the resultant force exerted on the non-preset type object with respect to each first distance to obtain the first gradient includes:

[0019] For each non-preset type object, select key pixel points at uniform intervals outside the contour of the non-preset type object;

[0020] Calculate the gradient of the resultant force on the key pixel points within the preset distance of the non-preset type object to obtain the first gradient.

[0021] In some embodiments of the present application, obtaining a travel path according to the first gradient corresponding to each non - preset type object includes:

[0022] Dividing the first gradient corresponding to each non - preset type object into multiple gradient levels;

[0023] Obtaining multiple gradient approximation points according to the multiple gradient levels;

[0024] Connecting the multiple gradient approximation points to form the travel path.

[0025] In some embodiments of the present application, dividing the first gradient corresponding to each non - preset type object into multiple gradient levels includes:

[0026] Performing normalization processing on the first gradient corresponding to each non - preset type object;

[0027] Dividing the normalized gradient into multiple gradient levels.

[0028] In some embodiments of the present application, obtaining multiple gradient approximation points according to the multiple gradient levels includes:

[0029] Selecting key pixel points at uniform intervals outside the non - preset type object, and calculating the gradient values of each key pixel point;

[0030] If the absolute value of the difference between the gradient value of the first point and the gradient value of the adjacent key pixel point is less than a preset threshold, determining that the adjacent key pixel point is the gradient approximation point of the first point; the first point is any key pixel point.

[0031] In some embodiments of the present application, determining whether a historical navigation route associated with the user's current position exists in historical data according to an image of the user's current environment includes:

[0032] Obtaining an image of the user's current environment;

[0033] Identifying the user's current position according to the image of the user's current environment;

[0034] Comparing the current position with the historical data to determine whether a historical navigation route associated with the user's current position exists in the historical data.

[0035] In some embodiments of the present application, obtaining the contours of each object in the image includes:

[0036] Performing filtering, denoising, and contrast enhancement processing on the image to obtain a pre - processed image;

[0037] Combining threshold segmentation with edge detection or region growing to segment all continuous regions in the preprocessed image;

[0038] Performing morphological operations on the continuous regions to obtain a segmented image, where the segmented image includes the contours of each continuous region.

[0039] In some embodiments of the present application, the method further includes:

[0040] In the case where the historical navigation route exists in the historical data, extracting the historical navigation route associated with the current position from the historical data as the travel path.

[0041] In some embodiments of the present application, the method further includes:

[0042] Associating and storing the current position and the travel path in the historical data.

[0043] According to another aspect of the embodiments of the present application, there is provided an apparatus for obtaining a travel path, including:

[0044] A determination module, configured to determine whether a historical navigation route associated with the current position of the user exists in historical data according to an image of the environment where the user is currently located;

[0045] A contour acquisition module, configured to acquire the contours of each object in the image in the case where the historical navigation route does not exist in the historical data;

[0046] An object type recognition module, configured to determine the type of each object as a preset type object or a non-preset type object;

[0047] A gradient acquisition module, configured to acquire a first gradient corresponding to each non-preset type object according to a preset potential field model, each preset type object, and the contours of each object; the first gradient is the resultant force gradient of the resultant force exerted on the non-preset type object by each preset type object at a first pixel point; the first pixel point is a pixel point within a preset area outside the contour of the non-preset type object;

[0048] A travel path acquisition module, configured to acquire a travel path according to the first gradient corresponding to each non-preset type object.

[0049] According to another aspect of the embodiments of the present application, there is provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the method for obtaining a travel path according to any embodiment of the present application.

[0050] According to another aspect of the embodiments of the present application, there is provided a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the method for obtaining a travel path according to any embodiment of the present application.

[0051] The technical solution provided by one aspect of the embodiments of the present application may include the following beneficial effects:

[0052] For the method for obtaining a travel path provided by the embodiments of the present application, according to an image of the environment where the user is currently located, it is determined whether a historical navigation route associated with the current position of the user exists in historical data. In the case where the historical navigation route does not exist in historical data, the outlines of the objects in the image are obtained, and it is determined that the type of each of the objects is a preset type object or a non-preset type object. According to a preset potential field model, each of the preset type objects, and the outlines of the objects, a first gradient corresponding to each of the non-preset type objects is obtained. The first gradient is the resultant force gradient of the resultant force received by the non-preset type object from each of the preset type objects at a first pixel point, and the first pixel point is a pixel point within a preset area outside the outline of the non-preset type object. According to the first gradient corresponding to each of the non-preset type objects, a travel path is obtained. This method identifies the objects in the environment where the user is currently located, fully considers the interaction forces between the objects, and thus can obtain a better travel path, can achieve a higher navigation accuracy rate, especially in scenarios with a small space and a relatively complex space structure, and has a wide range of applicability.

[0053] The above description is only an overview of the technical solution of the embodiments of the present application. In order to be able to understand the technical means of the embodiments of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the embodiments of the present application more obvious and understandable, the following specific embodiments of the present application are specifically given. Description of the Drawings

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0055] Figure 1 The flowchart of the method for obtaining a travel path according to an embodiment of the present application is shown.

[0056] Figure 2 The flowchart of identifying the objects in the image and obtaining the outlines of the objects in the image according to an embodiment of the present application is shown.

[0057] Figure 3 The flowchart of step S30 in an embodiment of the present application is shown.

[0058] Figure 4 The flowchart of step S301 in an embodiment of the present application is shown.

[0059] Figure 5 The original image and the perspective view after deformation of the original image are shown.

[0060] Figure 6 The structural block diagram of the acquisition device for the travel path in an embodiment of the present application is shown.

[0061] Figure 7 The structural block diagram of an electronic device in an embodiment of the present application is shown.

[0062] Figure 8 The schematic diagram of a computer-readable storage medium in an embodiment of the present application is shown. Detailed implementation manners

[0063] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0064] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the general understanding of those of ordinary skill in the art to which the present application belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have a meaning consistent with the meaning in the context of the prior art, and will not be interpreted in an idealized or overly formal sense unless specifically defined as here.

[0065] With the rapid development of navigation technology, its application scenarios in daily life are becoming more and more extensive. For example, vehicle satellite navigation technology has been widely applied in fields such as public transportation to provide positioning and navigation services for vehicles. In scenarios with a small space and a complex space structure, the navigation accuracy of the navigation technical solutions in the related art is relatively low. In some scenarios where the GPS positioning coordinates change little, such as in the route navigation application scenarios from different floors (such as underground garages) of a building to a station, or in mountainous environments with complex and intertwined multi-lines, the navigation accuracy is relatively low and may even fail.

[0066] In view of the problems existing in the related art, an embodiment of the present application provides a method for obtaining a travel route. First, according to an image of the user's current environment, it is determined whether a historical navigation route associated with the user's current position exists in historical data. In the case where the historical navigation route does not exist in historical data, the outlines of the objects in the image are obtained, and the type of each object is determined as a preset type object or a non-preset type object. According to a preset potential field model, each of the preset type objects, and the outlines of the objects, a first gradient corresponding to each non-preset type object is obtained. The first gradient is the resultant force gradient of the resultant force exerted on the non-preset type object by each of the preset type objects at a first pixel point, and the first pixel point is a pixel point within a preset area outside the outline of the non-preset type object. According to the first gradient corresponding to each non-preset type object, a travel route is obtained. This method identifies the objects in the user's current environment, fully considers the interaction forces between the objects, so as to be able to obtain a better travel route, achieve a higher navigation accuracy rate, especially in a scenario with a small space and a complex space structure, the navigation accuracy rate is higher, and the applicable range is wider.

[0067] The method for obtaining a travel route according to an embodiment of the present application can be applied to a navigation system, including but not limited to the navigation system of a vehicle.

[0068] Next, a method for obtaining a travel route, an apparatus for obtaining a travel route, an electronic device, and a computer-readable storage medium according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0069] Reference Figure 1 As shown, an embodiment of the present application provides a method for obtaining a travel route, which may include:

[0070] S10. According to an image of the user's current environment, determine whether a historical navigation route associated with the user's current position exists in historical data.

[0071] First, obtain an image of the user's current environment.

[0072] The navigation system of a vehicle includes parts such as a sensor module, an interface interaction module, and a processor. The processor includes modules such as an image analysis module and a position correction module. The interface interaction module of the navigation system provides a navigation task in the form of a software interaction interface. When a pedestrian has difficulty distinguishing the route in a local space, the navigation system can be turned on, and the destination can be set through the interface interaction module. The navigation system uses GPS signals, mobile phone sensors, and image road feature analysis functions to provide real-scene navigation for the user in an image enhancement manner to a place where it is easy to use the navigation system.

[0073] The sensor module may include a camera, and the camera of the navigation system can be used to obtain an image of the user's current environment. The camera is called to obtain a video or a picture, and the video or picture is saved to the system memory. For example, the camera can be rotated to shoot a video and upload the video to the server, or a landmark building can be photographed and the photo image can be uploaded to the server.

[0074] In a specific example, when the navigation system is turned on, the current system GPS coordinates and the mobile phone attitude data can be obtained, the mobile phone direction data can be obtained, and a (wired or offline) map can be loaded, etc. Before the navigation starts, the user inputs a destination, such as "XX Bus Station", and the current location is inside XX Building. The navigation system can obtain the relationship between the destination and the current coordinates through GPS, and use conventional navigation methods to plan a general route. The planned route usually includes a straight line from the mobile phone GPS coordinates to the nearest exit and the path between the nearest exit and the destination. If the user is in a complex environment, such as on a certain floor of a building with a complex structure and it is impossible to figure out how to get to the exit inside the floor, the local navigation function is enabled. After the local navigation function is started, the camera is turned on, and route-related information, such as "Go to Exit A on the 1st Floor", and the current location is shown on the real screen.

[0075] The camera is called to obtain a video or a picture and saved to the system memory. For example, the rotation of the camera can be controlled to record a video and upload the video to the server; or, a landmark building can be photographed and the landmark building photo can be uploaded to the server. Content thumbnails are formed and displayed in the UI in the system interface to facilitate the user to add or shoot images or videos multiple times and submit them.

[0076] Next, the user's current location is recognized based on the image of the user's current environment. After obtaining the image of the user's current environment, the image can be submitted and uploaded to the server or processed locally to recognize the current location corresponding to the image of the traveling environment for analyzing the roads that can be traveled around the current location.

[0077] Then, the recognized current location is compared with the historical data to determine whether the historical navigation route associated with the user's current location exists in the historical data. Specifically, the recognized current location is compared with the data in the database to determine whether the historical navigation route associated with the user's current location exists in the database. The database is used to store location information and navigation route information associated with the location information.

[0078] S20. In the case where the historical navigation route associated with the user's current location does not exist in the historical data, obtain the outlines of the objects in the image.

[0079] Specifically, a continuous region corresponds to an object, and extracting the contour of the continuous region yields the contour of the object. For example, an image S of the surrounding environment is captured using a camera, and the GPS, orientation, and pose information of the camera at this time are saved. Then, the contours of each continuous region in the image are obtained, and each contour corresponds to an object.

[0080] Reference Figure 2 As shown, in some embodiments, obtaining the contours of each object in the image may include:

[0081] S201. Process the image by filtering, denoising, and enhancing the contrast to obtain a preprocessed image.

[0082] S202. Combine threshold segmentation with edge detection or region growing to segment all continuous regions in the preprocessed image. The segmented image includes the contours of each of the continuous regions.

[0083] S203. Perform morphological operations on the continuous regions to obtain a segmented image, which includes the contours of each continuous region.

[0084] Specifically, first preprocess the image, such as filtering, denoising, enhancing the contrast, etc., to improve the accuracy of segmentation. Then, segment all continuous regions in the image through edge segmentation. According to the specific characteristics of the image, combine multiple segmentation methods, such as combining threshold segmentation with edge detection or region growing, to segment all continuous regions in the image. Perform morphological operations (such as dilation, erosion, opening operation, closing operation, etc.) and contour extraction on the segmented continuous regions to optimize the segmentation result, segment objects in multiple different regions in the image (for example, they can be labeled as C1, C2,..., Cn), and record their image contours to obtain a segmented image. The morphological operations include at least one of, but are not limited to, dilation, erosion, opening operation, and closing operation.

[0085] S30. Determine whether each object is a preset type object or a non-preset type object.

[0086] The objects in the image include preset type objects and non-preset type objects. A preset type object is an object for which it has been identified what kind of object it is, and a non-preset type object is an object for which it has not been identified specifically what kind of object it is. Specifically, using a pre-trained object recognition model, perform object recognition on the continuous regions according to the contours of each continuous region, determine the objects corresponding to each continuous region, then identify the types of each object, determine each preset type object and each non-preset type object, and store each object in association with its contour.

[0087] The object recognition model includes an image processing model, which is obtained by training a neural network (such as basic models like CNN, Transformer, etc.). It can recognize and segment typical objects in an image, such as pedestrians, buildings, trees, bridges, etc., providing data for subsequent scene location reasoning.

[0088] Specifically, the object recognition model can be used to automatically label the names of object types in the image as name, and match them with the contours Sn of the objects to form objects. Objects that match the current traffic mode, such as roads, bridges, stairs, etc., can be saved to the queue P. For example, the original image and the object Cx region extracted in the previous step are changed (resized) to a fixed-size image and input into the object recognition model to classify and match the objects segmented in the image. The classifications in the image include but are not limited to objects such as pedestrians, land animals, buildings, roads, trees, bridges, rivers, ditches, etc. Extract the contour parameters of all unanalyzed objects On in the image and save them as Sn, (n = 1, 2, 3,...). There are multiple recognized objects, which are saved as a queue (or an array). This queue is the queue of objects to be processed. The processing process is to take out an object from the queue in turn. If this object is the nth one, it is assigned and saved as On, where n represents the dequeue sequence number, and the contour parameters it extracts are saved as Sn. Non-preset type objects refer to objects whose contours are segmented but their types cannot be recognized. That is to say, the contours of non-preset type objects have been segmented, but their specific objects cannot be recognized; the recognized objects can be called preset type objects. Preset type objects are usually relatively common objects, such as people, trees, intersections, walls, doors, etc., and are therefore very easy to recognize. After recognizing each object, each object can be associated with its corresponding contour.

[0089] S40. According to the preset potential field model, each preset type object, and the contours of each object, obtain the first gradient corresponding to each non-preset type object.

[0090] The first gradient is the resultant force gradient of the resultant force exerted on the non-preset type object by each preset type object at the first pixel point; the first pixel point is a pixel point within a preset area outside the contour of the non-preset type object.

[0091] Exemplarily, the preset area outside the contour of the non-preset type object can be the area between the contour of the non-preset type object and the preset contour, where the preset contour has the same shape as the contour of the non-preset type object, and the geometric centers of the preset contour and the contour of the non-preset type object coincide.

[0092] The preset potential field model includes, but is not limited to, the improved Lennard-Jones potential field model. The improved Lennard-Jones potential field model (Modified Lennard-Jones Potential) is an optimized version proposed based on the classical L-J potential for different application scenarios and physical requirements.

[0093] Reference Figure 3 As shown, in some embodiments, according to the preset potential field model, each preset type of object, and the contour of each object, obtaining the first gradient corresponding to each non-preset type of object includes:

[0094] S401. According to the improved Lennard-Jones potential field model, for each non-preset type of object, obtain the resultant force exerted on the non-preset type of object by each preset type of object;

[0095] S402. For each non-preset type of object, calculate the rate of change of the resultant force exerted on the non-preset type of object with respect to each first distance to obtain the first gradient.

[0096] The first distance is the distance between the non-preset type of object and any preset type of object.

[0097] The improved Lennard-Jones potential field model combines the dynamic balance characteristics of gravitational and repulsive forces. At relatively long distances, the preset type of object exerts an effect similar to gravity on the non-preset type of object (such as guiding the path closer to the safe area), while at close range, it shows a repulsive force (to avoid colliding with obstacles). By calculating the gradient of the resultant force, the direction of the force on the non-preset type of object can be adjusted in real time, so as to reduce the collision incidence rate and improve the planning efficiency during path planning. For example, the gradient calculation of the first pixel point outside the contour can anticipate the influence range of obstacles in advance and reduce the incidence rate of local paths getting into deadlocks.

[0098] Combining the object contour information (such as geometric shape), adjusting the potential field parameters (such as the repulsive force action radius), makes the gradient direction more conform to the actual obstacle distribution. By calculating the rate of change of the resultant force with respect to distance (i.e., the gradient), it can quickly respond to the superimposed influence of multiple obstacles, for example, generating a smooth path at intersections or narrow channels.

[0099] Reference Figure 4 As shown, exemplarily, according to the improved Lennard-Jones potential field model, for each non-preset type of object, obtaining the resultant force exerted on the non-preset type of object by each preset type of object includes:

[0100] S4011. According to the gravitational conversion coefficient obtained through pre-training and the spatial distance between the first pixel point and the second pixel point, obtain the attractive force of the first pixel point on the second pixel point.

[0101] The first pixel point is any pixel point on the boundary line of any preset type of object; the second pixel point is any pixel point in the image.

[0102] Exemplarily, obtain the gravitational force of the preset type of object O in the image according to the improved Lennard-Jones potential field model: Assume that any point on the boundary S of the preset type of object O is q s , then in the improved Lennard-Jones potential field model, the attractive force U s exerted on any other pixel point q in the image by any point q att on the boundary of the preset type of object O is calculated by the following formula:

[0103] U att (q) = ηρ 2 (q, qs) = 2η(q - qs) 1 / 2 ,

[0104] where ρ(q, q s ) is a spatial distance calculation function for calculating the Euclidean distance between pixel point q and target point q s ; ρ(q, q s ) represents the Euclidean distance between any pixel point q (any pixel point q is the second pixel point) in the image space and the sampling point q s (sampling point q s is the first pixel point) on the boundary of the preset type of object; η is a gravitational conversion coefficient, indicating the strength of the attractive force of the object on the surrounding positions and marking the probability coefficient of a pedestrian moving towards the object at other position points. For example, if the object is an elevator, its conversion coefficient is greater than that of a tree, and the value of η in the model is obtained through model training, and different types of objects correspond to different η values.

[0105] According to the improved Lennard-Jones potential field model, the gravitational vector is the negative gradient of the gravitational potential field function. In the improved Lennard-Jones potential field model, the formula for calculating the negative gradient F att (q) is

[0106]

[0107] S4012. Obtain the repulsive force of the first pixel point on the second pixel point according to the repulsive force coefficient and potential field balance distance obtained by pre-training, and the spatial distance between the first pixel point and the second pixel point.

[0108] Obtain the repulsive force of the preset type of object O in the image according to the improved Lennard-Jones potential field model: Assume that any point on the boundary S of the preset type of object O is qs, then in the improved Lennard-Jones potential field model, the repulsive force Urep(q) exerted on any other pixel point q in the image by any point q s on the boundary S of the preset type of object O is calculated by the following formula:

[0109] When \(0\leq\rho(q,q_s)\leq\rho_s\), \(U_{rep}(q) = 0.5k(1 / \rho(q,q_s)-1 / \rho_0)\) 2 ; otherwise \(U_{rep}(q)=0\), where \(k\) is the repulsive force coefficient, \(\rho(q,q_s)\) represents the Euclidean distance between any pixel point \(q\) in the image space and the sampling point \(q_s\) on the boundary of the preset type object; \(\rho_0\) represents the potential field equilibrium distance. \(U_{rep}(q)\) refers to the repulsive force exerted on any point \(q\) in the image by any point \(q\) s on the boundary curve \(s\) of the preset type object \(O\), and for any point \(q\) s on the boundary curve \(s\) of the preset type object \(O\), when simplifying the calculation, only a few arbitrary points \(q\) s can be taken, for example, the average of the farthest and the nearest points. When it is complex, this formula is integrated along the boundary \(S\).

[0110] S4013. For the contour of each non - preset type object, the above - mentioned attractive force and the above - mentioned repulsive force, obtain the resultant force exerted on all pixel points in the non - preset type object by each preset type object.

[0111] Pixels inside each object in the image are subject to repulsive and attractive forces from other preset type objects. Therefore, according to the vector direction, the resultant force exerted on the non - preset type object is calculated as:

[0112] where \(N\) is the number of preset type objects.

[0113] In some embodiments, for each non - preset type object, calculating the rate of change of the resultant force exerted on the non - preset type object with respect to each first distance to obtain a first gradient may include: for each non - preset type object, uniformly spaced key pixel points are selected outside the contour of the non - preset type object; calculating the gradient of the resultant force with respect to the key pixel points within a preset distance of the non - preset type object to obtain a first gradient. The key pixel points within the preset distance are at least a part of the uniformly spaced key pixel points.

[0114] Exemplarily, outside the contour of the non - preset type object, a pixel point is selected as the starting point, and then pixel points are selected at uniform intervals. The starting point and the selected pixel points are all key pixel points. The key pixel points play a marking role, and the distance between every two adjacent key pixel points is equal.

[0115] Exemplarily, when obtaining the corresponding gradient for a non-preset type object in an image, first obtain the average distance between the pixel points within a preset distance around the non-preset type object and the non-preset type object, and then calculate the rate of change of the resultant force received by the non-preset type object with respect to this distance, that is, find the derivative of the resultant force with respect to this distance. After obtaining the derivative, the direction and magnitude of the resultant force of all pixel points within a preset distance around the non-preset type object on the non-preset type object can be obtained. For example, the repulsive force of a wall is relatively large, so the direction of its resultant force is outward, so the traveling direction should be along the direction away from the wall. In this way, the resultant force gradient in the path points to the next gradient change approaching point. Therefore, the passageway will form an attraction area in the image that is similar to its contour shape.

[0116] Discretize the preset area outside the contour into pixel points, and use image processing technology to quickly identify key pixel points, which can reduce the amount of calculation.

[0117] Utilize the prior knowledge of preset type objects. For example, directly invoking the potential field parameters of preset type objects (such as modeled static obstacles) can reduce repeated calculations. Infer the potential threat level of non-preset type objects through contour analysis. For example, a sharp contour may correspond to a high-risk area, and the repulsive force gradient needs to be enhanced, thereby realizing the adaptive processing of non-preset type objects.

[0118] Based on gradient-based path design, through gradient propagation, path oscillation can be reduced. The gradient calculation is based on a continuous potential field, and the generated path is naturally smooth, which can reduce jagged paths. The gradient direction synthesizes multiple factors such as path length and safety to form an optimal trade-off solution.

[0119] Through an improved Lennard-Jones potential field model, combining the dynamic characteristics of physical mechanics with the geometric constraints of path planning, it has good performance in terms of safety, computational efficiency, and adaptability to complex environments. The gradient dynamic response mechanism based on the contour and the efficient modeling of the superposition effect of multiple obstacles provide a better solution for path planning

[0120] S50. Obtain a traveling path according to the first gradient corresponding to each non-preset type object.

[0121] In some embodiments, obtaining a traveling path according to the first gradient corresponding to each non-preset type object includes: dividing the first gradient corresponding to each non-preset type object into multiple gradient levels; obtaining multiple gradient approaching points according to the multiple gradient levels; connecting the multiple gradient approaching points to form a traveling path.

[0122] Specifically, dividing the first gradient corresponding to each non-preset type object into multiple gradient levels includes: performing normalization processing on the first gradient corresponding to each non-preset type object; dividing the normalized gradient into multiple gradient levels.

[0123] The gradient proximity points are the resultant force relative to the equal-height gradient. After calculating the resultant force received by the objects of non-preset types in the image, the resultant force interval is normalized according to the maximum and minimum values of the resultant forces received by each non-preset type object in the image, and then divided into several levels, that is, gradient levels. To improve processing efficiency and reduce calculations, the second pixel points can be selected at intervals in the image, approximated by uniform interpolation. Therefore, gradient proximity points with close gradient values will be formed on the feasible road.

[0124] Exemplarily, according to multiple gradient levels, multiple gradient proximity points are obtained, including: key pixel points are selected at uniform intervals outside the objects of non-preset types, and the gradient values of each key pixel point are calculated; if the absolute value of the difference between the gradient value of the first point and the gradient value of the adjacent key pixel point is less than the preset threshold, the adjacent key pixel point is determined as the gradient proximity point of the first point; the first point is any key pixel point outside the object of non-preset type.

[0125] Specifically, for each object of non-preset type, according to the resultant force, the first gradient, and the contour corresponding to the object of non-preset type, it is determined whether the object of non-preset type is a feasible path matching the current traffic mode (such as vehicle driving). If so, it is added to the queue P. The orientation of each object in the queue P is marked in combination with GPS positioning and the azimuth and attitude information of the camera during photographing and displayed in the original image. Both staircase roads and vehicle roads can form effective attraction regions. According to features such as shape and surrounding objects, a neural network trained for this task will give a judgment on the suitable current traffic mode (such as the mode of taking a vehicle, etc.). The current traffic mode can be input by the user in the settings. If no traffic mode is input, the traffic mode is inferred by model matching according to the user's location and speed.

[0126] The interaction interface of the navigation system displays the travel path and relevant road analysis information, and is provided with user correction buttons, such as prompting whether the interface annotation is correct, floor correction, precise position correction, traffic mode correction selection, adding landmark angle images, etc. After completing the interaction correction, the best path navigation and alternative navigation routes are displayed in the interface, and positioning information such as floor, left and right, etc. is displayed in each scheme. It is coordinated with input controls such as voice interaction, image, video supplement, and route switching. During the interaction, as the input image changes, the relationship between the objects in the image can be inferred intelligently, and predicted or virtual images such as rotation and perspective are displayed. For example, according to the distribution of image objects and the horizontal field of view (HFOV) of the camera, the vertical division area, and the image is deformed into a perspective view mode, as shown in Figure 5 shown Figure 5The original image (a) and the perspective view (b) obtained by deforming the original image (a) are shown. During the interactive navigation using this navigation system, the data of the interactive process is accumulated and analyzed, and useful information is extracted and added to the database to update the service. For example, the resultant force diagram, environmental pictures, building layout features, landmark objects, building names, etc. during the navigation process are recorded to enrich the database.

[0127] In some embodiments, the method may further include:

[0128] S60. Associate and store the current position and the travel path in the historical data.

[0129] In this way, when other users pass through this current position, the historical navigation route associated with the current position can be directly extracted from the historical data as the travel path.

[0130] In some embodiments, the method may further include:

[0131] S70. When the historical navigation route associated with the user's current position exists in the historical data, extract the historical navigation route associated with the current position from the historical data as the travel path.

[0132] When the historical navigation route associated with the user's current position exists in the database, the travel route associated with the current position is extracted from the database. For example, according to the current position corresponding to the image of the travel environment, if the network server can be accessed, the identified current position is matched with the server database. Since a large number of historical search navigation routes are saved in the server in the form of image features, if the data of the historical navigation route associated with the user's current position exists in the database, the historical navigation route associated with the user's current position can be directly called, that is, the travel route matching the current position is obtained. In this way, complex path acquisition operations do not need to be performed again, which can save time and improve the efficiency of obtaining the travel route.

[0133] The descriptions of the above embodiments tend to emphasize the differences between the embodiments. Their similarities can be referred to each other. For the sake of brevity, they will not be elaborated herein.

[0134] Refer to Figure 6 As shown, another embodiment of the present application provides an apparatus for obtaining a travel route, which may include:

[0135] A determination module, configured to determine whether the historical navigation route associated with the user's current position exists in the historical data according to the image of the environment where the user is currently located;

[0136] A contour acquisition module, configured to acquire the contours of each object in the image when the historical navigation route does not exist in the historical data;

[0137] An object type recognition module, configured to determine that the type of each object is a preset type object or a non-preset type object;

[0138] A gradient acquisition module, configured to acquire a first gradient corresponding to each non-preset type object according to a preset potential field model, each of the preset type objects, and the contours of each object; the first gradient is the resultant force gradient of the resultant force exerted on the non-preset type object by each of the preset type objects at a first pixel point; the first pixel point is a pixel point within a preset area outside the contour of the non-preset type object;

[0139] A travel path acquisition module, configured to acquire a travel path according to the first gradient corresponding to each non-preset type object.

[0140] In some embodiments of the present application, the determination module is further specifically configured to: acquire an image of the environment where the user is currently located; identify the current position of the user according to the image of the environment where the user is currently located; compare the current position with the historical data to determine whether a historical navigation route associated with the current position of the user exists in the historical data.

[0141] In some embodiments, the preset potential field model includes an improved Lennard-Jones potential field model; the gradient acquisition module includes:

[0142] A resultant force acquisition sub-module, configured to acquire, according to the improved Lennard-Jones potential field model, the resultant force exerted on each non-preset type object by each of the preset type objects;

[0143] A first gradient acquisition sub-module, configured to calculate, for each non-preset type object, the rate of change of the resultant force exerted on the non-preset type object with respect to each first distance to obtain a first gradient; the first distance is the distance between the non-preset type object and any one of the preset type objects.

[0144] In some embodiments, the resultant force acquisition sub-module includes:

[0145] An attraction acquisition unit, configured to acquire the attraction of a first pixel point to a second pixel point according to a pre-trained gravitational conversion coefficient and the spatial distance between the first pixel point and the second pixel point; the first pixel point is any pixel point on the boundary line of any one of the preset type objects; the second pixel point is any pixel point in the image;

[0146] A repulsive force acquisition unit, configured to acquire the repulsive force of a first pixel point on a second pixel point according to the repulsive force coefficient and the potential field balance distance obtained by pre-training, and the spatial distance between the first pixel point and the second pixel point;

[0147] A resultant force acquisition unit, configured to acquire the resultant force exerted on all pixel points in the non-preset type object from each preset type object for the contour of each non-preset type object, the above-mentioned attractive force, and the above-mentioned repulsive force.

[0148] Exemplarily, the gradient acquisition module may include:

[0149] A selection unit, configured to select key pixel points at uniform intervals outside the contour of each non-preset type object for each non-preset type object;

[0150] A calculation unit, configured to calculate the gradient of the resultant force on the key pixel points within the preset distance of the non-preset type object to obtain a first gradient.

[0151] Exemplarily, the path acquisition module may include:

[0152] A division sub-module, configured to divide the first gradient corresponding to each non-preset type object into multiple gradient levels;

[0153] A gradient proximity point acquisition sub-module, configured to acquire multiple gradient proximity points according to the multiple gradient levels;

[0154] A connection sub-module, configured to connect the multiple gradient proximity points to form a travel path.

[0155] Exemplarily, the division sub-module includes:

[0156] A normalization unit, configured to perform normalization processing on the first gradient corresponding to each non-preset type object;

[0157] A gradient level division unit, configured to divide the gradient after normalization processing into multiple gradient levels.

[0158] Exemplarily, the gradient proximity point acquisition sub-module includes:

[0159] A gradient value calculation unit, configured to select key pixel points at uniform intervals outside the non-preset type object and calculate the gradient values of the key pixel points;

[0160] A determination unit, configured to determine that an adjacent key pixel point is a gradient proximity point of a first point if the absolute value of the difference between the gradient value of the first point and the gradient value of the adjacent key pixel point is less than a preset threshold; the first point is any key pixel point.

[0161] Exemplarily, the object type recognition module may include:

[0162] A segmentation sub-module, configured to segment continuous regions in an image to obtain a segmented image;

[0163] An identification sub-module, configured to use a pre-trained object recognition model to perform object recognition on the segmented image, and determine various preset type objects, various non-preset type objects, and the contours of each object.

[0164] Exemplarily, the segmentation sub-module may include:

[0165] A preprocessing unit, configured to perform filtering, denoising, and contrast enhancement processing on the image to obtain a preprocessed image;

[0166] A segmentation unit, configured to combine threshold segmentation with edge detection or region growing to segment all continuous regions in the preprocessed image;

[0167] A morphological operation unit, configured to perform morphological operations on the continuous regions to obtain a segmented image.

[0168] Exemplarily, the obtaining device may further include:

[0169] A travel path extraction module, configured to extract a historical navigation route associated with the current position from historical data as a travel path when the historical navigation route associated with the user's current position exists in the historical data.

[0170] Exemplarily, the obtaining device may further include:

[0171] An association storage module, configured to associate and store the current position and the travel path in the historical data.

[0172] The device for obtaining a travel path according to an embodiment of the present application determines whether a historical navigation route associated with the current position of the user exists in historical data based on an image of the environment where the user is currently located. In the case where the historical navigation route does not exist in the historical data, it obtains the contours of each object in the image, determines the type of each object as a preset type object or a non-preset type object, and obtains a first gradient corresponding to each non-preset type object according to a preset potential field model, each of the preset type objects, and the contours of the objects. The first gradient is the resultant force gradient of the resultant force exerted on the non-preset type object by each of the preset type objects at a first pixel point, and the first pixel point is a pixel point within a preset area outside the contour of the non-preset type object. According to the first gradient corresponding to each non-preset type object, it obtains a travel path. This method identifies each object in the environment where the user is currently located, fully considers the interaction forces between the objects, and thus can obtain a better travel path, achieve a higher navigation accuracy rate, especially in scenarios with a small space and a relatively complex space structure, and has a wide applicability range. Therefore, it identifies each object in the environment where the user is currently located, fully considers the interaction forces between the objects, and thus can obtain a better travel path, achieve a higher navigation accuracy rate, especially in scenarios with a small space and a relatively complex space structure, and has a wide applicability range.

[0173] The descriptions of the various embodiments above tend to emphasize the differences between the various embodiments. Their similarities or likenesses can be referred to each other. For the sake of brevity, they will not be elaborated herein.

[0174] Another embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program to implement the method for obtaining a travel path according to any of the above embodiments.

[0175] Refer to Figure 7 As shown, the electronic device 10 may include: a processor 100, a memory 101, a bus 102, and a communication interface 103. The processor 100, the communication interface 103, and the memory 101 are connected through the bus 102; a computer program executable on the processor 100 is stored in the memory 101, and when the processor 100 runs the computer program, it executes the method provided by any of the foregoing embodiments of the present application.

[0176] Among them, the memory 101 may include high-speed random access memory (RAM), and may also include non-volatile memory, such as at least one disk memory. The communication connection between the device network element and at least one other network element is realized through at least one communication interface 103 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0177] The bus 102 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 101 is used to store a program. After receiving an execution instruction, the processor 100 executes the program. Any implementation manner disclosed in the embodiments of the present application can be applied to the processor 100 or implemented by the processor 100.

[0178] The processor 100 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 100 or by instructions in the form of software. The above-mentioned processor 100 may be a general-purpose processor, which may include a central processing unit (CPU for short), a network processor (NP for short), etc.; it may 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, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register, etc. This storage medium is located in the memory 101, and the processor 100 reads the information in the memory 101 and combines its hardware to complete the steps of the above method.

[0179] The electronic device provided in the embodiments of the present application and the method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by it, including being able to obtain a better travel path, being able to achieve a higher navigation accuracy rate, especially having a higher navigation accuracy rate in scenarios with a small space and a relatively complex space structure, and having a wide range of applicability.

[0180] Another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. The computer program is executed by a processor to implement the method for obtaining a travel path according to any of the above embodiments. Refer to Figure 8 As shown, the computer-readable storage medium shown is an optical disc 20, on which a computer program (i.e., a program product) is stored. When the computer program runs on a processor, it will execute the method for obtaining a travel path provided by any of the foregoing embodiments.

[0181] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other optical and magnetic storage media, which will not be elaborated here one by one.

[0182] The computer-readable storage medium provided by the above embodiments of the present application and the method provided by the embodiments of the present application are based on the same inventive concept, and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored thereon, including being able to obtain a better travel path, being able to achieve a higher navigation accuracy rate, especially having a higher navigation accuracy rate in scenarios with a smaller space and a more complex space structure, and having a wider applicability range.

[0183] It should be noted that:

[0184] The term "module" is not intended to be limited to a specific physical form. Depending on the specific application, a module can be implemented as hardware, firmware, software, and / or a combination thereof. In addition, different modules can share common components or even be implemented by the same components. There may or may not be a clear boundary between different modules.

[0185] The algorithms and displays provided herein are not inherently related to any specific computer, virtual device, or other equipment. Various general-purpose devices can also be used in conjunction with the examples based herein. Based on the above description, the structure required to construct such a device is obvious. In addition, the present application is not directed to any specific programming language. It should be understood that the content of the present application described herein can be implemented using various programming languages, and the description of the specific language above is to disclose the best implementation manner of the present application.

[0186] It should be understood that although the steps in the flowchart of the accompanying drawings are shown sequentially in the direction of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise clearly stated in this document, there is no strict order restriction for the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0187] The above embodiments only represent the implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for obtaining a travel path, characterized in that: include: Determining, based on the image of the user's current environment, whether a historical navigation route associated with the user's current location exists in the historical data; In the case that the historical navigation route does not exist in the historical data, obtaining the outline of each object in the image; Determining whether the type of each of the objects is a preset type object or a non-preset type object; According to a preset potential field model, each of the preset type objects and the contour of each of the objects, obtaining a first gradient corresponding to each of the non-preset type objects; The first gradient is the resultant force gradient of the resultant force from each of the objects of the preset type on the non-preset type object at the first pixel point; the first pixel point is a pixel point in a preset area outside the outline of the non-preset type object; A travel path is acquired according to a first gradient corresponding to each of the non-preset type objects.

2. The method according to claim 1, characterized in that The preset potential field model includes a modified Leonard-Jones potential field model; and obtaining a first gradient corresponding to each of the non-preset type objects according to the preset potential field model, each of the preset type objects, and the contour of each of the objects, includes: According to the improved Leonard-Jones potential field model, for each of the non-preset type objects, obtaining the resultant force exerted on the non-preset type object from the preset type objects; For each of the non-preset type objects, the rate of change of the resultant force on the non-preset type object relative to each first distance is calculated to obtain the first gradient; the first distance is the distance between the non-preset type object and any of the preset type objects.

3. The method according to claim 2, characterized in that The step of obtaining, for each non-preset type object, a resultant force from each of the preset type objects to which the non-preset type object is subjected based on the improved Leonard-Jones potential field model comprises: According to the gravity conversion coefficient obtained by pre-training and the spatial distance between the first pixel point and the second pixel point, the attraction of the first pixel point to the second pixel point is obtained; the first pixel point is any pixel point on the boundary line of any of the preset types of objects; the second pixel point is any pixel point in the image; Obtain the repulsion of the first pixel point on the second pixel point according to the repulsion coefficient and the potential field equilibrium distance obtained through pre-training, and the spatial distance between the first pixel point and the second pixel point; With respect to the contour, the attractive force and the repulsive force of each of the non-preset type objects, the resultant force from each of the preset type objects received by all the pixel points in the non-preset type object is obtained.

4. The method according to claim 2, characterized in that: The step of calculating, for each of the non-preset type objects, a rate of change of the resultant force on the non-preset type object relative to each first distance to obtain the first gradient includes: For each of the non-preset type objects, selecting key pixel points at even intervals outside the contour of the non-preset type object; The gradient of the resultant force on the key pixel points within a preset distance of the non-preset type object is calculated to obtain the first gradient.

5. The method according to claim 4, characterized in that The acquiring a travel path according to the first gradient corresponding to each of the non-preset type objects includes: Dividing the first gradient corresponding to each of the non-preset type objects into a plurality of gradient levels; According to the plurality of gradient levels, obtaining a plurality of gradient approach points; The plurality of gradient approach points are connected to form the travel path.

6. The method according to claim 5, characterized in that The step of dividing the first gradient corresponding to each of the non-preset type objects into a plurality of gradient levels includes: Normalizing the first gradient corresponding to each of the non-preset type objects; The normalized gradient is divided into multiple gradient levels.

7. The method according to claim 5, characterized in that The step of acquiring a plurality of gradient approach points according to the plurality of gradient levels comprises: Select key pixel points at uniform intervals outside the non-preset type object, and calculate the gradient value of each of the key pixel points; If the absolute value of the difference between the gradient value of the first point and the gradient value of the adjacent key pixel point is less than a preset threshold, the adjacent key pixel point is determined to be a gradient close point of the first point; the first point is any key pixel point.

8. The method according to any one of claims 1 to 7, characterized in that The determining, based on the image of the user's current environment, whether a historical navigation route associated with the user's current location exists in historical data includes: Get an image of the user's current environment; Identifying the current location of the user based on the image of the environment in which the user is currently located; The current location is compared with the historical data to determine whether a historical navigation route associated with the user's current location exists in the historical data.

9. The method according to any one of claims 1 to 7, characterized in that: The obtaining of the contour of each object in the image comprises: Performing filtering, denoising and contrast enhancement on the image to obtain a preprocessed image; Combining threshold segmentation with edge detection or region growing to segment all continuous regions in the preprocessed image; A morphological operation is performed on the continuous regions to obtain a segmented image, wherein the segmented image includes the contours of each of the continuous regions.

10. The method according to any one of claims 1 to 7, characterized in that The method further comprises: In a case where the historical navigation route exists in the historical data, the historical navigation route associated with the current position is extracted from the historical data as a travel path.

11. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: The current position and the travel path are associated and stored in the historical data.

12. A device for acquiring a travel path, characterized in that: include: A determination module, configured to determine whether a historical navigation route associated with a current location of the user exists in the historical data based on an image of the user's current environment; A contour acquisition module, used for acquiring the contour of each object in the image when the historical navigation route does not exist in the historical data; An object type identification module, used to determine whether the type of each object is a preset type object or a non-preset type object; A gradient acquisition module, used to acquire a first gradient corresponding to each of the non-preset type objects according to a preset potential field model, each of the preset type objects and the contours of each of the objects; the first gradient is a resultant force gradient of the resultant force from each of the preset type objects on the non-preset type object at a first pixel point; the first pixel point is a pixel point in a preset area outside the contour of the non-preset type object; The travel path acquisition module is used to acquire the travel path according to the first gradient corresponding to each of the non-preset type objects.

13. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for acquiring a travel path according to any one of claims 1 to 11.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the method for acquiring a travel path according to any one of claims 1 to 11.

Images