CN116817907A

CN116817907A - Path generation method, path generation device, server and storage medium

Info

Publication number: CN116817907A
Application number: CN202210962608.7A
Authority: CN
Inventors: 孟庆虎; 王建坤; 孙植锐
Original assignee: Southwest University of Science and Technology
Current assignee: Southwest University of Science and Technology
Priority date: 2022-08-11
Filing date: 2022-08-11
Publication date: 2023-09-29

Abstract

The application is applicable to the technical field of computers and provides a path generation method, a path generation device, a server and a storage medium, wherein the method comprises the following steps: generating a starting point growth tree and a plurality of random growth trees according to the starting point information and the end point information; when the target random growth tree meeting the preset distance condition is detected, fusing the target random growth tree to a starting point growth tree; when a node of which the corresponding position belongs to the end point region exists in the starting point growing tree, a driving path for the target robot to drive from the starting point to the end point is generated according to the starting point growing tree. According to the application, the starting point growing tree from the starting point to the end point is formed through the growth and fusion of the starting point growing tree and the random growing tree, and the running path is obtained based on the starting point growing tree, so that a map is not required to be constructed, a large amount of calculation is consumed to search the running path, and the efficiency of generating the running path is improved.

Description

Path generation method, path generation device, server and storage medium

Technical Field

The present application belongs to the field of computer technology, and in particular, relates to a path generating method, a path generating device, a server, and a storage medium.

Background

With the development and progress of technology, mobile robots are widely used in various fields of production and life. During use of the mobile robot, it is often necessary to plan a path of the mobile robot to find a travel path for the mobile robot to move from a starting point to an ending point.

In the related art, environmental information around a mobile robot is generally collected by a sensor and a camera, and a map of the surrounding environment of the mobile robot is constructed by performing a large amount of computation on the collected environmental information, so that a travel path is generated based on the constructed map of the surrounding environment. Such construction of a surrounding environment map by means of the environmental information collected by the sensor and the camera generally requires a large amount of calculation to generate a travel path based on the surrounding environment map, resulting in low efficiency of generating the travel path.

Disclosure of Invention

The embodiment of the application provides a path generation method, a path generation device, a server and a storage medium, which can solve the problem that in the related art, a large amount of calculation amount is required to be consumed, so that the efficiency of generating a driving path is low.

A first aspect of an embodiment of the present application provides a path generating method, including:

Generating a starting point growing tree and a plurality of random growing trees according to the starting point information and the end point information of the target robot, wherein the starting point of the starting point growing tree is the starting point indicated by the starting point information, and the starting point of the random growing tree is a random position point;

if a target random growth tree meeting the preset distance condition is detected in the process of growing the starting point growth tree and the random growth tree, fusing the target random growth tree to the starting point growth tree according to the motion information of the target robot, the position information of each node in the starting point growth tree at the current moment and the position information of each node in the target random growth tree, and switching the starting point growth tree to the fused starting point growth tree;

when a node of which the corresponding position belongs to the end point region exists in the starting point growing tree, a driving path for the target robot to drive from the starting point to the end point is generated according to the starting point growing tree.

In some embodiments, fusing the target random growth tree to the starting point growth tree according to the motion information of the target robot, the position information of each node in the starting point growth tree at the current moment, and the position information of each node in the target random growth tree, including:

the following node selection steps are executed: selecting a first target node from the starting point growth tree, and selecting a second target node from the target random growth tree, wherein the first target node is a node meeting a preset distance condition in the starting point growth tree, and the second target node is a node meeting the preset distance condition in the target random growth tree;

Determining a target growing point which can be reached by the movement of the target robot according to the movement information of the target robot and the target Gaussian point of the selected second target node, connecting the target growing point with the first target point, and deleting the selected second target node in the target random growing tree;

and continuing to execute the node selection step until no node exists in the target random growth tree.

In some embodiments, prior to fusing the target random growth tree to the starting growth tree, the method further comprises:

and if the target nodes with the corresponding positions matched with the positions of the obstacles exist in the target random growth tree, deleting the target nodes in the target random growth tree.

In some embodiments, the method further comprises:

and in the process of growing the starting point growing tree and the random growing tree, if the random growing point is detected and the distance between the random growing point and the target growing tree meets the preset connection condition, fusing the random growing point into a node of the target growing tree, wherein the target growing tree comprises the starting point growing tree and/or the random growing tree.

In some embodiments, the method further comprises:

and if the distance between the random growth point and the target growth tree does not meet the preset connection condition, generating a new random growth tree by taking the random growth point as a starting point.

In some embodiments, the method further comprises:

and determining the tree distance between every two random growing trees according to the position information of the nodes in each random growing tree, and fusing at least two random growing trees with the corresponding tree distance meeting the preset fusion condition.

In some embodiments, the method further comprises:

when the preset growth conditions are met, controlling the starting point growth tree and/or the random growth tree to grow, wherein the preset growth conditions comprise at least one of the following: the number of times of growing the starting point growing tree and/or the random growing tree is smaller than the preset number of times of growing the starting point growing tree and/or the random growing tree, the growing time of the starting point growing tree and/or the random growing tree is smaller than the preset growing time, and no node of which the corresponding position belongs to the end point area exists in the starting point growing tree.

A second aspect of an embodiment of the present application provides a path generating apparatus, including:

an information acquisition unit, configured to generate a starting point growth tree and a plurality of random growth trees according to starting point information and end point information of the target robot, where the starting point of the starting point growth tree is a starting point indicated by the starting point information, and the starting point of the random growth tree is a random position point;

the information fusion unit is used for fusing the target random growth tree to the starting point growth tree according to the motion information of the target robot, the position information of each node in the starting point growth tree at the current moment and the position information of each node in the target random growth tree if the target random growth tree meeting the preset distance condition is detected in the process of growing the starting point growth tree and the random growth tree, and switching the starting point growth tree into the fused starting point growth tree;

And the path generation unit is used for generating a running path for the target robot to run from the starting point to the end point according to the starting point long tree when the node of which the corresponding position belongs to the end point area exists in the starting point growth tree.

A third aspect of the embodiments of the present application provides a server comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the path generation method provided in the first aspect when executing the computer program.

A fourth aspect of the embodiments of the present application provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the path generation method provided in the first aspect.

The path generation method, the path generation device, the server and the storage medium provided by the embodiment of the application have the following beneficial effects: first, according to the starting point information and the end point information of the target robot, a starting point growing tree and a plurality of random growing trees are generated, wherein the starting point of the starting point growing tree is the starting point indicated by the starting point information, and the starting point of the random growing tree is a random position point. Then, in the process of growing the starting point growing tree and the random growing tree, if the target random growing tree meeting the preset distance condition is detected, fusing the target random growing tree to the starting point growing tree according to the motion information of the target robot, the position information of each node in the starting point growing tree at the current moment and the position information of each node in the target random growing tree, and switching the starting point growing tree to the fused starting point growing tree. Finally, when a node of which the corresponding position belongs to the end point area exists in the starting point growing tree, a driving path for the target robot to drive from the starting point to the end point is generated according to the starting point growing tree. When the travel path of the target robot is generated, the start point growth tree which can run from the start point to the end point is formed through the growth and fusion of the start point growth tree and the random growth tree, so that the travel path for the target robot to run from the start point to the end point is obtained based on the start point growth tree, a map is not required to be constructed through a camera and a sensor, a large amount of calculation amount is consumed to search the travel path, and the efficiency of generating the travel path is improved.

It will be appreciated that the advantages of the second to fourth aspects may be found in the relevant description of the first aspect and are not repeated here.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for those skilled in the art.

FIG. 1 is a flow chart of an implementation of a path generation method according to an embodiment of the present application;

FIG. 2 is a flow chart of an implementation of fusing a target random growth tree to a starting point growth tree according to one embodiment of the present application;

FIG. 3 is a schematic diagram of an initial growth tree and a target random growth tree according to an embodiment of the present application;

FIG. 4 is a schematic diagram of selecting a target growth point according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a connection between a target growth point and a first target point according to an embodiment of the present application;

FIG. 6 is a schematic diagram illustrating deleting a selected second target node according to an embodiment of the present application;

FIG. 7 is a schematic diagram of Gaussian modeling of all nodes of a target random growth tree provided by an embodiment of the application;

FIG. 8a is a schematic diagram of a generated starting point growth tree and a plurality of random growth trees provided in accordance with one embodiment of the present application;

FIG. 8b is a schematic diagram of a target random growth tree that is detected to satisfy a predetermined distance condition according to an embodiment of the present application;

FIG. 8c is a schematic diagram of Gaussian modeling of nodes in a target random growth tree according to an embodiment of the application;

FIG. 8d is a schematic diagram of a target random growth tree fused to a starting point growth tree according to one embodiment of the present application;

FIG. 8e is a schematic diagram of a node in a starting point growing tree according to an embodiment of the present application, where the corresponding position belongs to an end point region;

FIG. 8f is a schematic diagram of generating a travel path according to an embodiment of the present application;

fig. 9 is a block diagram of a path generating apparatus according to an embodiment of the present application;

fig. 10 is a block diagram of a server according to an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

As used in the present description and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".

Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

In order to explain the technical scheme of the application, the following examples are used for illustration.

Referring to fig. 1, fig. 1 is a flowchart illustrating an implementation of a path generating method according to an embodiment of the present application, including:

step 101, generating a starting point growth tree and a plurality of random growth trees according to the starting point information and the end point information of the target robot.

The target robot is a robot that needs to perform path planning, such as a full-automatic navigation robot, an autopilot robot, an unmanned aerial vehicle transport robot, etc. that needs to perform path planning.

The start point information may be various information indicating the position of the start point, for example, longitude and latitude coordinates of the start point, coordinates of the start point in the target robot coordinate system, or even a preset position code such as a 001.

The destination information may be various information indicating the location of the destination, for example, latitude and longitude coordinates of the destination, coordinates of the destination in the target robot coordinate system, or even a predetermined location code such as B002.

Wherein the starting point of the starting point growing tree is the starting point indicated by the starting point information, and the starting point of the random growing tree is a random position point. Here, the random position point may be any point selected in a spatial range formed by the start point and the end point, and the selected random position point is used as the start point of the random growth tree.

In the present embodiment, the execution subject of the above-described path generation method is typically a server, such as a path generation server for generating a travel path for the target robot to travel from a start point to an end point. The server may be hardware or software. When the server is hardware, the server may be implemented as a distributed server cluster formed by a plurality of servers, or may be implemented as a single server. When the server is software, it may be implemented as a plurality of software or software modules, or may be implemented as a single software or software module, which is not particularly limited herein.

In practice, the execution body may generate a spatial range including the start point indicated by the start point information and the end point indicated by the end point information based on the start point information and the end point information of the target robot, and in the spatial range, the execution body may generate a start point growth tree with the position indicated by the start point information as the start point, and select any point in the spatial range as the start point to generate a random growth tree. Here, the execution body may select a plurality of random position points within a spatial range, and for each random position point, the execution body may generate a random growth tree with the random position point as a starting point. As one example, the execution body described above may employ a fast extended random tree algorithm (Rapidly-exploring Random Tree, RRT) for the starting point and each random location point, generating a starting point growth tree and a plurality of random growth trees. As another example, the execution subject described above may also employ a Multi-Tree rapid expansion random Tree algorithm (MT-RRT) to generate the starting growing Tree and the plurality of random growing trees in a spatial domain.

Step 102, in the process of growing the starting point growing tree and the random growing tree, if the target random growing tree meeting the preset distance condition is detected, fusing the target random growing tree to the starting point growing tree according to the motion information of the target robot, the position information of each node in the starting point growing tree at the current moment and the position information of each node in the target random growing tree, and switching the starting point growing tree to the fused starting point growing tree.

Wherein the preset distance condition is a preset distance condition. In practice, the preset distance condition may include: the minimum distance between the random growth tree and the starting point growth tree is less than a preset interval threshold. Here, the distance between the random growth tree and the starting point growth tree may be determined by a distance between a node in the random growth tree and a node in the starting point growth tree, and a minimum value among the distances between the node in the random growth tree and the node in the starting point growth tree is taken as a minimum distance between the random growth tree and the starting point growth tree.

Wherein the target random growth tree is a random growth tree satisfying a preset distance condition.

The motion information of the target robot may include a speed, an angular speed, an acceleration, and an angular acceleration of the target robot.

The position information of each node in the starting point growth tree may be the coordinates of each node in the starting point growth tree, and the position information of each node in the target random growth tree may be the coordinates of each node in the target random growth tree.

In practice, both the starting growing tree and the plurality of random growing trees in the spatial range will grow continuously. As an example, the execution body may implement the growth of the starting point growth tree and the plurality of random growth trees by taking an existing node in the starting point growth tree or the random growth tree as a center, randomly selecting a growth point within a preset range of the node, and connecting the growth point with the node in the center.

In practice, in the process of growing the starting point growing tree and the random growing tree, the executing body can obtain the minimum distance between each random growing tree and the starting point growing tree through the coordinates of each node in each random growing tree and the coordinates of each node in the starting point growing tree in a space range, and detect whether the random growing tree meets a preset distance condition or not through detecting the size relation between the minimum distance and a preset interval threshold value. When the minimum distance between the random growth tree and the starting point growth tree is smaller than a preset interval threshold, the executing body can judge that the random growth tree meets a preset distance condition, the random growth tree is used as a target random growth tree, and when the minimum distance between the random growth tree and the starting point growth tree is larger than or equal to the preset interval threshold, the executing body can judge that the random growth tree does not meet the preset distance condition, and the random growth tree can continue to grow.

After detecting the target random growth tree satisfying the preset distance condition, the execution body may fuse the target random growth tree to the starting point growth tree by the following steps one to six.

Step one, the executing body may establish a sampling range including all nodes of the target random growth tree based on the position information of each node in the target random growth tree. Here, the sampling range may be a range of all node compositions of the target random growth tree, or may be a range of areas including the target random growth tree.

And step two, the execution main body can randomly sample in a sampling range to obtain a random sampling point, and a target starting point growth tree node with the minimum distance from the random sampling point in the starting point growth tree is obtained through the position information of the random sampling point and the position information of each node in the starting point growth tree. Specifically, the executing body can determine the distances between the random sampling points and all nodes of the starting point growth tree through the coordinates of the random sampling points and the coordinates of all nodes in the starting point growth tree, so that a target starting point growth tree node with the minimum distance from the random sampling points in the starting point growth tree is obtained.

And thirdly, the execution main body can obtain a plurality of alternative position points through the motion information of the target robot. In practice, the executing body may obtain the maximum speed and the minimum speed of the target robot in the preset time step based on the speed, the acceleration and the preset time step in the motion information of the target robot, and obtain the speed value range of the target robot through the discrete parameters of the maximum speed, the minimum speed and the preset speed. Here, the speed value range is a range including a plurality of speed values of the target robot. For example, if the maximum speed of the target robot is 2, the minimum speed is 1, and the preset discrete parameter is 2 in the preset time step, the speed value range of the target robot in the preset time step may include {1,1.5,2}. The executing body can obtain the maximum angular velocity and the minimum angular velocity of the target robot in the preset time step based on the angular velocity, the angular acceleration and the preset time step in the motion information of the target robot, and obtain the angular velocity value range of the target robot through the maximum angular velocity, the minimum angular velocity and the preset angular velocity discrete parameters. Here, the angular velocity value range is a range including a plurality of angular velocity values of the target robot. For example, if the maximum angular velocity of the target robot is 1 and the minimum angular velocity is 0 and the preset discrete parameter is 2 in the preset time step, the range of the angular velocity value of the target robot in the preset time step may include {0,0.5,1}. After obtaining the speed value range and the angular speed value range within the preset time step, the executing body may combine the speed value in the speed value range and the angular speed in the angular speed value range to obtain a plurality of motion combinations, where each motion combination includes a speed value and an angular speed value, and the target robot moves to a corresponding candidate position point according to the speed value and the angular speed value in the motion combination. The execution body can obtain a plurality of alternative position points which can be reached by the target robot in a preset time step through the growth tree node of the target starting point and the obtained plurality of motion combinations.

And step four, the execution body can obtain the target position point meeting the preset position point selection condition from the plurality of the candidate position points through the position information of each candidate position point, the position information of the random sampling point and the preset position point selection condition. Here, the position point selection condition may be that a position point having the smallest cost to a random sampling point is selected from a plurality of candidate position points as the target position point. In practice, the execution body may pre-establish a cost function for representing the target robot from one point to another point, calculate a cost value from each candidate location point to a random sampling point through the cost function, and use the candidate location point with the smallest corresponding cost value as the target location point. Here, the cost function may be used to calculate a distance cost and/or an angle cost of the target robot from one point to another point, and when the cost function is used to calculate the distance cost and the angle cost, a distance cost parameter and an angle cost parameter may be set for the distance cost and the angle cost, respectively. For example, the above-described execution subject may calculate the cost value of the target robot from the candidate position point to the random sampling point by the following cost function:

C ₀ ＝w ₁ ·C ₁ +w ₂ ·∣C ₂ ∣

Wherein C is ₀ Is the cost value, w, of the target robot from the alternative position point to the random sampling point ₁ Is a distance cost parameter, C ₁ Is the distance cost, w, of the target robot from the alternative position point to the random sampling point ₂ Is an angle cost parameter, C ₂ Is the angular cost from the alternative position point to the random sampling point of the target robot, and the distanceSeparation cost C ₁ The determination can be made by the following formula:

wherein C is ₁ Is the distance cost of the target robot from the alternative position point to the random sampling point, x ₁ Position information, x, of the candidate position point ₀ Is the position information of random sampling points, |x ₁ -x ₀ || is x ₁ -x ₀ Euclidean norm, x _s Is the starting point position information, x _g Is the end point position information of the object, ||x _s -x _g || is x _s -x _g Euclidean norms of (c).

Cost of angle C ₂ The determination can be made by:

wherein C is ₂ Is the angular cost of the target robot from the alternative location point to the random sampling point,is the ordinate of the alternative location point, +.>Is the ordinate of the random sampling point, +.>Is the abscissa of the alternative location point, +.>Is the abscissa of the random sampling point, +.>Is the angular value of the target robot at the alternative location point.

And fifthly, the execution main body can fuse the target position point corresponding to the target random growth tree to the starting point growth tree in a mode of connecting the target position point and the target starting point growth tree node. In practice, the execution body may store the position information of the target position point in the start point growth tree, and use the target position point as a new node of the start point growth tree.

And step six, the execution main body can continue to randomly sample within the sampling range to obtain a new random sampling point, repeat the steps based on the new random sampling point to obtain a new target position point, and fuse the new target position point into the starting point growth tree until the random sampling frequency within the sampling range reaches the preset sampling frequency. Here, when the number of sampling times of the execution subject reaches a preset number of sampling times, the execution subject may fuse the target random growth tree to the starting point growth tree. The preset number of samples may be the same as the number of nodes of the target random growth tree.

After the target random growth tree is fused to the starting growth tree, the execution body may update node information of the starting growth tree, and switch the starting growth tree to the fused starting growth tree. Meanwhile, the execution main body can delete the target random tree and the nodes thereof, so that the influence on the growth and fusion of the starting point growth tree and other random growth trees due to the fact that the fused target random growth tree exists all the time is avoided.

Step 103, when there is a node whose corresponding position belongs to the end point region in the start point growth tree, a travel path for the target robot to travel from the start point to the end point is generated according to the start point growth tree.

The end point area is an area including an end point indicated by end point information, which is set in advance. In practice, the end point region may be a circular region with a preset length as a radius, and the end point is used as a center of a circle.

In practice, when there is a node whose corresponding position belongs to the end region in the start growth tree, the start growth tree and all the random growth trees in the spatial range stop growing.

In practice, the execution body may determine whether a node whose corresponding position belongs to the end region exists in the start growth tree by position information of each node in the start growth tree. When there is a node in the start growth tree whose corresponding position belongs to the end region, there is a node set in the start growth tree that can be connected from the start point to the end point, and the execution body can obtain a travel path for the target robot to travel from the start point to the end point through the node set in the start growth tree that can be connected from the start point to the end point. Specifically, the executing body may search for a target starting point growth tree node connected with a node corresponding to the position belonging to the end point region in the starting point growth tree through node information of the starting point growth tree, then search for a last starting point growth tree node connected with the target starting point growth tree node, sequentially search for the last starting point growth tree node, sequentially connect the searched node set connected from the starting point to the end point until the starting point of the starting point growth tree is found, and use the connected path as a running path of the target robot for the target robot to run from the starting point to the end point.

According to the path generation method provided by the embodiment, firstly, a starting point growth tree and a plurality of random growth trees are generated according to starting point information and end point information of a target robot, wherein the starting point of the starting point growth tree is the starting point indicated by the starting point information, and the starting point of the random growth tree is a random position point. Then, in the process of growing the starting point growing tree and the random growing tree, if the target random growing tree meeting the preset distance condition is detected, fusing the target random growing tree to the starting point growing tree according to the motion information of the target robot, the position information of each node in the starting point growing tree at the current moment and the position information of each node in the target random growing tree, and switching the starting point growing tree to the fused starting point growing tree. Finally, when a node of which the corresponding position belongs to the end point area exists in the starting point growing tree, a driving path for the target robot to drive from the starting point to the end point is generated according to the starting point growing tree. When the travel path of the target robot is generated, the start point growth tree which can run from the start point to the end point is formed through the growth and fusion of the start point growth tree and the random growth tree, so that the travel path for the target robot to run from the start point to the end point is obtained based on the start point growth tree, a map is not required to be constructed through a camera and a sensor, a large amount of calculation amount is consumed to search the travel path, and the efficiency of generating the travel path is improved.

Referring to fig. 2, fig. 2 is a flowchart of an implementation of merging a target random growth tree into a starting growth tree according to an embodiment of the present application, including:

step 201, the following node selection step is performed: a first target node is selected from the starting point growth tree and a second target node is selected from the target random growth tree.

The first target node is a node meeting a preset distance condition in the starting point growth tree, and the second target node is a node meeting the preset distance condition in the target random growth tree. The minimum distance between the starting point growth tree and the random growth tree is that the node in the corresponding starting point growth tree is a first target node, and the node in the corresponding random growth tree is a second target node.

In practice, the executing body can obtain the distance between each node in the starting point growing tree and each node in the target random growing tree through the position information of each node in the starting point growing tree at the current moment and the position information of each node in the target random growing tree, select the node in the starting point growing tree corresponding to the minimum distance as the first target node, and select the node in the random growing tree as the second target node.

Referring to fig. 3, fig. 3 is a schematic diagram of a starting growing tree and a target random growing tree according to an embodiment of the application. As shown in fig. 3, when the distance between the starting point growing tree and the random growing tree is the smallest, the node in the corresponding starting point growing tree is the node a, and the node B in the corresponding target random growing tree, the executing body may select the node a in the starting point growing tree as the first target node, and select the node B in the target random growing tree as the second target node.

Step 202, determining a target growing point which can be reached by the movement of the target robot according to the movement information of the target robot and the target Gaussian point of the selected second target node, connecting the target growing point with the first target point, and deleting the selected second target node in the target random growing tree.

The motion information of the target robot comprises the speed, the angular speed, the acceleration and the angular acceleration of the target robot.

And the target Gaussian points of the second target nodes are Gaussian modeling for the second target nodes to obtain Gaussian distribution ranges corresponding to the second target nodes, and the Gaussian points are randomly selected from the Gaussian distribution ranges.

In practice, the executing body may determine a target growing point that can be reached by the movement of the target robot according to the movement information of the target robot and the selected target gaussian point of the second target node by performing the following first to fifth steps, and connect the target growing point with the first target point.

The first step, the executing body may obtain a maximum speed and a minimum speed of the target robot within a preset time step based on the speed, the acceleration and the preset time step in the motion information of the target robot, and obtain a speed value range of the target robot through discrete parameters of the maximum speed, the minimum speed and the preset speed.

And a second step, the executing body can obtain the maximum angular velocity and the minimum angular velocity of the target robot in the preset time step based on the angular velocity, the angular acceleration and the preset time step in the motion information of the target robot, and obtain the angular velocity value range of the target robot through the maximum angular velocity, the minimum angular velocity and the preset angular velocity discrete parameters.

And thirdly, the executing body can combine the speed value in the speed value range and the angular speed in the angular speed value range to obtain a plurality of motion combinations, each motion combination comprises a speed value and an angular speed value, and the target robot moves to a corresponding growth point according to the speed value and the angular speed value in the motion combination. The execution body can obtain a plurality of growing points which can be reached by the target robot in a preset time step through the combination of the position information of the first target node and the obtained plurality of movements.

Fourth, the execution subject can calculate the growth points to the corresponding points through a pre-established cost functionAnd selecting a growing point with the lowest cost from each growing point to the target Gaussian point as a target growing point according to the cost of the target Gaussian point corresponding to the second target point. For example, referring to fig. 4, fig. 4 is a schematic diagram illustrating selecting a target growth point according to an embodiment of the application. As shown in fig. 4, the node a is a first target node in the starting point growth tree, the node B is a second target node in the target random growth tree, and the point G is a target gaussian point selected randomly from the gaussian distribution range, where the second target node is gaussian modeled by the second target node to obtain the gaussian distribution range corresponding to the second target node. The execution body obtains a growing point which can be reached by the target robot in a preset time step through the position information of the first target node A and a plurality of motion combinations, wherein the growing point comprises a growing point M ₁ Growth point M ₂ And a growth point M ₃ After that, the execution subject can obtain the growth point M through a pre-established cost function ₁ The cost to the target Gaussian point G is 2.5, and the growth point M ₂ The cost to the target Gaussian point G is 1, and the growth point M ₃ The cost to the target Gaussian point G is 3, and the growth point M is known by comparison ₂ The cost to the target Gaussian point G is minimal, and the execution body can select the growth point M ₂ As a target growth point.

Fifth, the execution body may connect the target growing point with the first target point, so that the target growing point becomes a new node of the starting point growing tree. For example, referring to fig. 5, fig. 5 is a schematic diagram of a connection between a target growth point and a first target point according to an embodiment of the application. As shown in FIG. 5, in determining M ₂ After the target growth point is reached, the execution body may execute the target growth point M ₂ Is connected with the first target point A so that the target growth point M ₂ Becomes a new node of the starting point growth tree.

After connecting the target growing point and the first target node, the executing body may delete the selected second target node in the target random growing tree by deleting the node information of the second target node from the target random growing tree. Referring to FIG. 6, FIG. 6 is a diagram illustrating a delete selected delete operation according to an embodiment of the present application Is a schematic diagram of a second target node of the network. As shown in FIG. 6, at the ligation target growth point M ₂ After the first target node a, the execution body deletes the second target node B from the target random growth tree.

Step 203, the node selection step is continued until no node exists in the target random growth tree.

In practice, the executing body may execute the node selection step for the target random growth tree, perform gaussian modeling on the nodes in the target random tree, select the target gaussian points from the gaussian distribution range corresponding to the nodes, obtain the target growth points through the target gaussian distribution points and the motion information of the target robot, and fuse the target growth points to the starting point growth tree until no nodes exist in the target random tree.

According to the path generation method provided by the embodiment, the second target node in the target random tree is subjected to Gaussian modeling, the target point is randomly selected from the Gaussian distribution range of the second target node, and the target growth point is obtained through the target point and the motion information of the target robot, so that the target growth point is close to the second target node as much as possible, the selection range of the target growth point is expanded, the condition that the second target node is used as the target growth point is avoided, the growth stability of the starting point growth tree is improved, and the efficiency of generating the driving path is improved.

In some embodiments, when the executing body detects the target random growth tree meeting the preset distance condition, it may also directly perform gaussian modeling on all nodes of the target random growth tree, referring to fig. 7, fig. 7 is a schematic diagram of performing gaussian modeling on all nodes of the target random growth tree according to an embodiment of the present application, and as shown in fig. 7, when detecting the target random growth tree meeting the preset distance condition, directly performing gaussian modeling on all nodes of the target random growth tree, so as to obtain a gaussian distribution range of each node. In practice, the executing body can mix the gaussian models of all nodes in the target random growth tree through the gaussian mixture model to obtain a gaussian distribution range corresponding to the target random growth tree, the gaussian distribution range corresponding to the target random growth tree can be used as heuristic information for sampling and used for guiding the executing body to sample, when the executing body selects sampling points for the target random growth tree, the sampling points can be made to be as close to all nodes of the target random growth tree as possible, meanwhile, sampling of all nodes of the target random growth tree is avoided, and the range of the sampling points is improved.

In some embodiments, prior to fusing the target random growth tree to the starting growth tree, the method may further comprise: and if the target nodes with the corresponding positions matched with the positions of the obstacles exist in the target random growth tree, deleting the target nodes in the target random growth tree.

The matching with the position of the obstacle may be that the distance between the node and the obstacle is smaller than a preset safety distance, or that the connecting line between the node and the starting point growth tree collides with the obstacle.

In practice, before the target random growth tree is fused to the starting point growth tree, all nodes in the target random growth tree are detected through the position information of each node in the target random growth tree and the pre-stored obstacle position information, and when the target node with the corresponding position matched with the obstacle position in the target random growth tree is detected, the target node is deleted from the target random growth tree. As an example, the execution body may compare the coordinates of each node in the target random growth tree and the connection line of the node and the starting point growth tree with the coordinate range of the obstacle, and if the coordinates of the node existing in the target random growth tree are within the coordinate range of the obstacle and/or the connection line of the node and the starting point growth tree is within the coordinate range of the obstacle, may determine that the corresponding position of the node matches the position of the obstacle, use the node as the target node, and delete the target node from the target random growth tree.

According to the node deleting method provided by the embodiment, before the target random growth tree is fused to the starting point growth tree, the target node matched with the obstacle position is deleted from the target random growth tree, so that the collision between the running path generated by the starting point growth tree and the obstacle is avoided, and the running path is invalid.

In some embodiments, the execution subject may generate the travel path as follows.

First, the execution body may generate the start-point growth tree and the plurality of random growth trees within a spatial range formed by the start point and the end point, referring to fig. 8a, fig. 8a is a schematic diagram of generating the start-point growth tree and the plurality of random growth trees according to an embodiment of the present application.

Then, the executing body may detect the distance between the starting point growing tree and the random growing tree by using the information of each node in the starting point growing tree and the information of each node in the random growing tree in the growing process of the starting point growing tree and the random growing tree, and when detecting the target random growing tree meeting the preset distance condition, the executing body may perform gaussian modeling on each node in the target random growing tree to obtain a gaussian distribution range corresponding to each node in the target random growing tree, please refer to fig. 8b and 8c, fig. 8b is a schematic diagram of detecting the target random growing tree meeting the preset distance condition provided by an embodiment of the present application, and fig. 8c is a schematic diagram of performing gaussian modeling on each node in the target random growing tree provided by an embodiment of the present application.

Then, the executing body may fuse the target random growth tree to the starting point growth tree, switch the starting point growth tree to the fused starting point growth tree, delete the target random tree growth tree and the node information in the target random growth tree, please refer to fig. 8d, fig. 8d is a schematic diagram of the fusion of the target random growth tree to the starting point growth tree according to an embodiment of the present application.

Next, the executing body may continue to detect the distance between the starting point growth tree and each random growth book within the spatial range, and fuse the target random growth book satisfying the preset distance condition to the starting point growth tree until there is a node in the starting point growth tree whose corresponding position belongs to the end point region, and please refer to fig. 8e, which is a schematic diagram of the starting point growth tree in which there is a node in the starting point growth tree whose corresponding position belongs to the end point region according to an embodiment of the present application.

Finally, when it is detected that there is a node whose corresponding position belongs to the destination area in the start point growth tree, the execution body may generate a travel path for the target robot to travel from the start point to the destination based on the start point growth tree, and referring to fig. 8f, fig. 8f is a schematic diagram of generating the travel path according to an embodiment of the present application.

In some embodiments, the method may further comprise: and in the process of growing the starting point growing tree and the random growing tree, if the random growing point is detected and the distance between the random growing point and the target growing tree meets the preset connection condition, fusing the random growing point into a node of the target growing tree.

Wherein the target growth tree comprises a starting growth tree and/or a random growth tree.

The preset connection condition may include that a distance between the random growth point and the target growth tree is smaller than a preset connection distance threshold. In practice, the distance between the random growth point and the target growth tree is typically very close when the distance between the random growth point and the target growth tree is less than a predetermined connection distance threshold.

In practice, in the process of growing the starting point growing tree and the random growing tree, the executing body may randomly generate random growing points in a space range formed by the starting point and the end point at intervals of preset time. When the random growth points are detected, the execution main body can obtain the distances between the random growth points and the nodes in the starting point growth tree and the distances between the random growth points and the nodes in the random growth tree through the position information of the random growth points, the position information of the nodes in the starting point growth tree and the position information of the nodes in all the random growth trees. When the random growth point is detected, and the distance between the random growth point and the target growth tree is smaller than a preset connection distance threshold value, the execution main body can store the position information of the random growth point into the target growth tree, and connect the random growth point with the node closest to the target growth tree, so that the random growth point is fused into the node of the target growth tree.

According to the random growth point fusion method provided by the embodiment, when the random growth points are detected, and the distance between the random growth points and the target growth tree is smaller than the preset connection distance threshold, the random growth points are fused into the nodes of the target growth tree, so that the phenomenon that a new random growth tree is generated by taking the random growth points close to the target growth tree as a starting point, and the newly generated random growth tree is intersected with the original target growth tree can be avoided.

In some embodiments, the method may further comprise: and if the distance between the random growth point and the target growth tree does not meet the preset connection condition, generating a new random growth tree by taking the random growth point as a starting point.

In practice, when the distance between the random growth point and the target growth tree does not meet the preset connection condition, the distance between the random growth point and the target growth tree is usually relatively long, and the execution body may generate a new random growth tree with the random growth point as a starting point by adopting an RRT algorithm or an MT-RRT algorithm.

According to the path generation method provided by the embodiment, when the distance between the random growth point and the target growth tree does not meet the preset connection condition, a new random growth tree is generated by taking the random growth point as a starting point, so that the generation speed of the growth tree in the space range can be improved, the starting point growth tree can be rapidly expanded in the space range, and the speed of generating the running path is improved.

In some embodiments, the method may further comprise: and determining the tree distance between every two random growing trees according to the position information of the nodes in each random growing tree, and fusing at least two random growing trees with the corresponding tree distance meeting the preset fusion condition.

Wherein the tree distance between every two random growth trees can be determined by the minimum distance between each node in one random growth tree and each node in another random growth tree.

The preset fusion condition is a preset fusion distance threshold. In practice, the distance between two random growth trees meeting the preset fusion condition is relatively close.

In practice, the executing body can obtain the minimum distance between every two random growth trees through the position information of each node in one random growth tree and the position information of each node in the other random growth tree, and the minimum distance is used as the tree distance between every two random upper trees.

In practice, after obtaining the tree distance between two random growth trees, the executing body may compare the tree distance with a preset fusion distance threshold, and when the tree distance is smaller than the preset fusion distance threshold, the executing body may fuse one random growth tree of the two random growth trees into the other random growth tree. As an example, the execution body may connect two nodes corresponding to two random growth trees with a minimum distance, and store all node information in one random growth tree into another random growth tree.

According to the method for fusing the random growth tree, at least two random growth trees with the corresponding tree distances meeting the preset fusion conditions are fused, so that the speed of fusing the random growth tree to the starting point growth tree can be increased, the growth speed of the starting point growth tree is increased, and the speed of generating a running path is increased.

In some embodiments, the method may further comprise: and when the preset growth conditions are met, controlling the starting point growth tree and/or the random growth tree to grow.

Wherein the preset growth conditions comprise at least one of the following: the number of times of growing the starting point growing tree and/or the random growing tree is smaller than the preset number of times of growing the starting point growing tree and/or the random growing tree, the growing time of the starting point growing tree and/or the random growing tree is smaller than the preset growing time, and no node of which the corresponding position belongs to the end point area exists in the starting point growing tree.

In practice, the execution body may count the number of times of growing the starting point growing tree and/or the random growing tree and the growing time of the starting point growing tree and/or the random growing tree, and compare the position information of each node in the starting point growing tree with the end point region.

In practice, when the number of times of growing the starting point growing tree and/or the random growing tree is smaller than the preset number of times of growing the starting point growing tree and/or the random growing tree, the growing time of the starting point growing tree and/or the random growing tree is smaller than the preset growing time, and no node with the corresponding position belonging to the end point area exists in the starting point growing tree, the executing body can continue to adopt the RRT algorithm or the MT-RRT algorithm to control the starting point growing tree and/or the random growing tree to grow.

In practice, when the number of times of growing the starting point growing tree and/or the random growing tree is greater than or equal to the preset number of times of growing the starting point growing tree and/or the random growing tree, the growing time of the starting point growing tree and/or the random growing tree is greater than or equal to the preset growing time, and a node with a corresponding position belonging to the end point area exists in the starting point growing tree, the executing body can stop using the tree growing algorithm, and control the starting point growing tree and/or the random growing tree to stop growing. In practice, after the execution body controls the starting point growth tree and/or the random growth tree to stop growing, the existing starting point growth tree and random growth tree can be deleted, and the starting point growth tree and the random growth tree can be regenerated in a space range by adopting an RRT algorithm or an MT-RRT algorithm.

According to the growth control method for the growth tree, when the preset growth conditions are met, the starting point growth tree and/or the random growth tree are controlled to grow, so that the stability of a generated running path can be improved; when the preset growth conditions are not met, the starting point growth tree and/or the random growth tree are controlled to stop growing, the existing starting point growth tree and random growth tree are deleted, the starting point growth tree and the random growth tree are regenerated in a space range, the starting point growth tree is prevented from being expanded in the space range all the time without nodes of which the corresponding positions belong to the end point area, and the efficiency of generating the running path is improved.

Referring to fig. 9, fig. 9 is a block diagram of a path generating device 900 according to an embodiment of the present application, including:

an information obtaining unit 901, configured to generate a starting point growing tree and a plurality of random growing trees according to starting point information and end point information of a target robot, where a starting point of the starting point growing tree is a starting point indicated by the starting point information, and a starting point of the random growing tree is a random position point;

the information fusion unit 902 is configured to fuse, when a target random growth tree satisfying a preset distance condition is detected during the growth of the starting point growth tree and the random growth tree, the target random growth tree to the starting point growth tree according to the motion information of the target robot, the position information of each node in the starting point growth tree at the current time, and the position information of each node in the target random growth tree, and switch the starting point growth tree to the fused starting point growth tree;

the path generation unit 903 is configured to generate a travel path for the target robot to travel from the start point to the end point according to the start point long tree when there is a node whose corresponding position belongs to the end point region in the start point long tree.

In some embodiments, the information fusion unit 902 includes a node selection module, a node connection module, and a selection circulation module (not shown in the figure), where the fusion of the target random growth tree to the starting growth tree is determined by a combination of the node selection module, the node connection module, and the selection circulation module according to the motion information of the target robot, the position information of each node in the starting growth tree at the current time, and the position information of each node in the target random growth tree in the information fusion unit 902.

The node selection module is used for selecting a second target node from the target random growth tree and selecting a first target node from the starting point growth tree, wherein the first target node is a node meeting a preset distance condition in the starting point growth tree, and the second target node is a node meeting the preset distance condition in the target random growth tree;

the node connection module is used for determining a target growing point which can be reached by the movement of the target robot according to the movement information of the target robot and the target Gaussian point of the selected second target node, connecting the target growing point with the first target point and deleting the selected second target node in the target random growing tree;

and the selecting and circulating module is used for continuously executing the node selecting step until no node exists in the target random growth tree.

In some embodiments, the apparatus further includes a node deleting unit (not shown in the figure) configured to delete the target node in the target random growth tree if it is detected that there is a target node in the target random growth tree whose corresponding position matches the obstacle position, before the target random growth tree is merged into the starting point growth tree.

In some embodiments, the apparatus further includes a random growth unit (not shown in the figure) configured to fuse the random growth points into nodes of the target growth tree if the random growth points are detected and a distance between the random growth points and the target growth tree satisfies a preset connection condition during the growth of the starting point growth tree and the random growth tree, where the target growth tree includes the starting point growth tree and/or the random growth tree.

In some embodiments, a random growth unit (not shown in the figures) is specifically further configured to: and if the distance between the random growth point and the target growth tree does not meet the preset connection condition, generating a new random growth tree by taking the random growth point as a starting point.

In some embodiments, the apparatus further includes a tree fusion unit (not shown in the figure) configured to determine a tree distance between every two random growing trees according to the position information of the nodes in each random growing tree, and fuse at least two random growing trees whose corresponding tree distances satisfy a preset fusion condition.

In some embodiments, the apparatus further comprises a growth control unit (not shown in the figure) for controlling the growth of the starting growing tree and/or the random growing tree when a preset growth condition is satisfied, wherein the preset growth condition includes at least one of the following: the number of times of growing the starting point growing tree and/or the random growing tree is smaller than the preset number of times of growing the starting point growing tree and/or the random growing tree, the growing time of the starting point growing tree and/or the random growing tree is smaller than the preset growing time, and no node of which the corresponding position belongs to the end point area exists in the starting point growing tree.

According to the device provided by the embodiment, firstly, a starting point growing tree and a plurality of random growing trees are generated according to starting point information and end point information of a target robot, wherein the starting point of the starting point growing tree is the starting point indicated by the starting point information, and the starting point of the random growing tree is a random position point. Then, in the process of growing the starting point growing tree and the random growing tree, if the target random growing tree meeting the preset distance condition is detected, fusing the target random growing tree to the starting point growing tree according to the motion information of the target robot, the position information of each node in the starting point growing tree at the current moment and the position information of each node in the target random growing tree, and switching the starting point growing tree to the fused starting point growing tree. Finally, when a node of which the corresponding position belongs to the end point area exists in the starting point growing tree, a driving path for the target robot to drive from the starting point to the end point is generated according to the starting point growing tree. When the travel path of the target robot is generated, the start point growth tree which can run from the start point to the end point is formed through the growth and fusion of the start point growth tree and the random growth tree, so that the travel path for the target robot to run from the start point to the end point is obtained based on the start point growth tree, a map is not required to be constructed through a camera and a sensor, a large amount of calculation amount is consumed to search the travel path, and the efficiency of generating the travel path is improved.

It should be understood that, in the block diagram of the path generating device 900 shown in fig. 9, each unit is configured to perform each step in the embodiments corresponding to fig. 1 and 2, and each step in the embodiments corresponding to fig. 1 and 2 is explained in detail in the foregoing embodiments, and specific reference is made to fig. 1 and 2 and the related descriptions in the embodiments corresponding to fig. 1 and 2, which are not repeated herein.

Referring to fig. 10, fig. 10 is a block diagram of a server 1000 according to an embodiment of the present application, where the server 1000 includes: at least one processor 1001 (only one processor is shown in fig. 10), a memory 1002, and a computer program 1003 stored in the memory 1002 and executable on the at least one processor 1001, such as a path generation program. The processor 1001, when executing the computer program 1003, implements the steps in the embodiments of the respective path generation methods described above. The processor 1001 executes the functions of the respective modules/units in the respective apparatus embodiments described above, for example, the functions of the information acquisition unit 901 to the path generation unit 903 shown in fig. 9 when executing the computer program 1003.

By way of example, computer program 1003 may be split into one or more units, one or more units being stored in memory 1002 and executed by processor 1001 to carry out the application. One or more elements may be a series of computer program instruction segments capable of performing a specified function, which are intended to describe the execution of the computer program 1003 in the server 1000. For example, the computer program 1003 may be divided into an information acquisition unit, an information fusion unit, and a path generation unit, and specific functions of each unit are described in the above embodiments, and are not described here again.

The server 1000 may be a computing device such as a server, desktop computer, tablet computer, cloud server, mobile terminal, and the like. The server 1000 may include, but is not limited to, a processor 1001, a memory 1002. It will be appreciated by those skilled in the art that fig. 9 is merely an example of a server 1000 and is not meant to limit the server 1000, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., a server may further include input-output devices, network access devices, buses, etc.

The processor 1001 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 1002 may be an internal storage unit of the server 1000, such as a hard disk or a memory of the server 1000. The memory 1002 may be an external storage device of the server 1000, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the server 1000. Alternatively, the memory 1002 may also include both internal storage units and external storage devices of the server 1000. The memory 1002 is used to store computer programs and other programs and data required by the turntable device. The memory 1002 may also be used to temporarily store data that has been output or is to be output.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated modules, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the present application implements all or part of the flow in the method of the above embodiment, and a computer program that can be implemented by a computer program to instruct related hardware may be stored in a computer readable storage medium, where the computer program when executed by a processor may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims

1. A method of path generation, the method comprising:

generating a starting point growing tree and a plurality of random growing trees according to starting point information and end point information of a target robot, wherein the starting point of the starting point growing tree is a starting point indicated by the starting point information, and the starting point of the random growing tree is a random position point;

And when a node of which the corresponding position belongs to the end point area exists in the starting point growing tree, generating a running path for the target robot to run from the starting point to the end point according to the starting point growing tree.

2. The path generating method according to claim 1, wherein the fusing the target random growth tree to the starting point growth tree based on the motion information of the target robot, the position information of each node in the starting point growth tree at the current time, and the position information of each node in the target random growth tree, comprises:

the following node selection steps are executed: selecting a first target node from the starting point growth tree, and selecting a second target node from the target random growth tree, wherein the first target node is a node meeting the preset distance condition in the starting point growth tree, and the second target node is a node meeting the preset distance condition in the target random growth tree;

determining a target growing point which can be reached by the movement of the target robot according to the movement information of the target robot and the target Gaussian point of the selected second target node, connecting the target growing point with the first target point, and deleting the selected second target node in the target random growth tree;

3. The path generation method according to claim 1, wherein before fusing the target random growth tree to the starting point growth tree, the method further comprises: and if the target node with the corresponding position matched with the obstacle position exists in the target random growth tree, deleting the target node in the target random growth tree.

4. The path generation method according to claim 1, characterized in that the method further comprises:

and in the process of growing the starting point growing tree and the random growing tree, if a random growing point is detected and the distance between the random growing point and a target growing tree meets a preset connection condition, fusing the random growing point into a node of the target growing tree, wherein the target growing tree comprises the starting point growing tree and/or the random growing tree.

5. The path generation method according to claim 4, characterized in that the method further comprises:

6. The path generation method according to claim 1, characterized in that the method further comprises:

7. The path generation method according to any one of claims 1 to 6, characterized in that the method further comprises:

when a preset growth condition is met, controlling the starting point growth tree and/or the random growth tree to grow, wherein the preset growth condition comprises at least one of the following steps: the number of times of the growth of the starting point growth tree and/or the random growth tree is smaller than a preset number of times of the growth of the starting point growth tree and/or the random growth tree, the growth time of the starting point growth tree and/or the random growth tree is smaller than a preset growth time, and no node with the corresponding position belonging to the terminal area exists in the starting point growth tree.

8. A path generating apparatus, comprising:

an information acquisition unit, configured to generate a starting point growth tree and a plurality of random growth trees according to starting point information and end point information of a target robot, where a starting point of the starting point growth tree is a starting point indicated by the starting point information, and a starting point of the random growth tree is a random position point;

and the path generation unit is used for generating a driving path for the target robot to drive from the starting point to the end point according to the starting point long tree when the node of which the corresponding position belongs to the end point area exists in the starting point long tree.

9. A server comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the path generation method according to any of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the path generation method according to any one of claims 1 to 7.