WO2021164277A1

WO2021164277A1 - Spatial sampling method, apparatus, device, and medium applied to path planning

Info

Publication number: WO2021164277A1
Application number: PCT/CN2020/120756
Authority: WO
Inventors: 何敏聪; 周宸; 周宝; 陈远旭
Original assignee: 平安科技（深圳）有限公司
Priority date: 2020-07-31
Filing date: 2020-10-14
Publication date: 2021-08-26
Also published as: CN111906765A; CN111906765B

Abstract

Provided are a spatial sampling method, apparatus, device, and medium applied to path planning, said method comprising: determining an effective point set S_G of a state space S by means of a pre-sampling method, any point in the effective point set S_G being mapped in a feasible region Q_L of a state space Q via a first mapping relationship; according to a preset random selection rule, selecting as an execution strategy a sampling strategy from among a designated number of sampling strategies, the designated number of sampling strategies comprising at least a first sampling strategy, a second sampling strategy, and a third sampling strategy. In the case of multiple state spaces and multiple constraints, the method can increase the processing efficiency of path planning and reduce sampling time.

Description

Spatial sampling method, device, equipment and medium applied to path planning

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on July 31, 2020, the application number is 202010763143.3, and the invention title is "Spatial sampling methods, devices, equipment and media applied to path planning", and its entire contents Incorporated in this application by reference.

Technical field

This application relates to the field of artificial intelligence, and in particular to a spatial sampling method, device, equipment and medium applied to path planning.

Background technique

In recent years, research on path planning methods has been increasing. Path planning algorithms are widely used in various motion control fields, such as robotic arms, intelligent driving, unmanned aerial vehicles, etc. Among them, the path planning method based on random sampling is one of the research hotspots. The path planning method based on random sampling refers to the method of sampling the state space (solution space) to establish road signs or path branches. This method is probabilistically complete, that is, if there is a solution between the start point and the end point, as long as the number of sampling points is sufficient, a feasible path can be generated.

Currently, there are many algorithms for generating paths based on sampling points, such as RRT (Rapid Expanding Random Tree Algorithm), PRM (Probabilistic Roadmap Algorithm), KPIECE (a motion planning algorithm based on decision tree sampling) and so on. These algorithms focus on path planning and do not involve the improvement of sampling strategies. The inventor realizes that for some state spaces with complex environments (such as multi-state spaces, multiple constraints, etc.), it takes a long time to generate sampling points, and it is even difficult to generate sampling points, which affects the time-consuming path planning.

Application content

Based on this, it is necessary to provide a spatial sampling method, device, equipment, and medium for path planning in response to the above technical problems, so as to solve the problem of difficult and time-consuming path planning sampling in a complex state space environment.

A spatial sampling method applied to path planning, including:

_{Determine the effective point set S G} of the state space S by a pre-sampling method, and any point in the effective point set S _G _{is mapped into the feasible region Q L} of the state space Q through the first mapping relationship;

According to a preset random selection rule, a sampling strategy is selected from a specified number of sampling strategies as the execution strategy, and the specified number of sampling strategies includes at least a first sampling strategy, a second sampling strategy, and a third sampling strategy. The first sampling strategy refers to sampling in the feasible region _{SL of the} state space S; the second sampling strategy refers to sampling in the effective point set S _G ; the third sampling strategy refers to randomly selecting points _{in the effective point set S G} B. Then select a point C belonging to the effective point set S _G within the specified range of the point B, and perform sampling at any point between the point B and the point C;

Sampling is performed according to the described execution strategy.

A space sampling device applied to path planning, including:

The pre-sampling module is used to determine the effective point set S _G of the state space S through a pre-sampling method, and any point in the effective point set S _G _{is mapped into the feasible region Q L} of the state space Q via a first mapping relationship;

The random selection strategy module is used to select a sampling strategy from a specified number of sampling strategies as the execution strategy according to a preset random selection rule. The specified number of sampling strategies at least include a first sampling strategy, a second sampling strategy, and The third sampling strategy, the first sampling strategy refers to sampling in the feasible region _{SL of the} state space S; the second sampling strategy refers to sampling in the effective point set S _G ; the third sampling strategy refers to the first effective The point set S _G randomly selects the point B, then selects _{the point C belonging to the effective point set S G} within the specified range of the point B, and performs sampling at any point between the point B and the point C;

The sampling module is used to perform sampling according to the execution strategy.

A computer device includes a memory, a processor, and computer-readable instructions that are stored in the memory and can run on the processor, and the processor implements the following steps when the processor executes the computer-readable instructions:

Sampling is performed according to the described execution strategy.

A computer-readable storage medium, which stores computer-readable instructions, so that the one or more processors execute the following steps:

Sampling is performed according to the described execution strategy.

The above-mentioned spatial sampling method, device, computer equipment and storage medium applied to path planning determine the effective point set SG of the state space S through the pre-sampling method, and any point in the effective point set SG is mapped in the first mapping relationship In the feasible region QL of the state space Q, the feasible point set of the path planning is divided. According to a preset random selection rule, a sampling strategy is selected from a specified number of sampling strategies as the execution strategy, and the specified number of sampling strategies includes at least a first sampling strategy, a second sampling strategy, and a third sampling strategy. The first sampling strategy refers to sampling in the feasible region _{SL of the} state space S; the second sampling strategy refers to sampling in the effective point set S _G ; the third sampling strategy refers to randomly selecting points _{in the effective point set S G} B. Then select the point C belonging to the effective point set S _G within the specified range of the point B, and perform sampling at any point between the point B and the point C to provide different sampling strategies and improve the flexibility of sampling. Sampling is performed according to the described execution strategy to complete the collection task. This application uses pre-sampling and real-time sampling (that is, sampling using an execution strategy), which can improve the sampling success rate, reduce repeated sampling, and solve the problem of low or no solution in path planning under the condition of multiple state spaces and multiple constraints. , Which greatly improves the processing efficiency of path planning and reduces sampling time.

The details of one or more embodiments of the present application are presented in the following drawings and description, and other features and advantages of the present application will become apparent from the description, drawings and claims.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings that need to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor.

FIG. 1 is a schematic diagram of an application environment of a spatial sampling method applied to path planning in an embodiment of the present application;

FIG. 2 is a schematic flowchart of a spatial sampling method applied to path planning in an embodiment of the present application;

Fig. 3 is a schematic diagram of the transformation between the feasible end space path and the axis space path of the 6-joint manipulator in an example;

4 is a schematic flowchart of a spatial sampling method applied to path planning in an embodiment of the present application;

Fig. 5 is a schematic diagram of an example when the point set S _LP in the state space S is mapped to the state space Q;

FIG. 6 is a schematic flowchart of a spatial sampling method applied to path planning in an embodiment of the present application;

FIG. 7 is a schematic diagram of an example when the point set Q _LT in the state space Q is mapped to the state space S;

FIG. 8 is a schematic flowchart of a spatial sampling method applied to path planning in an embodiment of the present application;

Fig. 9 is a schematic structural diagram of a spatial sampling device applied to path planning in an embodiment of the present application;

Fig. 10 is a schematic diagram of a computer device in an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

This solution belongs to the field of smart transportation, and the construction of smart cities can be promoted through this solution. The spatial sampling method applied to path planning provided in this embodiment can be applied in an application environment as shown in FIG. 1, where the client communicates with the server. Among them, the client includes, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented with an independent server or a server cluster composed of multiple servers.

In an embodiment, as shown in FIG. 2, a spatial sampling method applied to path planning is provided. Taking the method applied to the server in FIG. 1 as an example, the method includes the following steps:

_{S10. Determine the effective point set S G} of the state space S by a pre-sampling method, and any point in the effective point set S _G _{is mapped into the feasible region Q L} of the state space Q through the first mapping relationship.

In this embodiment, the state space S and the state space Q are different state spaces. In an example, the path of the robotic arm is usually planned in the end space SεSE(3) or the axis space QεR ⁿ (n is the number of joints). Here, the state space S is the end space, and the state space Q is the axis space. All points in the state space S can find corresponding points in the state space Q, that is, there is a mapping relationship between the points in the state space S and the corresponding points in the state space Q. Specifically, the mapping relationship from S to Q is the first mapping relationship, which can be expressed as: fK:

The mapping relationship from Q to S is the second mapping relationship, which can be expressed as: iK:

In this example, the first mapping relationship may also be referred to as a forward kinematics transformation relationship, and the second mapping relationship may also be referred to as an inverse kinematics transformation relationship. As shown in Fig. 3, Fig. 3 is a schematic diagram of the transformation between the feasible end space path and the axis space path of the 6-joint manipulator in an example. The end position of the 6-joint robotic arm is determined by the rotation angles of the six joints (ie, shafts). Among them, the angle of the first joint (that is, the rotation angle of the 1st axis on the left side of Fig. 3) can be mapped to the q1 coordinate on the upper right side of the figure. And so on. The angle of each first joint can be mapped to the corresponding axis space coordinates.

Here, although the points in the state space S can all find the corresponding points in the state space Q, the feasible regions of different spaces do not completely overlap. In other words, the points in the feasible region S _LP in the state space S that are mapped to the points in the state space Q do not necessarily fall _{within the feasible region Q L} of the state space Q. The pre-sampling method is used to determine the set of points that fall in the feasible region before and after mapping. In other words, the effective point set

and

Q _G is the effective point set S _G mapped to the point set on the state space Q. The effective point set S _G is the verified effective point taken in the space, which can ensure the validity of the sampling points during path planning, but the random exploration of the space is relatively low.

S20. Select a sampling strategy from a specified number of sampling strategies as an execution strategy according to a preset random selection rule, where the specified number of sampling strategies at least includes a first sampling strategy, a second sampling strategy, and a third sampling strategy. The first sampling strategy refers to sampling in the feasible region _{SL of the} state space S; the second sampling strategy refers to sampling in the effective point set S _G ; the third sampling strategy refers to sampling in the effective point set S _{G first.} Select point B, then select point C belonging to the effective point set S _G within the specified range of point B, and perform sampling at any point between point B and point C.

In this embodiment, the first sampling strategy has the strongest random exploratory property but has the lowest guarantee of effectiveness. The second sampling strategy has the strongest effectiveness, but the random exploration of the space is relatively low. The performance of the third sampling strategy is between the first sampling strategy and the second sampling strategy. In some cases, the specified number may be greater than 3, that is, there is a fourth sampling strategy, a fifth sampling strategy, and so on. Specifically, the corresponding fourth sampling strategy, fifth sampling strategy, etc. can be formulated according to actual needs, which will not be repeated here.

The preset random selection rules can be formulated according to actual needs. In some cases, when multiple sampling is required, only one of the sampling strategies can be selected as the execution strategy. Here, a variety of different sampling strategies are provided, which greatly improves the flexibility of sampling.

S30. Perform sampling according to the execution strategy.

In this embodiment, after the execution strategy is determined, sampling can be performed according to the execution strategy to complete point collection. In a path planning, if more than one point needs to be collected, the corresponding execution strategy needs to be adopted for sampling. These execution strategies can be the same or different.

Step S10-S30, it is determined by the effective pre-sampling point set S _G S is the state space, the active set to any point in the point S _G, the mapping in the first mapping relationship feasible region of the state space Q Q _L, In order to divide the feasible point set of path planning. According to a preset random selection rule, a sampling strategy is selected from a specified number of sampling strategies as the execution strategy, and the specified number of sampling strategies includes at least a first sampling strategy, a second sampling strategy, and a third sampling strategy. The first sampling strategy refers to sampling in the feasible region _{SL of the} state space S; the second sampling strategy refers to sampling in the effective point set S _G ; the third sampling strategy refers to randomly selecting points _{in the effective point set S G} B. Then select the point C belonging to the effective point set S _G within the specified range of the point B, and perform sampling at any point between the point B and the point C to provide different sampling strategies and improve the flexibility of sampling. Sampling is performed according to the described execution strategy to complete the collection task.

Optionally, please refer to Figures 4 and 5. Step S10, that is, determining the effective point set S _{G of the} state space S through the pre-sampling method, includes:

S101. Sampling uniformly in the feasible region S _{L of the} state space S to obtain a point set S _LP ;

S102. Map the point set S _LP to the state space Q _{according to the first mapping relationship to obtain a point set Q LP} ;

S103. Select a point in the feasible region Q _L from the point set Q _LP to obtain a point set Q _A ;

S104, select the point in the set S _LP set point corresponding to the point Q _A, generating point set S _A, the active point set comprising the set of points S _G S _A.

In this embodiment, the feasible area S _L in the state space S, S (the cylindrical part on the left in FIG. 5) and the feasible area Q _L in the state space Q, Q (the right cuboid in FIG. 5) are known. First, uniformly sample the point set S _LP _{in S L} (the point on the upper left side of the cylinder in Figure 5). _{Then the S LP is} mapped to the state space Q through the function iK _{, and the point set Q LP is obtained} (the white points inside the rectangular parallelepiped and the black points outside the rectangular parallelepiped in Figure 5). Finally, in Q _LP , the points that meet Q _L (white points in the cuboid) _{are screened out, and the corresponding sampling points are found in S LP} (the darker points in the lower left side of the cylinder in Figure 5), so as to obtain the state space The point set S _A effectively sampled by S, then:

S _A ={p|p∈S _LP ∧iK(p)∈Q _L }.

Here, the set point is a valid point set S _A S _G of the subset.

Optionally, please refer to FIGS. 6 and 7. Step S10, that is, determining the effective point set S _{G of the} state space S by the pre-sampling method includes:

S105. Sampling uniformly in the feasible region Q _{L of the} state space Q to obtain a point set Q _LT ;

S106: Map the point set Q _LT to the state space S _{according to the second mapping relationship to obtain the point set S LT} ;

S107. Select points within the feasible region _SL from the point set S _LT to obtain a point set S _QA , and the effective point set S _G includes the point set S _QA .

In this embodiment, first, _{uniform sampling is performed on Q L to} obtain a point set Q _LT (as shown in Figure 7 for points in a rectangular parallelepiped). _{Then the Q LT is} mapped to the state space S through the function fK to _{obtain the point set S LT} (the gray point in the uppermost cylinder on the left side of Fig. 7 and the black point outside the cylinder). Finally, the points that meet S _L are selected in S _LT (the gray points in the uppermost cylinder on the left side of Fig. 7), and the point set S _{QA is obtained} . which is:

S _QA ={p|pεQ _LT ∧fK(p)εS _L }.

Here, the point set S _QA is a subset of the effective point set S _G. S _G =S _QA ∪S _A. S _G is the set of points in the lowermost cylinder on the left side of Figure 7.

Optionally, as shown in FIG. 8, step S20, that is, selecting a sampling strategy from a specified number of sampling strategies according to a preset random selection rule as an execution strategy includes:

S201. Randomly generate a random number r, and the value range of the random number r is W;

S202: If the random number r is in the first interval X, select the first sampling strategy as the execution strategy;

S203: If the random number r is in the second interval Y, select the second sampling strategy as the execution strategy;

S204: If the random number r is in the third interval Z, select the third sampling strategy as the execution strategy;

in,

X∪Y∪Z=W.

In this embodiment, a random number r can be generated by a random number generation function, and the value interval of r is W, that is, r=rand(), r∈W.

In some cases, if the X, Y, Z are continuous segment, since X∪Y∪Z = W, W is present at the split point r _a, r _b, W is divided into the sections X, Y, Z.

Therefore, step S20 can be expressed as:

r=rand(),r∈[0,1]

if(r≤r _a ):

First sampling strategy

elseif(r _a ＜r≤r _b ):

Second sampling strategy

else:

The third sampling strategy.

Here, the sampling strategy is randomly selected as the real-time sampling stage. The three different sampling strategies provided in this embodiment have different characteristics. The first sampling strategy has the strongest random exploration but the lowest guarantee of effectiveness. The second sampling strategy has the strongest effectiveness, but the random exploration of the space is relatively low. The performance of the third sampling strategy is between the first sampling strategy and the second sampling strategy. When in use, the execution ratio can be adjusted according to the actual situation, so that the path planning sampling algorithm can strike a balance between efficiency and exploration performance.

Alternatively, W = [0,1], X is the first interval [0, r _a), said second section is Y [r _a, r _b), the third zone Z is [r _{_{b, 1], r a,}} r b is the hyper-parameters, and _{_{0 <r a <r b <}} 1.

In this embodiment, the random number r can be any number in [0,1]. r _a and r _b are hyper-parameters, and the values of these two hyper-parameters can be set according to actual needs to adjust the probability that different sampling strategies are selected.

It should be understood that the size of the sequence number of each step in the foregoing embodiment does not mean the order of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

In one embodiment, a spatial sampling device applied to path planning is provided, and the spatial sampling device applied to path planning corresponds to the spatial sampling method applied to path planning in the above-mentioned embodiment in a one-to-one correspondence. As shown in FIG. 9, the spatial sampling device applied to path planning includes a pre-sampling module 10, a random selection strategy module 20, and a sampling module 30. The detailed description of each functional module is as follows:

The pre-sampling module 10 is used to determine the effective point set S _G of the state space S by a pre-sampling method, and any point in the effective point set S _G _{is mapped into the feasible region Q L} of the state space Q via a first mapping relationship ；

The random selection strategy module 20 is configured to select a sampling strategy from a specified number of sampling strategies as an execution strategy according to a preset random selection rule, and the specified number of sampling strategies at least include a first sampling strategy and a second sampling strategy And the third sampling strategy, the first sampling strategy refers to sampling in the feasible region _{SL of the} state space S; the second sampling strategy refers to sampling in the effective point set S _G ; the third sampling strategy refers to sampling in the first The effective point set S _G randomly selects the point B, and then selects _{the point C belonging to the effective point set S G} within the specified range of the point B, and performs sampling at any point between the point B and the point C;

The sampling module 30 is configured to perform sampling according to the execution strategy.

Optionally, the pre-sampling module 10 includes:

The first sampling unit is used for _{uniform sampling in the feasible region SL of the} state space S to obtain the point set S _LP ;

The first mapping unit is configured to map the point set S _LP to the state space Q _{according to the first mapping relationship to obtain the point set Q LP} ;

The first selection unit is configured to select points in the feasible region Q _L _{from the point set Q LP} to obtain the point set Q _A ;

The first set point generation means, for selecting the set of points Q _A and the corresponding point of the point set S _LP, the generation point set S _A, the active point set comprising the set of points S _G S _A.

Optionally, the pre-sampling module 10 includes:

The second sampling unit is used for _{uniform sampling in the feasible region Q L of the} state space Q to obtain the point set Q _LT ;

The second mapping unit is configured to map the point set Q _LT to the state space S _{according to the second mapping relationship to obtain the point set S LT} ;

The second selection unit is configured to select points in the feasible region _SL _{from the point set S LT} to obtain a point set S _QA , and the effective point set S _G includes the point set S _QA .

Optionally, the random selection strategy module 20 includes:

Random number generating unit, used to randomly generate a random number r, the value range of the random number r is W;

The first selection strategy unit is configured to select the first sampling strategy as the execution strategy if the random number r is in the first interval X;

The second selection strategy unit is configured to select the second sampling strategy as the execution strategy if the random number r is in the second interval Y;

The third selection strategy unit is configured to select the third sampling strategy as the execution strategy if the random number r is in the third interval Z;

in,

X∪Y∪Z=W.

For the specific limitation of the spatial sampling device applied to path planning, please refer to the above limitation of the spatial sampling method applied to path planning, which will not be repeated here. Each module in the above-mentioned spatial sampling device applied to path planning can be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 10. The computer equipment includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The readable storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer readable instructions in the readable storage medium. The database of the computer device is used to store the data involved in the above-mentioned spatial sampling method applied to path planning. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer-readable instructions are executed by the processor to realize a spatial sampling method applied to path planning. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored on the memory and capable of running on the processor, and the processor implements the following steps when the processor executes the computer-readable instructions:

Sampling is performed according to the described execution strategy.

In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided. The readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media. Storage medium. The readable storage medium stores computer readable instructions, and when the computer readable instructions are executed by one or more processors, the following steps are implemented:

Sampling is performed according to the described execution strategy.

A person of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by instructing relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a non-volatile computer. In a readable storage medium, when the computer-readable instructions are executed, they may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not a limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the division of the above functional units and modules is used as an example. In practical applications, the above functions can be allocated to different functional units and modules as needed. Module completion, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still implement the foregoing The technical solutions recorded in the examples are modified, or some of the technical features are equivalently replaced; these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the application, and should be included in Within the scope of protection of this application.

Claims

A spatial sampling method applied to path planning, which includes:

Determine the effective point set S G of the state space S by a pre-sampling method, and any point in the effective point set S G is mapped into the feasible region Q L of the state space Q through the first mapping relationship;

According to a preset random selection rule, a sampling strategy is selected from a specified number of sampling strategies as the execution strategy, and the specified number of sampling strategies includes at least a first sampling strategy, a second sampling strategy, and a third sampling strategy. The first sampling strategy refers to sampling in the feasible region SL of the state space S; the second sampling strategy refers to sampling in the effective point set S G ; the third sampling strategy refers to randomly selecting points in the effective point set S G B. Then select a point C belonging to the effective point set S G within the specified range of the point B, and perform sampling at any point between the point B and the point C;

Sampling is performed according to the described execution strategy.
The spatial sampling method applied to path planning according to claim 1, wherein said determining the effective point set S G of the state space S by the pre-sampling method comprises:

Sampling uniformly in the feasible region S L of the state space S to obtain the point set S LP ;

Map the point set S LP to the state space Q according to the first mapping relationship to obtain the point set Q LP ;

Select a point in the feasible region Q L from the point set Q LP to obtain a point set Q A ;

Selecting the set of points in S LP set of points Q A and the corresponding points, generating a set point S A, the active point set comprising the set of points S G S A.
The spatial sampling method applied to path planning according to claim 1, wherein said determining the effective point set S G of the state space S by the pre-sampling method comprises:

Sampling uniformly in the feasible region Q L of the state space Q to obtain the point set Q LT ;

Map the point set Q LT to the state space S according to the second mapping relationship to obtain the point set S LT ;

A point within the feasible region SL is selected from the point set S LT to obtain a point set S QA , and the effective point set S G includes the point set S QA .
The spatial sampling method applied to path planning according to claim 1, wherein the selecting a sampling strategy from a specified number of sampling strategies as the execution strategy according to a preset random selection rule comprises:

Randomly generate random number r, the value range of random number r is W;

If the random number r is in the first interval X, the first sampling strategy is selected as the execution strategy;

If the random number r is in the second interval Y, the second sampling strategy is selected as the execution strategy;

If the random number r is in the third interval Z, the third sampling strategy is selected as the execution strategy;

in,
X∪Y∪Z=W.
Spatial sampling method as claimed in claim 4 is applied to path planning, where, W = [0,1], X is the first interval [0, r a), said second section is Y [r a , r b), the third zone Z is [r b, 1], r a, r b is the hyper-parameters, and 0 <r a <r b < 1.
A space sampling device applied to path planning, which includes:

The pre-sampling module is used to determine the effective point set S G of the state space S through a pre-sampling method, and any point in the effective point set S G is mapped into the feasible region Q L of the state space Q via a first mapping relationship;

The random selection strategy module is used to select a sampling strategy from a specified number of sampling strategies as the execution strategy according to a preset random selection rule. The specified number of sampling strategies at least include a first sampling strategy, a second sampling strategy, and The third sampling strategy, the first sampling strategy refers to sampling in the feasible region SL of the state space S; the second sampling strategy refers to sampling in the effective point set S G ; the third sampling strategy refers to the first effective The point set S G randomly selects the point B, then selects the point C belonging to the effective point set S G within the specified range of the point B, and performs sampling at any point between the point B and the point C;

The sampling module is used to perform sampling according to the execution strategy.
The spatial sampling device applied to path planning according to claim 6, wherein the pre-sampling module comprises:

The first sampling unit is used for uniform sampling in the feasible region SL of the state space S to obtain the point set S LP ;

The first mapping unit is configured to map the point set S LP to the state space Q according to the first mapping relationship to obtain the point set Q LP ;

The first selection unit is configured to select points in the feasible region Q L from the point set Q LP to obtain the point set Q A ;

The first set point generation means, for selecting the set of points Q A and the corresponding point of the point set S LP, the generation point set S A, the active point set comprising the set of points S G S A.
The spatial sampling device applied to path planning according to claim 6, wherein the pre-sampling module comprises:

The second sampling unit is used for uniform sampling in the feasible region Q L of the state space Q to obtain the point set Q LT ;

The second mapping unit is configured to map the point set Q LT to the state space S according to the second mapping relationship to obtain the point set S LT ;

The second selection unit is configured to select points in the feasible region SL from the point set S LT to obtain a point set S QA , and the effective point set S G includes the point set S QA .
According to the space sampling device applied to path planning according to claim 6, the random selection strategy module 20 includes:

Random number generating unit, used to randomly generate a random number r, the value range of the random number r is W;

The first selection strategy unit is configured to select the first sampling strategy as the execution strategy if the random number r is in the first interval X;

The second selection strategy unit is configured to select the second sampling strategy as the execution strategy if the random number r is in the second interval Y;

The third selection strategy unit is configured to select the third sampling strategy as the execution strategy if the random number r is in the third interval Z;

in,
X∪Y∪Z=W.
Space sampling applied to path planning apparatus according to claim 9, wherein, W = [0,1], X is the first interval [0, r a), said second section is Y [r a , r b), the third zone Z is [r b, 1], r a, r b is the hyper-parameters, and 0 <r a <r b < 1.
A computer device includes a memory, a processor, and computer readable instructions stored in the memory and capable of running on the processor, wherein, when the processor executes the computer readable instructions, the following is achieved step:

Determine the effective point set S G of the state space S by a pre-sampling method, and any point in the effective point set S G is mapped into the feasible region Q L of the state space Q through the first mapping relationship;

According to a preset random selection rule, a sampling strategy is selected from a specified number of sampling strategies as the execution strategy, and the specified number of sampling strategies includes at least a first sampling strategy, a second sampling strategy, and a third sampling strategy. The first sampling strategy refers to sampling in the feasible region SL of the state space S; the second sampling strategy refers to sampling in the effective point set S G ; the third sampling strategy refers to randomly selecting points in the effective point set S G B. Then select a point C belonging to the effective point set S G within the specified range of the point B, and perform sampling at any point between the point B and the point C;

Sampling is performed according to the described execution strategy.
The computer device according to claim 11, wherein said determining the effective point set S G of the state space S by the pre-sampling method comprises:

Sampling uniformly in the feasible region S L of the state space S to obtain the point set S LP ;

Map the point set S LP to the state space Q according to the first mapping relationship to obtain the point set Q LP ;

Select a point in the feasible region Q L from the point set Q LP to obtain a point set Q A ;

Selecting the set of points in S LP set of points Q A and the corresponding points, generating a set point S A, the active point set comprising the set of points S G S A.
The computer device according to claim 11, wherein said determining the effective point set S G of the state space S by the pre-sampling method comprises:

Sampling uniformly in the feasible region Q L of the state space Q to obtain the point set Q LT ;

Map the point set Q LT to the state space S according to the second mapping relationship to obtain the point set S LT ;

A point within the feasible region SL is selected from the point set S LT to obtain a point set S QA , and the effective point set S G includes the point set S QA .
11. The computer device according to claim 11, wherein said selecting a sampling strategy from a specified number of sampling strategies as an execution strategy according to a preset random selection rule comprises:

Randomly generate random number r, the value range of random number r is W;

If the random number r is in the first interval X, the first sampling strategy is selected as the execution strategy;

If the random number r is in the second interval Y, the second sampling strategy is selected as the execution strategy;

If the random number r is in the third interval Z, the third sampling strategy is selected as the execution strategy;

in,
X∪Y∪Z=W.
The computer apparatus according to claim 14, wherein, W = [0,1], X is the first interval [0, r a), said second section is Y [r a, r b), the said third zone Z is [r b, 1], r a, r b is the hyper-parameters, and 0 <r a <r b < 1.
One or more readable storage media storing computer readable instructions, when the computer readable instructions are executed by one or more processors, the one or more processors execute the following steps:

Determine the effective point set S G of the state space S by a pre-sampling method, and any point in the effective point set S G is mapped into the feasible region Q L of the state space Q through the first mapping relationship;

According to a preset random selection rule, a sampling strategy is selected from a specified number of sampling strategies as the execution strategy, and the specified number of sampling strategies includes at least a first sampling strategy, a second sampling strategy, and a third sampling strategy. The first sampling strategy refers to sampling in the feasible region SL of the state space S; the second sampling strategy refers to sampling in the effective point set S G ; the third sampling strategy refers to randomly selecting points in the effective point set S G B. Then select a point C belonging to the effective point set S G within the specified range of the point B, and perform sampling at any point between the point B and the point C;

Sampling is performed according to the described execution strategy.
The readable storage medium according to claim 16, wherein the determining the effective point set S G of the state space S by the pre-sampling method comprises:

Sampling uniformly in the feasible region S L of the state space S to obtain the point set S LP ;

Map the point set S LP to the state space Q according to the first mapping relationship to obtain the point set Q LP ;

Select a point in the feasible region Q L from the point set Q LP to obtain a point set Q A ;

Selecting the set of points in S LP set of points Q A and the corresponding points, generating a set point S A, the active point set comprising the set of points S G S A.
The readable storage medium according to claim 16, wherein the determining the effective point set S G of the state space S by the pre-sampling method comprises:

Sampling uniformly in the feasible region Q L of the state space Q to obtain the point set Q LT ;

Map the point set Q LT to the state space S according to the second mapping relationship to obtain the point set S LT ;

A point within the feasible region SL is selected from the point set S LT to obtain a point set S QA , and the effective point set S G includes the point set S QA .
15. The readable storage medium of claim 16, wherein the selecting a sampling strategy from a specified number of sampling strategies as the execution strategy according to a preset random selection rule comprises:

Randomly generate random number r, the value range of random number r is W;

If the random number r is in the first interval X, the first sampling strategy is selected as the execution strategy;

If the random number r is in the second interval Y, the second sampling strategy is selected as the execution strategy;

If the random number r is in the third interval Z, the third sampling strategy is selected as the execution strategy;

in,
X∪Y∪Z=W.
Readable storage medium according to claim 19, wherein, W = [0,1], X is the first interval [0, r a), said second section is Y [r a, r b) the third section is Z [r b, 1], r a, r b is the hyper-parameters, and 0 <r a <r b < 1.