CN115617025A

CN115617025A - Path planning method, device, equipment and computer readable storage medium

Info

Publication number: CN115617025A
Application number: CN202110783408.0A
Authority: CN
Inventors: 徐志浩; 胡晋; 沈慧
Original assignee: Alibaba Singapore Holdings Pte Ltd
Current assignee: Wuzhou Online E Commerce Beijing Co ltd
Priority date: 2021-07-12
Filing date: 2021-07-12
Publication date: 2023-01-17

Abstract

The disclosure relates to a path planning method, a device, equipment and a computer readable storage medium. The method comprises the following steps: acquiring a plurality of initial paths from a starting point to an end point; determining a homotopy value of each initial path according to the feature point position information of at least two feature points on each initial path and the obstacle position information of the target obstacles around each initial path, wherein the homotopy value is related to the obstacle identification of each target obstacle; and determining a target path from the plurality of initial paths according to the homotopy value of each initial route. The essence of the method is to introduce the homotopy theory in topology, change a logic problem into a calculation problem so as to narrow the screening range of a target path, reduce the calculation amount and reduce the requirement on the performance of equipment. The homotopy technology is used for replacing the artificial rules set through experience, and the defects that the artificial rules need to be infinitely increased along with the change of the environment, the environmental adaptability of the original artificial rules is poor, the originally feasible initial path can be filtered out and the like can be overcome.

Description

Path planning method, device, equipment and computer readable storage medium

Technical Field

The present disclosure relates to the field of automatic driving technologies, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for path planning.

Background

In the field of automatic driving (intelligent driving), there is a need to plan a driving path for an unmanned vehicle.

Usually, a plurality of initial paths are planned according to a starting point and an end point of the unmanned vehicle, and a target path is determined from the plurality of initial paths for the unmanned vehicle to use.

However, it is difficult to ensure that the target path determined from the plurality of initial paths is the optimal path.

Disclosure of Invention

In order to solve the technical problems or at least partially solve the technical problems, the present disclosure provides a path planning method, apparatus, device and computer-readable storage medium.

In a first aspect, an embodiment of the present disclosure provides a path planning method, including:

acquiring a plurality of initial paths from a starting point to an end point;

determining a homotopy value of each initial path according to the feature point position information of at least two feature points on each initial path and the obstacle position information of target obstacles around each initial path, wherein the homotopy value is related to the obstacle identification of each target obstacle;

and determining a target path from the plurality of initial paths according to the homotopy value of each initial route.

In a second aspect, an embodiment of the present disclosure provides a path planning apparatus, including:

the acquisition module is used for acquiring a plurality of initial paths from a starting point to an end point;

the first determining module is used for determining a homotopy value of each initial path according to the feature point position information of at least two feature points on each initial path and the obstacle position information of target obstacles around each initial path, wherein the homotopy value is related to the obstacle identification of each target obstacle;

and the second determining module is used for determining a target path from the plurality of initial paths according to the homotopy value of each initial route.

In a third aspect, an embodiment of the present disclosure provides an unmanned device, including:

a memory;

a processor; and

a computer program;

wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of the first aspect.

In a fourth aspect, the disclosed embodiments provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method of the first aspect.

The path planning method, the device, the equipment and the computer readable storage medium provided by the embodiment of the disclosure determine the homotopy value of each initial path according to the feature point position information of at least two feature points on each initial path and the obstacle position information of the target obstacles around each initial path; determining a target path from the plurality of initial paths according to the homotopy value of each initial path; the method and the device have the advantages that by introducing the homotopy theory in topology, a logic problem is changed into a computer executable calculation problem, so that the screening range of the target path is reduced, the calculation amount is reduced, the requirement on the performance of the equipment is lowered, and the aim of quickly determining the target path is fulfilled. According to the technical scheme provided by the embodiment of the disclosure, the artificial rules set through experience are replaced by homotopy calculation, and the defects that the artificial rules need to be infinitely increased along with the change of the environment, the environmental adaptability of the original artificial rules is deteriorated, the originally feasible initial path can be filtered out, and the like can be overcome.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.

In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present disclosure, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.

Fig. 1 is a flowchart of a path planning method provided in an embodiment of the present disclosure;

fig. 2 and fig. 3 are schematic diagrams of two road conditions provided by the embodiment of the disclosure;

fig. 4 is a schematic diagram of another road condition provided by the embodiment of the disclosure;

fig. 5 is a flowchart of a method for implementing S120 according to an embodiment of the present disclosure;

fig. 6 is a flowchart of another method for implementing S120 according to an embodiment of the present disclosure;

fig. 7 is a schematic diagram of another road condition provided by the embodiment of the disclosure;

fig. 8 is a schematic diagram of another road condition provided by the embodiment of the disclosure;

fig. 9 is a schematic structural diagram of a path planning apparatus according to an embodiment of the present disclosure;

fig. 10 is a schematic structural diagram of an embodiment of an unmanned aerial device provided in an embodiment of the present disclosure.

Detailed Description

In order that the above objects, features and advantages of the present disclosure may be more clearly understood, aspects of the present disclosure will be further described below. It should be noted that the embodiments and features of the embodiments of the present disclosure may be combined with each other without conflict.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced in other ways than those described herein; it is to be understood that the embodiments disclosed in the specification are only a few embodiments of the present disclosure, and not all embodiments.

As described in the background, it is often difficult to ensure that a target path determined from a plurality of initial paths is an optimal path. To solve this problem, an embodiment of the present disclosure provides a path planning method, which is described below with reference to specific embodiments.

Fig. 1 is a flowchart of a path planning method provided in the embodiment of the present disclosure. The present embodiment is applicable to a case where the client performs path planning for the unmanned vehicle, and the method may be executed by a path planning apparatus, the apparatus may be implemented in a software and/or hardware manner, and the apparatus may be configured in an unmanned device, such as an unmanned vehicle, an intelligent driving vehicle, a robot, and the like. Alternatively, the present embodiment may be applicable to a case where the server performs path planning for the unmanned vehicle, and the method may be executed by a path planning apparatus, where the apparatus may be implemented in a software and/or hardware manner, and the apparatus may be configured in an electronic device, such as a server.

As shown in fig. 1, the method comprises the following specific steps:

and S110, acquiring a plurality of initial paths from the starting point to the end point.

The initial path refers to a path that bypasses the obstacle (i.e., does not pass through the obstacle) and connects the start point and the end point. Fig. 2 and fig. 3 are schematic diagrams of two road conditions provided by the embodiment of the disclosure. In fig. 2 and 3, OBS1-OBS8 each represent an obstacle. In fig. 2, each of the paths 1 and 2 connects the start point and the end point, and each of the obstacles OBS1, OBS2, and OBS3 does not pass through any of them, and is an initial path. In fig. 3, path 3 and path 4 both connect the start point and the end point, and neither pass through any of obstacles OBS4, OBS5, OBS6, OBS7, and OBS8, and are also initial paths.

S120, determining a homotopy value of each initial path according to the feature point position information of at least two feature points on each initial path and the obstacle position information of the target obstacles around each initial path, wherein the homotopy value is related to the obstacle identification of each target obstacle.

The obstacle indicator is information that can distinguish an obstacle from other obstacles. The obstacle identifications of different obstacles are different. Illustratively, the identification of the obstacle may be a number of the obstacle.

If the initial path is considered to be a collection of points, the feature points are the points that make up the initial path. Alternatively, at least two points constituting the initial path may be randomly selected as the feature points, or points having a specific meaning may be selected. The characteristic points comprise at least one of the following: inflection points and extreme points. The method and the device can improve the accuracy of calculation of the homotopy value of the initial path.

The concept of Homotopy describes topologically a "continuous change" between two objects. Specifically, homotopy means that two topological spaces are homotopy if they can be changed from one to another through a series of successive transformations.

Specifically, two topological spaces X and Y are given. Consider two sequential functions, if there is one sequential mapping H

f，g：X→Y

H：X×[0，1]→Y

Such that:

then, the following steps are called: f, g (in Y) are homotopy.

In other words, each parameter t corresponds to a function H, which varies continuously from f to g as the parameter value t varies from 0 to 1.

h _t ：X→Y，

In this application, two initial paths are homotopy if they can complete the mutual transformation without touching the obstacle. In other words, if there is no obstacle between the two initial paths, the two initial paths are homotopy; otherwise, the two initial paths are different.

For example, in fig. 2, path 1 and path 2 are homotopic, because both trajectories are located on the same side of any obstacle, and the two trajectories can complete the interconversion without touching the obstacle. In fig. 3, paths 3 and 4 are different, and paths 3 and 4 are located on both sides of obstacles OBS6 and OBS7, and they cannot be mutually converted without touching the obstacles.

The homotopy value of the initial path may characterize the homotopy of the initial path. Whether the two initial paths are homotopy or not can be judged by comparing homotopy values of any two initial paths.

Optionally, in practice, if the difference between the homotopy values of the two initial paths is smaller than a set threshold, determining homotopy of the two initial paths; otherwise, the two initial paths are determined to be different. The advantage of such an arrangement is that the existence of calculation errors is fully considered, so that the result of whether the two finally determined initial paths are homotopy is accurately judged.

Furthermore, homotopy values of the two initial paths can be set to be the same, and homotopy of the two initial paths is determined; otherwise, the two initial paths are determined to be different. The setting and judging process is simple and easy to realize, and the time spent on judging whether the two initial paths are homotopy can be fully shortened.

If the homotopy values are imaginary numbers, the homotopy values are the same, that is, the real parts of the homotopy values of the two initial paths are equal, and meanwhile, the imaginary parts of the homotopy values of the two initial paths are also equal.

In practice, all obstacles around the initial path may be set as target obstacles when the present step is executed.

Alternatively, it is also possible to take only an obstacle located between any two initial paths as a target obstacle. Illustratively, in fig. 3, only OBS6 and OBS7 are both targeted obstacles, and OBS4, OBS5 and OBS8 are not targeted obstacles, where OBS4, OBS5 and OBS8 are ineffective obstacles.

The essence of this is that, before S120 is executed, obstacles around all the initial paths are screened, target obstacles are determined, and invalid obstacles unrelated to the initial paths are eliminated. The technical personnel in the field can understand that the invalid barriers are positioned on the same side of the two initial paths, the space between the two initial paths cannot be divided into two track spaces, the number of the invalid barriers has no influence on whether the two initial paths are homotopy, the invalid barriers are deleted, the calculation efficiency can be effectively improved, and the invalid calculation is reduced. The obstacle located between the two initial paths can cut the space between the two initial paths into two trajectory spaces, which directly affects the result of determining whether the two initial paths are homotopy.

S130, determining a target path from the plurality of initial paths according to the homotopy value of each initial path.

The target path is an optimal path, and it should be noted that a preset rule may be actually set to measure whether an initial path is an optimal path. The rule can be preset to be that the distance is shortest or the traffic signal light is minimum and the like. This is not limited by the present application.

Since the two initial paths are homotopy, which means that the two initial paths are located on the same side of any obstacle, the two initial paths may be considered similar, or the two initial paths may be considered as alternatives to each other. In practice, after S110 is executed, the obtained multiple initial paths may include paths of the same or different allenes.

A set of the plurality of initial paths determined in S110 is referred to as a trajectory set. It is assumed that the determined set of trajectories includes paths of a plurality of homologies. In this case, if trajectory pruning is not performed (trajectory pruning refers to removing similar trajectories, that is, only one homotopic path is reserved), a preset rule is directly used to measure one by one whether each initial path is an optimal path, and therefore, the calculation amount is huge, the requirement on the performance of equipment is high, and the target path is not favorably and rapidly determined. Therefore, a trace pruning is required for the trace set.

Accordingly, the specific implementation method of this step may include: determining a minimum complete set from the plurality of initial paths according to the homotopy value of each initial path, wherein homotopy values of any two initial paths included in the minimum complete set are different; the target path is determined from the minimal complete set.

The "any two initial paths included in the minimum complete set have different homotopy values", that is, any two initial paths in the minimum complete set are different from each other, and any two initial paths in the minimum complete set are different from each other and cannot be replaced by each other. In addition, the minimum complete set has completeness, that is, the initial paths in which the homotopes of the multiple initial paths determined in S110 are representative in the minimum complete set.

The step of determining the minimum complete set from the plurality of initial paths according to the homotopy value of each initial path means that the track set is subjected to track pruning.

For example, if 100 initial paths are determined in S110, if the initial paths with the same homotopy value are grouped into one group, it is assumed that the initial paths can be grouped into 13 groups, and any initial path from the 13 groups is taken as an element in the minimum complete set. The minimal complete set includes 13 initial paths. And then, determining a target path from the 13 initial paths in the minimum complete set according to a preset rule.

Or, if 100 initial paths are determined in total by S110, determining that the 100 initial paths have 13 different homotopic values, and directly selecting one representative initial path for each homotopic value from the 100 initial paths, where all the representative initial paths form a minimum complete set.

According to the technical scheme, the homotopy value of each initial path is determined according to the feature point position information of at least two feature points on each initial path and the obstacle position information of the target obstacles around each initial path; determining a target path from the plurality of initial paths according to the homotopy value of each initial path; the method changes a logic problem into a computer executable calculation problem by introducing the homotopy theory in the topology, so as to reduce the screening range of the target path, reduce the calculation amount, reduce the requirement on the performance of equipment and further realize the purpose of quickly determining the target path.

Fig. 4 is a schematic diagram of another road condition provided in the embodiment of the present disclosure. There are two feasible spaces in fig. 4, feasible space 1 and feasible space 2, respectively, and there are more than one initial path in each feasible space (illustratively, there are two initial paths in each feasible space in fig. 4). Through the track pruning, an initial track is expected to be output from each of the two feasible spaces, and then one of the initial tracks is selected as a target path through decision making for optimization. In the prior art, a preset manual rule set through experience is used for deletion, which may cause all initial tracks in the feasible space 1 to be deleted, the remaining initial tracks are all in the feasible space 2, and the final target track is determined incorrectly. This is an important reason that it is currently difficult to ensure that the target path determined from the plurality of initial paths is the optimal path.

As described above, two initial paths are different if there is an obstacle between them; otherwise, the two initial paths are homotopy. From the above, it can be obtained that the non-homotopy initial paths must be in different feasible spaces, and the homotopy initial paths must be in the same feasible space. For the situation in fig. 4, the above technical solution judges whether the two initial paths are homotopy or not through the homotopy value, and can obtain two trajectory sets with different homotopy values, that is, any initial path in one of the trajectory sets and any initial path in the other trajectory set are non-homotopy, so that the requirement that one initial path is output in each of two feasible spaces can be met, and it is further ensured that the target path determined from the multiple initial paths is the optimal path.

In addition, the technical scheme replaces the artificial rule set through experience through the homotopy technology, and the defects that the artificial rule needs to be infinitely increased along with the change of the environment, the environmental adaptability of the original artificial rule is poor, the originally feasible initial path can be filtered out and the like can be overcome.

According to the technical scheme, the homotopy value can be calculated only by selecting a few characteristic points from each initial path, instead of calculating all points forming the initial path, and the efficiency of calculating the homotopy value can be remarkably improved.

It should be noted that, when S120 is executed, multiple feature points may be selected from the same initial path, and the multiple feature points may include both a start point and an end point, may not include both a start point and an end point, and may include only one of the start point and the end point. However, it is impossible to set a plurality of feature points to include only a start point and an end point, because if only the start point and the end point are taken as feature points, it may cause the homotopy values obtained by calculation of the initial paths of different allenes to be the same, and cause a wrong determination result of whether the two initial paths are homotopy or not, so that the finally determined target path is not the optimal path.

In practice, there are various methods for implementing S120, and a flowchart of a method for implementing S120 is exemplarily given below. Fig. 5 is a flowchart of a method for implementing S120 according to an embodiment of the present disclosure. Referring to fig. 5, the method includes:

s121, determining the barrier homotopy description of any target barrier according to the feature point position information of two adjacent feature points on any initial path and the barrier position information of any target barrier around any initial path.

And S122, determining the description information of any target obstacle according to the obstacle identification and the obstacle homotopy description of any target obstacle.

And S123, determining the homotopy value of any initial path according to the description information of each target obstacle around any initial path.

Illustratively, referring to fig. 3, assume that the homotopy value for path 4 is calculated. Four feature points are selected from the path 4, which are respectively a starting point P, a feature point A, a feature point B and a terminal Q. By selecting these four feature points, path 4 can be divided into 3 path segments, which are: path segment 1 (corresponding to P to a segment), path segment 2 (corresponding to a to B segment), and path segment 3 (corresponding to B to Q segment).

By repeatedly performing S121 and S122, description information of each path segment with respect to any target obstacle can be obtained. Exemplarily, it is assumed that the obstacle obs6 and the obstacle obs7 are target obstacles in fig. 3. For the path segment 1, two adjacent feature points are the feature point P and the feature point a, respectively. For the obstacle obs6, by executing S121 and S122, the description information M1 of the target obstacle corresponding to both the path segment 1 and the obstacle obs6 can be obtained. For the obstacle obs7, by executing S121 and S122, the description information M2 of the target obstacle corresponding to both the path segment 1 and the obstacle obs7 can be obtained. By repeating this, it is possible to obtain the description information M3 of the target obstacle corresponding to the path segment 2 and the obstacle obs6 at the same time, the description information M4 of the target obstacle corresponding to the path segment 2 and the obstacle obs7 at the same time, the description information M5 of the target obstacle corresponding to the path segment 3 and the obstacle obs6 at the same time, and the description information M6 of the target obstacle corresponding to the path segment 3 and the obstacle obs7 at the same time.

The description information of the target obstacle is used for reflecting the relative position relation between the target obstacle and the path segment.

The essence of S123 is to perform summary processing on the description information of each path segment with respect to any target obstacle, so as to obtain a homotopy value of any initial path. Illustratively, the above M1, M2, M3, M4, M5, and M6 are summarized to obtain homotopy values of any initial path.

The essence of the technical scheme is that when the homotopy value of the initial path is calculated, the initial path is firstly subjected to segmentation processing, and then the segmentation processing results of the initial path are subjected to summary processing to obtain the final homotopy value. The whole calculation process is simple and easy to realize, the calculated homotopy value can fully reflect the position relation between the initial path and each target obstacle, the subsequent target path can be accurately determined, and the user experience is improved.

Fig. 6 is a flowchart of another method for implementing S120 according to an embodiment of the present disclosure. In FIG. 6, 1211-S1214 are further expansions of S121 in FIG. 5, and S1221-S1222 are further expansions of S122 in FIG. 5. Referring to fig. 6, the method includes:

s1211 converts feature point position information of two adjacent feature points on any one of the initial paths and obstacle position information of any one of target obstacles around the any one of the initial paths into imaginary numbers in an imaginary number domain, respectively.

For example, the following description will be given taking an example in which the obstacle position information of the target obstacle is converted into imaginary numbers in an imaginary number domain, respectively. The target obstacle can be regarded as a set of a series of points, any point forming the obstacle can be selected as a representative point of the target obstacle, and the position information of the representative point is the position information of the obstacle. If a rectangular coordinate system is used, the target obstacle position information may be represented as (x, y). And converting the X axis of the rectangular coordinate system into the real axis of the virtual number domain, and converting the Y axis of the rectangular coordinate system into the virtual axis of the virtual number domain, so that the position information (X, Y) of the target obstacle can be converted into X + iy. Alternatively, if the Frenet coordinate system is adopted, the target obstacle position information may be expressed as (l, s). When the Frenet coordinate system L axis is converted into the real axis in the imaginary domain and the Frenet coordinate system S axis is converted into the imaginary axis in the imaginary domain, the position information (L, S) of the target obstacle can be converted into L + is.

And S1212, calculating a first imaginary number difference between an imaginary number corresponding to the first characteristic point in the two characteristic points and an imaginary number corresponding to any target obstacle.

For example, the first imaginary difference corresponding to the first feature point a1 and the b-th target obstacle in the a-th path segment may be expressed as the following formula (1):

cmp _diff1 (a,b)＝z _a1 -obs _b (1)

wherein z is _a1 Is the imaginary number, obs, corresponding to the first feature point a1 in the a-th path segment _b The number is an imaginary number corresponding to the b-th target obstacle.

As will be understood by those skilled in the art, since the feature point position information and the position information of the target obstacle have been converted into imaginary numbers in the imaginary number domain, respectively, the first imaginary number difference obtained by substituting the converted imaginary numbers into the above equation is also an imaginary number.

S1213, calculating a second imaginary number difference between the imaginary number corresponding to the second feature point in the two feature points and the imaginary number corresponding to any target obstacle.

For example, the second imaginary difference corresponding to the second feature point a2 and the b-th target obstacle in the a-th path segment may be expressed as the following formula (2):

cmp _diff2 (a,b)＝z _a2 -obs _b (2)

wherein z is _a2 For the imaginary number, obs, corresponding to the second feature point _b The number is an imaginary number corresponding to the b-th target obstacle.

As will be understood by those skilled in the art, since the feature point position information and the position information of the target obstacle have been converted into imaginary numbers in the imaginary number domain before, respectively, the second imaginary number difference obtained when the converted imaginary numbers are substituted into the above equation is also an imaginary number.

And S1214, determining the obstacle homotopy description of any target obstacle according to the first imaginary number difference and the second imaginary number difference.

Optionally, the implementation method of this step may include: calculating a position difference according to the first imaginary number difference and the second imaginary number difference; calculating an angle difference according to the first imaginary number difference and the second imaginary number difference; and determining the obstacle homotopy description of any target obstacle according to the position difference and the angle difference.

For example, the position difference corresponding to the a-th path segment and the b-th target obstacle may be expressed as the following formula (3):

log _real (a,b)＝ln|cmp _diff1 (a,b)|-ln|cmp _diff2 (a,b)| (3)

the angle difference corresponding to the a-th path segment and the b-th target obstacle can be expressed as the following formula (4):

wherein, normaize [ arg (cmp) _diff1 (a,b))-arg(cmp _diff2 (a,b))]Is determined by determining an integer beta, such that | arg (cmp) _diff1 (a,b))-arg(cmp _diff2 (a, b)) +2 β π | is minimal.

When | arg (cmp) _diff1 (a,b))-arg(cmp _diff2 (a, b)) + 2. Beta. Pi. | (minimum), arg _diff (a,b)＝normalize[arg(cmp _diff1 (a,b))-arg(cmp _diff2 (a,b))]＝arg(cmp _diff1 (a,b))-arg(cmp _diff2 (a,b))+2βπ。

At this time, if arg (cmp) _diff1 (a,b))-arg(cmp _diff2 (a, b)) + 2. Beta. Pi. Is a negative angle, then arg _diff (a, b) is a negative angle.

If arg (cmp) _diff1 (a,b))-arg(cmp _diff2 (a, b)) + 2. Beta. Pi. Is a positive angle, then arg _diff And (a, b) is a positive angle. I.e. angle difference arg _diff (a, b) normalizing to get arg _diff (a,b)∈(-π～π)。

Alternatively, the obstacle homotopy description for any target obstacle may be expressed as the following equation (5):

that is, the position difference is taken as the real part and the angle difference is taken as the imaginary part.

S1221, determining an obstacle factor of any target obstacle according to the obstacle identification of any target obstacle.

And S1222, multiplying the obstacle factor of any target obstacle by the obstacle homotopy description to obtain the description information of any target obstacle.

Illustratively, obs is utilized _b-index Indicating the identity of the b-th target obstacle. In the technical scheme of the application, different barriers correspond to different identifiers, namely the identifier of each barrier is unique. The obstacle factor for any target obstacle may be denoted as A _b ＝obs _b-index And n is a constant, and the specific value of n is not limited.

The description information of the target obstacle corresponding to both the a-th path segment and the b-th target obstacle may be expressed as the following formula (6):

A _b *Z _a，b ＝(obs _b-index +n)*(log _real (a,b)+i*arg _diff (a,b)) (6)

Optionally, assuming that k feature points are selected in a certain initial path, the k feature points divide the initial path into k-1 path segments, and the initial path relates to c target obstacles in total, then the homotopy value of the initial path may be represented as the following formula (7):

fig. 7 is a schematic diagram of another road condition provided by the embodiment of the disclosure. In FIG. 7, (0, 0) indicates a starting point, and (7, 7) indicates an end point. The path of (0, 0) → (0, 7) → (7, 7) is the initial path 1. The path of (0, 0) → (7, 7) is the initial path 2. (2, 5) represents the position coordinates of the obstacle 1, and (5, 2) represents the position coordinates of the obstacle 2. The obstacle 1 and the obstacle 2 are symmetrical with respect to a line connecting the start point and the end point. In addition, points on the same trajectory are symmetrical with respect to a line connecting the obstacle 1 and the obstacle 2, for example, points a and B on the initial path 1 are symmetrical with respect to a line connecting the obstacle 1 and the obstacle 2. The points on the different initial paths are also symmetrical with respect to the line connecting obstacle 1 and obstacle 2.

3 points D1 (0, 0), D2 (0, 7) and D3 (7, 7) are selected from the initial path 1 as characteristic points. 3 points E1 (0, 0), E2 (7, 0), E3 (7, 7) are selected from the initial path 2 as feature points. Obs for position coordinates of obstacle 1 ₁ Indicates that the obstacle 1 is marked with obs _1-index And (4) showing. Obs for position coordinates of obstacle 2 ₂ Indicates that obs is used for marking the obstacle 2 _2-index And (4) showing. Denoting the homotopy value of initial path 1 by H1 and the homotopy value of initial path 2 by H2, there are:

make the obs corresponding to the obstacle 1 _1-index Obs corresponding to obstacle 2 is 1 _2-index Is 2, n is 0, then

A ₁ ＝obs _1-index +n＝1

A ₂ ＝obs _2-index +n＝2

H1＝2·i(113.2°)+4·i(66.8°)＝i(493.6°)

H2＝2·i(-66.8°)+4·i(-113.2°)＝i(-586.4°)

Since the homotopy value H1 of the initial path 1 and the homotopy value H2 of the initial path 2 are different, the initial path 1 and the initial path 2 are not similar. Both initial path 1 and initial path 2 should be considered as paths of the minimum complete set.

The technical scheme provides a specific homotopy value calculation method for the initial path, the whole calculation process is simple and easy to realize, the calculated homotopy value can fully reflect the position relation between the initial path and each target obstacle, the subsequent target path can be accurately determined, and the user experience is improved.

Fig. 8 is a schematic diagram of another road condition provided in the embodiment of the present disclosure. In FIG. 8, (0, 0) indicates a starting point, and (7, 7) indicates an end point. The path of (0, 0) → (7, 2) → (0, 5) → (7, 7) is the initial path 1. The path of (0, 0) → (2, 7) → (5, 0) → (7, 7) is the initial path 2. (2, 5) represents the position coordinates of the obstacle 1, and (5, 2) represents the position coordinates of the obstacle 2. The obstacle 1 and the obstacle 2 are symmetrical with respect to a line connecting the start point and the end point, and further, points on different initial paths are symmetrical with respect to a line connecting two target obstacles. For example, points (0, 5) on the initial path 1 and points (2, 7) on the initial path 2 are symmetrical with respect to a line connecting the obstacle 1 and the obstacle 2.

Studies have shown that for both cases, fig. 7 and 8, once the obstacle factor setting is not reasonable, initial path 1 and initial path 2, which are not homotopy in nature, are misjudged as homotopy. And in the technical scheme, the barrier factors are reasonably and skillfully set, so that the situation of homotopy misjudgment can be avoided. It is particularly applicable to two target obstacles symmetrically with respect to the line connecting the start point and the end point, to points on the same initial path symmetrically with respect to the line connecting the two target obstacles (as in the case of fig. 7), or to points on different initial paths symmetrically with respect to the line connecting the two target obstacles (as in the case of fig. 8).

Fig. 9 is a schematic structural diagram of a path planning apparatus according to an embodiment of the present disclosure. The path planning apparatus provided in the embodiment of the present disclosure may execute the processing procedure provided in the embodiment of the path planning method, as shown in fig. 9, the path planning apparatus includes:

an obtaining module 210, configured to obtain multiple initial paths from a starting point to an end point;

a first determining module 220, configured to determine a homotopy value of each initial path according to feature point position information of at least two feature points on each initial path and obstacle position information of target obstacles around each initial path, where the homotopy value is related to an obstacle identifier of each target obstacle;

a second determining module 230, configured to determine a target path from the multiple initial paths according to the homotopy value of each initial route.

Optionally, the second determining module 230 is configured to:

determining a minimum complete set from the plurality of initial paths according to the homotopy value of each initial path, wherein the homotopy values of any two initial paths included in the minimum complete set are different;

determining the target path from the minimal complete set.

Optionally, the first determining module 220 is configured to:

determining the barrier homotopy description of any target barrier according to the feature point position information of two adjacent feature points on any initial path and the barrier position information of any target barrier around the initial path;

determining the description information of any target obstacle according to the obstacle identification of any target obstacle and the obstacle homotopy description;

and determining the homotopy value of any initial path according to the description information of each target obstacle around any initial path.

Optionally, the first determining module 220 is configured to:

respectively converting the feature point position information of two adjacent feature points on any initial path and the obstacle position information of any target obstacle around the initial path into imaginary numbers in an imaginary number domain;

calculating a first imaginary number difference between an imaginary number corresponding to a first characteristic point of the two characteristic points and an imaginary number corresponding to any target obstacle;

calculating a second imaginary number difference between an imaginary number corresponding to a second feature point of the two feature points and an imaginary number corresponding to any target obstacle;

and determining the obstacle homotopy description of any target obstacle according to the first imaginary number difference and the second imaginary number difference.

Optionally, the first determining module 220 is configured to:

calculating a position difference according to the first imaginary number difference and the second imaginary number difference;

calculating an angle difference according to the first imaginary number difference and the second imaginary number difference;

and determining the obstacle homotopy description of any one target obstacle according to the position difference and the angle difference.

Optionally, the first determining module 220 is configured to:

determining an obstacle factor of any target obstacle according to the obstacle identification of any target obstacle;

multiplying the obstacle factor of any target obstacle by the obstacle homotopy description to obtain the description information of any target obstacle.

Optionally, the feature points include at least one of:

inflection points and extreme points.

The path planning apparatus in the embodiment shown in fig. 9 may be used to implement the technical solutions of the above method embodiments, and the implementation principles and technical effects are similar, which are not described herein again.

The internal functions and structure of the path planning apparatus, which may be implemented as an unmanned device, are described above. Fig. 10 is a schematic structural diagram of an embodiment of an unmanned aerial device provided in an embodiment of the present disclosure. Alternatively, the unmanned device may be an unmanned vehicle, a smart-drive automobile, a robot, or the like. As shown in fig. 10, the drone includes a memory 151 and a processor 152.

And a memory 151 for storing programs. In addition to the programs described above, the memory 151 may be configured to store various other data to support operations on the drone. Examples of such data include instructions for any application or method operating on the drone, contact data, phonebook data, messages, pictures, videos, and the like.

The memory 151 may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

A processor 152, coupled to the memory 151, that executes programs stored by the memory 151 to:

acquiring a plurality of initial paths from a starting point to an end point;

Further, as shown in fig. 10, the unmanned device may further include: communication components 153, power components 154, audio components 155, a display 156, and other components. Only some of the components are shown schematically in fig. 10 and do not mean that the drone includes only the components shown in fig. 10.

The communication component 153 is configured to facilitate wired or wireless communication between the drone and other devices. The drone may access a wireless network based on a communication standard, such as WiFi,2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 153 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 153 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

A power supply component 154 provides power to the various components of the drone. The power components 154 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the drone.

Audio component 155 is configured to output and/or input audio signals. For example, audio component 155 includes a Microphone (MIC) configured to receive external audio signals when the drone is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 151 or transmitted via the communication component 153. In some embodiments, audio component 155 also includes a speaker for outputting audio signals.

The display 156 includes a screen, which may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

In addition, a computer-readable storage medium is provided in the embodiments of the present disclosure, and a computer program is stored thereon, where the computer program is executed by a processor to implement the path planning method in the embodiments.

It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.

The foregoing are merely exemplary embodiments of the present disclosure, which enable those skilled in the art to understand or practice the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A path planning method, wherein the method comprises:

acquiring a plurality of initial paths from a starting point to an end point;

determining a homotopy value of each initial path according to the feature point position information of at least two feature points on each initial path and the obstacle position information of the target obstacles around each initial path, wherein the homotopy value is related to the obstacle identification of each target obstacle;

2. The method of claim 1, wherein determining a target path from the plurality of initial paths based on the homotopy value of each of the initial routes comprises:

determining the target path from the minimal complete set.

3. The method according to claim 1, wherein determining the homotopy value of each initial path according to the feature point position information of at least two feature points on each initial path and the obstacle position information of the target obstacles around each initial path comprises:

determining description information of any target obstacle according to the obstacle identification of any target obstacle and the obstacle homotopy description;

4. The method according to claim 3, wherein determining the obstacle homotopy description of any target obstacle according to the feature point position information of two adjacent feature points on any initial path and the obstacle position information of any target obstacle around the any initial path comprises:

5. The method of claim 4, wherein determining an obstacle homotopy description of the any target obstacle from the first and second imaginary differences comprises:

6. The method of claim 3, wherein determining the description information of any target obstacle according to the obstacle identification of any target obstacle and the obstacle homotopy description comprises:

7. The method of any of claims 1-6, wherein the feature points comprise at least one of:

inflection points and extreme points.

8. A path planning apparatus, comprising:

9. An unmanned device, comprising:

a memory;

a processor; and

a computer program;

wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method of any one of claims 1-7.