CN117647258A

CN117647258A - Path planning method, device, equipment and storage medium

Info

Publication number: CN117647258A
Application number: CN202311569159.0A
Authority: CN
Inventors: 梁琪
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-11-22
Filing date: 2023-11-22
Publication date: 2024-03-05

Abstract

The disclosure provides a path planning method, a path planning device, path planning equipment and a path planning storage medium, and relates to the technical field of artificial intelligence, in particular to the technical fields of automatic driving, intelligent home and the like. The specific implementation scheme is as follows: according to monitoring data of the obstacle, determining a distribution function representing the distribution of a repulsive force field, wherein a dependent variable of the distribution function is used for representing repulsive force generated by the obstacle aiming at the target self-moving equipment, and the independent variable is used for representing the relative distance between a path point position obtained by path planning and a reference area where the obstacle is located. Further, an objective function of path planning is determined from the distribution function. And planning a path according to the objective function to obtain a target path, wherein the relative distance between the path point position and the reference point position in the target path is used as an independent variable value to be substituted into the objective function, so that the dependent variable value of the objective function accords with a set condition.

Description

Path planning method, device, equipment and storage medium

Technical Field

The disclosure relates to the technical field of artificial intelligence, in particular to the technical fields of automatic driving, intelligent home furnishing and the like, and can be applied to path planning of vehicles such as vehicles, aircrafts, ships and the like, and path planning of intelligent home equipment such as sweeping robots, weeding machines and the like, and particularly relates to a path planning method, a device, equipment and a storage medium.

Background

The path planning mainly comprises the steps of defining an objective function (cost) and a constraint (constraint), and solving an optimization problem of the objective function under the constraint condition to realize the path planning under different scenes. The need for softer reference line similarity, somatosensory comfort, etc. is typically set as the objective function and the need for harder road boundaries, obstacle boundaries, etc. is set as the constraint in the path planning problem. In the obstacle avoidance scene, the obstacle avoidance is performed by adjusting the constraint, the path line shape is harder, and the effectiveness of corresponding loss items such as reference line similarity and comfort in the objective function can be directly damaged.

Therefore, there is a need for a way to adjust the path linearity as much as possible within the original constraint.

Disclosure of Invention

The disclosure provides a path planning method, a path planning device, path planning equipment and a storage medium.

According to an aspect of the present disclosure, there is provided a path planning method including:

acquiring monitoring data of an obstacle;

determining a distribution function representing the distribution of a repulsive force field according to the monitoring data of the obstacle, wherein a dependent variable of the distribution function is used for representing repulsive force generated by the obstacle aiming at a target self-mobile device, and the independent variable is used for representing the relative distance between a path point position obtained by path planning and a reference area where the obstacle is located;

Determining an objective function of path planning according to the distribution function;

and carrying out path planning according to the objective function to obtain a target path, wherein the relative distance between the path point in the target path and the reference point is used as an independent variable value to be substituted into the objective function, so that the dependent variable value of the objective function accords with a set condition.

According to another aspect of the present disclosure, there is provided a path planning apparatus including:

the acquisition module is used for acquiring monitoring data of the obstacle;

the first determining module is used for determining a distribution function representing the distribution of the repulsive force field according to the monitoring data of the obstacle, wherein a dependent variable of the distribution function is used for representing repulsive force generated by the obstacle aiming at the target self-mobile equipment, and the independent variable is used for representing the relative distance between a path point position obtained by path planning and a reference area where the obstacle is located;

the second determining module is used for determining an objective function of path planning according to the distribution function;

and the planning module is used for planning a path according to the objective function to obtain a target path, wherein the relative distance between the path point in the target path and the reference point is used as an independent variable value to be substituted into the objective function, so that the dependent variable value of the objective function accords with a set condition.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect embodiment of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of the first aspect embodiment of the present disclosure.

According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method as described in embodiments of the first aspect of the present disclosure.

According to the path planning method, the device, the equipment and the storage medium, a distribution function representing the distribution of the repulsive force field is determined according to the monitoring data of the obstacle, wherein a dependent variable of the distribution function is used for representing the repulsive force generated by the obstacle aiming at the target self-mobile equipment, and an independent variable is used for representing the relative distance between a path point position obtained by path planning and a reference area where the obstacle is located. Further, an objective function of path planning is determined from the distribution function. And planning a path according to the objective function to obtain a target path, wherein the relative distance between the path point position and the reference point position in the target path is used as an independent variable value to be substituted into the objective function, so that the dependent variable value of the objective function accords with a set condition.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 is a schematic flow chart of a path planning method according to an embodiment of the disclosure;

FIG. 2 is a flow chart of another path planning method provided by an embodiment of the present disclosure;

fig. 3 is a flow chart of a path planning method according to an embodiment of the disclosure;

FIG. 4 is a schematic illustration of key waypoints;

FIG. 5 is a schematic view of a reference area;

FIG. 6 is a schematic diagram of vectors;

FIG. 7 illustrates a flow execution path planning process;

FIG. 8 is a schematic diagram of the distribution of repulsive force fields;

fig. 9 is a schematic structural diagram of a path planning apparatus 900 according to an embodiment of the disclosure;

fig. 10 shows a schematic block diagram of an example electronic device 1000 that may be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the obstacle avoidance scenario, if one wants to adjust the path plan to bypass the obstacle, there are two ways, one is to modify the objective function, and the second is to modify the constraint. Generally, the magnitude of the penalty incurred by violating the constraint will be much greater than the objective function, i.e., the constraint is rigidly complied with when solving the optimization problem, so the most efficient way to adjust the line shape is to adjust the constraint. In the related art, a boundary range of the path planning may be determined according to the outer circumference of the obstacle, and the path planning may be performed within the boundary range.

However, the adjustment of the linear shape by adjusting the constraint is hard, the effectiveness of objective functions such as similarity of the reference line and comfort of the body feeling can be directly damaged, and in most optimization problems, the irregular constraint can increase the solving difficulty of the optimization problems. Therefore, there is a need for a way to adjust the path alignment as much as possible within the original constraint boundaries.

In order to solve the problem, in the embodiment, a repulsive force field is generated according to monitoring data of an obstacle, the repulsive force generated by the obstacle aiming at the target self-moving equipment is represented, and a process of pushing the target self-moving equipment relative to the obstacle is simulated. And combining the repulsive force field to construct an objective function, and solving an optimization problem in the original constraint boundary to obtain a planned objective path under the action of the repulsive force field, thereby realizing the obstacle avoidance effect.

It should be noted that, the target self-mobile device suitable for path planning in each embodiment may be path planning of vehicles such as vehicles, aircrafts and ships, and path planning applicable to intelligent home devices such as sweeping robots and weeder, and the type of the target sub-mobile device is not limited in this embodiment.

Fig. 1 is a flow chart of a path planning method provided in an embodiment of the present disclosure, as shown in fig. 1, the method provided in the embodiment may be executed by a device for path planning, where the device may be a cloud server, and may also be mounted on a target self-mobile device, which is not limited in this embodiment.

Step 101, obtaining monitoring data of the obstacle.

In some situations, the obstacle is a static obstacle, and the monitoring data may be used to indicate information such as a position and a contour of the obstacle, so as to describe a space occupied by the obstacle.

In some scenarios, the obstacle is a dynamic obstacle, and the monitoring data may include not only information such as a position and a contour that are also included in the static obstacle, but also motion data. For example: the motion data may be velocity, acceleration, etc., wherein it is noted that the velocity and acceleration may be vectors, i.e. indicating both magnitude and direction of motion.

Step 102, determining a distribution function representing the distribution of the repulsive force field according to the monitoring data of the obstacle, wherein a dependent variable of the distribution function is used for representing repulsive force generated by the obstacle aiming at the target self-mobile device, and the independent variable is used for representing the relative distance between a path point position obtained by path planning and a reference area where the obstacle is located.

Optionally, a spatial range occupied by the obstacle is determined based on the monitored data of the obstacle, so that a distribution function of the repulsive force field distribution is determined in this range. In some possible implementations, the center of the repulsive force field distribution may be located at the center of the obstacle, or may be located at a center point or neutral line determined with reference to the center of the obstacle. Therefore, when the target self-moving device approaches to the obstacle, the obstacle can apply a repulsive force field to the target self-moving device, and therefore path planning of the self-moving device is affected.

And step 103, determining an objective function of path planning according to the distribution function.

As a possible implementation, the distribution function is taken as an objective function of path planning.

As another possible implementation, the distribution function is taken as one loss term in an objective function of path planning, and the objective function may further include other multiple loss terms, so as to score the planned paths from different angles respectively, so as to select an optimal planned path as a target path for navigation. For example: a loss term based on a somatosensory comfort score and a loss term based on a similarity score with a reference line may also be included in the objective function. The reference line is a rough moving route indicating the target from the mobile device, and in general, the reference line may be a shortest route determined based on a set start point, an end point. In some special scenarios, such as a turn around scenario, the reference line may be determined not only based on the set start point, the end point, but also on the key route points, that is, the reference line is the shortest route determined based on the set start point, the end point, and the key route points.

When there are a plurality of obstacles, a corresponding distribution function is determined for each obstacle, and the distribution function corresponding to each obstacle is used as one loss term in the objective function to perform path planning.

And 104, planning a path according to the objective function to obtain a target path, wherein the relative distance between the path point in the target path and the reference point is substituted into the objective function as an independent variable value, so that the dependent variable value of the objective function meets a set condition.

Optionally, after determining the objective function, this is equivalent to solving an optimization problem. Each time a path point in a target path is solved, the path point is taken as the current point to continue to solve the next point. The relative distance between the path point in the target path and the reference point is used as an independent variable value to be substituted into the target function, so that the dependent variable value of the target function accords with a set condition. The setting condition may be that the dependent variable value of the objective function converges, or that the set condition is smaller than a set loss threshold.

In the embodiment of the disclosure, a distribution function representing the distribution of a repulsive force field is determined according to monitoring data of an obstacle, wherein a dependent variable of the distribution function is used for representing repulsive force generated by the obstacle aiming at a target self-mobile device, and the independent variable is used for representing the relative distance between a path point position obtained by path planning and a reference area where the obstacle is located. Further, an objective function of path planning is determined from the distribution function. And planning a path according to the objective function to obtain a target path, wherein the relative distance between the path point position and the reference point position in the target path is used as an independent variable value to be substituted into the objective function, so that the dependent variable value of the objective function accords with a set condition. In this embodiment, a repulsive field is generated according to the monitoring data of the obstacle, so as to characterize the repulsive force generated by the obstacle against the target self-moving device, and simulate pushing the target self-moving device away from the obstacle. And combining the repulsive force field to construct an objective function, and solving an optimization problem in the original constraint boundary to obtain a planned objective path under the action of the repulsive force field, thereby realizing the obstacle avoidance effect. Compared with the related art, the method for solving the optimization problem based on the related information construction constraint condition of the obstacle to obtain the planned path avoids the problem that the line shape is hard, maintains the effectiveness of objective functions such as similarity of the reference line and comfort of the body feeling, and solves the problem that the problem of solving the optimization problem is increased due to irregular constraint caused by the obstacle in the related art.

Fig. 2 is a flow chart of another path planning method according to an embodiment of the present disclosure, in which the strength of the repulsive field can be dynamically adjusted according to different obstacles. This is mainly to consider that the influence on the path planning will be different for different obstacles with different safety distances, so in this embodiment, the repulsive force field strength is dynamically adjusted according to the obstacles.

Step 201, determining the distance between the obstacle and the travelling direction of the target from the mobile device according to the current position of the obstacle in the monitoring data.

Wherein the direction of travel of the target from the mobile device may be determined based on a reference line of the target from the mobile device. The reference line is a rough moving route indicating the target from the mobile device, and is typically the shortest route determined based on the set start point and end point. In some special scenarios, such as a turn around scenario, the reference line may be determined not only based on the set start point, the end point, but also on the key route points, that is, the reference line is the shortest route determined based on the set start point, the end point, and the key route points.

Step 202, determining the upper limit of the intensity of the repulsive field according to the distance and/or the movement speed of the obstacle in the monitoring data.

Wherein the upper limit of the strength of the repulsive force field, i.e. the maximum repulsive force in the repulsive force field.

As one possible implementation manner, a mapping relationship between the pitch and the upper intensity limit is preset, the corresponding upper intensity limit is determined according to the pitch, and the pitch and the upper intensity limit are in a forward relationship, that is, the larger the pitch is, the larger the upper intensity limit is, so that the effect of repulsion force is still reflected under the condition of ensuring the larger pitch.

As another possible implementation manner, a mapping relationship between the movement speed and the intensity upper limit is preset, and the corresponding intensity upper limit is determined according to the movement speed, and the movement speed and the intensity upper limit are in a forward relationship, that is, the larger the movement speed is, the larger the intensity upper limit is. Since the consequences of a collision of an object with a faster movement speed are larger than those of an object with a slower movement speed, a larger safety distance is required to avoid the planned path approaching the obstacle. By setting a larger upper limit of intensity, stronger repulsive force can be acted on the target self-moving equipment, and the target self-moving equipment are prevented from being close to each other.

As yet another possible implementation, the pitch and the motion speed are weighted according to the corresponding weights, so as to obtain a final upper intensity limit, i.e. the two modes are fused, and both are considered. The weight corresponding to the pitch and the movement speed may be empirically set, and is not limited in this embodiment.

Further, the upper intensity limit is adjusted according to the similarity of the traveling direction of the target from the mobile device and the obstacle and/or according to the somatosensory comfort requirement information. The upper limit of the intensity can be more dynamic and is fit with the actual scene demand.

In step 203, an intensity coefficient is determined according to the intensity upper limit.

Alternatively, the upper intensity limit may be used as the intensity coefficient in a distribution function comprising two multiplied parameters, one of which is the intensity coefficient and the other of which is a standard distribution function characterizing the distribution morphology. The standard distribution function represents a gaussian distribution morphology in this example.

And 204, generating a distribution function according to the intensity coefficient, wherein a dependent variable of the function is used for representing repulsive force generated by the obstacle aiming at the target self-mobile device, and the independent variable is used for representing the relative distance between the route point position obtained by path planning and the reference area where the obstacle is located.

For example: the distribution function is denoted as w×g (d (x, y)). Wherein w is an intensity coefficient, x and y represent position coordinates of the path point positions obtained by path planning, and d is an independent variable of a Gaussian distribution function and used for representing the relative distance between the path point positions obtained by path planning and a reference area where the obstacle is located. The dependent variable of w x G (d (x, y)) is used to characterize the repulsive force of the obstacle against the target generated from the mobile device.

Step 205, determining an objective function of path planning according to the distribution function.

Reference is made to the related description of step 103 in the foregoing embodiment, which is not repeated in this embodiment.

And 206, performing path planning by using a function to obtain a target path, wherein the relative distance between the path point in the target path and the reference point is used as an independent variable value to be substituted into the target function, so that the dependent variable value of the target function accords with a set condition.

Reference is made to the related description of step 104 in the foregoing embodiment, which is not repeated in this embodiment.

In the embodiment of the disclosure, a distribution function representing the distribution of a repulsive force field is determined according to monitoring data of an obstacle, wherein a dependent variable of the distribution function is used for representing repulsive force generated by the obstacle aiming at a target self-mobile device, and the independent variable is used for representing the relative distance between a path point position obtained by path planning and a reference area where the obstacle is located. Further, an objective function of path planning is determined from the distribution function. And planning a path according to the objective function to obtain a target path, wherein the relative distance between the path point position and the reference point position in the target path is used as an independent variable value to be substituted into the objective function, so that the dependent variable value of the objective function accords with a set condition. In this embodiment, a repulsive field is generated according to the monitoring data of the obstacle, so as to characterize the repulsive force generated by the obstacle against the target self-moving device, and simulate pushing the target self-moving device away from the obstacle. And combining the repulsive force field to construct an objective function, and solving an optimization problem in the original constraint boundary to obtain a planned objective path under the action of the repulsive force field, thereby realizing the obstacle avoidance effect. Meanwhile, for different obstacles, the influence on the path planning is also different in consideration of different safety distances, so that the dynamic adjustment of the repulsive force field strength is also carried out according to the obstacles in the embodiment.

Fig. 3 is a flow chart of a path planning method provided by an embodiment of the present disclosure, in this embodiment, the repulsive force field distribution is gaussian distribution, that is, a distribution function representing the repulsive force field distribution is a gaussian distribution function. Due to the continuity of the Gaussian distribution function, the solving difficulty in the optimization problem is reduced, and the fact that the optimal solution exists in the objective function determined according to the Gaussian distribution function is guaranteed, so that path planning is conducted accordingly.

Step 301, determining whether obstacle avoidance is required according to the monitored data of the obstacle.

As a possible implementation, the first moment of movement of the obstacle to the critical passing point is predicted from the acceleration and the velocity in the monitored data of the obstacle. And predicting a second moment when the target moves from the mobile device to the key passing point according to the acceleration and the speed of the target from the mobile device. And determining that obstacle avoidance is required under the condition that the difference between the first moment and the second moment is smaller than a time threshold value. Otherwise, the obstacle avoidance is not needed, and the operation resources are saved.

In this embodiment, a vehicle turn-around scene is taken as an example to describe a key path point location. In the vehicle turn scene, as shown in fig. 4, the positions of the key passing points are indicated.

As shown in fig. 4, (1) indicates a target self-moving device, (2) indicates an obstacle, and (3) indicates a critical waypoint. The thin solid line in the figure indicates the reference line of the target from the mobile device, the arrow marked on the obstacle indicates the predicted travel direction of the obstacle, and the thicker solid line in the figure is the lane boundary line. In this scenario, the location of the turn-in turn is noted as the critical path point location.

Step 302, under the condition that obstacle avoidance is determined, determining a target line segment as a distribution center of a Gaussian distribution function, and determining the variance of the Gaussian distribution function according to the size of the set action range of the repulsive force field.

As one possible implementation, the target line segment may be determined in the following manner: determining an endpoint of the target line segment according to the current position of the obstacle in the monitoring data; and determining the other end point of the target line segment according to the travelling direction of the obstacle in the monitoring data and according to the key path point of the target self-mobile equipment, wherein the end point is a point which is positioned in the travelling direction of the obstacle and is closest to the key path point.

Alternatively, the variance σ of the gaussian distribution function may be preconfigured. I.e. the size of the range of action may be preconfigured, the repulsive force field only affecting the trajectories within the corresponding range, the trajectories outside the range being unaffected by it.

Further, based on the distribution center and the variance, the intensity coefficient may be dynamically adjusted according to the above embodiment, the intensity coefficient w is added to the gaussian distribution function to obtain a final gaussian distribution function w×g (d (x, y)),the specific manner of determining the intensity coefficient w may refer to the related description in the foregoing embodiment, which is not repeated in this embodiment.

And d is used as an independent variable of a Gaussian distribution function and used for representing the relative distance between the path point position obtained by path planning and a reference area where the obstacle is located. The dependent variable of w x G (d (x, y)) is used to characterize the repulsive force of the obstacle against the target generated from the mobile device.

As one possible implementation, the reference region may be determined in the following manner. According to the target line segment, two parallel lines perpendicular to the target line segment are determined; wherein the two parallel lines respectively pass through two endpoints of the target line segment. And taking the area surrounded by the target line segment and the two parallel lines as a reference area where the obstacle is located. As shown in fig. 5, the reference area is identified, the hatched portion in the drawing is the reference area, the left area in fig. 5 extends to the left, and the right area in fig. 5 extends to the right.

Accordingly, as shown in fig. 5, according to the reference area, the space is divided into six subspaces, and each subspace is used for calculating d in different manners, wherein the reference area is also used as a subspace, and a point d in the space takes a value of zero.

For example:

the division into six possibilities is to calculate d separately, mainly to make d continuous.

The above parameters are explained below in connection with fig. 6. An end point of a target line segment determined according to the current position of the obstacle is recorded as a starting point; the other end point of the target line segment is marked as an end point; p (P) ₀ Is a vector pointing from a start point to an end point. proj is a vector P pointing from any passing point (x, y) to the origin _x At P ₀ Projection length on the upper surface. projR is proj length-to-length P ₀ Is a length of (c). Cross is the vector P ₀ Sum vector P _x The positive and negative representation points (x, y) of the result are in the vector P ₀ Whether left or right of (a) may be defined as positive and negative in this embodiment.

By the method, d (x, y) corresponding to (x, y) can be determined, and repulsive force at (x, y) can be determined by substituting w×g (d (x, y)).

And 303, generating an objective function according to the determined Gaussian distribution function.

As a possible implementation, the determined gaussian distribution function is taken as a loss term C in the objective function C ₁ C, i.e ₁ =w×g (d (x, y)). Loss term C ₁ The design of the (2) is that the G Gaussian function and the d distance function are compounded, so that the continuity of the gradient and the second derivative can be ensured, and the optimization problem can be successfully solved.

The objective function C further includes various loss terms, and the description in step 103 may be referred to specifically, which is not repeated in this embodiment.

Step 304, path planning is performed according to the objective function to obtain the objective path.

Optionally, the determined passing point is taken as a reference point, and the first derivative and the second derivative of the objective function C at the reference point are determined. And determining candidate path points with the spacing conforming to the ratio at the periphery of the reference point according to the ratio between the first derivative and the second derivative of the reference point. And under the condition that the distance is smaller than or equal to a distance threshold value, the candidate route point positions are used as route point positions obtained by path planning. And updating the candidate route points to the reference points under the condition that the distance is larger than a distance threshold value, and re-executing the steps of determining the first derivative and the second derivative of the objective function at the reference points, and determining candidate route points with the distance conforming to the ratio at the periphery of the updated reference points according to the ratio between the first derivative and the second derivative of the reference points.

For example, take newton's method as an example to solve the optimization problem, where C (x, y) is the objective function:

first, an initial point such as (0, 0) is set;

secondly, deriving, namely solving the gradient of C (x, y) at an initial point, namely a jacobian matrix C_x;

thirdly, obtaining a second derivative, and obtaining a sea plug matrix C_xx of C (x, y) at an initial point;

fourth, updating the formula from the initial point x_old to the next point x_new

x_new＝x_old-C_x/C_xx

The loop performs the second through fourth steps, and when x_new is very close to x_old (e.g., x_new-x_old < 0.001), the loop may be ended with x_new at this time as the optimal value.

According to the method, a Gaussian distribution function representing the distribution of a repulsive force field is determined according to monitoring data of an obstacle, wherein a dependent variable of the Gaussian distribution function is used for representing repulsive force generated by the obstacle aiming at a target self-mobile device, and the independent variable is used for representing the relative distance between a path point position obtained by path planning and a reference area where the obstacle is located. Further, an objective function of path planning is determined from the gaussian distribution function. And planning a path according to the objective function to obtain a target path, wherein the relative distance between the path point position and the reference point position in the target path is used as an independent variable value to be substituted into the objective function, so that the dependent variable value of the objective function accords with a set condition. Because of the continuity of the gaussian distribution function, the first derivative and the second derivative are necessarily present, and therefore, the required passing point can be obtained through the formula.

In some possible embodiments, to perform the path planning of the vehicle, a developer is required to perform the path planning process in a flow as shown in fig. 7.

First, a reference line is constructed.

And secondly, constructing a driving boundary constraint.

Third, a loss term of the similarity of the reference lines is set.

And fourthly, setting a loss item of body feeling comfort.

And fifthly, setting related data of the repulsive field, including setting the influence range and effective conditions of the repulsive field.

And sixthly, determining a loss item of the repulsive field based on the related data of the set repulsive field. The method specifically comprises the steps of deciding whether a repulsive force field is needed to be used as a loss item according to actual scene requirements, calculating a target line segment to be used as a distribution center of the repulsive force field under the condition of determining the needed repulsive force field, determining an intensity upper limit, and determining the loss item corresponding to the repulsive force field according to the distribution center, an influence range and the intensity upper limit.

And seventh, solving an optimization problem by adopting an objective function formed by the constraint and the loss term to obtain a planned target path.

In this embodiment, a repulsive field is generated according to the monitoring data of the obstacle, so as to characterize the repulsive force generated by the obstacle against the target self-moving device, and simulate pushing the target self-moving device away from the obstacle. And combining the repulsive force field to construct an objective function, and solving an optimization problem in the original constraint boundary to obtain a planned objective path under the action of the repulsive force field, thereby realizing the obstacle avoidance effect. In this embodiment, the distribution of the repulsive field refers to gaussian distribution, as shown in fig. 8, which is a schematic diagram of the distribution of the repulsive field, as shown in fig. 8, where the X-axis and the Y-axis represent positions where the target is located from the mobile device, and N represents the repulsive force. Due to the continuity of the Gaussian distribution function, the solving difficulty in the optimization problem is reduced, and the fact that the optimal solution exists in the objective function determined according to the Gaussian distribution function is guaranteed, so that path planning is conducted accordingly.

Fig. 9 is a schematic structural diagram of a path planning apparatus 900 according to an embodiment of the present disclosure, as shown in fig. 9, including: an acquisition module 901, a first determination module 902, a second determination module 903, and a planning module 904.

An acquisition module 901, configured to acquire monitoring data of an obstacle;

a first determining module 902, configured to determine, according to the monitored data of the obstacle, a distribution function representing a distribution of a repulsive force field, where a dependent variable of the distribution function is used to represent repulsive force generated by the obstacle for a target self-mobile device, and the independent variable is used to represent a relative distance between a path point location obtained by path planning and a reference area where the obstacle is located;

a second determining module 903, configured to determine an objective function of path planning according to the distribution function;

and a planning module 904, configured to perform path planning according to the objective function, so as to obtain a target path, where a relative distance between a path point in the target path and the reference point is used as an argument value to be substituted into the objective function, so that the argument value of the objective function meets a set condition.

In some possible embodiments, the first determining module 902 is configured to:

Determining a distance between the obstacle and the travelling direction of the target self-mobile equipment according to the current position of the obstacle in the monitoring data;

determining an upper limit of the intensity of the repulsive field according to the distance and/or the movement speed of the obstacle in the monitoring data;

and determining the intensity coefficient in the distribution function according to the intensity upper limit.

and weighting the distance and the movement speed of the obstacle in the monitoring data to obtain the upper limit of the intensity of the repulsive force field.

and adjusting the upper intensity limit according to the similarity of the travelling directions of the target self-mobile equipment and the obstacle and/or according to the somatosensory comfort requirement information.

In some possible embodiments, the distribution function is a gaussian distribution function, the gaussian distribution function distribution center is a target line segment, and the first determining module 902 is configured to:

determining an endpoint of the target line segment according to the current position of the obstacle in the monitoring data;

and determining the other end point of the target line segment according to the travelling direction of the obstacle in the monitoring data and according to the key path point of the target self-mobile equipment, wherein the end point is a point which is positioned in the travelling direction of the obstacle and is closest to the key path point.

according to the target line segment, two parallel lines perpendicular to the target line segment are determined; wherein the two parallel lines respectively pass through two endpoints of the target line segment;

and taking the area surrounded by the target line segment and the two parallel lines as a reference area where the obstacle is located.

predicting a first moment when the obstacle moves to the key passing point according to the acceleration and the speed in the monitoring data of the obstacle;

predicting a second moment when the target moves from the mobile device to the key passing point according to the acceleration and the speed of the target from the mobile device;

and under the condition that the difference between the first moment and the second moment is smaller than a time threshold, determining a Gaussian distribution function representing the repulsive force field distribution according to the monitoring data of the obstacle.

In some possible embodiments, the distribution function is a gaussian distribution function, and the first determining module 902 is configured to:

and determining the variance of the Gaussian distribution function according to the magnitude of the repulsive force field setting action range.

In some possible embodiments, the planning module 904 is configured to:

the determined passing point is used as a reference point, and a first derivative and a second derivative of the objective function at the reference point are determined;

determining candidate path points with the spacing conforming to the ratio at the periphery of the reference point according to the ratio between the first derivative and the second derivative of the reference point;

and under the condition that the distance is smaller than or equal to a distance threshold value, the candidate route point positions are used as route point positions obtained by path planning.

In some possible embodiments, the planning module 904 is configured to:

and updating the candidate route points to the reference points under the condition that the distance is larger than a distance threshold value, and re-executing the steps of determining the first derivative and the second derivative of the objective function at the reference points, and determining candidate route points with the distance conforming to the ratio at the periphery of the updated reference points according to the ratio between the first derivative and the second derivative of the reference points.

In this embodiment, a repulsive field is generated according to the monitoring data of the obstacle, so as to characterize the repulsive force generated by the obstacle against the target self-moving device, and simulate pushing the target self-moving device away from the obstacle. And combining the repulsive force field to construct an objective function, and solving an optimization problem in the original constraint boundary to obtain a planned objective path under the action of the repulsive force field, thereby realizing the obstacle avoidance effect.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

Fig. 10 shows a schematic block diagram of an example electronic device 1000 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 10, the apparatus 1000 includes a computing unit 1001 that can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 1002 or a computer program loaded from a storage unit 1009 into a RAM (Random Access Memory ) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other by a bus 1004. An I/O (Input/Output) interface 1005 is also connected to bus 1004.

Various components in device 1000 are connected to I/O interface 1005, including: an input unit 1006 such as a keyboard, a mouse, and the like; an output unit 1007 such as various types of displays, speakers, and the like; a storage unit 1008 such as a magnetic disk, an optical disk, or the like; and communication unit 1009 such as a network card, modem, wireless communication transceiver, etc. Communication unit 1009 allows device 1000 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks.

The computing unit 1001 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 1001 include, but are not limited to, a CPU (Central Processing Unit ), GPU (Graphic Processing Units, graphics processing unit), various dedicated AI (Artificial Intelligence ) computing chips, various computing units running machine learning model algorithms, DSP (Digital Signal Processor ), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 performs the various methods and processes described above, such as methods. For example, in some embodiments, the method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1000 via ROM 1002 and/or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by computing unit 1001, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform the method in any other suitable way (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit System, FPGA (Field Programmable Gate Array ), ASIC (Application-Specific Integrated Circuit, application-specific integrated circuit), ASSP (Application Specific Standard Product, special-purpose standard product), SOC (System On Chip ), CPLD (Complex Programmable Logic Device, complex programmable logic device), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory, erasable programmable read-Only Memory) or flash Memory, an optical fiber, a CD-ROM (Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display ) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network ), WAN (Wide Area Network, wide area network), internet and blockchain networks.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual Private Server" or simply "VPS") are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.

It should be noted that, artificial intelligence is a subject of studying a certain thought process and intelligent behavior (such as learning, reasoning, thinking, planning, etc.) of a computer to simulate a person, and has a technology at both hardware and software level. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning/deep learning technology, a big data processing technology, a knowledge graph technology and the like.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A path planning method, comprising:

acquiring monitoring data of an obstacle;

2. The method of claim 1, wherein the determining a distribution function characterizing a repulsive field from the monitored data of the obstacle comprises:

3. The method of claim 2, wherein said determining an upper intensity limit of the repulsive field based on the spacing and/or the speed of movement of the obstacle in the monitored data comprises:

4. The method of claim 2, wherein the method further comprises:

5. The method of claim 1, wherein the distribution function is a gaussian distribution function, the gaussian distribution function distribution center being a target line segment, the method further comprising:

6. The method of claim 5, wherein the method further comprises:

7. The method of claim 5, wherein the determining a distribution function characterizing a repulsive force field distribution from the monitored data of the obstacle comprises:

8. The method of any of claims 1-7, wherein the distribution function is a gaussian distribution function, the method further comprising:

9. The method according to any one of claims 1-7, wherein said planning a path according to the objective function, to obtain a target path, comprises:

10. The method of claim 9, wherein the method further comprises:

11. The method according to any of claims 1-7, wherein said determining an objective function of a path plan from said distribution function comprises:

the distribution function is taken as a loss term in the objective function.

12. A path planning method, comprising:

the acquisition module is used for acquiring monitoring data of the obstacle;

13. The apparatus of claim 12, wherein the first determining module is configured to:

14. The apparatus of claim 13, wherein the first determining module is configured to:

15. The apparatus of claim 14, wherein the first determining module is configured to:

16. The apparatus of claim 12, wherein the distribution function is a gaussian distribution function, the gaussian distribution function distribution center is a target line segment, and the first determining module is configured to:

17. The apparatus of claim 16, wherein the first determining module is configured to:

18. The apparatus of claim 16, wherein the first determining module is configured to:

19. The apparatus of any of claims 12-18, wherein the distribution function is a gaussian distribution function, and the first determining module is configured to:

20. The apparatus of any of claims 12-18, wherein the planning module is configured to:

21. The apparatus of claim 20, wherein the planning module is configured to:

22. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.

23. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-11.

24. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-11.