WO2021082710A1

WO2021082710A1 - Unmanned boat path planning method, apparatus and device, and storage medium

Info

Publication number: WO2021082710A1
Application number: PCT/CN2020/112535
Authority: WO
Inventors: 翟懿奎; 张俊亮; 黄灏文; 余翠琳; 陈家聪; 柯琪锐; 梁艳阳; 王宏民
Original assignee: 五邑大学
Priority date: 2019-10-31
Filing date: 2020-08-31
Publication date: 2021-05-06
Also published as: CN110850873A; CN110850873B

Abstract

An unmanned boat path planning method, apparatus and device, and a storage medium. When an unmanned boat executes a task on a river surface, the unmanned boat may collide with a drifting obstacle and a static solid obstacle, which threatens the unmanned boat to a great extent. In order to enable the unmanned boat to safely avoid obstacles on the river surface and safely reach a target, a relative speed artificial potential field method is introduced, so as to prevent collision with dynamic and static obstacles; moreover, a new gravitational function is introduced and an escape force is added, so as to help the unmanned boat in solving the problem of not being able to reach the target and being stuck in a local extremum on the river surface. A global optimal path is planned in combination with a regressive search algorithm, so that the distance of a planned path from the position of the unmanned boat to a target position is greatly shortened, and the task execution efficiency of the unmanned boat is improved.

Description

Unmanned ship path planning method, device, equipment and storage medium

Technical field

The invention relates to the technical field of path planning, in particular to a method, device, equipment and storage medium for path planning of an unmanned ship.

Background technique

An unmanned ship is a small surface platform with autonomous planning and autonomous navigation capabilities, and can autonomously complete tasks such as environment perception and target detection. Compared with unmanned aerial vehicles, unmanned ship research started late, but its development is rapid. Unmanned ships are widely used in hydrological monitoring, geomorphological surveying and mapping, military reconnaissance and strikes and other fields. With the widespread application of unmanned ships in the field of water area measurement, how to plan the measurement path of unmanned ships has become the focus of attention. Usually, the ship will encounter various obstacles in the course of sailing. Considering that there is no staff on the unmanned ship to check the surrounding environment and avoid obstacles in time, the obstacles on the river surface are very likely to be dangerous to the unmanned ship. Therefore, the path planning of unmanned ships is particularly important. The path planning of the unmanned ship refers to the unmanned ship in the water environment where static and dynamic obstacles coexist, looking for a movement path from a given start point to the end point, and meets the measurement requirements, so that it can be safely and reliably in the process of measuring and sailing. Avoid all obstacles and reach the designated target point.

The artificial potential field method has the advantages of simple algorithm principle, simple and clear algorithm structure, and relatively smooth path, and has a relatively wide range of applications in obstacle avoidance problems. However, the traditional artificial potential field method cannot avoid the collision of dynamic obstacles, and it is easy to fall into the problem of local extreme value, and the problem of unreachable target may occur because the distance between the target point and the obstacle is too close. In the measurement path planning of the existing unmanned ships, most of them have already planned the global path, and the unmanned ship walks according to the designated planned path, thus ignoring the dynamic obstacles and the non-global path optimal situation, so seek It is particularly important that a better and improved artificial potential field method solves the above problems.

Summary of the invention

In order to solve the above problems, the purpose of the present invention is to provide an unmanned ship path planning method, device, equipment and storage medium, based on the artificial potential field method, combined with the relative speed and regression search algorithm to achieve the unmanned ship's motion Static obstacle avoidance and global optimal path planning, and the introduction of improved gravitational potential field function and escape force to improve the unreachable target and local extremum problems of unmanned ships.

The technical solutions adopted by the present invention to solve its problems are:

In the first aspect, an embodiment of the present invention proposes a path planning method for an unmanned ship, including:

Obtain the information needed for unmanned ship path planning;

Establish a coordinate system covering the entire river surface, construct an improved gravitational potential field function, a traditional repulsive potential field function and a repulsive potential field function combined with relative speed, calculate the magnitude and direction of the resultant force, and obtain the global path;

Use regression search algorithm to obtain the global optimal path;

Determine whether the unmanned ship falls into a local extreme value, and construct an escape force to escape the local extreme value to achieve obstacle avoidance until the unmanned ship reaches the target point.

Further, obtaining the information required for unmanned vessel path planning includes: real-time acquisition of target point location information, river surface environment information, obstacle location information, and unmanned vessel path planning required for unmanned vessel path planning through side scan sonar and on-board equipment. Ship location information.

Further, the establishment of a coordinate system covering the entire river surface, the construction of an improved gravitational potential field function, a traditional repulsive potential field function, and a repulsive potential field function combined with relative speed, calculate the magnitude and direction of the resultant force, and obtain the global path. The gravitational field function of is as follows:

Among them, ζ is a positive parameter, q _goal = (x _goal , y _goal ) ^t is the position of the goal point, q = (x, y) ^t is the position of the unmanned ship, d(q, q _goal ) = ∥q _goal -q∥ Is the relative distance between the position of the unmanned ship and the target point, D is a positive parameter and D<d(q _obstacle ,q _goal ), F _att (q) is the attraction of the target to the unmanned ship,

Is the negative gradient of the attractive potential function, which converges to zero when the unmanned ship reaches the target.

Further, the establishment of a coordinate system covering the entire river surface, the construction of an improved gravitational potential field function, a traditional repulsive potential field function, and a repulsive potential field function combined with relative speed, calculate the magnitude and direction of the resultant force, and obtain the global path. The repulsion field function of is as follows:

Wherein, η is a positive parameter, d ₀ is the distance to obstacles, d _i (q) for each of the obstacle to the nearest point of the robot;

The repulsion is the negative gradient of the potential field function of the repulsion, as follows:

among them,

And q _c = (x _cl ,y _c ) ^t is the closest point of the obstacle;

The repulsion field function combined with relative velocity is as follows:

Among them, n is the number of obstacles, and θ _i is the angle between the relative speed and the relative distance;

The corresponding repulsion determined by the relative velocity is:

Further, the establishment of a coordinate system covering the entire river surface, the construction of an improved gravitational potential field function, a traditional repulsive potential field function, and a repulsive potential field function combined with relative speed, calculate the magnitude and direction of the resultant force, and obtain the global path. The gravitational field function and the repulsive field function are superimposed to obtain the resultant potential field function as follows:

The resultant force is:

Further, the use of the regression search algorithm to obtain the global optimal path includes the following steps:

S1. Calculate the artificial force F(q) in the current state;

S2. The unmanned ship moves forward in the direction indicated by the force F(q) in the artificial situation;

S3, the coordinates to save the current T _i;

S4. The continuous point T _i ∈{T ₁ , T ₂ , ···, T _n } is the planned path of the improved artificial potential field method;

S5. Repeat step S3 until reaching the target position;

S6, search T _i regression;

S7. Starting from the starting point T ₁ , connect with the next point T _j ,j∈{2,3,4,...n} to form a line L _1,j ;

S8. If L _1,j does not pass through any obstacles and B is greater than B ₀ , save L _1,j and j=j+1 until j=n+1, and return to step S7;

S9. Otherwise, save L _1,j-1 and skip to step S10;

S10. If T _j-1 is not the last point, use point T _j-1 as the new starting point and return to step S7;

S11. Otherwise, skip to step S12;

S12. Obtain the global optimal path;

S13. The unmanned ship moves along the global optimal path.

In the second aspect, an embodiment of the present invention also provides a path planning device for an unmanned ship, including:

Obtaining information module, used to obtain the information needed for unmanned ship path planning;

Construct a force field module, which is used to establish a coordinate system covering the entire river surface, construct an improved gravitational potential field function, a traditional repulsive potential field function and a repulsive potential field function combined with relative speed, calculate the magnitude and direction of the resultant force, and obtain the global path;

The path optimization module is used to obtain the global optimal path by using the regression search algorithm;

The local extreme value judgement module is used to judge whether the unmanned ship falls into the local extreme value, so as to construct the escape force to escape the local extreme value to realize obstacle avoidance, until the unmanned ship reaches the target point.

In the third aspect, an embodiment of the present invention also proposes a path planning device for an unmanned ship, including:

At least one processor; and,

A memory communicatively connected with the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the method according to the first aspect of the present invention.

In the fourth aspect, the embodiment of the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to make a computer execute the method described in the first aspect of the present invention. The method described.

One or more technical solutions provided in the embodiments of the present invention have at least the following beneficial effects: The path planning method, device, equipment, and storage medium of an unmanned ship provided by the present invention introduce a relative velocity artificial potential field method, which can be It avoids collisions with dynamic and static obstacles, and the present invention introduces a new gravitational function and adds escape force to help unmanned ships improve the problem of unreachable targets and local extremes and inability to move on the river surface. The invention also combines the regression search algorithm to plan the global optimal path, which greatly reduces the distance of the planned path from the position of the unmanned ship to the target position, and improves the task execution efficiency of the unmanned ship.

Description of the drawings

The present invention will be further explained below with reference to the drawings and examples.

Fig. 1 is a schematic flow chart of a path planning method for an unmanned ship in a first embodiment of the present invention;

Figure 2 is a diagram of the gravitational potential field model in the first embodiment of the present invention;

Figure 3 is a diagram of a repulsive force potential field model with relative velocity introduced in the first embodiment of the present invention;

Fig. 4 is a model diagram of a regression search algorithm in the first embodiment of the present invention;

Figure 5 is a flowchart of the regression search algorithm in the first embodiment of the present invention;

Figure 6 is a specific flow chart of the method for unmanned ship path planning in the first embodiment of the present invention;

Figure 7 is a schematic structural diagram of an unmanned ship path planning device in a second embodiment of the present invention;

Fig. 8 is a schematic structural diagram of a path planning device for an unmanned ship in a third embodiment of the present invention.

Detailed ways

In order to make the objectives, technical solutions, and advantages of the present invention clearer, the following further describes the present invention in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not used to limit the present invention.

It should be noted that if there is no conflict, the various features in the embodiments of the present invention can be combined with each other, and all fall within the protection scope of the present invention. In addition, although the functional modules are divided in the schematic diagram of the device, and the logical sequence is shown in the flowchart, in some cases, the module division in the device may be different from the module division in the device, or the sequence shown in the flowchart may be executed. Or the steps described.

The embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

As shown in Figure 1, the first embodiment of the present invention provides a path planning method for an unmanned ship, including but not limited to the following steps:

S100: Obtain information needed for unmanned ship path planning;

S200: Establish a coordinate system covering the entire river surface, construct an improved gravitational potential field function, a traditional repulsive potential field function, and a repulsive potential field function combined with relative speed, calculate the magnitude and direction of the resultant force, and obtain a global path;

S300: Use regression search algorithm to obtain the global optimal path;

S400: Determine whether the unmanned ship falls into a local extreme value, and construct an escape force to escape the local extreme value to achieve obstacle avoidance until the unmanned ship reaches the target point.

Preferably, in step S100, side scan sonar and shipboard equipment are used to separately collect target point location information, river surface environment information, obstacle location information, and unmanned ship location information required for the unmanned ship's obstacle avoidance path planning in real time;

In step S200, the force field consists of two parts, one part is the gravitational field U _att (q) generated by the target point on the unmanned ship, and the other part is the repulsion field U _rep (q) generated by the obstacle against the unmanned ship. The ship acts together in the resultant force field produced by the combined action of the gravitational field and the repulsion field. Among them, the traditional gravitational field function is as follows:

Among them, ζ is a positive parameter, q _goal = (x _goal , y _goal ) ^t is the position of the goal point, q = (x, y) ^t is the position of the unmanned ship, d(q, q _goal ) = ∥q _goal -q∥ It is the relative distance between the position of the unmanned ship and the position of the target point.

The gravity function is as follows:

among them

Is the negative gradient of the gravitational potential field function. When the unmanned ship reaches the target, it converges to zero.

The traditional repulsion field function is as follows:

Repulsion is used to keep unmanned ships away from obstacles. However, when the unmanned ship is far away from obstacles, it cannot affect the movement of the unmanned ship, and the movement of the unmanned ship must not be affected. Where U _rep,i (q) is the repulsive force field of each obstacle, η is a positive parameter, d ₀ is the influence distance of the obstacle, and d _i (q) is the distance between the unmanned ship in each obstacle and the closest point. distance. Repulsion is the negative gradient of the potential field function of repulsion, as follows:

among them,

And q _c = (x _cl , y _c ) ^t is the closest point of the obstacle.

As shown in Figure 2, the present invention improves the gravitational potential field function, and the improved gravitational field function is:

Among them, ζ is a positive parameter, q _goal = (x _goal , y _goal ) ^t is the position of the goal point, q = (x, y) ^t is the position of the unmanned ship, d(q, q _goal ) = ∥q _goal -q∥ Is the relative distance between the position of the unmanned ship and the target point, and D is a positive parameter. To choose a suitable D, the following conditions must be met: D<d(q _obstacle ,q _goal ). Therefore, gravity is:

The main advantages of this feature are briefly described as follows:

If the unmanned ship reaches the goal, then d(q,q _goal )=0, so:

U _att (q)=0

If the unmanned ship is far away from the target

then:

Where the unmanned ship is far from the target point, the new attraction is stronger than the traditional attraction. When it is closer to the target point, the new attraction is stronger than the traditional attraction, which reduces the influence of obstacles near the target point and solves the problem of unreachable targets on the artificial potential field.

As shown in Figure 3, the relative velocity is introduced, and the repulsive force function determined by the relative velocity is added. The repulsive force potential function determined by the relative velocity is as follows:

Among them, n is the number of obstacles, and θ _i is the angle between the relative speed and the relative distance. If counterclockwise rotation is defined as a positive direction and clockwise is negative, then _{the range of θ i} is (-π, π), when θ _i belongs to (-π/2, π/2), it indicates that the unmanned ship and Obstacles are approaching.

The corresponding repulsion determined by the relative velocity is:

Superimpose the gravitational potential field function and the repulsive potential field function to obtain the resultant potential field function:

Therefore, the resultant force is:

The above method realizes the function that the artificial potential field method can avoid dynamic obstacles.

In step S300, an improved APF-based regression search algorithm is used, and the optimized path is calculated by connecting the consecutive points generated by the APF. Based on the regression search method, first, the initial point T ₁ between the starting points and the next point T _{2 are} connected as a straight line L _{1, 2} . Then it is judged whether L _{1, 2} passes through any obstacles, and _{whether the shortest distance B between L 1, 2} and the obstacles is greater than B ₀ . B unmanned boat to the shortest distance to the obstacle, and B ₀ is the safety distance, i.e. the scope of the obstacle, insofar as unmanned boat to the shortest distance to the obstacle is not of B ₀ ₀ B is greater than B , The unmanned ship is not affected by obstacles. As shown in Figure 4, if L _{1, 2} does not cross any obstacles and B is greater than B ₀ , _{reconnect T 1} and T ₃ to L ₁ , 3 and repeat the above steps. Until L _{1, i} , that is, T _i is the end point. Since T _i is not the last point, the next starting point is T _i and is similarly connected to the next point T _i+1 . The final best path is L _1,i and _Li,n .

As shown in Figure 5, using the regression search algorithm to obtain the global optimal path includes the following steps:

S1. Calculate the artificial force F(q) in the current state;

S3. Save the current coordinates to Ti;

S5. Repeat step S3 until reaching the target position;

S6, search T _i regression;

S9. Otherwise, save L _1,j-1 and skip to step S10;

S11. Otherwise, skip to step S12;

S12. Obtain the global optimal path;

S13. The unmanned ship moves along the global optimal path.

In step S400, it is judged whether the unmanned ship falls into a local extreme value, and the escape force is constructed to make it escape from the local extreme value to realize obstacle avoidance. The judgment condition of whether the unmanned ship falls into the local extreme value is as follows:

Where b and c are arbitrary constants. If the conditions are met, it can be determined that the unmanned ship is blocked at the local minimum position. Therefore, we activate the power to escape. If a local minimum is detected, the unmanned ship must reinitialize the potential field. In this step, an additional potential field is set in the area to keep the unmanned ship away from the local minimum. It is used to smoothly rotate the unmanned ship to reach the goal. The new repulsion is the sum of the classical repulsion and the proposed escape force equation:

The additional potential field is expressed as:

among them,

Is the component of escape force, α is the angle of rotation, which is randomly selected in [-π,0)∪(0,π],

Is a unit vector pointing from an obstacle to an unmanned ship

Is perpendicular to

The unit vector.

As shown in Fig. 6, in step S400, it is judged whether the unmanned ship falls into the local extreme value. If so, the escape force is constructed to escape the local extreme value, and step S100 is returned. If the unmanned ship does not fall into the local extreme value, it is judged Whether to reach the target point position, if yes, the path planning task ends; otherwise, continue to perform step S300.

In summary, compared with the prior art, the advantages of this dynamic global optimal path planning method for unmanned ships are:

1. The improved artificial potential field method adopted introduces the influence of the relative speed of moving objects on the basis of the traditional artificial potential field method based on the position field, and adds the repulsion function determined by the relative speed to realize the artificial potential field. Can avoid dynamic and static obstacles.

2. The improved artificial potential field method is adopted to reconstruct the gravitational function. The reconstructed optimized gravity function balances the changes of attractive force and repulsive force, and solves the problem of unreachable target.

3. The concept of escape force is introduced. When the algorithm judges that the unmanned ship falls into the local minimum, the escape force is activated to make the unmanned ship escape from the local minimum.

4. The improved algorithm combines the regression search algorithm on the basis of the improved artificial potential field method, so that the path obtained is the global optimal path.

In addition, as shown in FIG. 7, the second embodiment of the present invention provides a path planning device for an unmanned ship, including:

The obtaining information module 110 is used to obtain information required for the path planning of the unmanned ship;

Construct a force field module 120, which is used to establish a coordinate system covering the entire river surface, construct an improved gravitational potential field function, a traditional repulsive potential field function, and a repulsive potential field function combined with relative velocity, calculate the magnitude and direction of the resultant force, and obtain a global path ；

The path optimization module 130 is used to obtain the global optimal path by using a regression search algorithm;

The local extremum determining module 140 is used to determine whether the unmanned ship falls into a local extremum, so as to construct an escape force to escape the local extremum to achieve obstacle avoidance until the unmanned ship reaches the target point position.

The unmanned vessel path planning device in this embodiment is based on the same inventive concept as the unmanned vessel path planning method in the first embodiment. Therefore, the unmanned vessel path planning system in this embodiment has the same beneficial effects: The relative velocity artificial potential field method can avoid collisions between dynamic and static obstacles, and the present invention helps the unmanned ship to improve the unreachable target and the local extreme value on the river surface by introducing a new gravitational function and adding escape force. problem. The invention also combines the regression search algorithm to plan the global optimal path, which greatly reduces the distance of the planned path from the position of the unmanned ship to the target position, and improves the task execution efficiency of the unmanned ship.

As shown in FIG. 8, the third embodiment of the present invention also provides a path planning device for an unmanned ship, including:

At least one processor;

And a memory communicatively connected with the at least one processor;

Wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute any one of the instructions in the first embodiment. An unmanned ship path planning method.

As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions/modules corresponding to the virtual image control method in the embodiment of the present invention . The processor executes various functional applications and data processing of the stereo imaging processing device by running non-transitory software programs, instructions, and modules stored in the memory, that is, realizing the unmanned ship path planning method of any of the foregoing method embodiments.

The memory may include a storage program area and a storage data area, where the storage program area can store an operating system and an application program required by at least one function; the storage data area can store data created according to the use of the stereo imaging processing device, and the like. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the storage may optionally include storage remotely arranged with respect to the processor, and these remote storages may be connected to the stereoscopic projection device via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

The one or more modules are stored in the memory, and when executed by the one or more processors, the unmanned ship path planning method in any of the foregoing method embodiments, such as the method in the first embodiment, is executed Steps S100 to S400.

The fourth embodiment of the present invention also provides a computer-readable storage medium that stores computer-executable instructions that are executed by one or more control processors to enable the foregoing One or more processors execute an unmanned ship path planning method in the foregoing method embodiments, for example, the method steps S100 to S400 in the first embodiment.

The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

Through the description of the above implementation manners, those of ordinary skill in the art can clearly understand that each implementation manner can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. A person of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by instructing relevant hardware through a computer program. The program can be stored in a computer readable storage medium, and the program can be stored in a computer readable storage medium. When executed, it may include the procedures of the above-mentioned method embodiments. Wherein, the storage medium may be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.

The above is a detailed description of the preferred implementation of the present invention, but the present invention is not limited to the above-mentioned embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. Equivalent modifications or replacements are all included in the scope defined by the claims of this application.

Claims

A path planning method for an unmanned ship, which is characterized in that it includes:

Obtain the information needed for unmanned ship path planning;

Establish a coordinate system covering the entire river surface, construct an improved gravitational potential field function, a traditional repulsive potential field function and a repulsive potential field function combined with relative speed, calculate the magnitude and direction of the resultant force, and obtain the global path;

Use regression search algorithm to obtain the global optimal path;

Determine whether the unmanned ship falls into a local extreme value, and construct an escape force to escape the local extreme value to achieve obstacle avoidance until the unmanned ship reaches the target point.
The path planning method of an unmanned ship according to claim 1, wherein said obtaining the information required for the path planning of the unmanned ship comprises: real-time acquisition of the path of the unmanned ship through the side scan sonar and the shipboard equipment. The target point location information, river environment information, obstacle location information and unmanned ship location information required for planning.
The path planning method of an unmanned ship according to claim 1, characterized in that the establishment of a coordinate system covering the entire river surface, the construction of an improved gravitational potential field function, a traditional repulsion potential field function, and a repulsion combined with relative velocity Potential field function, calculate the magnitude and direction of the resultant force, and get the global path. Among them, the improved gravitational field function is as follows:

Among them, ζ is a positive parameter, q goal = (x goal , y goal ) t is the position of the goal point, q = (x, y) t is the position of the unmanned ship, d(q, q goal )=||q goal -q || is the relative distance between the position of the unmanned ship and the target point, D is a positive parameter and D<d(q obstacle ,q goal ), F att (q) is the attraction of the target to the unmanned ship,
Is the negative gradient of the attractive potential function, which converges to zero when the unmanned ship reaches the target.
The path planning method of an unmanned ship according to claim 1, characterized in that the establishment of a coordinate system covering the entire river surface, the construction of an improved gravitational potential field function, a traditional repulsion potential field function, and a repulsion combined with relative velocity Potential field function, calculate the magnitude and direction of the resultant force, and get the global path. The traditional repulsion field function is as follows:

Wherein, η is a positive parameter, d 0 is the distance to obstacles, d i (q) for each of the obstacle to the nearest point of the robot;

The repulsion is the negative gradient of the potential field function of the repulsion, as follows:

among them,
And q c = (x cl ,y c ) t is the closest point of the obstacle;

The function of the repulsion field combined with the relative velocity is as follows:

Among them, n is the number of obstacles, and θ i is the angle between the relative speed and the relative distance;

The corresponding repulsion determined by the relative velocity is:
The path planning method of an unmanned ship according to claim 1, characterized in that the establishment of a coordinate system covering the entire river surface, the construction of an improved gravitational potential field function, a traditional repulsion potential field function, and a repulsion combined with relative velocity Potential field function, calculate the magnitude and direction of the resultant force, and get the global path, where the gravitational field function and the repulsive force field function are superimposed to get the resultant potential field function as follows:

The resultant force is:
The path planning method for an unmanned ship according to claim 1, wherein said using a regression search algorithm to obtain a global optimal path comprises the following steps:

S1. Calculate the artificial force F(q) in the current state;

S2. The unmanned ship moves forward in the direction indicated by the force F(q) in the artificial situation;

S3, the coordinates to save the current T i;

S4. The continuous point T i ∈{T 1 , T 2 , ···, T n } is the artificial potential field plan path;

S5. Repeat step S3 until reaching the target position;

S6, search T i regression;

S7. Starting from the starting point T 1 , connect with the next point T j ,j∈{2,3,4,...n} to form a line L 1,j ;

S8. If L 1,j does not pass through any obstacles and B is greater than B 0 , save L 1,j and j=j+1 until j=n+1, and return to step S7;

S9. Otherwise, save L 1,j-1 and skip to step S10;

S10. If T j-1 is not the last point, use point T j-1 as the new starting point and return to step S7;

S11. Otherwise, skip to step S12;

S12. Obtain the global optimal path;

S13. The unmanned ship moves along the global optimal path.
The path planning method for an unmanned ship according to claim 1, wherein the judging whether the unmanned ship falls into a local extreme value is used to construct an escape force so that it can escape from the local extreme value to achieve obstacle avoidance, wherein no The conditions for judging whether the ship is trapped in a local extreme value are:

Where b and c are arbitrary constants.
A path planning device for an unmanned ship, which is characterized in that it comprises:

Obtaining information module, used to obtain the information needed for unmanned ship path planning;

Construct a force field module, which is used to establish a coordinate system covering the entire river surface, construct an improved gravitational potential field function, a traditional repulsive potential field function, and a repulsive potential field function combined with relative speed, calculate the magnitude and direction of the resultant force, and obtain the global path;

The path optimization module is used to obtain the global optimal path by using the regression search algorithm;

The local extreme value judgment module is used to judge whether the unmanned ship falls into a local extreme value, and to construct an escape force to escape the local extreme value to achieve obstacle avoidance until the unmanned ship reaches the target point.
An unmanned ship path planning device, which is characterized in that it includes:

At least one processor; and,

A memory communicatively connected with the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute any one of claims 1 to 6 Methods.
A computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to make a computer execute the method according to any one of claims 1 to 6 .