Ocean unmanned cluster path planning method and system based on intuitionistic fuzzy decision

Abstract

The invention relates to the technical field of path planning, in particular to an ocean unmanned cluster path planning method and system based on an intuitive fuzzy decision, and the method comprises the steps: simulating a task region state of an ocean unmanned cluster in a task space; setting an intuitionistic fuzzy set; and planning the full-coverage path of the ocean unmanned cluster. According to the invention, based on the intuitionistic fuzzy decision, the ocean unmanned cluster can effectively deal with the error problem in the task execution process, so that the full-coverage path planning for the task space is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and particularly relates to a method and system for path planning of unmanned marine swarms based on intuitionistic fuzzy decision-making. Background Art

[0002] An unmanned swarm is an unmanned system that can automatically navigate in the ocean. It can carry various functional modules according to mission requirements and autonomously complete a series of tasks. The unmanned swarm is one of the hotspots in the current research of marine vehicles. The unmanned swarm has the advantages of stronger environmental adaptability, fault tolerance, and robustness, and is widely used in water quality detection, surveying and mapping, and marine scientific research.

[0003] Full-coverage path planning search is one of the main directions of the application of unmanned swarms. In order to achieve a dead-angle-free search in the target area, it is necessary to design the path of each individual in the unmanned swarm through a full-coverage path planning algorithm. The increase in the number of unmanned swarms increases the complexity of the full-coverage path planning algorithm. In a complex environment, traditional path planning algorithms may fail because traditional algorithms have poor adaptability to complex environments, are difficult to handle irregular areas, and the positions, speeds, and behaviors of unmanned swarms are uncertain. Intuitionistic fuzzy decision-making quantifies uncertainty through membership (degree of trust) and non-membership (degree of distrust), making the decision more robust.

[0004] Intuitionistic fuzzy decision-making is widely used in problems involving inaccurate, uncertain, and fuzzy decision-making information. Unmanned swarms often face information inaccuracy caused by information transmission errors during the task execution process. Applying the intuitionistic fuzzy decision-making algorithm can effectively cope with the information inaccuracy of unmanned swarms caused by errors, and then achieve full-coverage path planning for unmanned swarms.

[0005] Therefore, it is necessary to provide a method and system for path planning of unmanned marine swarms based on intuitionistic fuzzy decision-making to solve the above problems. Summary of the Invention

[0006] The purpose of the present invention is to propose a full-coverage path planning algorithm for unmanned marine swarms based on intuitionistic fuzzy decision-making due to the deficiencies of the full-coverage path planning method for unmanned swarms. This method is based on intuitionistic fuzzy decision-making, enabling unmanned swarms to effectively cope with error problems during task execution and then achieve full-coverage path planning for the target area to solve existing problems.

[0007] A method for path planning of unmanned marine swarms based on intuitionistic fuzzy decision-making of the present invention adopts the following technical solutions, including: Based on the known task space, and using a grid model to simulate the task area state of the unmanned swarm in the task space; Obtain the position and traveling direction of the unmanned cluster in the mission space; set an intuitionistic fuzzy set according to the relative distance between two individuals in the unmanned cluster and the traveling direction of the unmanned cluster, where the intuitionistic fuzzy set includes: the collision cost and energy loss cost of the unmanned cluster; Design an intuitionistic fuzzy decision-based full-coverage path algorithm for the marine unmanned cluster based on the intuitionistic fuzzy set. In the mission space, plan the full-coverage path of the unmanned cluster according to the intuitionistic fuzzy decision-based full-coverage path algorithm for the unmanned cluster. Among them, in the path planning, when the unmanned cluster encounters an obstacle, determine the collision cost through the relative distance between two individuals in the unmanned cluster. When there is no collision risk, do not consider the energy loss cost and directly go straight around the obstacle for avoidance.

[0008] Preferably, the state of the mission area in the mission space includes: the state of the unplanned mission area, the state of the planned mission area in the mission space, and the state of the obstacle area in the mission space.

[0009] Preferably, the expression of the grid model is:

[0010] In the formula, represents the state of the mission area of the unmanned cluster in the mission space; 0 represents the state of the unplanned mission area in the mission space, 1 represents the state of the planned mission area in the mission space, and 5 represents the state of the obstacle area in the mission space.

[0011] Preferably, the unmanned cluster stores the planned mission area in real time during the traveling process in the mission space. When the unmanned cluster travels to a certain position and all three directions of forward, left turn, and right turn have been searched or it is impossible to move forward due to the existence of an obstacle, then search for the nearest unplanned mission area in the stored mission area and go there for planning.

[0012] Preferably, when encountering an obstacle during the process of going to the unplanned mission area, use the A* algorithm for obstacle avoidance.

[0013] Preferably, set the collision cost of the unmanned cluster according to the relative distance between two individuals in the unmanned cluster.

[0014] Preferably, set the energy loss cost of the unmanned cluster according to the traveling direction of the unmanned cluster.

[0015] Preferably, set the energy loss cost when the traveling direction of the unmanned cluster is a right turn to be greater than the energy loss cost when the traveling direction of the unmanned cluster is a left turn.

[0016] An intuitionistic fuzzy decision-based path planning system for marine unmanned clusters, including: A task area status simulation module, configured to simulate the task area status of an unmanned cluster in the task space based on a known task space and using a grid model; An intuitionistic fuzzy set setting module, configured to obtain the position and traveling direction of the unmanned cluster in the task space; and set an intuitionistic fuzzy set according to the relative distance between two individuals in the unmanned cluster and the traveling direction of the unmanned cluster, where the intuitionistic fuzzy set includes: the collision cost and energy loss cost of the unmanned cluster; And a path planning module, configured to design an intuitionistic fuzzy decision-based full-coverage path algorithm for an ocean unmanned cluster based on the intuitionistic fuzzy set, and plan the full-coverage path of the unmanned cluster in the task space according to the intuitionistic fuzzy decision-based full-coverage path algorithm for the unmanned cluster. Wherein, in path planning, when the unmanned cluster encounters an obstacle, the collision cost is determined by the relative distance between two individuals in the unmanned cluster, and when there is no collision risk, the energy loss cost is not considered, and it directly goes straight around the obstacle for avoidance.

[0017] The beneficial effects of the present invention are: The present invention first adopts a grid model that simulates the task area status in the task space by the grid method to provide accurate environmental change data for the unmanned cluster; secondly, an intuitionistic fuzzy decision-based full-coverage path planning algorithm for the collaborative search of the unmanned cluster is constructed, and at the same time, a priority strategy is combined based on the intuitionistic fuzzy decision-based full-coverage path planning algorithm for the collaborative search of the unmanned cluster, so as to avoid the generation of more sub-spaces and reduce the generation of duplicate paths, and finally confirm the final path of the unmanned cluster through multiple iterations. Based on intuitionistic fuzzy decision, the present invention enables the unmanned cluster to effectively cope with the error problem in the process of executing tasks, and further realizes the full-coverage path planning for the task space. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0019] Figure 1 It is a flowchart of a path planning method for an ocean unmanned cluster based on intuitionistic fuzzy decision of the present invention; Figure 2 It is a detailed flowchart of a path planning method for an ocean unmanned cluster based on intuitionistic fuzzy decision of the present invention; Figure 3 It is a schematic diagram of the grid model of the task space in the embodiment of the present invention; Figure 4The result graph of the segmented sub-intervals generated without using the priority strategy in the embodiments of the present invention; Figure 5 The result graph of surrounding the obstacle in the embodiments of the present invention; Figure 6 The final simulation result graph of the full-coverage path planning for the unmanned cluster in the embodiments of the present invention. Specific implementation manners

[0020] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0021] An embodiment of a method and system for path planning of an unmanned marine cluster based on intuitionistic fuzzy decision-making of the present invention, as Figure 1 and 2 shown, includes: S1. Simulate the task area state of the unmanned cluster in the task space; Specifically, based on the known task space, use the grid model to simulate the task area state of the unmanned cluster in the task space.

[0022] Exemplarily, in a specific embodiment, the task area state in the task space includes: the task area state that has not been planned, the task area state that has been planned in the task space, and the obstacle area state in the task space.

[0023] Exemplarily, the expression of the grid model is:

[0024] In the formula, represents the task area state of the coordinate point in the task space, where i and j respectively represent the horizontal and vertical coordinates of this point; 0 represents the task area state that has not been planned in the task space, 1 represents the task area state that has been planned in the task space, and 5 represents the obstacle area state in the task space, that is, the area that must be avoided from collision when the unmanned cluster works. This value does not have practical significance and is only a search area for distinguishing three different area states. That is, the grid method in this embodiment effectively simulates the task area state of the task space and provides a basis for the subsequent path planning algorithm.

[0025] Among them, in a specific embodiment, the result of the grid model simulating the task area state of the unmanned cluster in the task space is as Figure 3 shown, Figure 3The white area is the working area that the unmanned cluster needs to cover, and the black area is the obstacle area. The grid method effectively simulates the state of the working space.

[0026] S2. Set the intuitionistic fuzzy set; Specifically, obtain the position and traveling direction of the unmanned cluster in the task space; set the intuitionistic fuzzy set according to the relative distance between two individuals in the unmanned cluster and the traveling direction of the unmanned cluster, where the intuitionistic fuzzy set includes: the collision cost and energy loss cost of the unmanned cluster.

[0027] Exemplarily, in a specific embodiment, the intuitionistic fuzzy set is usually represented by three functions: membership degree, non-membership degree, and hesitation degree, which are used to represent the decision maker's degree of support, opposition, and hesitation for the decision. Compared with fuzzy decision-making, the introduction of non-decision membership degree and hesitation degree gives the decision maker a higher degree of freedom in the decision-making process, without having to choose between two absolute attitudes of support and opposition. Atanassov generalized the fuzzy set theory and obtained the common definition of the intuitionistic fuzzy set as follows:

[0028] In the formula, is the membership degree of element x ; is the non-membership degree of element x , and x is given different meanings according to different models. In this embodiment, it represents the relative distance between two individuals in two unmanned clusters and the traveling direction of the unmanned cluster. X is the range to which x belongs, that is:

[0029] And it satisfies:

[0030] For any , then there is:

[0031] represents the hesitation degree of element X to ; when = 0, the intuitionistic fuzzy set degenerates into a fuzzy set; therefore, the fuzzy set is a special case of the intuitionistic fuzzy set.

[0032] Define an intuitionistic fuzzy number , that is, the degree of trust and distrust of the system for the relative distance and traveling direction between unmanned clusters, where:

[0033] Among them, The score of is:

[0034] If is a set of intuitionistic fuzzy numbers, the intuitionistic fuzzy weighted average operator can be calculated as:

[0035] In the formula, represents the weight vector occupied by this attribute.

[0036] That is, in the embodiment, the adopted intuitionistic fuzzy set includes the collision cost related to the distance and the energy loss cost related to the traveling direction. In the relative distance of the unmanned cluster, when the distance between two individuals (UUV, AUV or unmanned boat) in the unmanned cluster is greater than 10, it is considered that there is a very small probability of collision. When the distance between two individuals in the unmanned cluster is between 1 and 10, it is considered that there is a certain probability of collision between the two individuals in the unmanned cluster. When the distance between two individuals in the unmanned cluster is less than 1, it is considered that there is a high probability of collision between the two. During the traveling process of the unmanned cluster, going straight has a low energy loss, while turning left and right relatively have a higher energy loss. Specifically, the energy loss fuzzy set can be modified according to the component layout of the actual unmanned cluster. Here, the energy loss of turning right is set higher than that of turning left in order to avoid preferentially selecting turning left when the two have the same weighted average after calculation; that is, the direct fuzzy set is shown in Table 1.

[0037] Table 1

[0038] S3. Plan the full-coverage path of the unmanned cluster; Specifically, design an algorithm for the full-coverage path of the unmanned cluster based on intuitionistic fuzzy decision-making based on the intuitionistic fuzzy set. In the task space, plan the full-coverage path of the unmanned cluster according to the algorithm for the full-coverage path of the unmanned cluster based on intuitionistic fuzzy decision-making. Among them, in the path planning, when the unmanned cluster encounters an obstacle, determine the collision cost through the relative distance between two individuals in the unmanned cluster. When there is no collision risk, do not consider the energy loss cost and directly go straight around the obstacle for avoidance.

[0039] Exemplarily, in a specific embodiment, when there are no obstacles in the task area, the multi-unmanned-cluster full-coverage path planning algorithm based on intuitionistic fuzzy decision-making can plan the path of the unmanned cluster. When there are obstacles in the task space, relying only on the intuitionistic fuzzy decision-making algorithm based on the intuitionistic fuzzy set will generate more segmented sub-intervals. Here, the segmented sub-interval refers to multiple closed sub-intervals formed by the unmanned cluster path dividing the un-searched area, such as Figure 4As shown in the figure, since the straight movement of the unmanned cluster will generate two closed sub-regions ① and ②, whether searching region ① first or region ② first, it is necessary to travel through a searched region when moving to the next region after finishing the search of the current region. Therefore, on the basis of using intuitionistic fuzzy decision-making to plan the full-coverage path of the unmanned cluster, a priority strategy is introduced to avoid path duplication caused by moving from one sub-region to the next after searching a sub-region.

[0040] Exemplarily, in a specific embodiment, the priority strategy is as follows: when the unmanned cluster encounters an obstacle, the collision cost is calculated by the relative distance between two individuals in the unmanned cluster. When there is no collision risk, there is no need to consider energy consumption, and the obstacle is avoided directly by the method of going straight around the obstacle. The result is as Figure 5 shown.

[0041] It should be noted that although the priority strategy can reduce the number of divided sub-regions to a certain extent, in the process of planning the full-coverage path of the unmanned cluster, partitioning may still not be completely avoided. Therefore, in the embodiment, when the unmanned cluster travels to a certain position, the three directions of forward, left turn, and right turn have all been searched or cannot move forward due to the existence of obstacles, but there are still unsearched regions in the entire working area, and the unmanned cluster needs to go to the unsearched regions for search. In order to find the nearest unsearched region as soon as possible, a memory function is added to the algorithm, that is, the unmanned cluster stores the planned task regions in real time during the movement in the task space; during the task execution, when the unmanned cluster does not need to search in the three directions of forward, left turn, and right turn or cannot move forward due to the existence of obstacles for search, it will search the stored planned task regions, that is, search for the nearest unplanned task region in the stored task regions from the current position and go there for planning; if an obstacle is encountered during the process of going to the unsearched region, the A* algorithm is used for obstacle avoidance. The final simulation result of the full-coverage path planning of the unmanned cluster is as Figure 6 shown, and it can be Figure 6 analyzed that through this algorithm, four AUV individuals can achieve full-coverage path search in the planned region, and when there are multiple obstacles with irregular shapes in the planned region, the four AUV individuals can all achieve collision avoidance for the obstacles.

[0042] An unmanned marine cluster path planning system based on intuitionistic fuzzy decision-making, comprising: a task area state simulation module, an intuitionistic fuzzy set setting module, and a path planning module. The task area state simulation module is used to simulate the task area state of the unmanned cluster in the task space based on the known task space and using a grid model; the intuitionistic fuzzy set setting module is used to obtain the position and traveling direction of the unmanned cluster in the task space; according to the relative distance between two individuals in the unmanned cluster and the traveling direction of the unmanned cluster, an intuitionistic fuzzy set is set, wherein the intuitionistic fuzzy set includes: the collision cost and energy loss cost of the unmanned cluster; the path planning module is used to design an unmanned cluster full-coverage path algorithm based on intuitionistic fuzzy decision-making based on the intuitionistic fuzzy set, and in the task space, plan the unmanned cluster full-coverage path according to the unmanned cluster full-coverage path algorithm based on intuitionistic fuzzy decision-making. Among them, in path planning, when the unmanned cluster encounters an obstacle, the collision cost is determined by the relative distance between two individuals in the unmanned cluster. When there is no collision risk, the energy loss cost is not considered, and the obstacle is directly bypassed by going straight.

[0043] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A marine unmanned swarm path planning method based on intuitionistic fuzzy decision making, characterized in that: include: Based on the known mission space, the grid model is used to simulate the mission area status of the marine unmanned cluster in the mission space; Obtain the position and direction of the unmanned cluster in the mission space; According to the relative distance between two individuals in the unmanned cluster and the moving direction of the unmanned cluster, an intuitionistic fuzzy set is set, wherein the intuitionistic fuzzy set includes: the collision cost and energy loss cost of the unmanned cluster; Based on intuitionistic fuzzy sets, an unmanned marine swarm full coverage path algorithm based on intuitionistic fuzzy decision-making is designed. In the task space, the unmanned swarm full coverage path is planned according to the unmanned swarm full coverage path algorithm based on intuitionistic fuzzy decision-making. In the path planning, when the unmanned swarm encounters an obstacle, the collision cost is determined by the relative distance between the two individuals in the unmanned swarm. When there is no collision risk, the energy loss cost is not considered, and the unmanned swarm goes straight around the obstacle to avoid it.

2. According to claim 1, a method for marine unmanned cluster path planning based on intuitionistic fuzzy decision making is characterized in that: The task area status in the task space includes: the unplanned task area status, the planned task area status in the task space, and the obstacle area status in the task space.

3. The method for marine unmanned cluster path planning based on intuitionistic fuzzy decision-making according to claim 1 is characterized in that: The expression of the grid model is: In the formula, Indicates the task area status of the unmanned cluster in the task space; 0 indicates the unplanned task area status in the task space, 1 indicates the planned task area status in the task space, and 5 indicates the obstacle area status in the task space.

4. The method for marine unmanned cluster path planning based on intuitionistic fuzzy decision-making according to claim 1 is characterized in that: The unmanned swarm stores the planned mission areas in real time while moving in the mission space. When the unmanned swarm moves to a certain position and the three directions of forward, left turn and right turn have been searched or it cannot move forward due to obstacles, it searches for the unplanned mission area closest to the current position in the stored mission area and goes there for planning.

5. The method for marine unmanned cluster path planning based on intuitionistic fuzzy decision-making according to claim 4 is characterized in that: When encountering obstacles while heading to an unplanned mission area, the A* algorithm is used to avoid obstacles.

6. The method for marine unmanned cluster path planning based on intuitionistic fuzzy decision-making according to claim 1 is characterized in that: The collision cost of the unmanned swarm is set according to the relative distance between two individuals in the swarm.

7. The method for marine unmanned cluster path planning based on intuitionistic fuzzy decision-making according to claim 1 is characterized in that: The energy loss cost of the unmanned cluster is set according to the moving direction of the unmanned cluster.

8. The method for marine unmanned cluster path planning based on intuitionistic fuzzy decision-making according to claim 1 is characterized in that: The energy loss cost when the unmanned cluster's moving direction is set to turn right is greater than the energy loss cost when the unmanned cluster's moving direction is set to turn left.

9. A marine unmanned swarm path planning system based on intuitionistic fuzzy decision making, characterized in that: include: The task area state simulation module is used to simulate the task area state of the unmanned cluster in the task space based on the known task space and using the grid model; Intuitionistic fuzzy set setting module, used to obtain the position and direction of travel of the unmanned cluster in the task space; According to the relative distance between two individuals in the unmanned cluster and the moving direction of the unmanned cluster, an intuitionistic fuzzy set is set, wherein the intuitionistic fuzzy set includes: the collision cost and energy loss cost of the unmanned cluster; And a path planning module, which is used to design an unmanned marine cluster full coverage path algorithm based on intuitionistic fuzzy decision-making based on intuitionistic fuzzy sets. In the task space, the unmanned cluster full coverage path is planned according to the unmanned cluster full coverage path algorithm based on intuitionistic fuzzy decision-making. In the path planning, when the unmanned cluster encounters an obstacle, the collision cost is determined by the relative distance between two individuals in the unmanned cluster. When there is no collision risk, the energy loss cost is not considered, and the unmanned cluster directly goes straight around the obstacle to avoid it.

Images