A dual-environment area coverage method for swarm robots based on herd foraging behavior

Abstract

The present invention discloses a method for covering dual-environment areas of a group robot based on the foraging behavior of a herd of animals, including: establishing an area coverage scene, initializing algorithm parameters; initializing the recorded information of the area to be covered, updating the information of the area to be covered, and obtaining a set of candidate points; if the set of candidate points is not empty, calculating a reward function for each candidate point, selecting a target point with the maximum reward as the next target position and going to the target point judgment step, and if the set of candidate points is empty, going to the path generation step; generating a path to the nearest uncovered target point, selecting the next target point in the path as the next target position; judging whether the maximum running time has been reached or all target points have been covered, if so, the task is completed, otherwise going to the scanning environment step after reaching the next target position. The present invention can be applied to coverage tasks of both bounded and borderless environments at the same time, breaking through the limitation that the prior art is only applicable to a single environment.

Description

Technical Field

[0001] The present invention relates to the technical field of collaborative control among multi-agent clusters, and in particular to a dual-environment area coverage method of a swarm robot based on herd foraging behavior. Background Art

[0002] The coverage path planning problem studies how to generate a path that covers all target points in the area of ​​interest. It has huge application space in robot applications such as ground cleaning, lawn mowing, terrain measurement, and environmental monitoring, and has received widespread attention from researchers.

[0003] However, while most existing methods perform well in bounded environments, they fail to work in unbounded environments, such as search and rescue, criminal catching, strategic reconnaissance, and map building. For example, in search and rescue missions, the victim is trapped or hidden in mountains, deserts, or at sea, and the environment faced is unbounded. The robot needs to start from the last location where the victim was seen and cover as many target points as possible within a limited time while ensuring that no points are missed within the coverage area. Irregular obstacles in the environment and interference from other robots may greatly mislead the robot and cause missed areas, thus increasing the difficulty of completing the task.

[0004] In addition, in some application scenarios, the robot needs to handle both bounded and unbounded environments, i.e., dual environments. For example, when performing the task of catching criminals in the city, the robot starts to cover the unbounded environment from the location where the criminal was last found. Once it encounters a building, the robot will enter it to cover the bounded environment, and continue to cover the unbounded environment when leaving the building. The difference between the bounded and unbounded environment coverage tasks makes it a challenging problem to come up with an algorithm that can be applied to dual environments.

[0005] Therefore, there is an urgent need to invent a dual-environment area coverage method that breaks through the limitation that the existing technology is only applicable to a single environment and can be applied to both bounded environments and non-boundary environments. Summary of the invention

[0006] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0007] In view of the above existing problems, the present invention is proposed.

[0008] Therefore, the technical problem solved by the present invention is that the prior art is limited to being applicable to a single environment.

[0009] To solve the above technical problems, the present invention provides the following technical solutions: establish an area coverage scenario and initialize algorithm parameters; each robot initializes its recorded information on the area to be covered, updates the information on the area to be covered by scanning the environment and communicating with other robots, and obtains a set of candidate points based on the information on the area to be covered; if the set of candidate points is not empty, calculates a reward function for each candidate point, selects the target point with the maximum reward as the next target position and proceeds to the target point judgment step; if the set of candidate points is empty, proceeds to the path generation step; generates a path to the nearest uncovered target point based on a point-to-point planner, and selects the next target point in the path as the next target position; determines whether the maximum running time has been reached or all target points have been covered, and if so, the task is completed, otherwise proceeds to the environment scanning step after reaching the next target position.

[0010] As a preferred solution of the method for dual-environment area coverage of a group robot based on herd foraging behavior described in the present invention, the establishment of an area coverage scenario and initialization of algorithm parameters include: using a set of target points to represent the area to be covered, initializing the positions of n robots, initializing the neighborhood range μ, and the reward function parameters λ, ω p ,ω s ,ω b , maximum running time t max , each robot initializes the position of its virtual herd Φ.

[0011] As a preferred solution of the group robot dual-environment area coverage method based on the herd foraging behavior described in the present invention, wherein: each robot initializes its recorded information of the area to be covered, updates the information of the area to be covered by scanning the environment and communicating with other robots, and obtains a set of candidate points based on the information of the area to be covered, including: robot i (1≤i≤n) initializes its uncovered target point set to an empty set, initializes its covered target point set to in is the initial position of robot i, initializes the set of target points occupied by obstacles to an empty set, and initializes the current destination target point The initial position The robot i scans the environment and adds all newly discovered target points to its uncovered target point set, determines the target points occupied by obstacles according to the positions and trajectories of the obstacles, and updates the uncovered target point set, the covered target point set and the target point set occupied by obstacles by sharing information with other robots; the candidate point set includes two parts, one is the uncovered and unoccupied target points located in the neighborhood of the destination target point, and the other is the uncovered and unoccupied target points located between the destination target point and the position of the robot virtual herd.

[0012] As a preferred solution of the method for covering dual-environment areas by a swarm robot based on herd foraging behavior described in the present invention, wherein: if the candidate point set is not empty, then calculating a reward function for each candidate point, and selecting the target point with the maximum reward as the next target position includes: the robot for each of its candidate points o j Calculate the total reward function R(o j ), the total reward function consists of five parts: the herd attraction reward R based on the virtual herd h , dynamic predator avoidance reward R based on other robots dp , smoothness reward R s , boundary reward R b And the omission weight W, which is calculated as follows:

[0013]

[0014] Among them, ω p ,ω s ,ω b denote the weight factors associated with the impact of dynamic predator avoidance reward, smoothness reward, and boundary reward, respectively.

[0015] As a preferred solution of the method for covering dual-environment areas by a swarm robot based on the herd foraging behavior of the present invention, wherein: the herd attraction reward R h The expression is:

[0016]

[0017] Among them, H(o j ) is a candidate point o j The distance to the virtual herd Φ, and are the maximum and minimum distances from the candidate target point of robot i to Φ, respectively.

[0018] As a preferred solution of the dual-environment area coverage method of a swarm robot based on herd foraging behavior of the present invention, wherein: the dynamic predator avoidance reward R dp The expression is:

[0019]

[0020] in, is the kth dynamic predator of robot i (k∈{1,2,…,n}\i), is the candidate point o j To the kth dynamic predator The distance and They are the candidate target points of robot i and The maximum and minimum distances, It is used to control the influence of the kth dynamic predator, which is calculated as follows:

[0021]

[0022] Among them, κ is the slope, a is the The distance to the kth dynamic predator, b is the effective range.

[0023] As a preferred solution of the method for covering dual-environment areas by a swarm robot based on herd foraging behavior described in the present invention, the smoothness reward R s The expression is:

[0024]

[0025] in, is the target point covered by robot i before, and are the maximum and minimum angles of all candidate point trajectories.

[0026] As a preferred solution of the method for covering dual-environment areas by a swarm robot based on herd foraging behavior described in the present invention, the boundary reward R b The expression is:

[0027]

[0028] Among them, B(o j ) is a candidate point o j The number of uncovered and unoccupied target points in the neighborhood, and yes The maximum and minimum values ​​of the number of uncovered and unoccupied target points in the neighborhood of each candidate point.

[0029] As a preferred solution of the method for covering dual-environment areas by a swarm robot based on herd foraging behavior of the present invention, the expression of the omission weight W is:

[0030]

[0031] Among them, λ is a weight factor.

[0032] As a preferred solution of the method for covering dual-environment areas of a swarm robot based on the foraging behavior of a herd of animals described in the present invention, wherein: the step of judging whether the maximum running time has been reached or all target points have been covered, if so, the task is completed, otherwise, after reaching the next target position, the step of scanning the environment includes: when the previous time t exceeds the maximum running time t maxWhen the task is completed, the task ends; when covering a bounded environment, the task ends after covering all reachable target points; the robot i reaches its destination target point After that, update the uncovered target point set, the covered target point set, and the destination target point set. and the previous step target point and to the new Move, when When not in the robot's neighborhood, a point-to-point planner is used to generate a movement path.

[0033] The beneficial effects of the present invention are as follows: the present invention can be applied to coverage tasks in both bounded and unbounded environments, breaking through the limitation that the prior art is only applicable to a single environment. It can plan a coverage path without missing any target points, can adaptively cover any two-dimensional surface, and can cope with unexpected situations in the environment, such as static and dynamic obstacles that suddenly appear or disappear. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0035] Figure 1 A schematic diagram of the basic flow of a method for covering dual-environment areas by a swarm robot based on herd foraging behavior provided by one embodiment of the present invention;

[0036] Figure 2 A schematic diagram of a coverage path of a swarm robot in a bounded environment according to a swarm robot dual-environment area coverage method based on a herd foraging behavior provided by an embodiment of the present invention;

[0037] Figure 3 A schematic diagram of the coverage path of a swarm robot in a borderless environment according to a swarm robot dual-environment area coverage method based on herd foraging behavior provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0039] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0040] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0041] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0042] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0043] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0044] Example 1

[0045] Reference Figure 1 , which is an embodiment of the present invention, provides a method for covering dual-environment areas by a swarm robot based on herd foraging behavior, comprising:

[0046] S1: Establish an area coverage scenario and initialize algorithm parameters.

[0047] It should be noted that establishing an area coverage scenario and initializing algorithm parameters include: using a set of target points to represent the area to be covered, initializing the positions of n robots, initializing the neighborhood range μ, and the reward function parameters λ, ωp ,ω s ,ω b , maximum running time t max , each robot initializes the position of its virtual herd Φ.

[0048] S2: Each robot initializes its recorded information of the area to be covered.

[0049] It should be noted that the specific step is: robot i (1≤i≤n) initializes its uncovered target point set to an empty set and initializes its covered target point set to in is the initial position of robot i, initializes the set of target points occupied by obstacles to an empty set, and initializes the current destination target point The initial position

[0050] S3: Update the information of the area to be covered by scanning the environment and communicating with other robots.

[0051] It should be noted that this step is specifically as follows: robot i scans the environment and adds all newly discovered target points to its uncovered target point set, determines the target points occupied by obstacles based on the positions and trajectories of the obstacles, and updates the uncovered target point set, the covered target point set, and the target point set occupied by obstacles by sharing information with other robots. It should be noted that new target points occupied by obstacles will also be added to the uncovered target point set, because obstacles may leave these positions in the future.

[0052] S4: Obtain a set of candidate points based on the information of the area to be covered.

[0053] It should be noted that the specific step is: robot i will go to the destination point In order to calculate the next target point to be covered on the way, it is necessary to determine the candidate point set first. The candidate point set consists of two parts: one is the uncovered and unoccupied target point in the neighborhood of the destination target point, and the other is the uncovered and unoccupied target point between the destination target point and the position of the robot virtual herd.

[0054] S5: If the candidate point set is not empty, calculate the reward function for each candidate point, select the target point with the maximum reward as the next target position and go to step S7. If the candidate point set is empty, go to step S6.

[0055] It should be noted that this step is specifically as follows: the robot j Calculate the total reward function R(o j ), the total reward function consists of five parts: the herd attraction reward R based on the virtual herd h, dynamic predator avoidance reward R based on other robots dp , smoothness reward R s , boundary reward R b And the omission weight W, which is calculated as follows:

[0056]

[0057] Among them, ω p ,ω s ,ω b denote the weight factors associated with the impact of dynamic predator avoidance reward, smoothness reward, and boundary reward, respectively.

[0058] Among them, the herd attraction reward R h The expression is:

[0059]

[0060] Among them, H(o j ) is a candidate point o j The distance to the virtual herd Φ, and are the maximum and minimum distances from the candidate target point of robot i to Φ respectively. The present invention introduces the herd foraging behavior mechanism in nature into the coverage algorithm, regards the robot as a young animal, and its virtual herd is placed in the environment. Inspired by the herd foraging mechanism, the robot tends to choose the candidate target point closer to the virtual herd, thereby generating a coverage path from near to far. In a bounded environment, the virtual herd Φ is usually placed on the boundary closest to the robot's starting position, while in a boundless environment, it is usually placed at the robot's starting position. When the starting positions of multiple robots are close, the virtual herd Φ can also be placed at their center.

[0061] Dynamic predator avoidance reward R dp The expression is:

[0062]

[0063] in, is the kth dynamic predator of robot i (k∈{1,2,…,n}\i), is the candidate point o j To the kth dynamic predator The distance and They are the candidate target points of robot i and The maximum and minimum distances, It is used to control the influence of the kth dynamic predator, which is calculated as follows:

[0064]

[0065] Among them, κ is the slope, a is the The distance to the kth dynamic predator, b is the effective range, distance The closer, The larger the value, the greater the impact of the dynamic predator when the distance between the two is far. In the present invention, each robot regards other robots as dynamic predators, and based on the repulsive force between prey and dynamic predators, collisions between robots are avoided, thus realizing adaptive coverage task allocation for group robots.

[0066] Smoothness Reward R s The expression is:

[0067]

[0068] in, is the target point covered by robot i before, and are the maximum and minimum angles of all candidate point trajectories. The robot will get a greater reward when moving in a straight line, thus avoiding the energy and time loss caused by frequent turns.

[0069] Boundary Reward R b The expression is:

[0070]

[0071] Among them, B(o j ) is a candidate point o j The number of uncovered and unoccupied target points in the neighborhood, and yes The maximum and minimum number of uncovered and unoccupied target points in the neighborhood of each candidate point. Additional rewards are given to target points located at the boundary of the surface and the coverage area, so that the coverage trajectory is more regular and the number of missed points is reduced.

[0072] The expression of the omitted weight W is:

[0073]

[0074] Where λ is a weight factor. The candidate points in the neighborhood have a higher probability of being missed points. If o j is In the neighborhood of j )=1. Otherwise, W(o j )≥1, therefore, not The candidate target points in the neighborhood have a larger omission weight, and the closer they are to the virtual herd, the greater their omission weight.

[0075] S6: Generate a path to the nearest uncovered target point based on the point-to-point planner, and select the next target point in the path as the next target location.

[0076] It should be noted that the specific step is: The nearest uncovered and unoccupied target point is considered a temporary target point, and a point-to-point planner such as A* or Dijkstra is used to find a path to the temporary target point. The temporary target point may change due to obstacles and the movement of other robots, so the next target point in the path is taken as the next target position.

[0077] S7: Determine whether the maximum running time has been reached or all target points have been covered. If so, the task is completed. Otherwise, go to step S3 after reaching the next target position.

[0078] It should be noted that this step is specifically as follows: when the previous time t exceeds the maximum running time t max When , the task ends; when covering a bounded environment, the task ends after covering all reachable target points; robot i reaches its destination target point After that, update the uncovered target point set, the covered target point set, and the destination target point set. and the previous step target point and to the new Move, when When not in the robot's neighborhood, a point-to-point planner is used to generate a movement path.

[0079] The present invention can be applied to coverage tasks in both bounded and unbounded environments, breaking through the limitation of the prior art that it is only applicable to a single environment; the present invention can plan a coverage path without missing any target points; the present invention can adaptively cover any two-dimensional surface and can cope with unexpected situations in the environment, such as static and dynamic obstacles that suddenly appear or disappear.

[0080] Example 2

[0081] Reference Figures 2-3 This is another embodiment of the present invention. Different from the first embodiment, this embodiment provides a verification test of a dual-environment area coverage method of a group robot based on the foraging behavior of an animal group. In order to verify and illustrate the technical effect adopted in this method, this embodiment adopts a traditional technical solution and a comparative test with the method of the present invention, and compares the test results by means of scientific argumentation to verify the real effect of this method.

[0082] In order to more intuitively verify the performance of the present invention in the area coverage task, the performance of the present invention is verified in a bounded environment and a boundless environment respectively. Figure 2 and Figure 3 These are the coverage paths planned by the present invention for the swarm robot in a bounded environment with obstacles and in an unbounded environment, respectively.

[0083] The experimental results show that the present invention has the ability to complete coverage tasks in both bounded and unbounded environments, breaking through the limitation that the prior art can only be applied to a single environment. In addition, as an online coverage path generation method, it has the ability to generate a coverage path without missing points, which can meet the needs of various coverage task application scenarios.

[0084] It should be appreciated that embodiments of the present invention may be implemented or enforced by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The method may be implemented in a computer program using standard programming techniques - including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes the computer to operate in a specific and predefined manner - according to the methods and drawings described in the specific embodiments. Each program may be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system. However, if desired, the program may be implemented in an assembly or machine language. In any case, the language may be a compiled or interpreted language. In addition, the program may be run on a programmed ASIC for this purpose.

[0085] Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. The computer program includes a plurality of instructions that may be executed by one or more processors.

[0086] Further, the method can be implemented in any type of computing platform that is operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, etc. Aspects of the present invention can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, an optical read and / or write storage medium, a RAM, a ROM, etc., so that it can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the process described herein. In addition, the machine-readable code, or part thereof, can be transmitted via a wired or wireless network. When such media includes instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor, the invention described herein includes these and other different types of non-transitory computer-readable storage media. When programmed according to the methods and techniques described in the present invention, the present invention also includes the computer itself. The computer program can be applied to input data to perform the functions described herein, thereby converting the input data to generate output data stored in a non-volatile memory. The output information can also be applied to one or more output devices such as a display. In a preferred embodiment of the present invention, the converted data represents a physical and tangible object, including a specific visual depiction of the physical and tangible object produced on a display.

[0087] As used in this application, the terms "component", "module", "system", etc. are intended to refer to a computer-related entity, which can be hardware, firmware, a combination of hardware and software, software, or software in operation. For example, a component can be, but is not limited to: a process running on a processor, a processor, an object, an executable file, a thread in execution, a program, and / or a computer. As an example, an application running on a computing device and the computing device can both be components. One or more components can exist in a process and / or thread in execution, and a component can be located in a computer and / or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures thereon. These components can communicate in a local and / or remote process manner, such as according to a signal having one or more data packets (e.g., data from a component that interacts with another component in a local system, a distributed system, and / or interacts with other systems in a signal manner through a network such as the Internet).

[0088] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for covering dual-environment areas by a swarm robot based on herd foraging behavior, characterized in that: include: Establish regional coverage scenarios and initialize algorithm parameters; Each robot initializes its recorded information of the area to be covered, updates the information of the area to be covered by scanning the environment and communicating with other robots, and obtains a set of candidate points based on the information of the area to be covered; Robot i initializes its uncovered target point set to an empty set and initializes its covered target point set to in is the initial position of robot i, initializes the set of target points occupied by obstacles to an empty set, and initializes the current destination target point The initial position The robot i scans the environment and adds all newly discovered target points to its uncovered target point set, determines the target points occupied by obstacles according to the positions and trajectories of the obstacles, and updates the uncovered target point set, the covered target point set, and the target point set occupied by obstacles by sharing information with other robots; The candidate point set includes two parts: one is the uncovered and unoccupied target points located in the neighborhood of the destination target point, and the other is the uncovered and unoccupied target points located between the destination target point and the position of the robot virtual herd; If the candidate point set is not empty, a reward function is calculated for each candidate point, a target point with the maximum reward is selected as the next target position and the process proceeds to the target point judgment step; if the candidate point set is empty, the process proceeds to the path generation step; If the candidate point set is not empty, then a reward function is calculated for each candidate point, and the target point with the maximum reward is selected as the next target position, including: The robot calculates the value of each candidate point o j Calculate the total reward function R(o j ), the total reward function consists of five parts: the herd attraction reward R based on the virtual herd h , dynamic predator avoidance reward R based on other robots dp , smoothness reward R s , boundary reward R b And the omission weight W, which is calculated as follows: Among them, ω p ,ω s ,ω b denote the weight factors related to the impact of dynamic predator avoidance reward, smoothness reward and boundary reward, respectively. represents the dynamic predator represented by robot n; The expression of the missing weight W is: Among them, λ is a weight factor, is the maximum distance from the candidate target point of robot i to Φ, H(o j ) is a candidate point o j The distance to the virtual herd Φ; Generate a path to the nearest uncovered target point based on the point-to-point planner, and select the next target point in the path as the next target location; Determine whether the maximum running time has been reached or all target points have been covered. If so, the task is completed. Otherwise, go to the environment scanning step after reaching the next target position.

2. The method for covering dual-environment areas by a swarm robot based on herd foraging behavior as claimed in claim 1, characterized in that: The establishment of the area coverage scenario and initialization of the algorithm parameters include: using a set of target points to represent the area to be covered, initializing the positions of n robots, initializing the neighborhood range μ, and the reward function parameters λ, ω p ,ω s ,ω b , maximum running time t max , each robot initializes the position of its virtual herd Φ.

3. The method for covering dual-environment areas by a swarm robot based on herd foraging behavior as claimed in claim 1, characterized in that: The herd attraction reward R h The expression is: Among them, H(o j ) is a candidate point o j The distance to the virtual herd Φ, and are the maximum and minimum distances from the candidate target point of robot i to Φ, respectively.

4. The method for covering dual-environment areas by a swarm robot based on herd foraging behavior as claimed in claim 1, characterized in that: The dynamic predator avoidance reward R dp The expression is: in, is the kth dynamic predator of robot i (k∈{1,2,…,n}\i), is the candidate point o j To the kth dynamic predator The distance and They are the candidate target points of robot i and The maximum and minimum distances, It is used to control the influence of the kth dynamic predator, which is calculated as follows: Among them, κ is the slope, a is the The distance to the kth dynamic predator, b is the effective range.

5. The method for covering dual-environment areas by a swarm robot based on herd foraging behavior as claimed in claim 1, characterized in that: The smoothness reward R s The expression is: in, is the target point covered by robot i before, and are the maximum and minimum angles of all candidate point trajectories.

6. The method for covering dual-environment areas by a swarm robot based on herd foraging behavior as claimed in claim 1, characterized in that: The boundary reward R b The expression is: Among them, B(o j ) is a candidate point o j The number of uncovered and unoccupied target points in the neighborhood, and yes The maximum and minimum values ​​of the number of uncovered and unoccupied target points in the neighborhood of each candidate point.

7. The method for covering dual-environment areas by a swarm robot based on herd foraging behavior as claimed in claim 1, characterized in that: The step of determining whether the maximum running time has been reached or all target points have been covered, if so, the task is completed, otherwise, after reaching the next target position, the step of scanning the environment includes: When the previous time t exceeds the maximum running time t max When , the task ends; When covering a bounded environment, the task will also end after covering all reachable target points; The robot i reaches its destination point After that, update the uncovered target point set, the covered target point set, and the destination target point set. and the previous step target point and to the new Move, when When not in the robot's neighborhood, a point-to-point planner is used to generate a movement path.

Images