Swarm robot collaborative hunting method and system based on improved gene regulatory network

Abstract

The present invention discloses a swarm robot collaborative hunting method, system, device and storage medium based on an improved gene regulatory network, wherein the improved gene regulatory network includes an upper network and an improved lower network, and the method includes: when the swarm robot detects a target in an unknown environment, the current position of the target, the current positions of all obstacles around the target and the current position of the swarm robot are obtained; in the upper network, the desired position of the swarm robot is determined according to the current position of the target and the current positions of all obstacles; in the improved lower network, the current position and the desired position of the swarm robot are processed in combination with a sliding mode controller to obtain the next position of the swarm robot; according to the next position of the swarm robot, the swarm robot is controlled to hunt towards the target. The present invention can improve the stability, robustness and efficiency of the swarm robot in an unknown environment in which the swarm robot performs collaborative movement in a polymerized hunting form formed on the target.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a group robot collaborative hunting method, system, equipment and storage medium based on an improved gene regulatory network. Background Art

[0002] Swarm robots are a collaborative whole, inspired by self-organizing systems in nature, such as bacteria, insects, fish or bird flocks, which are emergent group behaviors based on simple local interaction rules. Swarm robots can coordinate and collaborate with each other to solve problems or perform tasks. They have a more robust, more fault-tolerant and more flexible system than a single robot, and can adapt to environmental changes by adjusting their own behavior.

[0003] As a control model that simulates biological systems, gene regulatory networks describe the interactions and effects of cells or genes between cells. They can achieve autonomous regulation and collaborative work of robot cluster behaviors by imitating gene regulation. At present, some scholars have proposed to apply gene regulatory networks to the scenario of group robots cooperating to capture targets. On the basis of using gene regulatory networks, how to improve the tracking performance of group robots to achieve better collaborative capture effects is a hot topic for these scholars. Summary of the invention

[0004] The present invention provides a group robot collaborative hunting method, system, device and storage medium based on an improved gene regulatory network to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.

[0005] In a first aspect, a group robot collaborative hunting method based on an improved gene regulatory network is provided, wherein the improved gene regulatory network includes an upper network and an improved lower network, and the method includes:

[0006] When the swarm robot detects a target in an unknown environment, the current position of the target, the current positions of all obstacles around the target and the current position of the swarm robot are obtained;

[0007] In the upper network, a desired position of the swarm robot is determined according to the current position of the target and the current positions of all obstacles;

[0008] In the improved lower network, the current position and the desired position of the swarm robot are processed in combination with a sliding mode controller to obtain the next position of the swarm robot;

[0009] According to the next position of the swarm robots, the swarm robots are controlled to move toward the target for capture.

[0010] Further, determining the expected position of the swarm robot according to the current position of the target and the current positions of all obstacles includes:

[0011] Generate a current morphological gradient space about the target according to the current position of the target and the current positions of all obstacles;

[0012] Generate a current capture area for the target according to the current morphological gradient space;

[0013] The maximum boundary line contained in the current capture area is evenly divided to obtain the desired position of the swarm robot.

[0014] Furthermore, the sliding mode controller is constructed in the following manner:

[0015] Construct a state space model of the robot taking into account unknown external disturbances;

[0016] Considering the tracking deviation of the robot, a sliding mode function is constructed;

[0017] In combination with the state space model, the first-order derivative of the sliding mode function is performed to obtain a derivative function;

[0018] The derivative functions are combined with power exponential reaching laws to construct the sliding mode controller and determine its final output expression.

[0019] Furthermore, the step of combining the derivative functions with the power exponential reaching law to construct the sliding mode controller and determine its final output expression includes:

[0020] The derivative functions are combined with power exponential reaching laws to construct the sliding mode controller and determine its initial output expression;

[0021] Replacing the external interference contained in the initial output expression with the parameter to be solved to obtain a first output expression;

[0022] Determine an updated first derivative function by combining the first output expression and the derivative function;

[0023] According to the constraint condition of the Lyapunov function, in combination with the sliding mode function, the first derivative function and a given interference range, the value of the parameter to be solved is determined;

[0024] Substitute the value of the parameter to be solved into the first output expression to obtain the final output expression.

[0025] Further, the determining the value of the parameter to be solved according to the constraint condition of the Lyapunov function, in combination with the sliding mode function, the first derivative function and a given interference range includes:

[0026] The constraint condition of the Lyapunov function is that the product of the value of the sliding mode function and the value of the first derivative function is less than zero, and the interference range contains a minimum interference value and a maximum interference value;

[0027] When the value of the sliding mode function is greater than zero, determining the value of the parameter to be solved to be the minimum interference value so that the value of the first derivative function is less than zero;

[0028] When the value of the sliding mode function is less than zero, the value of the parameter to be solved is determined to be the maximum interference value, so that the value of the first derivative function is greater than zero.

[0029] Furthermore, the combined sliding mode controller processes the current position and the expected position of the swarm robot to obtain the next position of the swarm robot, including:

[0030] For any robot in the swarm of robots, determining a current tracking error of the robot according to a current position and a desired position of the robot;

[0031] Inputting the current tracking error of the robot into the sliding mode controller to obtain the current displacement of the robot;

[0032] According to the relationship between the current displacement of the robot and the given safety distance, combined with the current position of the robot, the next position of the robot is determined.

[0033] Further, the determining the next position of the robot according to the relationship between the current displacement of the robot and the given safety distance in combination with the current position of the robot comprises:

[0034] When the current displacement of the robot does not exceed the safety distance, the current position of the robot and the current displacement are added to obtain the next position of the robot;

[0035] When the current displacement of the robot exceeds the safety distance, the current position of the robot is used as the next position of the robot.

[0036] In a second aspect, a group robot collaborative hunting system based on an improved gene regulatory network is provided, wherein the improved gene regulatory network includes an upper network and an improved lower network, and the system includes:

[0037] The first module is used for obtaining the current position of the target, the current positions of all obstacles around the target and the current position of the group robot when the group robot detects the target in an unknown environment;

[0038] A second module is used to determine the desired position of the swarm robot in the upper network according to the current position of the target and the current positions of all obstacles;

[0039] A third module is used to process the current position and the expected position of the swarm robot in the improved lower layer network in combination with a sliding mode controller to obtain a next position of the swarm robot;

[0040] The fourth module is used to control the swarm robots to move toward the target for capture according to the next position of the swarm robots.

[0041] In a third aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the swarm robot collaborative hunting method based on an improved gene regulatory network as described in the first aspect.

[0042] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for collaborative hunting by swarm robots based on an improved gene regulatory network as described in the first aspect is implemented.

[0043] The present invention has at least the following beneficial effects: by introducing a sliding mode controller designed based on a power exponential convergence law into a lower network contained in an original gene regulatory network, the stability, robustness and efficiency of a group of robots performing coordinated motion in an aggregated capture form in an unknown environment can be improved while retaining the collision and obstacle avoidance advantages embodied by an upper network contained in the original gene regulatory network, thereby achieving the tracking performance of the group of robots on a target; and further considering external interferences such as physical constraints and model uncertainties in the sliding mode controller can improve the feasibility of the improved gene regulatory network in practical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation to the technical solution of the present invention.

[0045] Figure 1 It is a flow chart of a group robot collaborative hunting method based on an improved gene regulatory network in an embodiment of the present invention;

[0046] Figure 2is a schematic diagram of the morphological gradient space of the target in an embodiment of the present invention;

[0047] Figure 3 is a schematic diagram of a target capture area in an embodiment of the present invention;

[0048] Figure 4 is a schematic diagram of the motion control effect of the first robot in the prior art;

[0049] Figure 5 is a schematic diagram of the motion control effect of the first robot in an embodiment of the present invention;

[0050] Figure 6 Schematic diagram of the composition of a group robot collaborative hunting system based on an improved gene regulatory network in an embodiment of the present invention;

[0051] Figure 7 It is a schematic diagram of the hardware structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0053] It should be noted that, although the functional modules are divided in the system schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order from the module division in the system or the order in the flow chart. The terms "first", "second", "third", "fourth", etc. in the specification of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, such as processes, methods, systems, products or devices that include a series of steps or units, which are not necessarily limited to those steps or units clearly listed, but may include other steps or units inherent to these processes, methods, products or devices that are not clearly listed.

[0054] First, some of the terms involved in the present invention are explained as follows:

[0055] Gene Regulatory Network (GRN) refers to the network formed by the interaction between genes in a cell or a genome, specifically the interaction between genes caused by gene regulation. Gene regulatory network is the mechanism for controlling gene expression in organisms. The main processes of gene expression are transcription and translation. Common gene regulatory networks can be constructed based on Boolean networks, linear models, Markov models, Bayesian network models, etc.

[0056] Sliding mode control is often used in the field of robot trajectory tracking control. Its implementation principle is to design the sliding surface of the system. Under the action of the controller, the state of the system converges from outside the sliding surface to the sliding surface and gradually reaches the origin of the system.

[0057] Please refer to Figure 1 , Figure 1 1 is a flow chart of a group robot collaborative hunting method based on an improved gene regulatory network provided by an embodiment of the present invention. The improved gene regulatory network specifically includes an upper network and an improved lower network. The method includes the following steps:

[0058] Step S110: When the swarm robot detects a target in an unknown environment, the current position of the target, the current positions of all obstacles around the target, and the current position of the swarm robot are obtained;

[0059] Step S120: in the upper network, determining the desired position of the swarm robot according to the current position of the target and the current positions of all obstacles;

[0060] Step S130: In the improved lower layer network, the current position and the expected position of the swarm robot are processed in combination with a sliding mode controller to obtain a next position of the swarm robot;

[0061] Step S140: According to the next position of the swarm robots, control the swarm robots to move toward the target to perform capture.

[0062] In some embodiments of the present invention, the swarm robot mentioned in the above step S110 may be but is not limited to being composed of a plurality of quad-rotor drones of the same type, or a plurality of wheeled mobile robots of the same type driven by two wheels with differential speeds.

[0063] In some embodiments of the present invention, the implementation method of the above-mentioned step S110 is: control the swarm robots to perform autonomous detection in the unknown environment until any one of the swarm robots detects the target first, and define the robot that first detects the target as the reference robot; utilize the distance sensing device carried by the reference robot itself to obtain a first relative position relationship between the reference robot and the target and a second relative position relationship between the reference robot and each obstacle around the target within an allowable detection range defined by the distance sensing device; utilize the positioning device carried by each robot in the swarm robots to obtain the current position of each robot in the swarm robots; determine the current position of the target by combining the current position of the reference robot and the first relative position relationship between the reference robot and the target; determine the current position of each obstacle around the target by combining the current position of the reference robot and the second relative position relationship between the reference robot and each obstacle around the target.

[0064] In some embodiments of the present invention, the implementation process of step S120 includes but is not limited to the following:

[0065] Step S121: Based on the current positions of all obstacles and the current position of the target, determine the current morphological gradient space of the target. The mathematical expression used in this implementation process is as follows:

[0066]

[0067]

[0068]

[0069]

[0070]

[0071]

[0072] In the formula, p j a component of the protein concentration generated for the target or one of the obstacles, is the Laplace operator, defined as p j The second-order derivative of can be regarded as the diffusion process in the biological system, γ j is the current position of the target or one of the obstacles, N tis the total number of the target and all the obstacles, p is the comprehensive protein concentration generated by the target and all the obstacles, g1, g2 and g3 are all morphological gradient spaces, where g3 refers to the current morphological gradient space about the target, g3 is regulated by g1 and g2, g1 and g2 are both regulated by p, θ1, θ2, θ3 and k1 are all given regulatory parameters, x and z are reference parameters, mainly used to describe the expansion form of the sig function;

[0073] It should be noted that each position in the current morphological gradient space corresponds to a concentration value. For the target, the concentration value corresponding to its position is the highest (a positive value) and spreads evenly around, and the concentration value decreases until it reaches zero as the distance increases; for any obstacle among all the obstacles, the concentration value corresponding to its position is the lowest (a negative value) and spreads evenly around, and the concentration value increases until it reaches zero as the distance increases;

[0074] Step S122: Based on the current morphological gradient space, a current capture area of ​​the target is determined by mapping the three-dimensional space to a two-dimensional plane;

[0075] Exemplarily, assuming that there are only two obstacles around the target, the morphological gradient space about the target is generated based on the above mathematical expression, such as Figure 2 As shown, the morphological gradient space is then mapped to a two-dimensional plane, as Figure 3 As shown, the middle closed area on the two-dimensional plane is the capture area of ​​the target, corresponding to the area where the positive concentration value in the morphological gradient space is located, and the left and right closed areas on the two-dimensional plane are the influence areas of the two obstacles, corresponding to the areas where the two negative concentration values ​​in the morphological gradient space are located;

[0076] Step S123, processing the maximum boundary line contained in the current capture area according to the uniform division principle to obtain the desired position of the swarm robot;

[0077] That is to say, the group robot is composed of K robots, and K positions are evenly selected on the maximum boundary line, and the K positions are K expected positions corresponding to the K robots.

[0078] In some embodiments of the present invention, the construction process of the sliding mode controller mentioned in the above step S130 includes but is not limited to the following:

[0079] Step A1: Taking into account unknown external disturbances, which include physical constraints and model uncertainties, the state space model of the robot is defined as:

[0080]

[0081] Step A2: Taking into account the tracking deviation of the robot, the tracking deviation is the position tracking deviation, and the sliding mode function is defined as:

[0082]

[0083] e(t)=x d -x(t),

[0084] Step A3: taking a first-order derivative of the sliding mode function, and in the derivation process, substituting the mathematical expression of the state space model into the first-order derivative, so as to obtain the derivative function:

[0085]

[0086] Step A4: Define the power exponential reaching law as:

[0087]

[0088] Among them, x(t) is the current position of the robot, is the first-order derivative of x(t), is the second-order derivative of x(t), u(t) is the sliding mode control law, d(t) is the external disturbance, s(t) is the sliding mode function, is the derivative function, which can also be called the first-order derivative of s(t), e(t) is the position error function, is the first-order derivative of e(t), is the second-order derivative of e(t), c is the given control parameter that makes the sliding mode function s(t) satisfy the Hurwitz theorem, c>0, x d is the desired position of the robot, For x d The first derivative of For x d The second-order derivative of , f(x,t), b, ξ, α and k2 are all given control parameters, b>0, ξ>0, 0<α<1, k2>0, sgn refers to the sign function, t is time;

[0089] Step A5: Combining the power exponential reaching law and the derivative function, construct a sliding mode controller and determine its corresponding final output expression, and limit the input of the sliding mode controller to the tracking deviation of the robot and the output to the displacement of the robot.

[0090] More specifically, the implementation process of the above step A5 includes but is not limited to the following:

[0091] Step A5.1: Combining the power exponential reaching law and the derivative function, a sliding mode controller is constructed and its corresponding initial output expression is determined as:

[0092]

[0093] Step A5.2: Use the parameter d to be solved o The external disturbance d(t) contained in the initial output expression is replaced to obtain the first output expression:

[0094]

[0095] Step A5.3: Combine the derivative function and the first output expression to determine the updated first derivative function as follows:

[0096]

[0097] Step A5.4: Based on the constraint condition of the Lyapunov function (i.e., the Lyapunov function), according to the preset interference range, the first derivative function, and the sliding mode function, the parameter to be solved d is obtained. o The implementation process is divided into the following two cases:

[0098] The constraint condition of the Lyapunov function is set according to the result of its first-order derivative, which is determined as the value of the sliding mode function s(t) and the first derivative function The product of the values ​​of is less than zero, that is Thus, the stability of the Lyapunov function is ensured so that the system converges; and the interference range is determined as [d L ,d U ],d L is the minimum interference value, d U is the maximum interference value, d L and d U are all positive real numbers;

[0099] When the value of the sliding mode function s(t) is greater than zero, to ensure that the first derivative function The value of is less than zero, the minimum interference value d L As the parameter to be solved d o The value output of

[0100] When the value of the sliding mode function s(t) is less than zero, to ensure that the first derivative function The value of is greater than zero, the maximum interference value d U As the parameter to be solved d o The value output of

[0101] Step A5.5: Set the parameter to be solved d o The value of is substituted into the first output expression to obtain the final output expression.

[0102] In some embodiments of the present invention, taking any one robot in the swarm robot as an example, the implementation process of the above step S130 includes but is not limited to the following:

[0103] Step S131, based on the expected position and the current position of the robot, calculating the current tracking error of the robot by subtracting the two;

[0104] Step S132: using the sliding mode controller to process the current tracking error of the robot to obtain the current displacement of the robot;

[0105] Step S133: based on the relationship between the preset safety distance and the current displacement of the robot, and in combination with the current displacement of the robot, the next position of the robot is obtained. This implementation process is specifically divided into the following two cases:

[0106] The safety distance is mainly set to avoid collision between two robots in the group of robots due to excessive speed;

[0107] When the current displacement of the robot is less than or equal to the safety distance, the current displacement and the current position of the robot are added to obtain a next position of the robot;

[0108] When the current displacement of the robot is greater than the safety distance, the current position of the robot is directly output as the next position of the robot, that is, the robot does not move.

[0109] More specifically, when the swarm robots walk on the ground to capture the target, the desired position of the robots includes the desired position of the X-axis and the desired position of the Y-axis, the current position of the robots includes the current position of the X-axis and the current position of the Y-axis, and the current displacement of the robots output by the sliding mode controller includes the displacement of the X-axis and the displacement of the Y-axis;

[0110] When the X-axis displacement and the Y-axis displacement are both less than or equal to the safety distance, the current X-axis position is added to the X-axis displacement, and the current Y-axis position is added to the Y-axis displacement to obtain the next position of the robot;

[0111] When at least one of the X-axis displacement and the Y-axis displacement is greater than the safety distance, the current X-axis position and the current Y-axis position are formed into a next position of the robot.

[0112] More specifically, when the swarm robots fly in the air to capture the target, the desired positions of the robots include the desired X-axis position, the desired Y-axis position, and the desired Z-axis position, and the current positions of the robots include the current X-axis position, the current Y-axis position, and the current Z-axis position. At this time, the current displacement of the robots output by the sliding mode controller includes the X-axis displacement, the Y-axis displacement, and the Z-axis displacement;

[0113] When the X-axis displacement, the Y-axis displacement, and the Z-axis displacement are all less than or equal to the safety distance, the current X-axis position is added to the X-axis displacement, the current Y-axis position is added to the Y-axis displacement, and the current Z-axis position is added to the Z-axis displacement to obtain the next position of the robot;

[0114] When at least one of the X-axis displacement, the Y-axis displacement and the Z-axis displacement is greater than the safety distance, the current X-axis position, the current Y-axis position and the current Z-axis position form the next position of the robot.

[0115] In order to further demonstrate that the implementation effect of the above-mentioned technical scheme proposed in the present invention is better, the prior art applied to the collaborative capture task of swarm robots is introduced here for comparative explanation. The prior art is recorded in a public document named "A Hierarchical Gene Regulatory Network for Adaptive Multirobot Pattern Formation", which mainly proposes a hierarchical gene regulatory network for adaptive pattern generation, in which the upper network is used to generate a concentration field according to the object, and the lower network is used to execute robot motion control to collaboratively capture the target in a dynamic environment.

[0116] When setting an application scenario in which the same group of robots sets out from the same location in the same unknown environment to capture the same target, the group of robots is controlled by using the existing technology, and the group of robots is controlled by using the above technical solution proposed by the present invention. At this time, any one robot included in the group of robots (hereinafter described as the first robot) is taken as an example to observe the motion control effect of the first robot under different control modes. Figure 4 and Figure 5 shown.

[0117] Due to the algorithmic limitations of the hierarchical gene regulatory network (its lower layer network needs to introduce multiple motion strategies for operation), Figure 4 This reflects that the displacement of the first robot at each moment cannot exceed 0.2. However, due to the introduction of a sliding mode controller (which has the characteristic of fast response) in the lower network of the gene regulatory network, Figure 5 It reflects that the displacement of the first robot at some moments is greater than 0.2, which means that after applying the above technical solution proposed by the present invention, compared with the prior art, the first robot can reach the vicinity of the target at a faster speed to achieve better tracking and capturing effects.

[0118] In addition, Figure 4 and Figure 5 There is obvious chattering phenomenon in both, but after time 180 (that is, there are no obstacles that will affect the movement of the target and the first robot), Figure 4 The chattering phenomenon shown in the figure is irregular and is mainly the result of the interaction between the various motion strategies. Figure 5 The chattering phenomenon shown in FIG. 1 is obviously tending to be regular, which is mainly caused by the curve characteristics of the sgn function set in the sliding mode controller.

[0119] In an embodiment of the present invention, by introducing a sliding mode controller designed based on the power exponential convergence law into the lower network contained in the original gene regulatory network, the stability, robustness and efficiency of the swarm robots performing coordinated motion in an aggregated capture form in an unknown environment can be improved while retaining the collision and obstacle avoidance advantages embodied by the upper network contained in the original gene regulatory network, thereby achieving the tracking performance of the swarm robots on the target; and by further considering external interference such as physical constraints and model uncertainty in the sliding mode controller, the feasibility of the improved gene regulatory network in practical applications can be improved.

[0120] Please refer to Figure 6 , Figure 6 : is a schematic diagram of the composition of a group robot collaborative hunting system based on an improved gene regulatory network provided by an embodiment of the present invention, wherein the improved gene regulatory network specifically includes an upper network and an improved lower network, and the system includes:

[0121] The first module 210 is used to obtain the current position of the target, the current positions of all obstacles around the target, and the current position of the swarm robot when the swarm robot detects the target in an unknown environment;

[0122] A second module 220 is used to determine the desired position of the swarm robot in the upper network based on the current positions of all obstacles and the current position of the target;

[0123] A third module 230 is used to process the desired position and current position of the swarm robot in the improved lower layer network in combination with a sliding mode controller to obtain a next position of the swarm robot;

[0124] The fourth module 240 is used to control the swarm robots to move toward the target based on the next position of the swarm robots, so as to capture the target.

[0125] The contents of the above method embodiments are all applicable to the present system embodiments. The functions implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are the same as those of the above method embodiments, which will not be repeated here.

[0126] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, a group robot collaborative capture method based on an improved gene regulatory network in the above embodiment is implemented. Wherein, the computer-readable storage medium includes but is not limited to any type of disk (including floppy disk, hard disk, optical disk, CD-ROM, and magneto-optical disk), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic card or optical card. In other words, the storage device includes any medium that stores or transmits information in a readable form by a device (such as a computer, a mobile phone, etc.), which can be a read-only memory, a disk or an optical disk, etc.

[0127] also, Figure 7 3 is a schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention, wherein the computer device includes a processor 320, a memory 330, an input unit 340, a display unit 350 and other devices. Those skilled in the art can understand that Figure 7The device structure device shown does not constitute a limitation on all devices, and may include more or fewer components than shown, or combine certain components. The memory 330 can be used to store the computer program 310 and various functional modules, and the processor 320 runs the computer program 310 stored in the memory 330, thereby executing various functional applications and data processing of the device. The memory can be an internal memory or an external memory, or include an internal memory and an external memory. The internal memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, or a random access memory. The external memory may include a hard disk, a floppy disk, a U disk, a magnetic tape, etc. The memory 330 disclosed in the embodiment of the present invention includes but is not limited to the above-mentioned types of memory. The memory 330 disclosed in the embodiment of the present invention is only an example and not a limitation.

[0128] The input unit 340 is used to receive the input of the signal and the keyword input by the user. The input unit 340 may include a touch panel and other input devices. The touch panel can collect the user's touch operation on or near it (such as the user's operation on or near the touch panel using any suitable object or accessory such as a finger, a stylus, etc.), and drive the corresponding connection device according to a pre-set program; other input devices may include but are not limited to one or more of a physical keyboard, a function key (such as a playback control key, a switch key, etc.), a trackball, a mouse, a joystick, etc. The display unit 350 can be used to display the information input by the user or the information provided to the user and various menus of the terminal device. The display unit 350 can be in the form of a liquid crystal display, an organic light emitting diode, etc. The processor 320 is the control center of the terminal device, which uses various interfaces and lines to connect various parts of the entire device, and executes various functions and processes data by running or executing software programs and / or modules stored in the memory 330, and calling data stored in the memory 330.

[0129] As an embodiment, the computer device includes a processor 320, a memory 330 and a computer program 310, wherein the computer program 310 is stored in the memory 330 and is configured to be executed by the processor 320, and the computer program 310 is configured to execute a swarm robot collaborative hunting method based on an improved gene regulatory network in the above-mentioned embodiment.

[0130] Although the description of the present application has been quite detailed and specifically describes several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be regarded as providing a broad possible interpretation of these claims by reference to the attached claims, taking into account the prior art, so as to effectively cover the intended scope of the present application. In addition, the above description of the present application is based on the embodiments foreseeable by the inventor, and its purpose is to provide a useful description, and those non-substantial changes to the present application that have not yet been foreseen may still represent equivalent changes to the present application.

Claims

1. A group robot collaborative hunting method based on an improved gene regulatory network, characterized in that: The improved gene regulatory network includes an upper network and an improved lower network, and the method includes: When the swarm robot detects a target in an unknown environment, the current position of the target, the current positions of all obstacles around the target and the current position of the swarm robot are obtained; In the upper network, a desired position of the swarm robot is determined according to the current position of the target and the current positions of all obstacles; In the improved lower network, the current position and the desired position of the swarm robot are processed in combination with a sliding mode controller to obtain the next position of the swarm robot; According to the next position of the swarm robots, controlling the swarm robots to move toward the target to perform capture; The sliding mode controller is constructed in the following way: Construct a state space model of the robot taking into account unknown external disturbances; Considering the tracking deviation of the robot, a sliding mode function is constructed; In combination with the state space model, the first-order derivative of the sliding mode function is performed to obtain a derivative function; The derivative functions are combined with power exponential reaching laws to construct the sliding mode controller and determine its final output expression; The step of combining the derivative functions with the power exponential reaching law to construct the sliding mode controller and determine its final output expression includes: The derivative functions are combined with power exponential reaching laws to construct the sliding mode controller and determine its initial output expression; Replacing the external interference contained in the initial output expression with the parameter to be solved to obtain a first output expression; Determine an updated first derivative function by combining the first output expression and the derivative function; According to the constraint condition of the Lyapunov function, in combination with the sliding mode function, the first derivative function and a given interference range, the value of the parameter to be solved is determined; Substitute the value of the parameter to be solved into the first output expression to obtain the final output expression.

2. The method for collaborative hunting by swarm robots based on an improved gene regulatory network according to claim 1, characterized in that: Determining the desired position of the swarm robot according to the current position of the target and the current positions of all obstacles includes: Generate a current morphological gradient space about the target according to the current position of the target and the current positions of all obstacles; Generate a current capture area for the target according to the current morphological gradient space; The maximum boundary line contained in the current capture area is evenly divided to obtain the desired position of the swarm robot.

3. The method for collaborative hunting by swarm robots based on an improved gene regulatory network according to claim 1, characterized in that: The step of determining the value of the parameter to be solved according to the constraint condition of the Lyapunov function, in combination with the sliding mode function, the first derivative function and a given interference range includes: The constraint condition of the Lyapunov function is that the product of the value of the sliding mode function and the value of the first derivative function is less than zero, and the interference range contains a minimum interference value and a maximum interference value; When the value of the sliding mode function is greater than zero, determining the value of the parameter to be solved to be the minimum interference value so that the value of the first derivative function is less than zero; When the value of the sliding mode function is less than zero, the value of the parameter to be solved is determined to be the maximum interference value, so that the value of the first derivative function is greater than zero.

4. The method for collaborative hunting by swarm robots based on an improved gene regulatory network according to claim 1, characterized in that: The combining sliding mode controller processes the current position and the expected position of the swarm robot to obtain the next position of the swarm robot, including: For any robot in the swarm of robots, determining a current tracking error of the robot according to a current position and a desired position of the robot; Inputting the current tracking error of the robot into the sliding mode controller to obtain the current displacement of the robot; According to the relationship between the current displacement of the robot and the given safety distance, combined with the current position of the robot, the next position of the robot is determined.

5. The method for collaborative hunting by swarm robots based on an improved gene regulatory network according to claim 4, characterized in that: Determining the next position of the robot according to the relationship between the current displacement of the robot and the given safety distance in combination with the current position of the robot comprises: When the current displacement of the robot does not exceed the safety distance, the current position of the robot and the current displacement are added to obtain the next position of the robot; When the current displacement of the robot exceeds the safety distance, the current position of the robot is used as the next position of the robot.

6. A swarm robot collaborative hunting system based on an improved gene regulatory network, characterized in that: The improved gene regulatory network includes an upper network and an improved lower network, and the system includes: The first module is used for obtaining the current position of the target, the current positions of all obstacles around the target and the current position of the group robot when the group robot detects the target in an unknown environment; A second module is used to determine the desired position of the swarm robot in the upper network according to the current position of the target and the current positions of all obstacles; A third module is used to process the current position and the expected position of the swarm robot in the improved lower layer network in combination with a sliding mode controller to obtain a next position of the swarm robot; A fourth module is used to control the swarm robots to move toward the target to perform capture according to the next position of the swarm robots; The sliding mode controller is constructed in the following way: Construct a state space model of the robot taking into account unknown external disturbances; Considering the tracking deviation of the robot, a sliding mode function is constructed; In combination with the state space model, the first-order derivative of the sliding mode function is performed to obtain a derivative function; The derivative functions are combined with power exponential reaching laws to construct the sliding mode controller and determine its final output expression; The step of combining the derivative functions with the power exponential reaching law to construct the sliding mode controller and determine its final output expression includes: The derivative functions are combined with power exponential reaching laws to construct the sliding mode controller and determine its initial output expression; Replacing the external interference contained in the initial output expression with the parameter to be solved to obtain a first output expression; Determine an updated first derivative function by combining the first output expression and the derivative function; According to the constraint condition of the Lyapunov function, in combination with the sliding mode function, the first derivative function and a given interference range, the value of the parameter to be solved is determined; Substitute the value of the parameter to be solved into the first output expression to obtain the final output expression.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: The processor executes the computer program to implement the swarm robot collaborative hunting method based on the improved gene regulatory network as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the swarm robot collaborative hunting method based on an improved gene regulatory network as described in any one of claims 1 to 5 is implemented.

Images