CN114326747A - Multi-target enclosure control method and device for group robots and computer equipment - Google Patents
Multi-target enclosure control method and device for group robots and computer equipment Download PDFInfo
- Publication number
- CN114326747A CN114326747A CN202210013119.7A CN202210013119A CN114326747A CN 114326747 A CN114326747 A CN 114326747A CN 202210013119 A CN202210013119 A CN 202210013119A CN 114326747 A CN114326747 A CN 114326747A
- Authority
- CN
- China
- Prior art keywords
- robot
- position information
- target
- robots
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 108090000623 proteins and genes Proteins 0.000 claims abstract description 58
- 238000005457 optimization Methods 0.000 claims abstract description 31
- 230000003044 adaptive effect Effects 0.000 claims abstract description 22
- 230000009471 action Effects 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 230000005684 electric field Effects 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 230000006870 function Effects 0.000 claims description 21
- 239000013598 vector Substances 0.000 claims description 20
- 230000033001 locomotion Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 12
- 230000004888 barrier function Effects 0.000 claims description 11
- 238000013459 approach Methods 0.000 claims description 6
- 230000001133 acceleration Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 5
- 102000004169 proteins and genes Human genes 0.000 description 16
- 239000002245 particle Substances 0.000 description 11
- 238000010586 diagram Methods 0.000 description 6
- 238000009792 diffusion process Methods 0.000 description 5
- 230000008447 perception Effects 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000001105 regulatory effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000012010 growth Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002195 synergetic effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 101100165993 Escherichia phage N15 gene 8 gene Proteins 0.000 description 1
- 101710160621 Fusion glycoprotein F0 Proteins 0.000 description 1
- 108700005075 Regulator Genes Proteins 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000010261 cell growth Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000003116 impacting effect Effects 0.000 description 1
- 230000003834 intracellular effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 230000007261 regionalization Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Feedback Control In General (AREA)
Abstract
The application relates to a multi-target enclosure control method and device for swarm robots and computer equipment. The method comprises the following steps: inputting position information, target position information and obstacle position information of the current robot, obstacle information sent by other robots in a sensing area and neighbor position information of the other robots into a pre-constructed adaptive cooperative gene regulation and control network, outputting an enclosure mode and action information of the current robot, and constructing an updating formula for optimizing individual positions and speeds in a population based on an artificial electric field algorithm; according to the updating formula, carrying out optimization calculation on the influence factors and the weights to obtain optimized influence factors and optimized weights; and inputting the optimized influence factors and the optimized weight into the self-adaptive cooperative gene regulation and control network so that the self-adaptive cooperative gene regulation and control network outputs maneuvering information for target capture of the group robots. By adopting the method, the group trapping efficiency can be improved.
Description
Technical Field
The application relates to the technical field of robot enclosure navigation, in particular to a swarm robot multi-target enclosure control method, a swarm robot multi-target enclosure control device and computer equipment.
Background
A multi-robot system (MRS), also known as a swarm robot, is composed of a large number of small, simple robots (with a definite language: any one has a certain autonomy, limited communication capabilities and computational resources). Therefore, it is necessary to systematize robots in MRS individually, and through close mutual cooperation and cooperation, advantages such as completion of complex tasks, spatial-temporal distribution work, functions, and perceptual distribution that a single robot does not have can be brought. Furthermore, due to the extremely attractive properties of a single robot, such as low cost, high adaptability and high reliability, MRS has been successfully applied in a wide range of fields, including marine exploration, medical services, search and rescue, positioning and navigation, etc. Meanwhile, with the rapid development of MRS theory and application, the cooperative capture of targets by using group robots is becoming a new research direction.
At present, target containment, especially for randomly moving targets, is a very challenging task. This not only requires close cooperation of robots in MRS to track closely targets, but also their perception and adaptation to the surrounding dynamic environment in real time. Therefore, how and better to create a complete and reliable enclosure around the target after it is detected becomes a key and difficult point of this task, which has led to increased attention in the research on cooperative control strategies for group agents. Currently, methods for forming a multi-robot shape structure and pattern can be broadly classified into five categories according to control methods: 1) a virtual structure method; 2) leader-follower method; 3) an artificial potential field method; 4) a behavior-based approach; 5) intelligent algorithm excited by natural life.
Despite the above considerable research on the methods of multi-robot shape construction and pattern formation, self-organizing MRS still has a number of unsolved problems: for example, a strict and complex global coordinate system is needed for acquiring environment information by relying on a large amount of communication between intelligent bodies and behavior control, the intelligent bodies are difficult to cooperate to consider surrounding intelligent bodies or obstacles in the environment, dynamic targets are easy to escape from an enclosure, and the like.
Disclosure of Invention
In view of the above, it is necessary to provide a multi-target enclosure control method, apparatus and computer device for swarm robots, aiming at the above technical problems.
A swarm robot multi-target enclosure control method comprises the following steps:
inputting position information, target position information and obstacle position information of the current robot, obstacle information sent by other robots in a sensing area and neighbor position information of the other robots into a pre-constructed adaptive cooperative gene regulation and control network, and outputting an enclosure capture mode and action information of the current robot; the trapping mode is obtained by weighting target position information, neighbor position information and obstacle position information through influence factors, and the action information is obtained by weighting each moving strategy through weights;
establishing an updating formula for optimizing the position and the speed of individuals in the population based on an artificial electric field algorithm;
according to the updating formula, carrying out optimization calculation on the influence factors and the weights to obtain optimized influence factors and optimized weights;
and inputting the optimization influence factors and the optimization weights into the self-adaptive cooperative gene regulation and control network so that the self-adaptive cooperative gene regulation and control network outputs maneuvering information for target capture of the group robots.
In one embodiment, the method further comprises the following steps: inputting the position information, the target position information, the obstacle position information of the current robot, the obstacle information sent by other robots in the sensing area and the neighbor position information of other robots into a pre-constructed adaptive cooperative gene regulation and control network, and outputting the trapping mode of the current robot as follows:
P＝ωtPt+ωnPn+ωoPo
wherein P represents a trapping mode, PtComponent of the hunting pattern, P, representing a determination of target position informationnRepresenting the component of the trapping pattern, P, determined by the neighbor location informationoAn entrapment mode component representing the determination of the obstacle position information; omegat、ωn and ωoAll represent influencing factors.
In one embodiment, the mobility policy includes: the robot approach or departure strategy comprises a robot approach or departure strategy, a robot low-density motion tendency strategy, a robot high-density motion tendency strategy and a robot reverse direction motion strategy; further comprising: inputting the position information, the target position information, the obstacle position information of the current robot, the obstacle information sent by other robots in the sensing area and the neighbor position information of other robots into a pre-constructed adaptive cooperative gene regulation and control network, and outputting the action information of the current robot as follows:
wherein ,SiIndicating the position vector of the ith robot, tiUnit vector, n, representing the proximity or distance of the robot to the target strategyiUnit vector representing low-density motion tendency strategy of robot, ciUnit vector, o, representing a high-density motion trend strategy for a robotiUnit vector, r, representing a strategy for counter-directional movement of the robot1-r4Both represent weights.
In one embodiment, the method further comprises the following steps: based on the artificial field algorithm, an updating formula for optimizing the position and the speed of the individual in the population is constructed as follows:
wherein ,
representing the velocity of robot i at time t +1,
representing the velocity of the robot i at time t,
represents the acceleration to which the ith robot is subjected;
indicating the position of robot i at time t +1,
indicating the position of robot i at time t.
In one embodiment, the method further comprises the following steps: dividing the enclosure area according to the perception radius of the robot to obtain a plurality of sub-areas, and setting a weight value for each sub-area;
assigning values to the robot, the barrier and the blank area in the surrounding area of the target of the surrounding area;
obtaining the enclosure capturing strength according to the weight of each subarea, the assignment of the robot, the barrier and the blank area;
determining the enclosure occupancy rate according to the angle of the robot for limiting the target;
and constructing an evaluation function for evaluating the surrounding capture effect of the group robots according to the surrounding capture strength and the surrounding capture occupancy rate.
In one embodiment, the method further comprises the following steps: and according to the weight of each subregion, the robot, the barrier and the blank region assignment, obtaining the enclosure capturing strength as follows:
wherein λ represents a weight for each sub-region, T represents a robot, an obstacle, and a blank region assignment,
representing the maximum value of the trapping intensity.
In one embodiment, the method further comprises the following steps: according to the angle of the robot for limiting the target, determining the enclosure capture occupancy as follows:
wherein ,θiRepresenting the angle at which the robot acts to limit the target.
In one embodiment, the merit function includes: a first merit function and a second merit function; further comprising: carrying out average weighting on the enclosure intensity and the enclosure occupancy within a preset time to obtain a first evaluation function;
and carrying out maximum value weighting on the enclosure intensity and the enclosure occupancy within preset time to obtain a second evaluation function.
A swarm robot multi-target enclosure control device, the device comprising:
the capture output module is used for inputting the position information, the target position information and the obstacle position information of the current robot, the obstacle information sent by other robots in the sensing area and the neighbor position information of other robots into a pre-constructed adaptive cooperative gene regulation and control network and outputting the capture mode and the action information of the current robot; the trapping mode is obtained by weighting target position information, neighbor position information and obstacle position information through influence factors, and the action information is obtained by weighting each moving strategy through weights;
the updating module is used for constructing an updating formula for optimizing the position and the speed of the individual in the population based on an artificial electric field algorithm;
the optimization module is used for carrying out optimization calculation on the influence factors and the weights according to the updating formula to obtain optimized influence factors and optimized weights;
and the optimization output module is used for inputting the optimization influence factors and the optimization weights into the self-adaptive cooperative gene regulation and control network so that the self-adaptive cooperative gene regulation and control network outputs maneuvering information for target enclosure of the group robots.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
inputting position information, target position information and obstacle position information of the current robot, obstacle information sent by other robots in a sensing area and neighbor position information of the other robots into a pre-constructed adaptive cooperative gene regulation and control network, and outputting an enclosure capture mode and action information of the current robot; the trapping mode is obtained by weighting target position information, neighbor position information and obstacle position information through influence factors, and the action information is obtained by weighting each moving strategy through weights;
establishing an updating formula for optimizing the position and the speed of individuals in the population based on an artificial electric field algorithm;
according to the updating formula, carrying out optimization calculation on the influence factors and the weights to obtain optimized influence factors and optimized weights;
and inputting the optimization influence factors and the optimization weights into the self-adaptive cooperative gene regulation and control network so that the self-adaptive cooperative gene regulation and control network outputs maneuvering information for target capture of the group robots.
On the basis of a self-adaptive cooperative gene regulation and control network, when a trapping mode is generated in Layer1 of a model, the multi-target trapping control method, the multi-target trapping control device and the computer equipment can fuse and consider various situation information of a target, a neighbor and an obstacle, and optimize the weight of the information of the target, the neighbor and the obstacle according to a task environment so as to generate a surrounding ring more efficiently and accurately. Secondly, in the Layer2 of the model, when the robot movement is guided, the weight relation of four concentration vectors is further measured, so that the robot can form an enclosure more quickly and firmly in an enclosure task.
Drawings
FIG. 1 is a schematic flow chart of a multi-target enclosure control method for group robots in one embodiment;
FIG. 2 is a schematic diagram of a framework for an adaptive cooperative gene regulation network in one embodiment;
FIG. 3 is a schematic structural diagram of the division of the trapping region in another embodiment;
FIG. 4 is a block diagram of a multi-target enclosure control device of the group robot in one embodiment;
FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, a swarm robot multi-target enclosure control method is provided, which includes the following steps:
and 102, inputting the position information, the target position information and the obstacle position information of the current robot, the obstacle information sent by other robots in the sensing area and the neighbor position information of other robots into a pre-constructed adaptive cooperative gene regulation and control network, and outputting the capture mode and the action information of the current robot.
The capture mode is obtained by weighting target position information, neighbor position information and obstacle position information through influence factors, and the action information is obtained by weighting each moving strategy through weights.
And 104, constructing an updating formula for optimizing the position and the speed of the individual in the population based on an artificial electric field algorithm.
And 106, performing optimization calculation on the influence factors and the weights according to the updating formula to obtain optimized influence factors and optimized weights.
And 108, inputting the optimization influence factors and the optimization weights into the adaptive cooperative gene regulation and control network so that the adaptive cooperative gene regulation and control network outputs maneuvering information for target capture of the group robots.
On the basis of a self-adaptive cooperative gene regulation and control network, when a trapping mode is generated in Layer1 of a model, the multi-target trapping control method for the group robots can fuse and consider various situation information of targets, neighbors and obstacles, and optimize the weight of the information of the targets, the neighbors and the obstacles according to a task environment so as to generate a surrounding ring more efficiently and accurately. Secondly, in the Layer2 of the model, when the robot movement is guided, the weight relation of four concentration vectors is further measured, so that the robot can form an enclosure more quickly and firmly in an enclosure task.
In one embodiment, the existing gene regulatory network is improved, and a gene regulatory network Co-GRN with a high synergistic mechanism is provided, and the model of the gene regulatory network is shown in FIG. 2. It contains a total of two key modules. The Layer1 can fuse multi-state potential information of a target, a neighbor and an obstacle, and collaboratively generate a capture mode; layer2 can direct the robot to act more efficiently, adapt to the patterns generated by Layer1 and complete the enclosure task. In the network, robot represents the robot, P represents the protein concentration, and gene represents the gene fragment. Each robot corresponds to a cell containing multiple proteins. This means that each cell has multiple gene segments to control its growth, and the external environment including targets, obstacles, neighbors can cause changes in intracellular protein concentration, ultimately controlling its growth and development. That is, each robot has many gene segments that regulate changes in its internal protein concentration, ultimately controlling the robot's pattern generation and movement.
Co-GRN is designed primarily based on the cell growth mechanism of the organism, which cells can communicate via the medium of protein concentration. Similarly, the robot can acquire information of the surrounding environment through diffusion and perception of protein concentration to guide the robot to move.
When a robot diffuses positional information through protein concentration, its positional protein GiTraditionally, exponential diffusion, but the additional diffusion source protein F addediIs non-exponential diffusion. Gi and FiAre defined as Eq. (1) and Eq. (2), respectively:
wherein ,PG and PFAre each protein Gi and FiConcentration of (a) (. sigma.)iIs the distance from the diffusion source. The concentration ratio of the two proteins is represented by k1 and k2And (6) determining. Alpha and z are both positive constants which determine the slope and variance of the sigmoid function, respectively. After fusion of the protein, the concentration spread changes almost linearly, see Eq (3):
in the proposed Co-GRN model, the swarm robots can acquire the relative position relation with the target, the neighbor and the barrier boundary through the position sensor within a certain communication range. For more efficient robot movement, more accurate containment patterns need to be generated. Thus, the designed Layer1 will fuse multi-state potential information of targets, neighbors, obstacles to generate trapping patterns.
As shown in fig. 2, the target triangle will diffuse the protein concentration information of its position into Layer 1. Obtaining target concentration information in the global environment through the following Eq. (4) and Eq. (5)
wherein ,PjDenotes the j (th)thConcentration information of individual targets, then P1 tIs the sum of the concentration information of all targets. P1 tWill activate the robots R respectivelyiGene1, Gene2, resulting in protein concentration values
And
and (4) changing. Followed by
And
in turn, Gene3 will be activated, resulting in a protein concentration value PtA change in (c). And P istThe trapping mode determined by the target concentration information is expressed by the following specific formula:
in fig. 2, a neighbor robot means a neighbor robot within a robot sensing range. These neighbors will also diffuse the protein concentration information of their location into Layer 1. The concentration information and P of all neighbors can be obtained through Eq. (9) and Eq. (10)1 n[18]：
wherein ,nnRepresenting the number of all neighbor robots within a robot's perception range. Similarly, after regulation and control of Gene4 and Gene5, a trapping pattern P determined by neighbor concentration information can be finally obtainedn. In different task scenarios, the parameter values in the equation need to be adjusted so as to keep a proper distance between the robot and the neighbor, and the specific formula is as follows:
in the present invention, a special robot is used to simulate an obstacle, and these robots are referred to as virtual robots. Thus, protein concentration information P of the disorder1 oAlso through the regulation of Gene4 and Gene5, and finally generating the information of the concentration of the obstacleThe specific formula of the determined trapping mode is as follows:
in order to control the robot more accurately and take the influence of a target, a neighbor and an obstacle on an enclosure mode into consideration in a fusion manner, a final enclosure mode P is transferred into Layer2 for mode construction after being regulated and controlled by Gene6, the position information, the target position information and the obstacle position information of the current robot, the obstacle information sent by other robots in a sensing area and the neighbor position information of other robots are input into a pre-constructed adaptive coordinated Gene regulation and control network, and the enclosure mode of the current robot is output as follows:
P＝ωtPt+ωnPn+ωoPo
wherein P represents a trapping mode, PtComponent of the hunting pattern, P, representing a determination of target position informationnRepresenting the component of the trapping pattern, P, determined by the neighbor location informationoAn entrapment mode component representing the determination of the obstacle position information; omegat、ωn and ωoAll represent influencing factors.
In the structure of Co-GRN, Layer1 is mainly responsible for the generation of an adaptive mode, and Layer2 accurately guides the movement of the robot according to the generation mode. In the network, the sum of the respective modes of a target, a neighbor and a barrier, namely a final capture mode P, is converted into the sum of concentration vectors through gene regulation, and the vectors guide a robot group to adapt to a generation mode more quickly and complete a capture task better.
When guiding specific actions of the robot, the most critical regulatory Gene is Gene7, and the specific formula is as follows:
wherein, i is 1,2, N represents the number of all the trapping robots, and the concentration SiRepresents a robot RiThe position vector of (2). Four parameters r1，r2，r3，r4Respectively, the weight of the corresponding concentration vector.
In Eq. (18), unit concentration vector tiDepending on the target, which directs the robot to approach or move away from the target, the calculation formula is as follows:
wherein ,TnIs an object of trapping, GiAnd
respectively, the position concentration information of the robot and the target. If the distance of the robot from the task target exceeds the distance limit of the current target
The robot is guided close to the target. However, it can be dangerous if too close to the target, resulting in population damage.
In Eq. (18), robot RiThe number of all neighbor robots in the sensing range is NiConcentration vector niIs the concentration sum of all neighboring robot positions, which guides the robot to tend to the area of low concentration, and the calculation formula is as follows:
in Eq. (18), concentration vector ciUnder the regulation of Gene8, it directs the robot to move to the position with highest concentration in the global trapping mode if GmaxThe maximum value of the concentration at the position is expressed by the following calculation formula [18 ]]：
In Eq. (18), in robot RiThe number of the surrounding neighbor robots is equal to that of neighbors with the distance less than the safety distance
Then the concentration vector oiThe robot is guided to move in the opposite direction, and the calculation formula is as follows [18 ]]：
Finally, Gene9 is also required for the final trapping pattern GiThe control is carried out to prevent the robot from impacting an obstacle in the moving process, and a specific formula is as follows [18 ]]：
In one embodiment, based on the artificial electric field algorithm, an update formula for optimizing the position and the speed of individuals in the population is constructed as follows:
wherein ,
representing the velocity of robot i at time t + 1,
representing the velocity of the robot i at time t,
represents the acceleration to which the ith robot is subjected;
indicating the position of robot i at time t + 1,
indicating the position of robot i at time t.
In particular, Co-GRN with a synergistic mechanism, we can note ωt，ωn，ωo，r1，r2，r3，r4These seven parameters, which greatly affect the final result in Layer1 and Layer2, directly determine the quality of the trapping performance. Therefore, in order to make Co-GRN with cooperative trapping mechanism more adaptive to task environment, we need to optimize these core parameters. And fusing an artificial electric field algorithm with Co-GRN.
The application of the artificial electric field algorithm is described in detail by taking a system with particles as an example. The position of each particle in the search space in d-dimension is first defined according to the following formula:
wherein ,
representing the coordinates of the ith particle in the d-dimension. At the number of iterations t, the electric field force exerted on particle i by particle j is:
wherein ,Qi(t) and Qj(t) are the charge amounts of particle i and particle j, respectively, at the number of iterations t. k (t) is a coulomb constant, with the number of iterations dynamically changing, ε is a very small positive number, Rij(t) is the Euclidean distance between two particles. Thus, the total force exerted on the ith particle is defined by the following equation:
according to Newton's law of motion, we can obtain that the acceleration to which the ith particle is subjected is:
furthermore, the velocity magnitude of the ith particle at the next moment is equal to the sum of the current acceleration and the current velocity component, and the specific velocity and position updating formula is as follows:
through repeated iteration of the above process, the optimal solution of the optimization problem, namely the values of seven core parameters in Co-GRN, can be finally obtained.
In one embodiment, the method comprises the steps that an enclosure area is divided into a plurality of sub-areas according to the perception radius of the robot, and a weight is set for each sub-area; assigning values to the robot, the barrier and the blank area in the surrounding area of the target of the surrounding area; obtaining the enclosure capturing strength according to the weight of each subarea, the assignment of the robot, the barrier and the blank area; determining the enclosure occupancy rate according to the angle of the robot for limiting the target; and constructing an evaluation function for evaluating the surrounding capture effect of the group robots according to the surrounding capture strength and the surrounding capture occupancy rate.
Specifically, as shown in fig. 3, the capture area is divided into three sub-areas, which are: the first region1, the second region2 and the third region3 are the first region when the distance between the first region and the target is too close or too far, the capture weight of the first region is recorded as lambda 11 is ═ 1; most suitably, the second region is weighted by λ 22; if the distance is too far away from the target, the area which can not generate the trapping effect is a third area, and the weight is recorded as lambda30. Meanwhile, a capture value T is respectively given to the robot, the barrier and the blank in the surrounding environment of the target1＝1，T2＝1.5，T3＝0。
In one embodiment, the capture strength is obtained according to the weight of each sub-region and the assignment of the robot, the obstacle and the blank region:
wherein λ represents a weight for each sub-region, T represents a robot, an obstacle, and a blank region assignment,
representing the maximum value of the trapping intensity.
In one embodiment, according to the angle of the robot for limiting the target, the enclosure capture occupancy is determined as follows:
wherein ,θiRepresenting the angle at which the robot acts to limit the target.
In one embodiment, the merit function includes: the first evaluation function and the second evaluation function are obtained by carrying out average weighting on the enclosure capturing strength and the enclosure capturing occupancy within preset time; and carrying out maximum value weighting on the trapping strength and the trapping occupancy within the preset time to obtain a second evaluation function.
Specifically, in order to better perform quantitative evaluation on the trapping result, two new evaluation indexes of the fitness function are defined through weighting on the basis of the indexes introduced above. One is an average value index Ave, namely, firstly, aiming at each target, calculating the average value of the capture intensity and the average value of the capture occupancy within a certain time, then averaging the capture intensity and the capture occupancy of the target, and weighting and summing the two average values by 50% respectively to obtain a final average value index; and the other is a maximum value index Max, namely within a certain time, the trapping strength and the trapping occupancy of the target are respectively summed according to the proportion of 50 percent, then the weighted sum value just calculated by the target at each time is summed, then the sum values at different times are compared, and the maximum value is taken as the maximum value index.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 1 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 4, there is provided a swarm robot multi-target enclosure control device, including: an enclosure output module 402, an update module 404, an optimization module 406, and an optimization output module 408, wherein:
an enclosure output module 402, configured to input position information of the current robot, target position information, obstacle information sent by other robots in the sensing area, and neighbor position information of the other robots into a pre-constructed adaptive cooperative gene regulation and control network, and output an enclosure mode and action information of the current robot; the trapping mode is obtained by weighting target position information, neighbor position information and obstacle position information through influence factors, and the action information is obtained by weighting each moving strategy through weights;
an updating module 404, configured to construct an updating formula for optimizing the position and speed of the individual in the population based on an artificial electric field algorithm;
the optimization module 406 is configured to perform optimization calculation on the impact factors and the weights according to the update formula to obtain optimized impact factors and optimized weights;
and an optimization output module 408, configured to input the optimization influence factors and the optimization weights to the adaptive cooperative gene regulation and control network, so that the adaptive cooperative gene regulation and control network outputs maneuvering information for target capture of the group robots.
For specific limitations of the multi-target capturing control device for the group robot, reference may be made to the above limitations of the multi-target capturing control method for the group robot, and details are not repeated here. All or part of the modules in the multi-target capture control device for the group robots can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 5. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize the multi-target capture control method for the swarm robots. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, a computer device is provided, comprising a memory storing a computer program and a processor implementing the steps of the method in the above embodiments when the processor executes the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method in the above-mentioned embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A multi-target enclosure control method for swarm robots is characterized by comprising the following steps:
inputting position information, target position information and obstacle position information of the current robot, obstacle information sent by other robots in a sensing area and neighbor position information of the other robots into a pre-constructed adaptive cooperative gene regulation and control network, and outputting an enclosure capture mode and action information of the current robot; the trapping mode is obtained by weighting target position information, neighbor position information and obstacle position information through influence factors, and the action information is obtained by weighting each moving strategy through weights;
establishing an updating formula for optimizing the position and the speed of individuals in the population based on an artificial electric field algorithm;
according to the updating formula, carrying out optimization calculation on the influence factors and the weights to obtain optimized influence factors and optimized weights;
and inputting the optimization influence factors and the optimization weights into the self-adaptive cooperative gene regulation and control network so that the self-adaptive cooperative gene regulation and control network outputs maneuvering information for target capture of the group robots.
2. The method according to claim 1, wherein the inputting the position information, the target position information, the obstacle position information of the current robot, the obstacle information sent by other robots in the sensing area and the neighbor position information of other robots into a pre-constructed adaptive cooperative gene regulation and control network and outputting the capture mode of the current robot comprises:
inputting the position information, the target position information, the obstacle position information of the current robot, the obstacle information sent by other robots in the sensing area and the neighbor position information of other robots into a pre-constructed adaptive cooperative gene regulation and control network, and outputting the trapping mode of the current robot as follows:
P＝ωtPt+ωnPn+ωoPo
wherein P represents a trapping mode, PtComponent of the hunting pattern, P, representing a determination of target position informationnRepresenting the component of the trapping pattern, P, determined by the neighbor location informationoAn entrapment mode component representing the determination of the obstacle position information; omegat、ωn and ωoAll represent influencing factors.
3. The method of claim 1, wherein the mobility policy comprises: the robot approach or departure strategy comprises a robot approach or departure strategy, a robot low-density motion tendency strategy, a robot high-density motion tendency strategy and a robot reverse direction motion strategy;
the method for inputting position information, target position information, obstacle position information of the current robot, obstacle information sent by other robots in the sensing area and neighbor position information of other robots into a pre-constructed adaptive cooperative gene regulation and control network and outputting action information of the current robot comprises the following steps:
inputting the position information, the target position information, the obstacle position information of the current robot, the obstacle information sent by other robots in the sensing area and the neighbor position information of other robots into a pre-constructed adaptive cooperative gene regulation and control network, and outputting the action information of the current robot as follows:
wherein ,SiIndicating the position vector of the ith robot, tiUnit vector, n, representing the proximity or distance of the robot to the target strategyiUnit vector representing low-density motion tendency strategy of robot, ciUnit vector, o, representing a high-density motion trend strategy for a robotiUnit vector, r, representing a strategy for counter-directional movement of the robot1-r4Both represent weights.
4. The method of claim 1, wherein constructing an updated formula that optimizes the location and velocity of individuals in the population based on an artificial electric field algorithm comprises:
based on an artificial electric field algorithm, an updating formula for optimizing the position and the speed of individuals in the population is constructed as follows:
wherein ,
representing the velocity of robot i at time t +1,
representing the velocity of the individual i at time t,
representing the acceleration to which the ith individual is subjected;
representing the position of the individual i at time t +1,
representing the position of the individual i at time t.
5. The method according to any one of claims 1 to 4, further comprising:
dividing the enclosure area according to the distance between the robot and the target to obtain a plurality of sub-areas, and setting a weight value for each sub-area;
assigning values to the robot, the barrier and the blank area in the surrounding area of the target of the surrounding area;
obtaining the enclosure capturing strength according to the weight of each subarea, the assignment of the robot, the barrier and the blank area;
determining the enclosure occupancy rate according to the angle of the robot for limiting the target;
and constructing an evaluation function for evaluating the surrounding capture effect of the group robots according to the surrounding capture strength and the surrounding capture occupancy rate.
6. The method of claim 5, wherein obtaining the containment strength according to the weight of each subregion and the robot, obstacle, and blank area assignments comprises:
and according to the weight of each subregion, the robot, the barrier and the blank region assignment, obtaining the enclosure capturing strength as follows:
wherein λ represents a weight for each sub-region, T represents a robot, an obstacle, and a blank region assignment,
representing the maximum value of the trapping intensity.
7. The method of claim 5, wherein determining the containment occupancy based on the angle at which the robot acts to limit the target comprises:
according to the angle of the robot for limiting the target, determining the enclosure capture occupancy as follows:
wherein ,θiRepresenting the angle at which the robot acts to limit the target.
8. The method according to any one of claims 5-7, wherein the merit function comprises: a first merit function and a second merit function;
the method for constructing the evaluation function for evaluating the trapping effect of the group robots according to the trapping strength and the trapping occupancy comprises the following steps:
carrying out average weighting on the enclosure intensity and the enclosure occupancy within a preset time to obtain a first evaluation function;
and carrying out maximum value weighting on the enclosure intensity and the enclosure occupancy within preset time to obtain a second evaluation function.
9. A multi-target enclosure control device for swarm robots is characterized by comprising:
the capture output module is used for inputting the position information, the target position information and the obstacle position information of the current robot, the obstacle information sent by other robots in the sensing area and the neighbor position information of other robots into a pre-constructed adaptive cooperative gene regulation and control network and outputting the capture mode and the action information of the current robot; the trapping mode is obtained by weighting target position information, neighbor position information and obstacle position information through influence factors, and the action information is obtained by weighting each moving strategy through weights;
the updating module is used for constructing an updating formula for optimizing the position and the speed of the individual in the population based on an artificial electric field algorithm;
the optimization module is used for carrying out optimization calculation on the influence factors and the weights according to the updating formula to obtain optimized influence factors and optimized weights;
and the optimization output module is used for inputting the optimization influence factors and the optimization weights into the self-adaptive cooperative gene regulation and control network so that the self-adaptive cooperative gene regulation and control network outputs maneuvering information for target enclosure of the group robots.
10. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 8 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210013119.7A CN114326747B (en) | 2022-01-06 | 2022-01-06 | Multi-target capture control method and device for group robot and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210013119.7A CN114326747B (en) | 2022-01-06 | 2022-01-06 | Multi-target capture control method and device for group robot and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114326747A true CN114326747A (en) | 2022-04-12 |
| CN114326747B CN114326747B (en) | 2023-10-24 |
Family
ID=81024051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210013119.7A Active CN114326747B (en) | 2022-01-06 | 2022-01-06 | Multi-target capture control method and device for group robot and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114326747B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115455812A (en) * | 2022-08-25 | 2022-12-09 | 临涣水务股份有限公司 | Water supply pump station optimization method and system |
| CN115629600A (en) * | 2022-08-01 | 2023-01-20 | 北方工业大学 | Multi-machine cooperative trapping method in complex dynamic security environment based on buffer voronoi diagram |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016045615A1 (en) * | 2014-09-25 | 2016-03-31 | 科沃斯机器人有限公司 | Robot static path planning method |
| CN112462779A (en) * | 2020-11-30 | 2021-03-09 | 汕头大学 | Group robot dynamic capture control method and system based on gene regulation network |
| CN112527020A (en) * | 2020-11-30 | 2021-03-19 | 汕头大学 | Target capture control method and system based on group robots |
| WO2021065501A1 (en) * | 2019-09-30 | 2021-04-08 | 日本電気株式会社 | Passage possibility determining method, passage possibility determining device, and travel route generation system |
| CN112684700A (en) * | 2020-11-30 | 2021-04-20 | 汕头大学 | Multi-target searching and trapping control method and system for swarm robots |
| CN113172626A (en) * | 2021-04-30 | 2021-07-27 | 汕头大学 | Intelligent robot group control method based on three-dimensional gene regulation and control network |
| CN113485340A (en) * | 2021-07-12 | 2021-10-08 | 汕头大学 | Distributed enclosure control method and system for group robots |
| CN113580129A (en) * | 2021-07-19 | 2021-11-02 | 中山大学 | Multi-target cooperative trapping method, device and medium based on robot |
-
2022
- 2022-01-06 CN CN202210013119.7A patent/CN114326747B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016045615A1 (en) * | 2014-09-25 | 2016-03-31 | 科沃斯机器人有限公司 | Robot static path planning method |
| WO2021065501A1 (en) * | 2019-09-30 | 2021-04-08 | 日本電気株式会社 | Passage possibility determining method, passage possibility determining device, and travel route generation system |
| CN112462779A (en) * | 2020-11-30 | 2021-03-09 | 汕头大学 | Group robot dynamic capture control method and system based on gene regulation network |
| CN112527020A (en) * | 2020-11-30 | 2021-03-19 | 汕头大学 | Target capture control method and system based on group robots |
| CN112684700A (en) * | 2020-11-30 | 2021-04-20 | 汕头大学 | Multi-target searching and trapping control method and system for swarm robots |
| CN113172626A (en) * | 2021-04-30 | 2021-07-27 | 汕头大学 | Intelligent robot group control method based on three-dimensional gene regulation and control network |
| CN113485340A (en) * | 2021-07-12 | 2021-10-08 | 汕头大学 | Distributed enclosure control method and system for group robots |
| CN113580129A (en) * | 2021-07-19 | 2021-11-02 | 中山大学 | Multi-target cooperative trapping method, device and medium based on robot |
Non-Patent Citations (2)
| Title |
|---|
| 张红强;吴亮红;周游;章兢;周少武;刘朝华: "复杂环境下群机器人自组织协同多目标围捕", 控制理论与应用, no. 005, pages 1054 - 1062 * |
| 范衠;王诏君;石泽;王琛;王柳;蔡堉伟;黄华兴;宁为博;董朝晖;李文姬;朱贵杰;李恪;李兵;谷敏强;朱晓敏;包卫东: "基于合作自主定位的群体模式自动生成方法", 汕头大学学报(自然科学版), no. 002, pages 14 - 28 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115629600A (en) * | 2022-08-01 | 2023-01-20 | 北方工业大学 | Multi-machine cooperative trapping method in complex dynamic security environment based on buffer voronoi diagram |
| CN115629600B (en) * | 2022-08-01 | 2023-12-12 | 北方工业大学 | Multi-machine collaborative trapping method based on buffer Wino diagram in complex dynamic security environment |
| CN115455812A (en) * | 2022-08-25 | 2022-12-09 | 临涣水务股份有限公司 | Water supply pump station optimization method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114326747B (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Das et al. | Multi-robot path planning using improved particle swarm optimization algorithm through novel evolutionary operators | |
| CN114326747A (en) | Multi-target enclosure control method and device for group robots and computer equipment | |
| US10589368B2 (en) | Machine learning device having function of adjusting welding positions of core in wire electric discharge machine | |
| Ni et al. | An improved spinal neural system-based approach for heterogeneous AUVs cooperative hunting | |
| JP5448841B2 (en) | Method for computer-aided closed-loop control and / or open-loop control of technical systems, in particular gas turbines | |
| US11897066B2 (en) | Simulation apparatus | |
| Kuo et al. | A migrant-inspired path planning algorithm for obstacle run using particle swarm optimization, potential field navigation, and fuzzy logic controller | |
| CN113609786A (en) | Mobile robot navigation method and device, computer equipment and storage medium | |
| Tan et al. | Multi-type task allocation for multiple heterogeneous unmanned surface vehicles (USVs) based on the self-organizing map | |
| CN113778127A (en) | Unmanned aerial vehicle reconnaissance path planning method and device based on genetic algorithm | |
| Ordaz-Rivas et al. | Autonomous foraging with a pack of robots based on repulsion, attraction and influence | |
| Jiang et al. | Generative adversarial interactive imitation learning for path following of autonomous underwater vehicle | |
| Allison et al. | Uav collaborative search using probabilistic finite state machines | |
| Veselov et al. | Management of Behavior of a Swarm of Robots Applicable to the Tasks of Monitoring a Some Territory | |
| Wu et al. | Multi-robot target entrapment using cooperative hierarchical gene regulatory network | |
| Peng et al. | Pattern formation in constrained environments: A swarm robot target trapping method | |
| CN113790729B (en) | Unmanned overhead traveling crane path planning method and device based on reinforcement learning algorithm | |
| CN111882577B (en) | Group obstacle avoidance and consistent traveling method and device based on field-of-view perception | |
| Jain et al. | Peregrine preying pattern-based differential evolution | |
| Valdez et al. | Nature-Inspired Optimization Algorithms for Neuro-Fuzzy Models in Real-World Control and Robotics Applications. | |
| Blinov et al. | Deep q-learning algorithm for solving inverse kinematics of four-link manipulator | |
| Al-Hussaini et al. | A policy synthesis-based framework for robot rescue decision-making in multi-robot exploration of disaster sites | |
| Edwards et al. | Stochastic nonlinear ensemble modeling and control for robot team environmental monitoring | |
| Rao et al. | A trust based navigation control for multi-robot to avoid deadlock in a static environment using improved Krill Herd | |
| da Silva Tchilian et al. | Assisted teleoperation for a human-swarm interaction system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |