Robot control methods, devices, electronic equipment and storage media

Abstract

This invention provides a robot control method that obtains a first robot's probability of intercepting a second robot and a second probability of intercepting a target object at a current moment, wherein the target object is an object contested by the first and second robots. Based on the first and second interception probabilities, a distribution scheme between the first robot and the second robot and the target object is determined. The first robot is then controlled according to the distribution scheme. By determining the distribution scheme using the first robot's probability of intercepting the second robot and the target object at the current moment, and then controlling the first robot to intercept objects based on the distribution scheme, the method allows for real-time adjustment of the first robot's distribution scheme for interception, improving interception flexibility.

Description

Technical Field

[0001] This invention relates to the field of automatic control, and more particularly to a robot control method, device, electronic device, and storage medium. Background Technology

[0002] With the development of robots, robots have begun to appear on the competitive stage. Compared with one-on-one robot competitions, many-on-many robot competitions require cooperation between multiple robots and more complex decision-making. For example, in robot soccer, the defending side needs to intercept the attacking side. The existing interception methods are mostly positional interception, that is, one-on-one interception, which is relatively rigid and lacks flexibility. Summary of the Invention

[0003] This invention provides a robot control method aimed at solving the problems of rigid and inflexible robot interception methods in the prior art. By determining the first robot's allocation scheme for the second robot and the target object based on the first robot's initial interception probability against the second robot and the second interception probability against the target object at the current moment, the first robot can be controlled to intercept the target object using this allocation scheme. This allows for real-time adjustment of the first robot's allocation scheme, improving interception flexibility.

[0004] In a first aspect, embodiments of the present invention provide a robot control method, the method comprising:

[0005] The first robot obtains the first interception probability of the second robot and the second interception probability of the target object at the current moment, wherein the target object is the object contested by the first robot and the second robot;

[0006] Based on the first interception probability and the second interception probability, determine the allocation scheme of the first robot for the second robot and the target object;

[0007] The first robot is controlled according to the allocation scheme.

[0008] Optionally, obtaining the first interception probability of the first robot against the second robot and the second interception probability against the target object at the current moment includes:

[0009] Obtain the position distribution of the first robot at the current moment, the position distribution probability of the second robot, and the position distribution probability of the target object;

[0010] Based on the position distribution of the first robot at the current moment and the position distribution probability of the second robot, determine the first interception probability of the first robot against the second robot;

[0011] Based on the position distribution of the first robot at the current moment and the position distribution probability of the target object, the second interception probability of the first robot for the target object is determined.

[0012] Optionally, determining the allocation scheme between the first robot and the second robot and the target object based on the first interception probability and the second interception probability includes:

[0013] Determine the constraints and decision variables;

[0014] The first objective function is determined based on the first interception probability and the second interception probability;

[0015] Based on the decision variables, determine the second objective function;

[0016] Based on the constraints, the first objective function, and the second objective function, determine the allocation strategy optimization model;

[0017] Based on the allocation strategy optimization model, the allocation scheme of the first robot for the second robot and the target object is determined.

[0018] Optionally, the determination of constraints includes:

[0019] The allocation quantity constraint is determined based on the number of the first robot and the number of the second robot;

[0020] Predict the first intercept line for the second robot and the second intercept line for the target object, and determine the distance constraint based on the first intercept line and the second intercept line;

[0021] The constraint conditions are determined based on the allocation quantity constraint and the distance constraint.

[0022] Optionally, determining the allocation quantity constraint based on the number of the first robot and the number of the second robot includes:

[0023] It is determined that at least one of the first robots is assigned to the target object;

[0024] The number of the first robots assigned to each second robot is less than or equal to 1;

[0025] Determine that the first robot is fully allocated.

[0026] Optionally, the prediction of the first intercept line for the second robot and the second intercept line for the target object includes:

[0027] Based on the position distribution of the first robot at the current moment, the position distribution probability of the second robot, and the speed of the first robot, a first interception line is determined for the first robot against the second robot;

[0028] Based on the position distribution of the first robot at the current moment, the position distribution probability of the target object, and the speed of the first robot, a second interception line for the first robot against the target object is determined.

[0029] Optionally, determining the decision variables includes:

[0030] The first decision variable is determined based on the interception status of each of the first robots against any one of the second robots;

[0031] A second decision variable is determined based on the interception status of each of the first robots toward the target object.

[0032] In a second aspect, embodiments of the present invention provide a robot control device, the device comprising:

[0033] The acquisition module is used to acquire the first interception probability of the first robot against the second robot and the second interception probability of the target object at the current moment, wherein the target object is the object contested by the first robot and the second robot;

[0034] The determination module is used to determine the allocation scheme of the first robot for the second robot and the target object based on the first interception probability and the second interception probability;

[0035] The control module is used to control the first robot according to the allocation scheme.

[0036] Thirdly, embodiments of the present invention provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the robot control method provided in embodiments of the present invention.

[0037] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the robot control method provided in the embodiments of the present invention.

[0038] In this embodiment of the invention, a first interception probability of the first robot against the second robot and a second interception probability against a target object are obtained at the current moment. The target object is the object contested by the first robot and the second robot. Based on the first and second interception probabilities, an allocation scheme for the first robot to the second robot and the target object is determined. The first robot is then controlled according to the allocation scheme. By determining the allocation scheme for the first robot to the second robot and the target object using the first and second interception probabilities at the current moment, and then controlling the first robot to intercept using the allocation scheme, the allocation scheme of the first robot can be adjusted in real time for interception, improving the flexibility of interception. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart of a robot control method provided in an embodiment of the present invention;

[0041] Figure 2 This is a schematic diagram of the structure of a robot control device provided in an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] Please see Figure 1 , Figure 1 This is a flowchart of a robot control method provided in an embodiment of the present invention, such as... Figure 1 As shown, the robot control method includes the following steps:

[0045] 101. Obtain the first interception probability of the first robot against the second robot and the second interception probability against the target object at the current moment.

[0046] In this embodiment of the invention, the first robot and the second robot are mobile robots, and the target object is an object contested by the first robot and the second robot. The first robot and the second robot are used to compete for the target object. The number of the first robot and the second robot is the same, and the number of the target object is generally one. One first robot can only intercept one second robot or one target object. The first interception probability refers to the probability that the second robot is intercepted at the current moment, and the second interception probability refers to the probability that the target object is intercepted at the current moment.

[0047] Specifically, the position distribution of the first robot may differ at different times; therefore, the first and second interception probabilities may also differ at different times. The first interception probability is determined based on the current position distribution of the first and second robots. The closer the positions of the first and second robots, the higher the first interception probability, which ranges from 0 to 1. Similarly, the second interception probability is determined based on the current position distribution of the first robot and the target object. The closer the positions of the first robot and the target object, the higher the second interception probability, which also ranges from 0 to 1.

[0048] 102. Based on the first interception probability and the second interception probability, determine the allocation scheme of the first robot for the second robot and the target object.

[0049] In this embodiment of the invention, the optimization objective is to maximize the combined interception probability of the first interception probability and the second interception probability. The optimization objective can be solved by optimization algorithms such as implicit enumeration, branch and bound method, dynamic programming method, particle swarm algorithm, genetic algorithm, and ant colony algorithm.

[0050] Specifically, the solution process takes maximizing the overall interception probability as the optimization objective, and uses the combination of the first robot being assigned to the second robot or the target object as the variable, and solves for the optimization objective through the above optimization algorithm.

[0051] 103. Control the first robot according to the allocation plan.

[0052] In this embodiment of the invention, after obtaining the allocation scheme, the allocation scheme is formed into control instructions corresponding to each first robot, and the control instructions are sent to the corresponding first robots so that each first robot can perform the corresponding action according to the corresponding control instructions.

[0053] In this embodiment of the invention, a first interception probability of the first robot against the second robot and a second interception probability against a target object are obtained at the current moment. The target object is the object contested by the first robot and the second robot. Based on the first and second interception probabilities, an allocation scheme for the first robot to the second robot and the target object is determined. The first robot is then controlled according to the allocation scheme. By determining the allocation scheme for the first robot to the second robot and the target object using the first and second interception probabilities at the current moment, and then controlling the first robot to intercept using the allocation scheme, the allocation scheme of the first robot can be adjusted in real time for interception, improving the flexibility of interception.

[0054] Optionally, in the steps of obtaining the first interception probability of the first robot against the second robot and the second interception probability against the target object at the current moment, the position distribution of the first robot, the position distribution probability of the second robot, and the position distribution probability of the target object at the current moment can be obtained; the first interception probability of the first robot against the second robot can be determined based on the position distribution of the first robot at the current moment and the position distribution probability of the second robot; and the second interception probability of the first robot against the target object can be determined based on the position distribution of the first robot at the current moment and the position distribution probability of the target object.

[0055] In this embodiment of the invention, the position distribution of the first robot at the current moment can be obtained by the positioning device inside the first robot. The first robot is also equipped with an image acquisition device, which acquires images of the second robot and the target object to obtain an image containing the second robot and the target object. The positions of the second robot and the target object are detected by the image containing the second robot and the target object.

[0056] Based on the positions of the first and second robots, their relative motion relationship is determined, and the expected intersection time and position are calculated. At the expected intersection time, the overlapping portion of their expected intersection positions constitutes the interception zone of the first robot against the second robot, and the size of this interception zone is closely related to the interception probability of the first robot against the second robot. In fact, the interception probability of the first robot against the second robot mainly depends on two factors: the interception performance of the first robot itself and the position distribution of the second robot. The interception performance of the first robot is represented by its interception probability function. At the expected intersection time, for position (x, y) within the interception zone, the interception probability of the first robot against the second robot can be expressed as f(x, y) = A(x, y) * B(x, y), where A(x, y) is the interception probability function of the first robot at position (x, y), and B(x, y) is the position distribution probability function of the second robot. Integrating the interception probability of the first robot against the second robot at the aforementioned position (x, y) yields the first interception probability of the first robot against the second robot within the interception zone.

[0057] Based on the positions of the first robot and the target object, their relative motion relationship is determined, and the expected intersection time and expected intersection position are calculated. At the expected intersection time, the overlapping portion of the expected intersection positions of the first robot and the target object constitutes the interception zone of the first robot against the target object, and the size of the interception zone is closely related to the interception probability of the first robot against the target object. In fact, the interception probability of the first robot against the target object mainly depends on two aspects: the interception performance of the first robot itself and the position distribution of the target object. The interception performance of the first robot is represented by its interception probability function. At the expected intersection time, for position (x, y) within the interception zone, the interception probability of the first robot against the target object can be expressed as g(x, y) = A(x, y) * C(x, y), where A(x, y) is the interception probability function of the first robot at position (x, y), and C(x, y) is the position distribution probability function of the target object. Integrating the interception probability of the first robot against the target object at the aforementioned position (x, y) yields the second interception probability of the first robot against the target object within the interception zone.

[0058] Optionally, in the step of determining the allocation scheme of the first robot for the second robot and the target object based on the first interception probability and the second interception probability, the following steps can be taken: determining the constraints and decision variables; determining the first objective function based on the first interception probability and the second interception probability; determining the second objective function based on the decision variables; determining the allocation strategy optimization model based on the constraints, the first objective function, and the second objective function; and determining the allocation scheme of the first robot for the second robot and the target object based on the allocation strategy optimization model.

[0059] In this embodiment of the invention, there are N first robots and N second robots. Only M second robots that enter the defense area can be intercepted, where M is less than or equal to N. The first objective function can be to maximize the overall interception probability, and the second objective function can be to maximize the remaining total power.

[0060] Optionally, in the step of determining the decision variables, a first decision variable can be determined based on the interception status of each first robot against any second robot; and a second decision variable can be determined based on the interception status of each first robot against the target object. The first decision variable is whether to assign the nth first robot to the mth second robot, and the second decision variable is whether to assign the rth first robot to the target object.

[0061] In the steps of determining the allocation strategy optimization model based on constraints, the first objective function, and the second objective function; and determining the allocation scheme of the first robot for the second robot and the target object based on the allocation strategy optimization model, the final objective function can be determined as maxZ = max f(x,y)*g(x,y)*maxE, where max f(x,y)*g(x,y) represents maximizing the overall interception probability, maxE represents maximizing the remaining total battery power, and E = a n,m *E0+b r *E1, where a n,m This indicates whether to assign the nth first robot to the mth second robot. If a n,m =0, which means that the nth first robot will not be assigned to the mth second robot. If a n,m =1, which means that the nth first robot is assigned to the mth second robot; b r Indicates whether to assign the r-th first robot to the target object; if b r =0, which means that the r-th first robot will not be assigned to the target object. If b r =1, which means that the r-th first robot is assigned to the target object, and E1 represents the amount of electricity required to intercept the target object. The above constraints can be understood as the range of conditions for solving the problem.

[0062] The optimization algorithm for maxZ = max f(x,y)*g(x,y)*maxE can be solved under the constraints using methods such as implicit enumeration, branch and bound, dynamic programming, particle swarm optimization, genetic algorithm, and ant colony optimization. This yields a... n,m and b r The value of a, according to a n,m The value of b determines whether to assign the nth first robot to the mth second robot. r The value of is used to assign the r-th first robot to the target object, thus obtaining the corresponding allocation scheme.

[0063] Optionally, in the step of determining the constraint conditions, the allocation quantity constraint can be determined based on the number of the first robot and the number of the second robot; the first interception line for the second robot and the second interception line for the target object can be predicted, and the distance constraint can be determined based on the first interception line and the second interception line; the constraint conditions can be determined based on the allocation quantity constraint and the distance constraint.

[0064] In this embodiment of the invention, the above-mentioned allocation quantity constraint is used to constrain the number of the first robot allocated to the second robot, the above-mentioned distance constraint is used to constrain the first robot to intercept the second robot when the distance is less than or equal to the first interception line, and is used to constrain the first robot to intercept the target object when the distance is less than or equal to the second interception line.

[0065] Optionally, in the step of determining the allocation quantity constraint based on the number of first robots and the number of second robots, it can be determined that the target object is allocated at least one first robot; that the number of first robots allocated to each second robot is less than or equal to 1; and that the first robots are fully allocated.

[0066] In this embodiment of the invention, since the target object is a contested object, at least one first robot is assigned to participate in the direct contestation of the target object, prioritizing the contested object. This avoids situations where no first robot participates in the contestation of the target object. The number of second robots assigned to the first robots is less than or equal to one, thus preventing multiple first robots from intercepting the same second robot. When the number of first robots in the defense area is equal to or less than the sum of the number of second robots and the number of target objects, it is determined that all first robots are fully assigned to ensure the interception effect.

[0067] Optionally, in the step of predicting the first intercept line for the second robot and the second intercept line for the target object, the first intercept line for the first robot against the second robot can be determined based on the position distribution of the first robot at the current moment, the position distribution probability of the second robot, and the speed of the first robot; the second intercept line for the first robot against the target object can be determined based on the position distribution of the first robot at the current moment, the position distribution probability of the target object, and the speed of the first robot.

[0068] In this embodiment of the invention, the relative motion relationship between the first robot and the second robot is determined based on their positions, and then the expected intersection time and expected intersection position of the first robot and the second robot are calculated. At the expected intersection time, the overlapping portion of the expected intersection positions of the first robot and the second robot constitutes the interception zone of the first robot against the second robot, and the leading edge of the interception zone can be used as the first interception line of the first robot against the second robot. Similarly, the relative motion relationship between the first robot and the target object is determined based on their positions, and then the expected intersection time and expected intersection position of the first robot and the target object are calculated. At the expected intersection time, the overlapping portion of the expected intersection positions of the first robot and the target object constitutes the interception zone of the first robot against the target object, and the leading edge of the interception zone can be used as the second interception line of the first robot against the target object.

[0069] It should be noted that the robot control method provided in this embodiment of the invention can be applied to intelligent robots, smartphones, computers, servers and other devices that can perform robot control methods.

[0070] Optional, please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a robot control device provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the device includes:

[0071] The acquisition module 201 is used to acquire the first interception probability of the first robot against the second robot and the second interception probability against the target object at the current moment, wherein the target object is the object contested by the first robot and the second robot;

[0072] The determining module 202 is used to determine the allocation scheme of the first robot for the second robot and the target object based on the first interception probability and the second interception probability;

[0073] The control module 203 is used to control the first robot according to the allocation scheme.

[0074] Optionally, the acquisition module 201 includes:

[0075] The acquisition submodule is used to acquire the position distribution of the first robot at the current moment, the position distribution probability of the second robot, and the position distribution probability of the target object.

[0076] The first determining submodule is used to determine the first interception probability of the first robot against the second robot based on the position distribution of the first robot at the current time and the position distribution probability of the second robot.

[0077] The second determining submodule is used to determine the second interception probability of the first robot for the target object based on the position distribution of the first robot at the current moment and the position distribution probability of the target object.

[0078] Optionally, the determining module 202 includes:

[0079] The third determination submodule is used to determine the constraints and decision variables;

[0080] The fourth determining submodule is used to determine the first objective function based on the first interception probability and the second interception probability;

[0081] The fifth determining submodule is used to determine the second objective function based on the decision variables;

[0082] The sixth determining submodule is used to determine the allocation strategy optimization model based on the constraints, the first objective function, and the second objective function;

[0083] The seventh determination submodule is used to determine the allocation scheme of the first robot for the second robot and the target object based on the allocation strategy optimization model.

[0084] Optionally, the third determining submodule includes:

[0085] The first determining unit is configured to determine the allocation quantity constraint based on the number of the first robot and the number of the second robot;

[0086] The second determining unit is used to predict the first interception line for the second robot and the second interception line for the target object, and to determine the distance constraint based on the first interception line and the second interception line;

[0087] The third determining unit is used to determine the constraint conditions based on the allocation quantity constraint and the distance constraint.

[0088] Optionally, the first determining unit includes:

[0089] A first determining subunit is used to determine that at least one of the first robots is assigned to the target object;

[0090] The second determining subunit is used to determine that the number of the first robots assigned to each second robot is less than or equal to 1;

[0091] The third determining subunit is used to determine the complete allocation of the first robot.

[0092] Optionally, the second determining unit includes:

[0093] The fourth determining subunit is used to determine the first interception line of the first robot against the second robot based on the position distribution of the first robot at the current moment, the position distribution probability of the second robot, and the speed of the first robot.

[0094] The fifth determining subunit is used to determine the second interception line of the first robot for the target object based on the position distribution of the first robot at the current time, the position distribution probability of the target object, and the speed of the first robot.

[0095] Optionally, the third determining submodule includes:

[0096] The fourth determining unit is used to determine the first decision variable based on the interception status of each of the first robots against any one of the second robots;

[0097] The fifth determining unit is used to determine the second decision variable based on the interception status of each of the first robots on the target object.

[0098] It should be noted that the robot control device provided in this embodiment of the invention can be applied to intelligent robots, smartphones, computers, servers and other devices that can perform robot control methods.

[0099] The robot control device provided in this embodiment of the invention can implement all the processes implemented by the robot control method in the above-described method embodiments, and can achieve the same beneficial effects. To avoid repetition, further details are omitted here.

[0100] See Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, such as... Figure 3 As shown, it includes: a memory 302, a processor 301, and a computer program for a robot control method stored in the memory 302 and executable on the processor 301, wherein:

[0101] The processor 301 is used to call the computer program stored in the memory 302 and perform the following steps:

[0102] The first robot obtains the first interception probability of the second robot and the second interception probability of the target object at the current moment, wherein the target object is the object contested by the first robot and the second robot;

[0103] Based on the first interception probability and the second interception probability, determine the allocation scheme of the first robot for the second robot and the target object;

[0104] The first robot is controlled according to the allocation scheme.

[0105] Optionally, the process of obtaining the first interception probability of the first robot against the second robot and the second interception probability against the target object at the current moment, executed by processor 301, includes:

[0106] Obtain the position distribution of the first robot at the current moment, the position distribution probability of the second robot, and the position distribution probability of the target object;

[0107] Based on the position distribution of the first robot at the current moment and the position distribution probability of the second robot, determine the first interception probability of the first robot against the second robot;

[0108] Based on the position distribution of the first robot at the current moment and the position distribution probability of the target object, the second interception probability of the first robot for the target object is determined.

[0109] Optionally, the step of determining the allocation scheme between the first robot and the second robot and the target object based on the first interception probability and the second interception probability, executed by the processor 301, includes:

[0110] Determine the constraints and decision variables;

[0111] The first objective function is determined based on the first interception probability and the second interception probability;

[0112] Based on the decision variables, determine the second objective function;

[0113] Based on the constraints, the first objective function, and the second objective function, determine the allocation strategy optimization model;

[0114] Based on the allocation strategy optimization model, the allocation scheme of the first robot for the second robot and the target object is determined.

[0115] Optionally, the determination of constraints executed by processor 301 includes:

[0116] The allocation quantity constraint is determined based on the number of the first robot and the number of the second robot;

[0117] Predict the first intercept line for the second robot and the second intercept line for the target object, and determine the distance constraint based on the first intercept line and the second intercept line;

[0118] The constraint conditions are determined based on the allocation quantity constraint and the distance constraint.

[0119] Optionally, the process executed by processor 301 to determine the allocation quantity constraint based on the number of the first robot and the number of the second robot includes:

[0120] It is determined that at least one of the first robots is assigned to the target object;

[0121] The number of the first robots assigned to each second robot is less than or equal to 1;

[0122] Determine that the first robot is fully allocated.

[0123] Optionally, the prediction of the first intercept line for the second robot and the second intercept line for the target object executed by the processor 301 includes:

[0124] Based on the position distribution of the first robot at the current moment, the position distribution probability of the second robot, and the speed of the first robot, a first interception line is determined for the first robot against the second robot;

[0125] Based on the position distribution of the first robot at the current moment, the position distribution probability of the target object, and the speed of the first robot, a second interception line for the first robot against the target object is determined.

[0126] Optionally, the determination of decision variables executed by processor 301 includes:

[0127] The first decision variable is determined based on the interception status of each of the first robots against any one of the second robots;

[0128] A second decision variable is determined based on the interception status of each of the first robots toward the target object.

[0129] The electronic device provided in this embodiment of the invention can implement all the processes implemented by the robot control method in the above-described method embodiments, and can achieve the same beneficial effects. To avoid repetition, further details are omitted here.

[0130] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the robot control method provided in this invention and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0131] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (RON), or random access memory (RAN), etc.

[0132] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A robot control method, characterized in that, Includes the following steps: The first robot obtains the first interception probability of the second robot and the second interception probability of the target object at the current moment, wherein the target object is the object contested by the first robot and the second robot; Based on the first interception probability and the second interception probability, a distribution scheme for the first robot with respect to the second robot and the target object is determined. Specifically, based on the number of the first robot and the number of the second robot, a quantity constraint is determined; based on the position distribution of the first robot at the current moment, the position distribution probability of the second robot, and the speed of the first robot, a first interception line is determined for the first robot against the second robot; based on the position distribution of the first robot at the current moment, the position distribution probability of the target object, and the speed of the first robot, a second interception line is determined for the first robot against the target object, and a distance constraint is determined based on the first and second interception lines; based on the quantity constraint and the distance constraint, constraint conditions are determined; based on the interception state of each first robot against any second robot, a first decision variable is determined; based on the interception state of each first robot against the target object, a second decision variable is determined; and based on the first interception probability and the second interception probability, a first objective function is determined. Based on the decision variables, a second objective function is determined; based on the constraints, the first objective function, and the second objective function, an allocation strategy optimization model is determined; based on the allocation strategy optimization model, an allocation scheme for the first robot to the second robot and the target object is determined. The first robot is controlled according to the allocation scheme.

2. The robot control method as described in claim 1, characterized in that, The process of obtaining the first robot's first interception probability against the second robot and the second interception probability against the target object at the current moment includes: Obtain the position distribution of the first robot at the current moment, the position distribution probability of the second robot, and the position distribution probability of the target object; Based on the position distribution of the first robot at the current moment and the position distribution probability of the second robot, determine the first interception probability of the first robot against the second robot; Based on the position distribution of the first robot at the current moment and the position distribution probability of the target object, the second interception probability of the first robot for the target object is determined.

3. The robot control method as described in claim 1, characterized in that, The step of determining the allocation quantity constraint based on the number of the first robot and the number of the second robot includes: It is determined that at least one of the first robots is assigned to the target object; The number of the first robots assigned to each second robot is less than or equal to 1; Determine that the first robot is fully allocated.

4. A robot control device, characterized in that, The device comprises: The acquisition module is used to acquire the first interception probability of the first robot against the second robot and the second interception probability of the target object at the current moment, wherein the target object is the object contested by the first robot and the second robot; The determination module is used to determine the allocation scheme of the first robot for the second robot and the target object based on the first interception probability and the second interception probability. Specifically, it determines the allocation quantity constraint based on the number of the first robot and the number of the second robot; it determines the first interception line of the first robot for the second robot based on the position distribution of the first robot at the current time, the position distribution probability of the second robot, and the speed of the first robot; it determines the second interception line of the first robot for the target object based on the position distribution of the first robot at the current time, the position distribution probability of the target object, and the speed of the first robot, and determines the distance constraint based on the first interception line and the second interception line; it determines the constraint condition based on the allocation quantity constraint and the distance constraint; it determines the first decision variable based on the interception state of each first robot for any second robot; it determines the second decision variable based on the interception state of each first robot for the target object; it determines the first objective function based on the first interception probability and the second interception probability; it determines the second objective function based on the decision variable; it determines the allocation strategy optimization model based on the constraint condition, the first objective function, and the second objective function; and it determines the allocation scheme of the first robot for the second robot and the target object based on the allocation strategy optimization model. The control module is used to control the first robot according to the allocation scheme.

5. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the robot control method as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the robot control method as described in any one of claims 1 to 3.

Images