Obstacle avoidance control method and device of nuclear power wiping robot and electronic equipment

Abstract

The invention is suitable for the technical field of robot obstacle avoidance, and provides an obstacle avoidance control method and device for a nuclear power wiping robot and electronic equipment, and the method comprises the steps: determining a target motion state of the nuclear power wiping robot when it is detected that an obstacle exists in the motion direction of the nuclear power wiping robot, the target motion state is determined according to the obstacle information of the obstacle and the real-time motion state of the nuclear power wiping robot and is used for indicating the motion state that the nuclear power wiping robot should reach; taking the target motion state as the input of a pre-trained adjustment network, and obtaining a target output by the adjustment network to obtain a target control quantity; and according to the target control quantity, a driving motor is controlled to control the nuclear power wiping robot to perform obstacle avoidance motion, and the driving motor is a motor corresponding to a driving wheel of the nuclear power wiping robot. The movement stability of obstacle avoidance of the nuclear power wiping robot can be improved.

Description

Technical Field

[0001] The present application belongs to the field of robot obstacle avoidance technology, and in particular to an obstacle avoidance control method, device and electronic equipment for a nuclear power cleaning robot. Background Art

[0002] During the operation of a nuclear power plant, a large amount of cooling water passes through the reactor pool to maintain the normal temperature of the reactor. During the cooling water circulation process, nuclear waste is usually deposited on the bottom of the reactor pool. In order to ensure the cleanliness of the internal environment of the reactor pool, when the reactor is shut down, it is usually necessary to clean the reactor pool and then wipe the residual water at the bottom of the pool to prevent the residual water that may contain radioactivity from corroding the reactor equipment and causing pollution. In order to improve the safety of wiping the residual water in the reactor pool, nuclear power wiping robots are currently usually used to replace manual labor to clean and wipe the reactor pool.

[0003] At present, when encountering an obstacle, the nuclear power wiping robot is usually controlled to slow down to avoid the obstacle and then accelerate. However, since there are usually many nuclear power equipment in the reactor pool, in order to reduce the probability of safety accidents, the obstacle avoidance control of the nuclear power wiping robot has more stringent stability requirements. That is, the existing obstacle avoidance control method through sudden speed change is difficult to meet the obstacle avoidance control requirements of the nuclear power wiping robot in the nuclear power scenario. Summary of the invention

[0004] The embodiments of the present application provide an obstacle avoidance control method, device and electronic equipment for a nuclear power wiping robot, which can improve the movement stability of the nuclear power wiping robot in avoiding obstacles.

[0005] In a first aspect, an embodiment of the present application provides an obstacle avoidance control method for a nuclear power cleaning robot, comprising:

[0006] In the case where an obstacle is detected in the moving direction of the nuclear power wiping robot, a target moving state of the nuclear power wiping robot is determined, wherein the target moving state is determined according to the obstacle information of the obstacle and the real-time moving state of the nuclear power wiping robot, and is used to indicate the moving state that the nuclear power wiping robot should reach;

[0007] The target motion state is used as the input of the pre-trained regulation network to obtain the target control amount output by the regulation network, and the regulation network is used to analyze the control amount required for the nuclear power wiping robot to smoothly reach the target motion state to obtain the target control amount;

[0008] The driving motor is controlled according to the target control amount to control the nuclear power wiping robot to perform obstacle avoidance movement, and the driving motor is a motor corresponding to the driving wheel of the nuclear power wiping robot.

[0009] In a possible implementation manner of the first aspect, determining the target motion state of the nuclear power wiping robot includes:

[0010] Performing dynamic window calculation according to the real-time motion state and the obstacle information to obtain the obstacle avoidance path and obstacle avoidance motion speed of the nuclear power wiping robot;

[0011] The target motion state is determined according to the obstacle avoidance path and the obstacle avoidance motion speed.

[0012] In a possible implementation of the first aspect, performing dynamic window calculation according to the real-time motion state and the obstacle information to obtain an obstacle avoidance path and an obstacle avoidance motion speed of the nuclear power wiping robot includes:

[0013] Determine a plurality of candidate motion speeds and candidate paths corresponding to the candidate motion speeds according to the motion model of the nuclear power wiping robot and the real-time motion state;

[0014] Evaluate each candidate path by using a set evaluation function and the obstacle information to obtain a score corresponding to each candidate path;

[0015] The obstacle avoidance path and the obstacle avoidance movement speed of the nuclear power wiping robot are determined according to the candidate path with the highest score and the corresponding candidate movement speed.

[0016] In a possible implementation manner of the first aspect, controlling the drive motor according to the target control amount includes:

[0017] The drive motor is subjected to feedforward control and / or feedback control according to the target control amount.

[0018] In a possible implementation manner of the first aspect, performing feedforward control and / or feedback control on the drive motor according to the target control amount includes:

[0019] When the nuclear power wiping robot is in the water absorption operation stage, the drive motor is subjected to the feedforward control and the feedback control according to the target control amount;

[0020] When the nuclear power wiping robot is in a non-water absorption stage, the drive motor is subjected to the feedforward control or the feedback control according to the target control amount.

[0021] In a possible implementation of the first aspect, when an obstacle is detected in the movement direction of the nuclear power wiping robot, determining the target movement state of the nuclear power wiping robot includes:

[0022] When the nuclear power wiping robot is in the water absorption operation stage and the obstacle is detected in the movement direction of the nuclear power wiping robot, the target movement state of the nuclear power wiping robot is determined at a set first frequency;

[0023] When the nuclear power wiping robot is in the non-water absorption operation stage and the obstacle is detected in the movement direction of the nuclear power wiping robot, the target movement state of the nuclear power wiping robot is determined by a set second frequency, and the second frequency is lower than the first frequency.

[0024] In a possible implementation of the first aspect, before determining the target motion state of the nuclear power wiping robot when an obstacle is detected in the motion direction of the nuclear power wiping robot, the method further includes:

[0025] According to the environmental map of the reactor pool and the real-time motion state of the nuclear power wiping robot, it is detected whether there is the obstacle in the motion direction of the nuclear power wiping robot, and / or, by using a ranging sensor, it is detected whether there is the obstacle in the motion direction of the nuclear power wiping robot, and the environmental map is used to indicate the obstacles existing in the reactor pool.

[0026] In a second aspect, an embodiment of the present application provides an obstacle avoidance control device for a nuclear power wiping robot, comprising:

[0027] A target motion state determination module is used to determine the target motion state of the nuclear power wiping robot when an obstacle is detected in the motion direction of the nuclear power wiping robot. The target motion state is determined according to the obstacle information of the obstacle and the real-time motion state of the nuclear power wiping robot, and is used to indicate the motion state that the nuclear power wiping robot should reach;

[0028] A target control amount determination module is used to use the target motion state as the input of a pre-trained regulation network to obtain the target control amount output by the regulation network, wherein the regulation network is used to analyze the control amount required for the nuclear power wiping robot to smoothly reach the target motion state to obtain the target control amount;

[0029] The obstacle avoidance control module is used to control the driving motor according to the target control amount to control the nuclear power wiping robot to perform obstacle avoidance movement. The driving motor is the motor corresponding to the driving wheel of the nuclear power wiping robot.

[0030] In a third aspect, an embodiment of the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the obstacle avoidance control method for the nuclear power wiping robot described in the first aspect are implemented.

[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the obstacle avoidance control method of the nuclear power wiping robot described in the first aspect above.

[0032] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the obstacle avoidance control method of the nuclear power wiping robot described in the first aspect above.

[0033] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0034] In the embodiment of the present application, when an obstacle is detected in the direction of motion of the nuclear power wiping robot, the target motion state of the nuclear power wiping robot is first determined based on the obstacle information of the obstacle and the real-time motion state of the nuclear power wiping robot, and the target motion state is the motion state that the nuclear power wiping robot should reach to avoid the obstacle. Since the adjustment network can analyze the control amount required for the nuclear power wiping robot to smoothly reach the target motion state, the target control amount corresponding to the target motion state is obtained through the adjustment network analysis, and then the driving motor of the nuclear power wiping robot is controlled according to the target control amount, so that the nuclear power wiping robot can be controlled to smoothly change the motion state of the nuclear power wiping robot, effectively avoiding the impact and vibration caused by the sudden change of the motion state of the nuclear power wiping robot, and improving the motion stability of the nuclear power wiping robot in the process of avoiding obstacles, thereby reducing the risk of collision between the nuclear power wiping robot and obstacles such as nuclear power equipment, and effectively improving nuclear power safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0036] Figure 1 It is a flow chart of an obstacle avoidance control method for a nuclear power wiping robot provided in one embodiment of the present application;

[0037] Figure 2 It is a structural schematic diagram of an obstacle avoidance control device of a nuclear power wiping robot provided in an embodiment of the present application;

[0038] Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0040] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0041] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0042] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0043] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways.

[0044] Embodiment 1:

[0045] Figure 1 A schematic flow chart of an obstacle avoidance control method for a nuclear power cleaning robot provided in an embodiment of the present application is shown, and is described in detail as follows:

[0046] S101. When an obstacle is detected in the moving direction of the nuclear power wiping robot, the target motion state of the nuclear power wiping robot is determined. The target motion state is determined based on the obstacle information of the obstacle and the real-time motion state of the nuclear power wiping robot, and is used to indicate the motion state that the nuclear power wiping robot should reach.

[0047] The movement directions of the nuclear power wiping robot include but are not limited to forward, backward, left turn and right turn.

[0048] It should be understood that the motion state of the nuclear power wiping robot includes but is not limited to information such as the motion speed, motion direction, motion trajectory (also called motion path), position and posture of the nuclear power wiping robot.

[0049] It should be understood that obstacle information includes but is not limited to information such as the location, size, posture, type and possible safety hazards of the obstacle.

[0050] It should be noted that the target motion state can be the motion state that the nuclear power wiping robot should reach at the next moment, or it can be the motion state that the nuclear power wiping robot should reach within the target time period after the current moment (such as within 2 seconds after the current moment), which can be set according to the actual application scenario. Optionally, the duration of the target time period can be determined according to the obstacle information (such as position and size) of the obstacle through a deep learning model or other intelligent algorithms, or it can be set or input by the user.

[0051] It should be understood that when determining the target motion state of the nuclear power wiping robot based on the real-time motion state of the nuclear power wiping robot and the obstacle information of the obstacle, the target motion state is determined based on the purpose of avoiding the obstacle. The process of controlling the nuclear power wiping robot from the real-time motion state to reach the target motion state is also the process of controlling the nuclear power wiping robot to avoid obstacles.

[0052] Optionally, when determining the target motion state, the obstacle avoidance path of the nuclear power wiping robot can be analyzed according to the real-time motion state and obstacle information through algorithms such as rule-based obstacle avoidance algorithms or deep learning algorithms, and then the target motion state of the nuclear power wiping robot is determined based on the analyzed obstacle avoidance path. The target motion state of the nuclear power wiping robot can also be determined by manual analysis or other methods, which can be specifically set according to the actual application scenario.

[0053] It should be understood that the method of detecting whether there are obstacles in the direction of movement of the nuclear power wiping robot can be set according to the actual application scenario, and no specific restrictions are made here. For example, the movement path of the nuclear power wiping robot can be set in advance according to the environmental map of the reactor pool, and the environmental map can reflect the obstacles existing in the reactor pool. Therefore, the movement path can be set in combination with the existing obstacles. In the process of controlling the nuclear power wiping robot to move according to the set movement path, it can be predicted whether there are obstacles in the direction of movement of the nuclear power wiping robot in combination with the real-time movement state of the nuclear power wiping robot, and when there are obstacles, the obstacle information of the obstacle can be obtained in combination with the environmental map.

[0054] In some embodiments, when an obstacle is detected in the direction of motion of the nuclear power wiping robot, and the distance between the obstacle and the nuclear power wiping robot is less than or equal to a distance threshold (such as 1 meter), the target motion state of the nuclear power wiping robot is determined to control the nuclear power wiping robot to avoid the obstacle. The distance threshold can be automatically determined by a deep learning model such as a large model or other intelligent algorithm based on information such as the nature and distribution of obstacles in the reactor pool, or can be set or input by the user, and is not specifically limited here.

[0055] In an embodiment of the present application, when an obstacle is detected in the movement direction of the nuclear power wiping robot, the movement state that the nuclear power wiping robot should reach to avoid the obstacle is determined based on the real-time movement state of the nuclear power wiping robot and the obstacle information of the obstacle, and the target movement state is obtained to control the movement of the nuclear power wiping robot according to the target movement state, thereby realizing obstacle avoidance control of the nuclear power wiping robot.

[0056] S102. Use the target motion state as the input of the pre-trained regulation network to obtain the target control quantity output by the regulation network. The regulation network is used to analyze the control quantity required for the nuclear power wiping robot to smoothly reach the target motion state to obtain the target control quantity.

[0057] It should be understood that the adjustment network can be constructed based on a multi-layer perceptron, a convolutional neural network, a recurrent neural network or a fuzzy neural network, and can be specifically configured according to actual application requirements.

[0058] The target control quantity is the physical quantity or parameter used to control the operation of the motor, such as voltage signal, current signal, output torque or input frequency.

[0059] The nuclear power wiping robot smoothly reaches the target motion state means that the nuclear power wiping robot can gradually adjust its motion state in a stable, continuous and non-dramatic manner, and finally reaches the target motion state.

[0060] In some embodiments, training data can be constructed based on the motion data of the nuclear power wiping robot in various operation stages and various motion states, and the adjustment network is trained through the training data, so that the adjustment network can better learn the mapping relationship between the motion state of the nuclear power wiping robot and the control amount of the driving motor during the training process, so that the pre-trained adjustment network can quickly and accurately analyze the control amount required for the nuclear power wiping robot to smoothly reach the target motion state from the current motion state, and obtain the required target control amount.

[0061] In some embodiments, the above-mentioned adjustment network can be a network constructed according to a radial basis function network (RBFN), and the radial basis function network has a strong nonlinear mapping ability, which can realize the modeling of the complex motion of the nuclear power wiping robot, that is, it can better handle nonlinear factors such as friction and load changes in the dynamics of the nuclear power wiping robot, so as to better approximate the target motion state of the nuclear power wiping robot, and predict a continuously and uniformly changing target control quantity. Furthermore, the drive motor is controlled based on the continuously and uniformly changing target control quantity output by the radial basis function network, which can better realize the smooth adjustment of the motor output of the drive motor, thereby realizing the smooth adjustment of the motion state of the nuclear power wiping robot.

[0062] In the embodiment of the present application, the control amount required for the nuclear power wiping robot to smoothly reach the target motion state is quickly and accurately analyzed through a pre-trained adjustment network, and the target control amount is obtained, so that the output of the drive motor of the nuclear power wiping robot can be smoothly adjusted according to the target control amount with higher accuracy, thereby smoothly adjusting the motion state of the nuclear power wiping robot, effectively reducing the probability of the nuclear power wiping robot generating impact and vibration due to changes in the motion state, which is beneficial to improving the stability and reliability of the obstacle avoidance motion of the nuclear power wiping robot.

[0063] S103. Control the driving motor according to the target control amount to control the nuclear power cleaning robot to perform obstacle avoidance movement. The driving motor is a motor corresponding to the driving wheel of the nuclear power cleaning robot.

[0064] It should be understood that when the nuclear power wiping robot includes at least two independent driving wheels, the regulation network will respectively predict the target control amount of the driving motor corresponding to each driving wheel, and control the corresponding driving motor based on the target control amount.

[0065] In the embodiment of the present application, when an obstacle is detected in the motion direction of the nuclear power wiping robot, the target motion state of the nuclear power wiping robot is first determined according to the obstacle information of the obstacle and the real-time motion state of the nuclear power wiping robot, and the target motion state is the motion state that the nuclear power wiping robot should reach in order to avoid the obstacle. Since the adjustment network can analyze the control amount required for the nuclear power wiping robot to smoothly reach the target motion state, the target control amount corresponding to the target motion state is obtained by adjusting the network analysis, and the drive motor of the nuclear power wiping robot is controlled according to the target control amount, and the output of the drive motor can be smoothly changed, so that the motion state of the nuclear power wiping robot can be smoothly changed in the process of controlling the nuclear power wiping robot to perform obstacle avoidance movement, effectively avoiding the impact and vibration of the nuclear power wiping robot caused by the sudden change of the motion state, and improving the motion stability of the nuclear power wiping robot during the obstacle avoidance movement, thereby reducing the risk of collision between the nuclear power wiping robot and obstacles such as nuclear power equipment, and effectively improving nuclear power safety.

[0066] In some embodiments, the above-mentioned determination of the target motion state of the above-mentioned nuclear power cleaning robot includes:

[0067] Dynamic window calculation is performed according to the above-mentioned real-time motion state and the above-mentioned obstacle information to obtain the obstacle avoidance path and obstacle avoidance motion speed of the above-mentioned nuclear power wiping robot.

[0068] The target motion state is determined according to the obstacle avoidance path and the obstacle avoidance motion speed.

[0069] The above-mentioned Dynamic Window Approach (DWA) is an algorithm for path planning and obstacle avoidance. The dynamic window operation calculates a dynamic window by considering the robot's speed and acceleration limits, as well as obstacles in the environment. The dynamic window operation evaluates all possible moves within the dynamic window to find the optimal path to avoid obstacles.

[0070] In order to improve the obstacle avoidance control effect of the nuclear power wiping robot, when an obstacle is detected in the movement direction of the nuclear power wiping robot, dynamic window operation can be performed according to the obstacle information of the existing obstacle and the real-time motion state of the nuclear power wiping robot. The optimal path and obstacle avoidance movement speed of the nuclear power wiping robot to avoid the obstacle are determined through dynamic window operation.

[0071] Since the dynamic window operation can fully consider the physical limitations and environmental conditions of the nuclear power wiping robot based on the real-time motion state and obstacle information of the nuclear power wiping robot when planning the path, and generate the obstacle avoidance path and obstacle avoidance motion speed that best suits the nuclear power wiping robot, therefore, the target motion state that the nuclear power wiping robot needs to achieve is determined according to the optimal path and obstacle avoidance motion speed obtained by the dynamic window operation, and the nuclear power wiping robot is subsequently controlled to perform obstacle avoidance motion based on the target motion state, which can ensure that the nuclear power wiping robot can avoid the obstacle safely and efficiently, and is conducive to improving the obstacle avoidance control effect of the nuclear power wiping robot.

[0072] In some embodiments, the above-mentioned dynamic window calculation is performed according to the above-mentioned real-time motion state and the above-mentioned obstacle information to obtain the obstacle avoidance path and obstacle avoidance motion speed of the above-mentioned nuclear power cleaning robot, including:

[0073] According to the motion model of the nuclear power wiping robot and the real-time motion state, a plurality of candidate motion speeds and candidate paths corresponding to the candidate motion speeds are determined.

[0074] Each of the candidate paths is evaluated by using a set evaluation function and the obstacle information to obtain a score corresponding to each of the candidate paths.

[0075] The obstacle avoidance path and the obstacle avoidance movement speed of the nuclear power wiping robot are determined based on the candidate path with the highest score and the corresponding candidate movement speed.

[0076] It should be understood that the motion model of the nuclear power wiping robot may include the law of change of the state parameters of the nuclear power wiping robot (such as position, speed, angular velocity and heading angle, etc.) over time, and may also include speed limit information such as the maximum speed, maximum angular velocity and maximum acceleration of the nuclear power wiping robot.

[0077] Specifically, after obtaining the motion model and real-time motion state of the nuclear power wiping robot, the various speeds that the nuclear power wiping robot may reach based on the current motion state (i.e., the real-time motion state) can be analyzed according to the motion model of the nuclear power wiping robot, thereby determining the range of motion speeds that the nuclear power wiping robot may reach under the constraints of its motion model and real-time motion state. This motion speed range can be regarded as a dynamic window.

[0078] After obtaining the dynamic window, the movement speed and angular velocity can be sampled within the dynamic window according to the set resolution (such as the speed resolution is 0.1 meters per second, and the angular velocity resolution is 0.05 radians per second) to obtain a series of candidate speed combinations. Then, for each speed combination, the motion trajectory of the nuclear power wiping robot when it moves under the speed combination is predicted based on the operation model of the nuclear power wiping robot.

[0079] It should be understood that the speed in the speed combination is the movement speed of the nuclear power wiping robot, reflecting the instantaneous rate of the nuclear power wiping robot in its forward direction, and the angular velocity is the rate at which the nuclear power wiping robot rotates around its reference point (such as the center point), reflecting the rate at which the heading angle of the nuclear power wiping robot changes over time. Through the speed and angular velocity in different speed combinations, different motion trajectories of the nuclear power wiping robot can be predicted. It can be considered that the speed in the speed combination is the above-mentioned candidate motion speed, and the motion trajectory corresponding to the speed combination is the above-mentioned candidate path.

[0080] In some embodiments, considering that the motion model of the nuclear power wiping robot is usually smooth, in order to better analyze the change of the angular velocity of the nuclear power wiping robot, the motion speed and angular velocity of the nuclear power wiping robot can be described by discrete single-axis linear velocity and angular velocity.

[0081] It should be understood that the set evaluation function can be set or input by the user, or can be obtained by analyzing the obstacle avoidance requirements of the nuclear power wiping robot in the reactor pool through a large model or other intelligent algorithms.

[0082] Optionally, the set evaluation function may include multiple evaluation factors and the weight corresponding to each evaluation factor. When evaluating the candidate path using the set evaluation function and the above-mentioned obstacle information, the score corresponding to each evaluation factor may be calculated, and then the score corresponding to the candidate path may be obtained based on each first score and the corresponding weight.

[0083] As an example, the evaluation function may include evaluation factors such as obstacle avoidance capability, heading target, and obstacle avoidance efficiency. The obstacle avoidance capability is the ability of the nuclear power wiping robot to avoid obstacles, and the score corresponding to the obstacle avoidance capability can be determined according to the distance between the nuclear power wiping robot and the obstacle; the heading target is the ability of the nuclear power wiping robot to move toward the original moving target point, and the score corresponding to the heading target can be determined according to the angle difference between the heading and the target point when the nuclear power wiping robot moves to the end of the candidate path; the obstacle avoidance efficiency is the efficiency of the nuclear power wiping robot to avoid the obstacle, and the score corresponding to the obstacle avoidance efficiency can be determined according to the candidate movement speed and the candidate path.

[0084] In this example, the evaluation function can be expressed as follows:

[0085] G(ν,ω)=α*heading(ν,ω)+β*dist(ν,ω)+γ*velpcity(ν,ω)

[0086] ν,ω represent the speed and angular velocity corresponding to the candidate path, G(ν,ω) represents the score corresponding to the candidate path; heading(ν,ω) represents the score corresponding to the target, α represents the weight corresponding to the target; dist(ν,ω) represents the score corresponding to the obstacle avoidance ability, β represents the weight corresponding to the obstacle avoidance ability; velpcity(ν,ω) represents the score corresponding to the obstacle avoidance efficiency, γ represents the weight corresponding to the obstacle avoidance efficiency.

[0087] In other embodiments, in order to fully ensure nuclear power safety, the evaluation elements in the evaluation function may also include at least one of safety and environmental impact. The safety, i.e., the safety of the nuclear power wiping robot in avoiding obstacles along the candidate path, can be determined based on the possibility of collision with the obstacle when the nuclear power wiping robot moves along the candidate path, or based on the duration of exposure to high radiation areas when the wiping robot moves along the candidate path; the environmental impact may be the degree of impact on the surrounding environment caused by vibration and noise generated when the nuclear power wiping robot avoids obstacles along the candidate path, or the possibility of leakage or diffusion of radioactive materials when the nuclear power wiping robot avoids obstacles along the candidate path.

[0088] In some embodiments, after determining the obstacle avoidance path and obstacle avoidance movement speed of the nuclear power wiping robot according to the candidate path with the highest score and its corresponding candidate movement speed, when determining the target movement state according to the obstacle avoidance path and obstacle avoidance movement speed, the determined target movement state may include angle difference, distance and obstacle avoidance movement speed, the angle difference refers to the angle difference between the heading angle of the nuclear power wiping robot moving along the obstacle avoidance path to the end of the path and the target point, and the distance refers to the distance between the nuclear power wiping robot and the obstacle when performing obstacle avoidance movement along the obstacle avoidance path. Correspondingly, the input of the adjustment network includes the angle difference, distance and obstacle avoidance movement speed.

[0089] It should be noted that during the analysis process, the adjustment network usually maps the angle difference, distance and obstacle avoidance motion speed in vector form from low dimension to high dimension through the hidden layer. At this time, the number of hidden layers in the adjustment network should be greater than the number of input data, that is, the number of hidden layers should be greater than 3.

[0090] In an embodiment of the present application, multiple feasible candidate paths and candidate movement speeds are predicted through dynamic window operations, and then the candidate path with the best obstacle avoidance effect is determined through an evaluation function as the obstacle avoidance path of the nuclear power wiping robot, thereby determining the movement speed and path adopted by the nuclear power wiping robot to avoid obstacles, thereby ensuring the obstacle avoidance effect of the nuclear power wiping robot.

[0091] In some embodiments, controlling the drive motor according to the target control amount includes:

[0092] The drive motor is subjected to feedforward control and / or feedback control according to the target control amount.

[0093] The above-mentioned feedforward control is an open-loop control method that performs compensation according to disturbances (such as changes in load).

[0094] The above-mentioned feedback control is a closed-loop control method that measures the output signal of the motor (such as speed or position, etc.), compares it with the expected signal, generates an error signal, and then adjusts the input control signal (such as voltage or current) according to the error signal to control the actual output signal of the motor to conform to the expected signal.

[0095] Since the nuclear power wiping robot is usually affected by factors such as load and reactor pool radiation during movement, the actual speed of its drive motor deviates from the expected speed, thereby affecting the movement speed of the nuclear power wiping robot. Therefore, when the drive motor is controlled according to the target control amount, the drive motor can be feedback controlled according to the target drive amount. Since feedback control can continuously obtain (such as once per second) the real-time output (such as speed or output torque, etc.) of the drive motor, the drive motor is adjusted according to the deviation between the latest real-time output and the expected output, and the closed-loop control is improved to better eliminate the deviation of the actual output of the motor. Therefore, feedback control of the drive motor according to the target control amount can better ensure the accuracy of the actual output of the drive motor and realize accurate control of the obstacle avoidance movement of the nuclear power wiping robot.

[0096] Alternatively, considering that the computing resources of the nuclear power wiping robot are usually limited, in order to reduce the computational complexity and control complexity of the nuclear power wiping robot during obstacle avoidance, the drive motor can be feedforward controlled according to the target control amount. Since the open-loop feedforward control can predict disturbances in advance and compensate for disturbances, and there is no need to continuously pay attention to the deviation between the actual output and the expected output of the drive motor, the feedforward control of the drive motor according to the target control amount can reduce the complexity of the control process of the drive motor while better suppressing the operation deviation of the drive motor caused by disturbances and ensuring the accuracy of the actual output of the drive motor.

[0097] In some embodiments, in order to maximize the control effect of the drive motor, when controlling the drive motor according to the target control quantity, the drive motor can also be subjected to a composite control including feedforward control and feedback control. The control method combining feedforward and feedback can ensure the control accuracy, stability and response speed of the nuclear power wiping robot during the movement process, thereby ensuring that the nuclear power wiping robot can complete the task efficiently and stably.

[0098] In an embodiment of the present application, when the drive motor is controlled according to the target control amount to control the nuclear power wiping robot to perform obstacle avoidance movement, the drive motor will be feedforward controlled and / or feedback controlled according to actual needs. The feedforward control and / or feedback control can reduce the impact of factors such as the reactor pool environment on the drive motor, thereby ensuring the control effect of the drive motor and thus ensuring the obstacle avoidance performance of the nuclear power wiping robot.

[0099] In some embodiments, the feedforward control and / or feedback control of the drive motor according to the target control amount includes:

[0100] When the nuclear power wiping robot is in the water absorption operation stage, the drive motor is subjected to the feedforward control and the feedback control according to the target control amount.

[0101] When the nuclear power wiping robot is in a non-water absorption stage, the drive motor is subjected to the feedforward control or the feedback control according to the target control amount.

[0102] The above-mentioned water absorption operation stage refers to the operation stage in which the nuclear power wiping robot extracts the residual water at the bottom of the reactor pool through equipment with strong adsorption capacity such as vacuum motors during movement.

[0103] The above-mentioned non-water absorption operation stage refers to the stage in which the nuclear power wiping robot performs operations other than extracting residual water (such as wiping or dose detection, etc.) during the movement, such as the mapping operation stage, the wiping operation stage or the detection operation stage.

[0104] Since the nuclear power wiping robot needs to absorb the residual water at the bottom of the reactor pool during the water absorption operation stage, the load of the nuclear power wiping robot will continue to increase during the work process, and the ground conditions will usually change to a certain extent, causing the load of the nuclear power wiping robot to change continuously, that is, there is a continuous disturbance. Therefore, when controlling the nuclear power wiping robot to perform obstacle avoidance movement, if it is currently in the water absorption operation stage, the drive motor can be subjected to a composite control combining feedforward control and feedback control according to the target control amount. Since the feedforward control can compensate in advance the impact of disturbances such as load changes of the nuclear power wiping robot on the drive motor during the obstacle avoidance movement by predicting, and the feedback control can continuously obtain the latest real-time output of the drive motor, adjust the drive motor according to the deviation between the latest real-time output and the expected expectation, and further eliminate the output deviation of the drive motor, therefore, the control method combining feedforward control and feedback control can better guarantee the motion control accuracy and control stability of the nuclear power wiping robot in the water absorption operation stage during the obstacle avoidance movement, thereby ensuring that the nuclear power wiping robot can perform obstacle avoidance movement efficiently and stably.

[0105] Among them, since the load and ground conditions of the nuclear power wiping robot change little when the nuclear power wiping robot is performing operations such as wiping or testing, that is, the load changes little, and the degree of influence on the actual output of the target motor is low. Therefore, when controlling the nuclear power wiping robot to perform obstacle avoidance movement, when the nuclear power wiping robot is currently in a non-water absorption operation stage (that is, when the nuclear power wiping robot is in any operation stage other than the water absorption operation stage), the drive motor can be feedforward controlled or feedback controlled according to the target control amount. Among them, the control mode of the nuclear power wiping robot can be determined according to actual needs, for example, the control mode of the nuclear power wiping robot can be determined as feedforward control or feedback control according to the current operation stage of the nuclear power wiping robot, the disturbance status of the current operation stage, or the computing resources of the nuclear power wiping robot.

[0106] For example, when there is a large disturbance in the current operation stage of the nuclear power wiping robot (such as the frequency of the disturbance is greater than or equal to the frequency threshold, such as 0.4), or when the available computing resources of the nuclear power wiping robot are lower than the set computing threshold, the nuclear power wiping robot can be feedforward controlled according to the target control quantity; otherwise, the nuclear power wiping robot can be feedback controlled according to the target control quantity.

[0107] In an embodiment of the present application, when the nuclear power wiping robot is in the water absorption operation stage with continuous disturbance, the drive motor is subjected to a composite control including feedforward control and feedback control according to the target control quantity; when the nuclear power wiping robot is in the non-water absorption operation stage, the drive motor is subjected to a single control according to the target control quantity. This can better determine the motor control mode of the obstacle avoidance movement according to the disturbance situation in the process of controlling the nuclear power wiping robot to perform obstacle avoidance movement. While improving the accuracy of the obstacle avoidance control of the nuclear power wiping robot, it can reasonably control the complexity and control cost of the obstacle avoidance control of the nuclear power wiping robot to achieve the best obstacle avoidance control effect.

[0108] In some embodiments, when an obstacle is detected in the moving direction of the nuclear power cleaning robot, determining the target moving state of the nuclear power cleaning robot includes:

[0109] When the nuclear power wiping robot is in the water absorption operation stage and the obstacle is detected to exist in the movement direction of the nuclear power wiping robot, the target movement state of the nuclear power wiping robot is determined with a set first frequency.

[0110] When the nuclear power wiping robot is in the non-water absorption operation stage and the obstacle is detected in the movement direction of the nuclear power wiping robot, the target movement state of the nuclear power wiping robot is determined by a set second frequency, and the second frequency is lower than the first frequency.

[0111] Since the nuclear power wiping robot needs to absorb residual water at the bottom of the reactor pool during the water absorption operation stage, the load of the nuclear power wiping robot will usually continue to increase during the water absorption operation, causing continuous interference to the drive motor of the nuclear power wiping robot, which has a significant impact on the motion state of the nuclear power wiping robot. Therefore, in an embodiment of the present application, when an obstacle is detected in the motion direction of the nuclear power wiping robot, if the nuclear power wiping robot is currently in the water absorption operation stage, a higher first frequency is set (such as 5 seconds each time) to determine the target motion state of the nuclear power wiping robot, that is, in the process of obstacle avoidance control of the nuclear power wiping robot, the obstacle avoidance motion speed and motion direction of the nuclear power wiping robot are updated at a higher first frequency, so that it can respond to environmental changes and changes in the real-time motion state of the nuclear power wiping robot more promptly, reduce the risk of collision, and help the nuclear power wiping robot that is continuously interfered with to maintain high safety and flexibility in the complex environment of the reactor pool.

[0112] Taking into account that the nuclear power wiping robot is less disturbed during movement when it is in the non-water absorption operation stage, the target motion state of the nuclear power wiping robot can be determined by setting a lower second frequency (such as 10 seconds each time), that is, in the process of obstacle avoidance control of the nuclear power wiping robot, the obstacle avoidance motion speed and motion direction of the nuclear power wiping robot are updated with a lower second frequency. While ensuring the accuracy of the nuclear power wiping robot's obstacle avoidance motion, the computing resources occupied by the obstacle avoidance control are reduced.

[0113] In an embodiment of the present application, taking into account the different degrees of interference with the driving motor of the nuclear power wiping robot in various operating stages, when an obstacle is detected in the movement direction of the nuclear power wiping robot, the frequency of updating the target motion state is determined in combination with the current operating stage of the nuclear power wiping robot, that is, the update frequency of the target motion state is determined according to the degree of interference with the driving motor, and the target motion state is determined based on the update frequency, thereby controlling the speed of responding to environmental changes during the obstacle avoidance movement of the nuclear power wiping robot, thereby improving the flexibility and safety of the obstacle avoidance movement of the nuclear power wiping robot.

[0114] In some embodiments, when an obstacle is detected in the moving direction of the nuclear power cleaning robot, before determining the target moving state of the nuclear power cleaning robot, the method further includes:

[0115] According to the environmental map of the reactor pool and the real-time motion state of the nuclear power wiping robot, it is detected whether there are the above-mentioned obstacles in the motion direction of the nuclear power wiping robot, and / or, by using a ranging sensor, it is detected whether there are the above-mentioned obstacles in the motion direction of the nuclear power wiping robot. The above-mentioned environmental map is used to indicate the obstacles existing in the above-mentioned reactor pool.

[0116] Since the environmental map can reflect the obstacles existing in the entire reactor pool, that is, it reflects the global information of the reactor pool, and the real-time motion state of the nuclear power wiping robot can better reflect the motion conditions such as the current position and motion speed of the nuclear power wiping robot, when detecting whether there are obstacles in the motion direction of the nuclear power wiping robot, the layout of the environment surrounding the nuclear power wiping robot can be better understood based on the global map and the real-time motion state of the nuclear power wiping robot, so that it can be comprehensively and accurately judged whether there are obstacles in the motion direction of the nuclear power wiping robot.

[0117] Alternatively, in order to improve the real-time performance of obstacle detection, a ranging sensor (such as an ultrasonic ranging sensor, etc.) mounted on the nuclear power wiping robot can be used to detect whether there is an obstacle in the direction of its movement. The ranging sensor can detect whether there is an obstacle in the direction of movement and the distance of the existing obstacle by transmitting and receiving signals in real time, thereby being able to detect in real time whether there is an obstacle in the direction of movement, so that when an obstacle is detected, the nuclear power wiping robot can be controlled in time to perform obstacle avoidance movement, which is beneficial to improving the obstacle avoidance effect of the nuclear power wiping robot in a reactor pool with a complex environment.

[0118] In other embodiments, whether there are obstacles in the direction of movement of the nuclear power wiping robot can be detected by combining environmental map detection with distance sensor detection. Since preliminary detection can be performed at the global level through environmental map and the real-time movement state of the nuclear power wiping robot, and real-time accurate detection can be performed through the distance sensor, therefore, by combining the two to detect whether there are obstacles in the direction of movement of the nuclear power wiping robot, the nuclear power wiping robot can be better controlled to avoid obstacles in the case of dynamic obstacles in the reactor pool, effectively enhancing the navigation and obstacle avoidance capabilities of the nuclear power wiping robot in the complex reactor pool, thereby improving the obstacle avoidance effect of the nuclear power wiping robot.

[0119] In some embodiments, a target detection method can be used to detect whether there are obstacles in the direction of movement of the nuclear power wiping robot. The target detection method is a detection method that matches the current operation stage of the nuclear power wiping robot. It should be understood that the detection method can include the above-mentioned environmental map detection and ranging sensor detection. As an example, when the current operation stage of the nuclear power wiping robot is the water absorption operation stage, the target detection method can include environmental map detection and ranging sensor detection, that is, by combining environmental map detection with ranging sensor detection to detect whether there are obstacles in the direction of movement of the nuclear power wiping robot; when the current operation stage of the nuclear power wiping robot is the non-water absorption operation stage, the target detection method can be environmental map detection or ranging sensor detection.

[0120] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0121] Embodiment 2:

[0122] Corresponding to the obstacle avoidance control method of the nuclear power wiping robot described in the above embodiment, Figure 2 A structural block diagram of the obstacle avoidance control device of the nuclear power wiping robot provided in an embodiment of the present application is shown. For the sake of convenience of explanation, only the parts related to the embodiment of the present application are shown.

[0123] Reference Figure 2 The device includes: a target motion state determination module 21, a target control amount determination module 22 and an obstacle avoidance control module 23.

[0124] The target motion state determination module 21 is used to determine the target motion state of the nuclear power wiping robot when an obstacle is detected in the motion direction of the nuclear power wiping robot. The target motion state is determined based on the obstacle information of the obstacle and the real-time motion state of the nuclear power wiping robot, and is used to indicate the motion state that the nuclear power wiping robot should reach.

[0125] The target control quantity determination module 22 is used to use the above-mentioned target motion state as the input of the pre-trained regulation network to obtain the target control quantity output by the above-mentioned regulation network. The above-mentioned regulation network is used to analyze the control quantity required for the above-mentioned nuclear power wiping robot to smoothly reach the above-mentioned target motion state to obtain the above-mentioned target control quantity.

[0126] The obstacle avoidance control module 23 is used to control the driving motor according to the above-mentioned target control amount to control the above-mentioned nuclear power wiping robot to perform obstacle avoidance movement. The above-mentioned driving motor is the motor corresponding to the driving wheel of the above-mentioned nuclear power wiping robot.

[0127] In the embodiment of the present application, when an obstacle is detected in the motion direction of the nuclear power wiping robot, the target motion state of the nuclear power wiping robot is first determined according to the obstacle information of the obstacle and the real-time motion state of the nuclear power wiping robot, and the target motion state is the motion state that the nuclear power wiping robot should reach in order to avoid the obstacle. Since the adjustment network can analyze the control amount required for the nuclear power wiping robot to smoothly reach the target motion state, the target control amount corresponding to the target motion state is obtained by adjusting the network analysis, and the drive motor of the nuclear power wiping robot is controlled according to the target control amount, and the output of the drive motor can be smoothly changed, so that the motion state of the nuclear power wiping robot can be smoothly changed in the process of controlling the nuclear power wiping robot to perform obstacle avoidance movement, effectively avoiding the impact and vibration of the nuclear power wiping robot caused by the sudden change of the motion state, and improving the motion stability of the nuclear power wiping robot during the obstacle avoidance movement, thereby reducing the risk of collision between the nuclear power wiping robot and obstacles such as nuclear power equipment, and effectively improving nuclear power safety.

[0128] In some embodiments, the target motion state determination module 21 includes:

[0129] The dynamic window operation unit is used to perform dynamic window operation according to the above-mentioned real-time motion state and the above-mentioned obstacle information to obtain the obstacle avoidance path and obstacle avoidance motion speed of the above-mentioned nuclear power wiping robot.

[0130] The target motion state determination unit is used to determine the target motion state according to the obstacle avoidance path and the obstacle avoidance motion speed.

[0131] In some embodiments, the target motion state determination module 21 further includes:

[0132] The candidate motion speed determination unit is used to determine multiple candidate motion speeds and candidate paths corresponding to the candidate motion speeds according to the motion model of the nuclear power wiping robot and the real-time motion state.

[0133] The evaluation unit is used to evaluate each of the candidate paths by using a set evaluation function and the obstacle information to obtain a score corresponding to each of the candidate paths.

[0134] The obstacle avoidance motion speed determination unit is used to determine the obstacle avoidance path and the obstacle avoidance motion speed of the nuclear power wiping robot according to the candidate path with the highest score and the corresponding candidate motion speed.

[0135] In some embodiments, the obstacle avoidance control module 23 includes:

[0136] The motor control unit is used to perform feedforward control and / or feedback control on the drive motor according to the target control amount.

[0137] In some embodiments, the obstacle avoidance control module 23 includes:

[0138] The composite control unit is used to perform the feedforward control and the feedback control on the driving motor according to the target control amount when the nuclear power wiping robot is in the water absorption operation stage.

[0139] A single control unit is used to perform the above-mentioned feedforward control or the above-mentioned feedback control on the above-mentioned driving motor according to the above-mentioned target control amount when the above-mentioned nuclear power wiping robot is in a non-water absorption stage.

[0140] In some embodiments, the target motion state determination module 21 includes:

[0141] The first sampling unit is used to determine the target motion state of the nuclear power wiping robot at a set first frequency when the nuclear power wiping robot is in the water absorption operation stage and the obstacle is detected in the motion direction of the nuclear power wiping robot.

[0142] The second sampling unit is used to determine the target motion state of the nuclear power wiping robot with a set second frequency when the nuclear power wiping robot is in a non-water absorption operation stage and the obstacle is detected in the motion direction of the nuclear power wiping robot. The second frequency is lower than the first frequency.

[0143] In some embodiments, the obstacle avoidance control device of the nuclear power cleaning robot further includes:

[0144] A detection module is used to detect whether the above-mentioned obstacles exist in the movement direction of the above-mentioned nuclear power wiping robot according to the environmental map of the reactor pool and the above-mentioned real-time movement state of the above-mentioned nuclear power wiping robot, and / or to detect whether the above-mentioned obstacles exist in the movement direction of the above-mentioned nuclear power wiping robot through a ranging sensor, and the above-mentioned environmental map is used to indicate the obstacles existing in the above-mentioned reactor pool.

[0145] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0146] Embodiment three:

[0147] Figure 3 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 As shown, the electronic device 3 of this embodiment includes: at least one processor 30 ( Figure 3Only one processor is shown in the figure), a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30, wherein the processor 30 implements the steps in any of the above-mentioned method embodiments when executing the computer program 32.

[0148] The electronic device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will appreciate that Figure 3 It is only an example of the electronic device 3 and does not constitute a limitation on the electronic device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0149] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0150] In some embodiments, the memory 31 may be an internal storage unit of the electronic device 3, such as a hard disk or memory of the electronic device 3. In other embodiments, the memory 31 may also be an external storage device of the electronic device 3, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 3. Further, the memory 31 may also include both an internal storage unit of the electronic device 3 and an external storage device. The memory 31 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0151] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0152] An embodiment of the present application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps in any of the above-mentioned method embodiments when executing the computer program.

[0153] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0154] An embodiment of the present application provides a computer program product. When the computer program product runs on an electronic device, the electronic device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0155] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0156] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0157] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0158] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0159] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0160] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An obstacle avoidance control method for a nuclear power wiping robot, characterized in that: include: In the case where an obstacle is detected in the moving direction of the nuclear power wiping robot, a target moving state of the nuclear power wiping robot is determined, wherein the target moving state is determined according to the obstacle information of the obstacle and the real-time moving state of the nuclear power wiping robot, and is used to indicate the moving state that the nuclear power wiping robot should reach; The target motion state is used as the input of the pre-trained regulation network to obtain the target control amount output by the regulation network, and the regulation network is used to analyze the control amount required for the nuclear power wiping robot to smoothly reach the target motion state to obtain the target control amount; The driving motor is controlled according to the target control amount to control the nuclear power wiping robot to perform obstacle avoidance movement, and the driving motor is a motor corresponding to the driving wheel of the nuclear power wiping robot.

2. The obstacle avoidance control method of the nuclear power wiping robot according to claim 1, characterized in that: Determining the target motion state of the nuclear power wiping robot includes: Performing dynamic window calculation according to the real-time motion state and the obstacle information to obtain the obstacle avoidance path and obstacle avoidance motion speed of the nuclear power wiping robot; The target motion state is determined according to the obstacle avoidance path and the obstacle avoidance motion speed.

3. The obstacle avoidance control method of the nuclear power wiping robot as claimed in claim 2, characterized in that: The method of performing dynamic window calculation according to the real-time motion state and the obstacle information to obtain the obstacle avoidance path and obstacle avoidance motion speed of the nuclear power wiping robot includes: Determine a plurality of candidate motion speeds and candidate paths corresponding to the candidate motion speeds according to the motion model of the nuclear power wiping robot and the real-time motion state; Evaluate each candidate path by using a set evaluation function and the obstacle information to obtain a score corresponding to each candidate path; The obstacle avoidance path and the obstacle avoidance movement speed of the nuclear power wiping robot are determined according to the candidate path with the highest score and the corresponding candidate movement speed.

4. The obstacle avoidance control method for a nuclear power cleaning robot according to claim 1, characterized in that: The step of controlling the drive motor according to the target control amount comprises: The drive motor is subjected to feedforward control and / or feedback control according to the target control amount.

5. The obstacle avoidance control method for a nuclear power cleaning robot as claimed in claim 4, characterized in that: The performing feedforward control and / or feedback control on the drive motor according to the target control amount includes: When the nuclear power wiping robot is in the water absorption operation stage, the drive motor is subjected to the feedforward control and the feedback control according to the target control amount; When the nuclear power wiping robot is in a non-water absorption stage, the drive motor is subjected to the feedforward control or the feedback control according to the target control amount.

6. The obstacle avoidance control method for a nuclear power cleaning robot according to claim 1, characterized in that: In the case where an obstacle is detected in the moving direction of the nuclear power wiping robot, determining the target moving state of the nuclear power wiping robot comprises: When the nuclear power wiping robot is in the water absorption operation stage and the obstacle is detected in the movement direction of the nuclear power wiping robot, the target movement state of the nuclear power wiping robot is determined at a set first frequency; When the nuclear power wiping robot is in the non-water absorption operation stage and the obstacle is detected in the movement direction of the nuclear power wiping robot, the target movement state of the nuclear power wiping robot is determined by a set second frequency, and the second frequency is lower than the first frequency.

7. The obstacle avoidance control method of a nuclear power cleaning robot according to any one of claims 1 to 6, characterized in that: In the case where an obstacle is detected in the moving direction of the nuclear power wiping robot, before determining the target moving state of the nuclear power wiping robot, the method further includes: According to the environmental map of the reactor pool and the real-time motion state of the nuclear power wiping robot, it is detected whether there is the obstacle in the motion direction of the nuclear power wiping robot, and / or, by using a ranging sensor, it is detected whether there is the obstacle in the motion direction of the nuclear power wiping robot, and the environmental map is used to indicate the obstacles existing in the reactor pool.

8. An obstacle avoidance control device for a nuclear power wiping robot, characterized in that: include: A target motion state determination module is used to determine the target motion state of the nuclear power wiping robot when an obstacle is detected in the motion direction of the nuclear power wiping robot. The target motion state is determined according to the obstacle information of the obstacle and the real-time motion state of the nuclear power wiping robot, and is used to indicate the motion state that the nuclear power wiping robot should reach; A target control amount determination module is used to use the target motion state as the input of a pre-trained regulation network to obtain the target control amount output by the regulation network, wherein the regulation network is used to analyze the control amount required for the nuclear power wiping robot to smoothly reach the target motion state to obtain the target control amount; The obstacle avoidance control module is used to control the driving motor according to the target control amount to control the nuclear power wiping robot to perform obstacle avoidance movement. The driving motor is the motor corresponding to the driving wheel of the nuclear power wiping robot.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that When the computer program product runs on an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 7.

Images