Dredging method of robot for nuclear power seawater pump room, robot, storage medium and program product

Abstract

The invention discloses a dredging method of a robot for a nuclear power seawater pump room, the robot, a storage medium and a program product, and the method comprises the steps: receiving a task instruction corresponding to a dredging task of the nuclear power seawater pump room, and collecting environment image data through an image collection device arranged on the robot, environmental sonar data are collected through a sonar sensor; according to the task instruction, the environment image data, the environment sonar data and a task planning model, determining a plurality of sub-tasks and environment feature data corresponding to the dredging task; and determining associated feature data according to the plurality of sub-tasks, the environment feature data and a feature fusion model, and determining a target dredging path corresponding to the dredging task according to the associated feature data, a preset constraint condition of the robot and a path planning model. According to the technical scheme, the safety, efficiency and intelligent level of the dredging operation of the robot in the nuclear power seawater pump room can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of robot applications, and in particular to a robot dredging method for a nuclear power seawater pump room, the robot, a storage medium and a program product. Background Art

[0002] The cooling water system of a nuclear power plant mainly relies on seawater pump rooms to provide cooling water. However, seawater contains a large amount of silt and marine organisms. These substances will affect the flow of cooling water in the pump room, reduce cooling efficiency, and even cause safety accidents in serious cases.

[0003] In the prior art, dredging in seawater pumphouses mostly relies on manual operations, requiring significant manpower and time. Furthermore, the complex underwater environment presents significant challenges. This makes dredging work risky, difficult, inefficient, costly, and ineffective. Summary of the Invention

[0004] The present invention provides a robot dredging method, a robot, a storage medium and a program product for use in a nuclear power seawater pump room, so as to solve the technical problems in the related art of artificial underwater dredging, such as high risk, great difficulty, low efficiency, high cost and poor dredging effect.

[0005] According to one aspect of the present invention, a robot dredging method for a nuclear power seawater pump room is provided, the method comprising:

[0006] Receive task instructions corresponding to the desilting task of the nuclear power seawater pump room, collect environmental image data through the image acquisition device set on the robot, and collect environmental sonar data through the sonar sensor;

[0007] Determining a plurality of subtasks and environmental feature data corresponding to the dredging task according to the task instruction, the environmental image data, the environmental sonar data, and a task planning model, wherein the environmental feature data includes image feature data and sonar feature data;

[0008] Determine associated feature data based on the plurality of subtasks, the environmental feature data and the feature fusion model, and determine a target dredging path corresponding to the dredging task based on the associated feature data, the preset constraints of the robot and the path planning model; wherein the associated feature data is used to indicate the association relationship between the environmental feature data and the dredging operation in the task instruction.

[0009] According to another aspect of the present invention, there is provided a robot desilting device for a nuclear power seawater pump room, the device comprising:

[0010] An information acquisition module is used to receive task instructions corresponding to the desilting task of the nuclear power seawater pump room, collect environmental image data through the image acquisition device provided on the robot, and collect environmental sonar data through the sonar sensor;

[0011] an information fusion module, configured to determine a plurality of subtasks and environmental feature data corresponding to the dredging task based on the task instruction, the environmental image data, the environmental sonar data, and a task planning model, wherein the environmental feature data includes image feature data and sonar feature data;

[0012] The dredging path determination module is used to determine the associated feature data based on the multiple subtasks, the environmental feature data and the feature fusion model, and determine the target dredging path corresponding to the dredging task based on the associated feature data, the preset constraints of the robot and the path planning model; wherein the associated feature data is used to indicate the association relationship between the environmental feature data and the dredging operation in the task instruction.

[0013] According to another aspect of the present invention, there is provided a robot, comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the robot dredging method for a nuclear power seawater pump room as described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a processor to implement the robot dredging method for a nuclear power seawater pump room described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the robot dredging method for a nuclear power seawater pump room as described in any one of the embodiments of the present invention.

[0019] The technical solution provided by the embodiment of the present invention can provide necessary planning data for the subsequent movement of the robot and improve the efficiency of path planning by receiving task instructions corresponding to the dredging task of the nuclear power seawater pump room, collecting environmental image data through the image acquisition device set on the robot, and collecting environmental sonar data through the sonar sensor; by determining multiple subtasks and environmental feature data corresponding to the dredging task according to the task instructions, the environmental image data, the environmental sonar data and the task planning model, it can automatically realize a more refined division of the dredging task to be performed by the robot, and automatically identify the environmental feature data. Since the environmental feature data includes image feature data and sound feature data, The characteristic data is obtained, so that environmental data can be obtained from multiple dimensions, providing more accurate path planning data for robot movement; by determining the associated characteristic data according to a plurality of the subtasks, the environmental characteristic data and the feature fusion model, and determining the target dredging path corresponding to the dredging task according to the associated characteristic data, the preset constraints of the robot and the path planning model, and by associating the environmental characteristic data with the dredging operation in the task instruction, the planned target dredging path can be more adapted to the dredging task, so that the robot can reasonably and effectively perform the dredging task, thereby improving the safety, efficiency, intelligence level and cleaning effect of the robot in the process of dredging the nuclear power seawater pump room.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 1 is a flow chart of a method for desilting a nuclear power plant seawater pump room using a robot according to a first embodiment of the present invention;

[0023] Figure 2 This is a flow chart of a robot dredging method for a nuclear power seawater pump room according to a second embodiment of the present invention;

[0024] Figure 3 This is a structural block diagram of a robot dredging device for a nuclear power seawater pump room provided in a third embodiment of the present invention;

[0025] Figure 4A schematic structural diagram of a robot for implementing the robot dredging method for a nuclear power seawater pump room provided in the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described in the embodiments of the present invention are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "objective", "first", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0029] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0030] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0031] Example 1

[0032] Figure 1A flowchart of a dredging method for a robot used in a nuclear power seawater pump room is provided for the first embodiment of the present invention. This embodiment is applicable to dredging operations in a nuclear power seawater pump room. The method can be performed by a dredging device of a robot used in a nuclear power seawater pump room. The dredging device of the robot can be implemented in the form of hardware and / or software. Optionally, it can be configured in a robot to implement the dredging method for a robot used in a nuclear power seawater pump room in the embodiment of the present invention. Figure 1 As shown, the method may specifically include:

[0033] S110, receiving a task instruction corresponding to a dredging task of a nuclear power seawater pump room, collecting environmental image data through an image acquisition device provided on the robot, and collecting environmental sonar data through a sonar sensor.

[0034] The nuclear power plant's seawater pump room is the robot's workspace for performing dredging operations and is typically an enclosed space. A dredging task is the robot's task during dredging. Task instructions are specific action instructions for the robot during dredging operations, instructing the robot on how to perform specific dredging operations. Task instructions primarily include text and / or voice instructions. For example, text instructions can be issued by inputting text, such as "Go to the sedimentation cleanup area and avoid critical equipment." Voice instructions are user-sent voice content, which can be converted to the corresponding text. An image acquisition device is a device used by the robot to capture images of the nuclear power plant's seawater pump room environment. Environmental image data refers to images of the nuclear power plant's seawater pump room environment captured using the robot's camera and / or other sensors with image acquisition capabilities. Environmental sonar data refers to environmental information about the nuclear power plant's seawater pump room captured using the robot's sonar sensor.

[0035] Specifically, in an embodiment of the present invention, the robot's specific dredging task information can be determined through task instructions to guide the robot to perform corresponding dredging actions in the nuclear power seawater pump room. The collected environmental image data and environmental sonar data provide the robot with environmental information data in the nuclear power seawater pump room to plan the robot's movement path and dredging position in the nuclear power seawater pump room. By combining the task instructions sent by the user with the environmental image of the nuclear power seawater pump room, this technical solution can provide the robot with accurate nuclear power seawater pump room environmental information and dredging task information, allowing the robot to successfully complete the dredging operation in the nuclear power seawater pump room based on the specific dredging task information.

[0036] S120. Determine a plurality of subtasks and environmental feature data corresponding to the dredging task according to the task instruction, the environmental image data, the environmental sonar data, and a task planning model, wherein the environmental feature data includes image feature data and sonar feature data.

[0037] The task planning model can be understood as a pre-trained machine learning model that can perform task partitioning operations. Specifically, the task planning model can be trained based on multiple sample tasks and multiple subtasks corresponding to the sample tasks with expected outputs. The machine learning model may include, but is not limited to, a language model with parameters for predicting magnitude, a hierarchical task network, and a search-based planning model.

[0038] Subtasks refer to the multiple task stages and their specific task contents obtained by decomposing task instructions using the task planning model. For example, when the instruction task is "go to clean the sedimentation area and avoid key equipment", the task instruction is decomposed to obtain subtask 1: explore the environment and identify obstacles, with a priority of 1. (Prioritize obstacle avoidance safety); subtask 2: identify and locate the sedimentation area, with a priority of 2; subtask 3: perform dredging while avoiding key equipment, with a priority of 3. It should be noted that when the robot is performing the dredging task, it must first ensure its own safety, and then perform the corresponding dredging task. Therefore, it is necessary to first identify the obstacles in the nuclear power seawater pump room and enable the robot to complete the obstacle avoidance operation to prevent the robot from colliding with the obstacles and affecting the robot's safety.

[0039] Environmental feature data includes image feature data and sonar feature data. Image feature data refers to at least one of the following image information, including pipelines, sediment, and pump room structures, extracted from environmental image data using image processing techniques. This information is relevant to the robot's path and dredging operations. For example, information types may include: Obstacle 1: Pipeline, Location [x1, y1, z1]; Obstacle 2: Pump room structure, Location [x2, y2, z2]; Sediment Area: Location [x3, y3, z3], Area n square meters; Obstacle 3: Unknown Object, Distance 5 meters, Circular Shape. Sonar feature data refers to at least one of the following information, including distance, shape, and size, extracted from environmental sonar data using sonar processing techniques. Environmental feature data can be used to identify specific obstacle information, guiding the robot in better obstacle avoidance. It should be noted that, under certain operating conditions, sonar sensors can also be used to collect environmental information about nuclear power plant seawater pump rooms, not just obstacle feature information. For example, when the visual environment image display of the underwater environment is poor, the sonar sensor can be used to obtain specific information about the surrounding environment.

[0040] Specifically, in an embodiment of the present invention, the task instructions, the environmental image data, and the environmental sonar data can be input into a task planning model to obtain multiple subtasks, image feature data, and sonar feature data corresponding to the dredging task. By using the task planning model to comprehensively analyze and process the task instructions, environmental image data, and environmental sonar data, multiple subtasks corresponding to the task instructions with more specific task content are obtained. This allows the robot to perform dredging operations in the nuclear power plant seawater pump room according to the task content of the subtasks, thereby ensuring the robot's ultimate dredging effect in the nuclear power plant seawater pump room.

[0041] S130. Determine associated feature data based on the plurality of subtasks, the environmental feature data and the feature fusion model, and determine a target dredging path corresponding to the dredging task based on the associated feature data, the preset constraints of the robot and the path planning model; wherein the associated feature data is used to indicate the association relationship between the environmental feature data and the dredging operation in the task instruction.

[0042] Among them, the preset constraint conditions of the robot can be at least one of the constraint conditions (conditions that need to be met) set for the position, state, working power, dredging operation range and other information of the dredging tools possessed by the robot. The actual working capacity of the robot can be determined based on the preset constraint conditions. For example, by presetting the constraint conditions, the dredging working range and capacity of the robot can be determined in advance, so as to make reasonable adaptive adjustments to the robot's route of travel, so that the robot can efficiently complete the dredging operation of the target sedimentation area. For example, the first dredging tool of the robot is located above the camera of the robot. If the preset constraint condition of the first dredging tool is that the maximum extension range is 3 meters, then the first dredging tool can perform dredging operations at a position 3 meters away from the sedimentation area, and adjust the position of the robot as the dredging progresses.

[0043] Among them, the path planning model can be understood as a pre-trained machine learning model that can perform path planning operations. Specifically, the path planning model can be obtained by training the machine learning model based on multiple training sample tasks, training environment feature data and preset constraints of the robot. The machine learning model may include but is not limited to a language model with parameters of the prediction magnitude, a convolutional neural network, and a multi-agent path planning model. The target dredging path is the actual navigation path that the robot travels when performing dredging operations. The target dredging path can be determined based on the environmental data collected in real time, or it can be predicted based on the environmental data collected within a certain period of time by performing comprehensive analysis and processing on the environmental data collected within a certain period of time. The feature fusion model can generally include but is not limited to a model with data analysis and processing, and can generally include one of the models such as a splicing fusion model, a graph neural network fusion model and a time series feature fusion model.

[0044] Specifically, this technical solution can conduct a comprehensive analysis of multiple sub-tasks and environmental feature data based on the feature fusion model, determine the correlation between the environmental feature data and the dredging operations in the task instructions, and then determine the action instructions taken by the robot in different task stages based on the correlation, so that the robot can dredge different target sedimentation areas according to the actual environmental conditions data.

[0045] Furthermore, the path planning model can be used to process the associated feature data and the preset constraints of the robot to determine the target dredging path that the robot meets during the actual dredging operation. In this way, the constraint information of the robot's dredging tools can be actually combined to plan the robot's optimal dredging path under real-time environmental data, thereby improving the robot's dredging efficiency in the target sedimentation area using dredging tools.

[0046] In one embodiment, after collecting environmental image data through the image acquisition device provided on the robot and collecting environmental sonar data through the sonar sensor, it also includes: obtaining environmental map data of the nuclear power seawater pump room, and updating the environmental map data according to the environmental image data and the environmental sonar data collected by the robot; wherein the environmental map data at least includes position data of the pump room structure area, pipeline area and sediment area of ​​the nuclear power seawater pump room; determining environmental change data according to the environmental image data and the environmental sonar data, and determining the task execution stage of the robot according to the environmental image data, the environmental sonar data and the updated environmental map data; determining the environmental perception range according to the environmental change data and the task execution stage, and adjusting the working status of the image acquisition device and the sonar sensor according to the environmental perception range. By adopting this technical solution, environmental image data and environmental sonar data can be associated with environmental map data, so as to update the environmental map data and environmental change data acquired by the robot in real time based on the environmental image data and environmental sonar data, thereby determining the task execution stage in the robot's dredging task and timely adjusting the corresponding environmental perception range according to the task execution stage and environmental change data to enhance the monitoring effect of the environment.

[0047] The environmental map data refers to the pre-established map data content within the nuclear power seawater pump room. This map data content can provide the robot with global information about the nuclear power seawater pump room environment, serving as the data basis for the robot to perform one or more operations such as planning paths, identifying key areas (such as pipelines, pump room structures, sedimentation areas), and dividing task stages.

[0048] Environmental change data refers to the differences between environmental information collected at different times, and can also be generally understood as event information indicating an expected change in the environment. Optionally, determining environmental change data based on the environmental image data and the environmental sonar data may include: acquiring environmental image data at multiple times to determine image difference data; determining sonar difference data based on the environmental sonar data at multiple times; and determining environmental change data based on the image difference data and the sonar difference data. Exemplarily, the image difference data may include, but is not limited to, at least one of obstacle change data, image brightness change data, and image color change data within the image. Sonar difference data may include, but is not limited to, data on changes in the number of characteristic obstacles and / or object positions.

[0049] As an optional implementation scheme of the embodiment of the present disclosure, the environmental perception range is determined according to the environmental change data and the task execution stage, including: when the environmental change data exceeds a preset data change threshold corresponding to the environmental change data and the task execution stage has not changed, determining the environmental perception range according to the environmental change data; when the task execution stage changes and the environmental change data does not exceed the preset data change threshold corresponding to the environmental change data, determining the environmental perception range according to the task execution stage; when the task execution stage changes and the environmental change data exceeds the preset data change threshold corresponding to the environmental change data, determining the preset environmental perception range as the environmental perception range of the robot; when the task execution stage has not changed and the environmental change data does not exceed the preset data change threshold corresponding to the environmental change data, determining the environmental perception range currently being used by the robot as the environmental perception range, that is, maintaining the environmental perception range of the robot without adjustment.

[0050] The robot's task execution phase refers to the multiple subtasks obtained after decomposing the task instructions. Multiple subtasks correspond to different task phases. The division of task phases can be predetermined based on environmental map data or determined based on the environmental information recognized by the robot. For example, if the robot recognizes that it is currently far away from the pipeline and sediment, the system switches the task phase to "exploration"; if the robot recognizes that it is currently in a sediment area, the system switches the task phase to "dredging"; if the robot recognizes that it is currently in a pipeline structure, the system switches the task phase to "obstacle avoidance." The environmental perception range includes global perception (environmental exploration) and local high-precision perception (dredging operations). When using global perception, sonar can be used for large-scale environmental scanning and obstacle location. When using local high-precision perception, the perception range can be narrowed, and visual sensors and sonar can be used to accurately identify and locate target sediments.

[0051] Specifically, the present application obtains pre-stored environmental map data of the nuclear power seawater pump room, and updates and corrects the environmental map data based on the actual collected environmental data, thereby determining the robot's task execution stage based on the environmental change data, and executing corresponding environmental perception modes for different task stages to achieve accurate collection of the nuclear power seawater pump room environment, thereby obtaining accurate environmental information on the location of obstacles and sedimentation areas.

[0052] The technical solution provided by the embodiment of the present invention can provide necessary planning data for the subsequent movement of the robot and improve the efficiency of path planning by receiving task instructions corresponding to the dredging task of the nuclear power seawater pump room, collecting environmental image data through the image acquisition device set on the robot, and collecting environmental sonar data through the sonar sensor; by determining multiple subtasks and environmental feature data corresponding to the dredging task according to the task instructions, the environmental image data, the environmental sonar data and the task planning model, it can automatically realize a more refined division of the dredging task to be performed by the robot, and automatically identify the environmental feature data. Since the environmental feature data includes image feature data and sound feature data, The characteristic data can be obtained from multiple dimensions, which can be used as a basis for more accurate path planning for robot movement; by determining the associated characteristic data according to a plurality of the subtasks, the environmental characteristic data and the feature fusion model, the target dredging path corresponding to the dredging task is determined according to the associated characteristic data, the preset constraints of the robot and the path planning model, and by associating the environmental characteristic data with the dredging operation in the task instruction, the planned target dredging path can be more adapted to the dredging task, so that the robot can reasonably and effectively perform the dredging task, thereby improving the safety, efficiency, intelligence level and cleaning effect of the robot in the process of dredging the nuclear power seawater pump room.

[0053] Example 2

[0054] Figure 2 The flowchart of a dredging method for a robot used in a nuclear power seawater pump room is provided in the second embodiment of the present invention. The solution in this embodiment is a refinement of the technical solution after the target dredging path corresponding to the dredging task is determined according to the associated feature data, the preset constraints of the robot and the path planning model on the basis of the above embodiment. Optionally, after the target dredging path corresponding to the dredging task is determined according to the associated feature data, the preset constraints of the robot and the path planning model, it also includes: determining environmental change data according to the environmental image data and the environmental sonar data, generating environmental change prompt information according to the environmental change data, and updating the target dredging path corresponding to the dredging task according to the environmental change data. For specific implementation methods, please refer to the description of this embodiment. Among them, technical features that are the same or similar to those in the above embodiments are not repeated here. Figure 2 As shown, the method may specifically include:

[0055] S210, receiving a task instruction corresponding to a dredging task of a nuclear power seawater pump room, collecting environmental image data through an image acquisition device provided on the robot, and collecting environmental sonar data through a sonar sensor.

[0056] S220, determining a plurality of subtasks and environmental feature data corresponding to the dredging task according to the task instruction, the environmental image data, the environmental sonar data, and a task planning model, wherein the environmental feature data includes image feature data and sonar feature data;

[0057] S230: Determine associated feature data based on the plurality of subtasks, the environmental feature data, and the feature fusion model; and determine a target dredging path corresponding to the dredging task based on the associated feature data, preset constraints of the robot, and a path planning model; wherein the associated feature data is used to indicate an association relationship between the environmental feature data and the dredging operation in the task instruction;

[0058] S240: Determine environmental change data based on the environmental image data and the environmental sonar data, generate environmental change prompt information based on the environmental change data, and update the target dredging path corresponding to the dredging task based on the environmental change data.

[0059] The environment change prompt information refers to the prompt information issued when the environment is determined to have changed. For example, the prompt information may include at least one of a flashing icon, a color change (such as red indicating a warning), a pop-up message notification, and the like.

[0060] Specifically, when environmental change data is determined based on environmental image data and environmental sonar data, a pop-up message notification can be generated in a timely manner. By responding to the pop-up message notification, the latest dredging path corresponding to the dredging task can be updated. This technical solution determines the robot's dredging route based on real-time environmental change data, enabling the robot to have better route timeliness during the dredging process, thereby obtaining the optimal path in changing environments and helping to improve the execution efficiency of dredging tasks.

[0061] In an optional embodiment, the environmental change data includes change data of the sediment diffusion area and / or change data of the obstacle data; the determining of the environmental change data based on the environmental image data and the environmental sonar data includes: determining the sediment diffusion area based on the environmental image data at multiple moments, and determining the change data of the sediment diffusion area based on the sediment diffusion area at multiple moments; and / or determining the obstacle data based on the environmental image data and / or the environmental sonar data at multiple moments, and determining the change data of the obstacle data based on the obstacle data at multiple moments.

[0062] Among them, the sediment diffusion area refers to the area where part of the sediment is affected by the dredging action when the robot is performing dredging operations, and the sediment movement and diffusion are carried out; the change data of the sediment diffusion area refers to the change data that continuously decreases when the sediment is cleaned after the sediment diffusion movement.

[0063] By adopting the technical solution of the present invention, environmental change data can also be predicted based on environmental data at different times, so as to determine possible environmental change data in advance, thereby better serving the robot's dredging operations and path planning.

[0064] In one embodiment, after determining the target dredging path corresponding to the dredging task based on the associated feature data, the preset constraints of the robot and the path planning model, it also includes: in response to an event in which the task instruction changes, updating the target dredging path corresponding to the dredging task based on the updated task instruction, the environmental image data, the environmental sonar data and the task planning model.

[0065] Specifically, when the robot receives an updated task instruction issued by a user during the dredging process, it will generate a response message indicating that the task instruction has changed. In response to this message, the robot analyzes the new task instruction and determines the updated task content. Based on the updated task content, environmental image data, the environmental sonar data, and the task planning model, the robot obtains a dredging path corresponding to the updated task content. This technical solution can promptly respond to changes in task instructions sent by users during the dredging process to meet dynamically changing task execution requirements, promptly adjust the robot's dredging operations, and promptly process user-ordered tasks, thereby better meeting user dredging needs.

[0066] In one embodiment, after determining the target dredging path corresponding to the dredging task based on the associated feature data, the preset constraints of the robot and the path planning model, it also includes: controlling the robot to move to the task execution area corresponding to the subtask according to the target dredging path, and controlling the robot to perform the dredging operation corresponding to the subtask within the task execution area; in response to a cleaning completion trigger event, determining the sediment cleaning effect based on the environmental image data and the environmental sonar data.

[0067] Among them, the task execution area refers to the area where sediment exists and the robot needs to perform dredging; the cleaning effect can refer to the amount of remaining sediment after the robot's dredging operation, or it can be understood as the area of ​​sediment in the target execution area after the dredging operation, etc.

[0068] Specifically, based on the obtained target desilting path, the robot is controlled to move to the task execution area corresponding to each subtask and perform desilting operations on the target task execution area. When the robot completes the desilting operation in the task execution area, it outputs a desilting completion message indicating that desilting has been completed in the task execution area corresponding to the current subtask. In response to the desilting completion message, the robot determines that desilting has been completed in the target task execution area, i.e., that the current subtask is completed. Environmental image data and environmental sonar data of the target task execution area are then collected to determine the amount of remaining sediment after the robot performs the desilting operation on the target task execution area. It should be noted that in this technical solution, the cleaning effect determination threshold after desilting by the robot is generally set to 5% of the remaining sediment amount. That is, if the remaining sediment amount is within 5%, the sediment cleaning effect is considered to meet expectations, and the desilting operation on the target task execution area is terminated. It should be added that the remaining sediment amount threshold can also be set according to the actual target execution area to adapt to the actual desilting environment of different target execution areas.

[0069] In one embodiment, after determining the sediment cleaning effect based on the environmental image data and the environmental sonar data, it also includes: in response to an event that the cleaning effect does not achieve the expected effect, regenerating a dredging instruction corresponding to the subtask based on the cleaning effect, and controlling the robot to continue to perform the dredging operation according to the dredging instruction.

[0070] Specifically, after determining the sediment cleaning effect, if the remaining sediment amount is within 5%, the robot does not need to perform secondary dredging. If the remaining sediment amount is greater than 5%, the robot needs to perform secondary dredging according to the regenerated dredging instructions. By performing secondary dredging on the target execution area that does not meet the cleaning effect, the dredging effect of the sediment area in the target execution area can be guaranteed.

[0071] The technical solution provided by the embodiment of the present invention determines the environmental change data through the environmental image data and the environmental sonar data, thereby realizing dynamic detection of the dredging environment and timely discovering environmental changes that may affect the smooth execution of the dredging task. Then, by generating environmental change prompt information based on the environmental change data, the robot can quickly and intuitively understand the change through the environmental change prompt information when the environment changes. By updating the target dredging path corresponding to the dredging task according to the environmental change data, the robot can effectively respond to environmental changes in the complex environment of the nuclear power seawater pump room and timely adjust the optimal travel path to improve the travel efficiency and safety of the robot during the dredging process.

[0072] Example 3

[0073] Figure 3This is a block diagram of a robot desilting device for a nuclear power seawater pump room provided in the third embodiment of the present invention. The device can be implemented by software and / or hardware and can be configured in the robot. Figure 3 As shown, the robot desilting device for a nuclear power seawater pump room of this embodiment may include: an information acquisition module 301, an information fusion module 302 and a desilting path determination module 303.

[0074] Among them, the information acquisition module 301 is used to receive task instructions corresponding to the dredging task of the nuclear power seawater pump room, collect environmental image data through the image acquisition device set on the robot, and collect environmental sonar data through the sonar sensor; the information fusion module 302 is used to determine multiple subtasks and environmental feature data corresponding to the dredging task according to the task instructions, the environmental image data, the environmental sonar data and the task planning model, wherein the environmental feature data includes image feature data and sonar feature data; the dredging path determination module 303 is used to determine associated feature data according to the multiple subtasks, the environmental feature data and the feature fusion model, and determine the target dredging path corresponding to the dredging task according to the associated feature data, the preset constraints of the robot and the path planning model; wherein the associated feature data is used to indicate the association relationship between the environmental feature data and the dredging operation in the task instruction.

[0075] The technical solution provided by the embodiment of the present invention receives the task instructions corresponding to the dredging task of the nuclear power seawater pump room through the information acquisition module 301, collects environmental image data through the image acquisition device set on the robot, and collects environmental sonar data through the sonar sensor, which can provide necessary planning data for the subsequent movement of the robot and improve the efficiency of path planning; through the information fusion module 302, multiple subtasks and environmental feature data corresponding to the dredging task are determined according to the task instructions, the environmental image data, the environmental sonar data and the task planning model, which can automatically realize a more refined division of the dredging task to be performed by the robot and automatically identify the environmental feature data. Since the environmental feature data includes image features, The data and sonar feature data can obtain environmental data from multiple dimensions, which can be used as a basis for more accurate path planning for robot movement; the dredging path determination module 303 determines the associated feature data according to the multiple subtasks, the environmental feature data and the feature fusion model, and determines the target dredging path corresponding to the dredging task according to the associated feature data, the preset constraints of the robot and the path planning model. By associating the environmental feature data with the dredging operation in the task instruction, the planned target dredging path can be more adapted to the dredging task, so that the robot can reasonably and effectively perform the dredging task, thereby improving the safety, efficiency, intelligence level and cleaning effect of the robot in the process of dredging the nuclear power seawater pump room.

[0076] Based on the above-mentioned optional technical solutions, the robot desilting device for a nuclear power seawater pump room provided in this embodiment may optionally further include: an environmental map data determination module, a task execution stage determination module, and a working state adjustment module. The environmental map data determination module is configured to, after the image acquisition device provided on the robot acquires environmental image data and the sonar sensor acquires environmental sonar data, obtain environmental map data of the nuclear power seawater pump room, and update the environmental map data based on the environmental image data and the sonar data acquired by the robot; the environmental map data at least includes location data of the pump room structure area, pipeline area, and sediment area of ​​the nuclear power seawater pump room; the task execution stage determination module is configured to determine environmental change data based on the environmental image data and the sonar data, and determine the robot's task execution stage based on the environmental image data, the sonar data, and the updated environmental map data; and the working state adjustment module is configured to determine an environmental perception range based on the environmental change data and the task execution stage, and adjust the working states of the image acquisition device and the sonar sensor based on the environmental perception range.

[0077] Based on the above-mentioned optional technical solutions, the robot dredging device for a nuclear power seawater pump room provided in this embodiment may optionally further include a dredging path updating module. The dredging path updating module is configured to, after determining the target dredging path corresponding to the dredging task based on the associated feature data, the robot's preset constraints, and the path planning model, determine environmental change data based on the environmental image data and the environmental sonar data, generate environmental change prompt information based on the environmental change data, and update the target dredging path corresponding to the dredging task based on the environmental change data.

[0078] Based on the above-mentioned optional technical solutions, optionally, the environmental change data includes sediment diffusion area change data and / or obstacle data change data. Furthermore, the dredging path update module may also include: a sediment diffusion area change data determination unit and an obstacle data change data determination unit. The sediment diffusion area change data determination unit is used to determine the sediment diffusion area based on the environmental image data at multiple moments, and determine the sediment diffusion area change data based on the sediment diffusion area at multiple moments; the obstacle data change data determination unit is used to determine obstacle data based on the environmental image data and / or environmental sonar data at multiple moments, and determine the obstacle data change data based on the obstacle data at multiple moments.

[0079] Based on the above-mentioned optional technical solutions, optionally, the dredging path update module can also be used to update the target dredging path corresponding to the dredging task according to the associated feature data, the preset constraints of the robot and the path planning model, in response to an event in which the task instructions change, according to the updated task instructions, the environmental image data, the environmental sonar data and the task planning model.

[0080] Based on the above-mentioned optional technical solutions, the robot dredging device for a nuclear power seawater pump room provided in this embodiment may optionally further include: a dredging control module and a cleaning effect determination module. The dredging control module is configured to control the robot to move to a task execution area corresponding to the subtask according to the target dredging path, and to control the robot to perform the dredging operation corresponding to the subtask within the task execution area; and the cleaning effect determination module is configured to determine the sediment cleaning effect based on the environmental image data and the environmental sonar data in response to a cleaning completion trigger event.

[0081] Based on the above optional technical solutions, the cleaning effect determination module may optionally further include a secondary silt removal unit. The secondary silt removal unit is configured to, after determining the sediment cleaning effect based on the environmental image data and the environmental sonar data, regenerate a silt removal instruction corresponding to the subtask based on the cleaning effect in response to an event that the cleaning effect does not achieve the expected effect, and control the robot to continue the silt removal operation based on the silt removal instruction.

[0082] The robotic dredging device for a nuclear power plant seawater pump room provided in an embodiment of the present invention can execute any of the robotic dredging methods for a nuclear power plant seawater pump room described in any of the embodiments of the present invention, and includes the functional modules and beneficial effects corresponding to executing the robotic dredging method for a nuclear power plant seawater pump room. For technical details not fully described in this embodiment, please refer to the robotic dredging method for a nuclear power plant seawater pump room described in any of the embodiments of the present invention.

[0083] Example 4

[0084] Figure 4 A schematic diagram of a robot 10 that can be used to implement an embodiment of the present invention is shown. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit implementation of the invention described and / or claimed herein.

[0085] like Figure 4 As shown, the robot 10 includes at least one processor 11 and memory, such as a read-only memory (ROM) 12 and a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores a computer program product executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded from the storage unit 18 into the random access memory (RAM) 13. The RAM 13 can also store various programs and data required for the operation of the robot 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0086] Various components in the robot 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, optical disk, etc.; and a communication unit 19, such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the robot 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0087] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for determining the thickness of a weathered crust reservoir.

[0088] In some embodiments, the method for determining the thickness of a weathered crust reservoir layer can be implemented as a computer program product, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the robot 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the thickness of a weathered crust reservoir layer described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for determining the thickness of a weathered crust reservoir layer in any other appropriate manner (e.g., by means of firmware).

[0089] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0090] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0091] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0092] To provide interaction with a user, the systems and techniques described herein can be implemented on a robot having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the robot. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0093] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0094] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0095] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0096] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A robot dredging method for a nuclear power seawater pump room, characterized in that: include: Receive task instructions corresponding to the desilting task of the nuclear power seawater pump room, collect environmental image data through the image acquisition device set on the robot, and collect environmental sonar data through the sonar sensor; Determining a plurality of subtasks and environmental feature data corresponding to the dredging task according to the task instruction, the environmental image data, the environmental sonar data, and a task planning model, wherein the environmental feature data includes image feature data and sonar feature data; Determine associated feature data based on the plurality of subtasks, the environmental feature data and the feature fusion model, and determine a target dredging path corresponding to the dredging task based on the associated feature data, the preset constraints of the robot and the path planning model; wherein the associated feature data is used to indicate the association relationship between the environmental feature data and the dredging operation in the task instruction.

2. The robot desilting method for a nuclear power seawater pump room according to claim 1, characterized in that: After collecting environmental image data by the image acquisition device provided on the robot and collecting environmental sonar data by the sonar sensor, the method further includes: Acquire environmental map data of a nuclear power seawater pump room, and update the environmental map data based on the environmental image data and the environmental sonar data collected by the robot; wherein the environmental map data at least includes location data of a pump room structure area, a pipeline area, and a sediment area of ​​the nuclear power seawater pump room; determining environmental change data based on the environmental image data and the environmental sonar data, and determining a task execution phase of the robot based on the environmental image data, the environmental sonar data, and the updated environmental map data; The environmental perception range is determined according to the environmental change data and the task execution stage, and the working states of the image acquisition device and the sonar sensor are adjusted according to the environmental perception range.

3. The robot dredging method for a nuclear power seawater pump room according to claim 1, characterized in that: After determining the target dredging path corresponding to the dredging task according to the associated feature data, the preset constraint conditions of the robot and the path planning model, the method further includes: Environmental change data is determined based on the environmental image data and the environmental sonar data, environmental change prompt information is generated based on the environmental change data, and a target dredging path corresponding to the dredging task is updated based on the environmental change data.

4. The robot dredging method for a nuclear power seawater pump room according to claim 3, characterized in that: The environmental change data includes change data of a sediment diffusion area and / or change data of obstacle data; and determining the environmental change data based on the environmental image data and the environmental sonar data includes: Determining a sediment diffusion area based on the environmental image data at multiple moments, and determining change data of the sediment diffusion area based on the sediment diffusion area at multiple moments; and / or, Obstacle data is determined based on the environmental image data and / or the environmental sonar data at multiple moments, and change data of the obstacle data is determined based on the obstacle data at multiple moments.

5. The robot desilting method for a nuclear power seawater pump room according to claim 1, characterized in that: After determining the target dredging path corresponding to the dredging task according to the associated feature data, the preset constraint conditions of the robot and the path planning model, the method further includes: In response to an event in which the task instruction changes, a target dredging path corresponding to the dredging task is updated according to the updated task instruction, the environmental image data, the environmental sonar data, and the task planning model.

6. The robot desilting method for a nuclear power seawater pump room according to claim 1, characterized in that: After determining the target dredging path corresponding to the dredging task according to the associated feature data, the preset constraint conditions of the robot and the path planning model, the method further includes: Control the robot to move to a task execution area corresponding to the subtask according to the target dredging path, and control the robot to perform the dredging operation corresponding to the subtask within the task execution area; In response to a cleaning completion trigger event, a sediment cleaning effect is determined according to the environmental image data and the environmental sonar data.

7. The robot dredging method for a nuclear power seawater pump room according to claim 6, characterized in that: After determining the sediment cleaning effect according to the environmental image data and the environmental sonar data, the method further includes: In response to an event that the cleaning effect does not achieve the expected effect, a dredging instruction corresponding to the subtask is regenerated according to the cleaning effect, and the robot is controlled to continue to perform the dredging operation according to the dredging instruction.

8. A robot, characterized in that: The robot comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the robot dredging method for a nuclear power seawater pump room according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the robot dredging method for a nuclear power seawater pump room according to any one of claims 1 to 7 when executed.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the robot dredging method for a nuclear power seawater pump room according to any one of claims 1 to 7.

Images