Task allocation method and system for multiple underwater robots

Abstract

The invention discloses a task allocation method and system for multiple underwater robots, and relates to the technical field of robot control. When the system runs, environment data are collected in real time through a data collection module and a plurality of integrated sensors, a real-time environment data set is formed, preprocessing is carried out through a data processing module, and the real-time environment data set is obtained; a real-time environment data set is formed after processing, a robot work task execution state model is established through a state evaluation module, a machine operation state index Ztzs is obtained, association with a preset task list is carried out through a task distribution module, and related distribution strategies including priority-based distribution and polling distribution are used. The generated task list is allocated to the underwater robot, the underwater robot executing the allocated task is monitored in real time through the monitoring module, the progress of the monitored task and the state of the robot are fed back, self-adaptive regulation and control are performed according to the feedback result, and the accuracy and flexibility of task allocation are improved.

Description

Technical Field

[0001] The present invention relates to the field of robot control technology, and in particular to a task allocation method and system for multiple underwater robots. Background Art

[0002] Underwater robot technology is an important branch of marine engineering and underwater detection. Its main applications include marine resource exploration, environmental monitoring, military reconnaissance and underwater rescue. In these applications, the collaborative work of multiple underwater robot systems is particularly critical. Through reasonable task allocation and coordination, the work efficiency and task completion quality of the multi-robot system can be effectively improved.

[0003] At present, multi-underwater robot systems face many challenges in the process of task allocation and execution. Traditional task allocation methods are mostly based on preset task plans and static allocation strategies, and lack the ability to respond to real-time environmental changes and robot status. This method often leads to unreasonable task allocation, inability to fully utilize the capabilities of the robot, and may even lead to task failure. In addition, the existing monitoring and feedback mechanism is relatively simple, unable to evaluate the robot's status and task progress in real time, and lacks an effective adaptive control mechanism, which further limits the performance of the multi-robot system. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method and system for allocating tasks to multiple underwater robots, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a task allocation system for multiple underwater robots, including a data acquisition module, a data processing module, a state evaluation module, a task allocation module and a monitoring module; The data acquisition module collects environmental data in real time through a number of integrated sensors to form a real-time environmental data group, and transmits it to the data processing module for processing through a communication network; The data processing module pre-processes the acquired real-time environmental data group, including data cleaning processing, data filtering processing and feature extraction, extracts environmental fluctuation environmental information, and forms a processed real-time environmental data group; The state evaluation module establishes a robot work task execution state model according to the acquired real-time environmental data group, evaluates the states of several robots in real time, including position, energy and task load information, and obtains the machine operation state index Ztzs; The task allocation module associates the acquired machine operation status index Ztzs with a preset task list, and uses relevant allocation strategies, including priority-based allocation and round-robin allocation, to allocate the generated task list to the underwater robot; The monitoring module monitors the underwater robot executing the assigned task in real time, and provides feedback on the progress of the monitoring task and the status of the robot, and performs adaptive regulation based on the feedback results.

[0006] Preferably, the data acquisition module includes an acquisition unit and a transmission unit; The acquisition unit collects environmental data in real time through a number of integrated sensors to form a real-time environmental data group, and the sensors include sonar, camera and water quality sensor; Among them, the real-time environmental data group includes terrain and obstacle data, image and video data, water quality physical data, water quality chemical data, and water flow and pressure data; The transmission unit packages the real-time environment data group, marks the current underwater robot unique sequence information, timestamp information and machine position information, and sends it to the data processing module for preprocessing.

[0007] Preferably, the data processing module includes a processing unit and an extraction unit; The processing unit performs preprocessing on the acquired real-time environment data group, including data cleaning processing and data filtering processing, wherein data cleaning includes using mean filtering, median filtering and Kalman filtering to clean the data, thereby removing noise in the data, and data filtering includes using the three sigma principle and box plot method to filter the data, thereby detecting and removing abnormal values; The extraction unit performs feature extraction on the preprocessed real-time environmental data group to form a real-time environmental data group processed after feature extraction, including terrain feature extraction, water quality feature extraction, water flow change feature extraction and temperature fluctuation feature extraction.

[0008] Preferably, the mean filtering included in data cleaning is cleaned by the following calculation formula: ; In the formula, represents the cleaned data, Ys represents the original data, represents the i-th data point after cleaning, represents the i-th original data point, k represents the half-width value of the filter window, represents the coefficient for taking the average of the data points in the window, Represents the sum of all data points within the window range; Feature extraction includes terrain feature extraction obtained through the Canny edge detection formula: ; ; In the formula, Indicates the gradient strength of the pixel point on the x-axis and y-axis. Represents the gradient value of the pixel point (x, y) on the x-axis. Represents the gradient value of the pixel point (x, y) on the y-axis. represents the gradient direction angle, Represents the inverse tangent function.

[0009] Preferably, the state assessment module comprises a modeling unit; The modeling unit performs feature selection processing based on the acquired real-time environment data set to obtain the robot's state, including the machine position , Machine Energy , Task Load and work efficiency The processed data is divided into training set and test set according to the preset ratio of 80:20, and the robot task execution state model is established using the multivariate linear regression machine learning model. The status of several robots is evaluated in real time through training, and the machine operation state index Ztzs is obtained. The underwater robot task coordination and allocation is carried out according to the machine operation state index Ztzs.

[0010] Preferably, the machine location Obtained through the following calculation formula: ; In the formula, They represent the coordinate values ​​of robot k in three-dimensional space respectively; The machine energy Obtained through the following calculation formula: ; In the formula, represents the initial energy value of robot k, represents the energy consumed by robot k, p represents the total number of completed tasks, and q represents the qth task; The task load Obtained through the following calculation formula: ; In the formula, represents the load weight ratio value of the current task w, m represents the total number of current tasks, and w represents the wth current task; The working efficiency Obtained through the following calculation formula: ; In the formula, Indicates the total time required to complete the task.

[0011] Preferably, the machine operation status index Ztzs is obtained by the following calculation formula: ; In the formula, represents the modular intercept term, , , and They represent the regression coefficients, Indicates the machine location, represents the machine energy, represents the task load, Indicates work efficiency, represents the error constant term.

[0012] Preferably, the task assignment module includes an association unit; The association unit associates the acquired machine operation status index Ztzs with a preset task list, and uses relevant allocation strategies, including auction method and genetic algorithm, to allocate the generated task list to the underwater robot; Among them, the task list is allocated by the following association method, and is associated with the preset task list according to the machine operation status index Ztzs: ; In the formula, represents the task assigned to robot k, f represents the task-state association function, which is to associate the task with the robot state through predefined rules, Ztzs represents the machine operation state index, Represents a preset task list; Among them, the acquisition of f includes rule formulation, heuristic algorithms and machine learning models; Among them, the rules are formulated: ; In the formula, Indicates high priority tasks, Represents a low priority task, represents the machine operation status index of robot k, and Z represents the preset threshold of the status index.

[0013] Preferably, the monitoring module includes a monitoring unit and a feedback unit; The monitoring unit monitors the underwater robots that perform the assigned tasks in real time, and marks and transmits the status of each underwater robot monitored in real time, including position information, energy information and task progress information; The feedback unit feeds back the real-time information acquired by the monitoring unit to adaptively adjust and record the execution of the task allocation of the underwater robot, and then updates the task progress status in real time through the feedback information.

[0014] A task allocation method for multiple underwater robots includes the following steps: Step 1: The data acquisition module collects environmental data in real time through a number of integrated sensors to form a real-time environmental data group, and transmits it to the data processing module for processing through a communication network; Step 2: The data processing module pre-processes the acquired real-time environmental data group, including data cleaning, data filtering and feature extraction, extracts environmental fluctuation information, and forms a processed real-time environmental data group; Step 3: The state evaluation module establishes a robot task execution state model based on the acquired real-time environmental data set, evaluates the states of several robots in real time, including position, energy and task load information, and obtains the machine operation state index Ztzs; Step 4: The task allocation module associates the obtained machine operation status index Ztzs with the preset task list, and uses relevant allocation strategies, including priority-based allocation and polling allocation, to allocate the generated task list to the underwater robot; Step 5: The monitoring module monitors the underwater robot that is performing the assigned task in real time, and provides feedback on the progress of the monitoring task and the status of the robot, and performs adaptive regulation based on the feedback results.

[0015] The present invention provides a task allocation method and system for multiple underwater robots, which has the following beneficial effects: (1) When the system is running, the data acquisition module collects environmental data in real time through several integrated sensors to form a real-time environmental data group. The data processing module preprocesses the data to form a processed real-time environmental data group. The state evaluation module establishes a robot work task execution state model based on the acquired real-time environmental data group, evaluates the states of several robots in real time, including position, energy and task load information, and obtains the machine operation state index Ztzs. The task allocation module associates the acquired machine operation state index Ztzs with the preset task list, and uses relevant allocation strategies, including priority-based allocation and polling allocation, to allocate the generated task list to the underwater robot. The monitoring module monitors the underwater robot that executes the assigned task in real time, and provides feedback on the progress of the monitoring task and the robot status. Adaptive regulation is performed based on the feedback results, which improves the accuracy and flexibility of task allocation, optimizes resource utilization, and improves the efficiency and reliability of task completion, ensuring that the system can operate stably and efficiently in a complex and changeable underwater environment.

[0016] (2) By machine location , Machine Energy , Task Load and work efficiency The acquisition of the machine operation status index Ztzs can achieve real-time acquisition of the robot's precise position in three-dimensional space, which is helpful for task allocation and path planning, and monitors the robot's energy consumption to ensure that the energy status is considered when allocating tasks to avoid task failure due to insufficient energy. At the same time, the load of the current task is evaluated to ensure that the robot performs the task within its load capacity to avoid overload. Finally, the efficiency of the robot in completing the task is evaluated, which helps to optimize task allocation, improve the overall task completion speed, and comprehensively reflect the robot's status. Task allocation and regulation are carried out through this index to ensure efficient operation of the system.

[0017] (3) The machine operation status index Ztzs is dynamically associated and assigned with the preset task list, and the assigned tasks are monitored and feedback is provided to achieve rapid adaptation to environmental changes and task requirements, thereby improving the flexibility and responsiveness of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flowchart diagram of a task allocation system for multiple underwater robots according to the present invention; Figure 2 The figure is a schematic diagram of the steps of a method for allocating tasks to multiple underwater robots according to the present invention. DETAILED DESCRIPTION

[0019] 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 described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0020] Underwater robot technology is an important branch of marine engineering and underwater detection. Its main applications include marine resource exploration, environmental monitoring, military reconnaissance and underwater rescue. In these applications, the collaborative work of multiple underwater robot systems is particularly critical. Through reasonable task allocation and coordination, the work efficiency and task completion quality of the multi-robot system can be effectively improved.

[0021] At present, multi-underwater robot systems face many challenges in the process of task allocation and execution. Traditional task allocation methods are mostly based on preset task plans and static allocation strategies, and lack the ability to respond to real-time environmental changes and robot status. This method often leads to unreasonable task allocation, inability to fully utilize the capabilities of the robot, and may even lead to task failure. In addition, the existing monitoring and feedback mechanism is relatively simple, unable to evaluate the robot's status and task progress in real time, and lacks an effective adaptive control mechanism, which further limits the performance of the multi-robot system.

[0022] Example 1 The present invention provides a task allocation system for multiple underwater robots. Figure 1 , including data acquisition module, data processing module, status assessment module, task allocation module and monitoring module; The data acquisition module collects environmental data in real time through a number of integrated sensors to form a real-time environmental data group, and transmits it to the data processing module for processing through a communication network; The data processing module pre-processes the acquired real-time environmental data group, including data cleaning processing, data filtering processing and feature extraction, extracts environmental fluctuation environmental information, and forms a processed real-time environmental data group; The state evaluation module establishes a robot work task execution state model according to the acquired real-time environmental data group, evaluates the states of several robots in real time, including position, energy and task load information, and obtains the machine operation state index Ztzs; The task allocation module associates the acquired machine operation status index Ztzs with a preset task list, and uses relevant allocation strategies, including priority-based allocation and round-robin allocation, to allocate the generated task list to the underwater robot; The monitoring module monitors the underwater robot executing the assigned task in real time, and provides feedback on the progress of the monitoring task and the status of the robot, and performs adaptive regulation based on the feedback results.

[0023] In this embodiment, the data acquisition module collects environmental data in real time through several integrated sensors to form a real-time environmental data group, which is preprocessed by the data processing module to form a processed real-time environmental data group, and the state evaluation module establishes a robot work task execution state model according to the acquired real-time environmental data group, evaluates the states of several robots in real time, including position, energy and task load information, and obtains the machine operation state index Ztzs, and associates the acquired machine operation state index Ztzs with a preset task list through the task allocation module, and uses relevant allocation strategies, including priority-based allocation and polling allocation, to allocate the generated task list to the underwater robot, and monitors the underwater robot that executes the allocated task in real time through the monitoring module, and feeds back the progress of the monitoring task and the robot state, and performs adaptive regulation according to the feedback results, thereby improving the accuracy and flexibility of task allocation, optimizing resource utilization, and improving the efficiency and reliability of task completion, thereby ensuring that the system can operate stably and efficiently in a complex and changeable underwater environment.

[0024] Example 2 This embodiment is explained in Example 1, please refer to Figure 1,Specifically: the data acquisition module includes an acquisition unit and a transmission unit; The acquisition unit collects environmental data in real time through a number of integrated sensors to form a real-time environmental data group, and the sensors include sonar, camera and water quality sensor; Among them, the real-time environmental data group includes terrain and obstacle data, image and video data, water quality physical data, water quality chemical data, and water flow and pressure data; The transmission unit packages the real-time environment data group, marks the current underwater robot unique sequence information, timestamp information and machine position information, and sends it to the data processing module for preprocessing.

[0025] The data processing module includes a processing unit and an extraction unit; The processing unit performs preprocessing on the acquired real-time environment data group, including data cleaning processing and data filtering processing, wherein data cleaning includes using mean filtering, median filtering and Kalman filtering to clean the data, thereby removing noise in the data, and data filtering includes using the three sigma principle and box plot method to filter the data, thereby detecting and removing abnormal values; The extraction unit performs feature extraction on the preprocessed real-time environmental data group to form a real-time environmental data group processed after feature extraction, including terrain feature extraction, water quality feature extraction, water flow change feature extraction and temperature fluctuation feature extraction.

[0026] The mean filtering included in data cleaning is cleaned by the following calculation formula: ; In the formula, represents the cleaned data, Ys represents the original data, represents the i-th data point after cleaning, represents the i-th original data point, k represents the half-width value of the filter window, represents the coefficient for taking the average of the data points in the window, Represents the sum of all data points within the window range; Feature extraction includes terrain feature extraction obtained through the Canny edge detection formula: ; ; In the formula, Indicates the gradient strength of the pixel point on the x-axis and y-axis. Represents the gradient value of the pixel point (x, y) on the x-axis. Represents the gradient value of the pixel point (x, y) on the y-axis. represents the gradient direction angle, Represents the inverse tangent function.

[0027] Example 3 This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the state assessment module includes a modeling unit; The modeling unit performs feature selection processing based on the acquired real-time environment data set to obtain the robot's state, including the machine position , Machine Energy , Task Load and work efficiency The processed data is divided into training set and test set according to the preset ratio of 80:20, and the robot task execution state model is established using the multivariate linear regression machine learning model. The status of several robots is evaluated in real time through training, and the machine operation state index Ztzs is obtained. The underwater robot task coordination and allocation is carried out according to the machine operation state index Ztzs.

[0028] Machine location Obtained through the following calculation formula: ; In the formula, They represent the coordinate values ​​of robot k in three-dimensional space respectively; The machine energy Obtained through the following calculation formula: ; In the formula, represents the initial energy value of robot k, represents the energy consumed by robot k, p represents the total number of completed tasks, and q represents the qth task; The task load Obtained through the following calculation formula: ; In the formula, represents the load weight ratio value of the current task w, m represents the total number of current tasks, and w represents the wth current task; The working efficiency Obtained through the following calculation formula: ; In the formula, Indicates the total time required to complete the task.

[0029] The machine operation status index Ztzs is obtained by the following calculation formula: ; In the formula, represents the modular intercept term, , , and They represent the regression coefficients, Indicates the machine location, represents the machine energy, represents the task load, Indicates work efficiency, represents the error constant term.

[0030] In this embodiment, the machine position , Machine Energy , Task Load and work efficiency The acquisition of the machine operation status index Ztzs can achieve real-time acquisition of the robot's precise position in three-dimensional space, which is helpful for task allocation and path planning, and monitors the robot's energy consumption to ensure that the energy status is considered when allocating tasks to avoid task failure due to insufficient energy. At the same time, the load of the current task is evaluated to ensure that the robot performs the task within its load capacity to avoid overload. Finally, the efficiency of the robot in completing the task is evaluated, which helps to optimize task allocation, improve the overall task completion speed, and comprehensively reflect the robot's status. Task allocation and regulation are carried out through this index to ensure efficient operation of the system.

[0031] Example 4 This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the task assignment module includes an association unit; The association unit associates the acquired machine operation status index Ztzs with a preset task list, and uses relevant allocation strategies, including auction method and genetic algorithm, to allocate the generated task list to the underwater robot; Among them, the task list is allocated by the following association method, and is associated with the preset task list according to the machine operation status index Ztzs: ; In the formula, represents the task assigned to robot k, f represents the task-state association function, which is to associate the task with the robot state through predefined rules, Ztzs represents the machine operation state index, Represents a preset task list; Among them, the acquisition of f includes rule formulation, heuristic algorithms and machine learning models; Among them, the rules are formulated: ; In the formula, Indicates high priority tasks, Represents a low priority task, represents the machine operation status index of robot k, and Z represents the preset threshold of the status index.

[0032] The monitoring module includes a monitoring unit and a feedback unit; The monitoring unit monitors the underwater robots that perform the assigned tasks in real time, and marks and transmits the status of each underwater robot monitored in real time, including position information, energy information and task progress information; The feedback unit feeds back the real-time information acquired by the monitoring unit to adaptively adjust and record the execution of the task allocation of the underwater robot, and then updates the task progress status in real time through the feedback information.

[0033] In this embodiment, the machine operation status index Ztzs is dynamically associated and assigned with a preset task list, and the assigned tasks are monitored and feedback is provided, so as to quickly adapt to environmental changes and task requirements and improve the flexibility and responsiveness of the system.

[0034] Example 5 A task allocation method for multiple underwater robots, please refer to Figure 2 , specifically: including the following steps: Step 1: The data acquisition module collects environmental data in real time through a number of integrated sensors to form a real-time environmental data group, and transmits it to the data processing module for processing through a communication network; Step 2: The data processing module pre-processes the acquired real-time environmental data group, including data cleaning, data filtering and feature extraction, extracts environmental fluctuation information, and forms a processed real-time environmental data group; Step 3: The state evaluation module establishes a robot task execution state model based on the acquired real-time environmental data set, evaluates the states of several robots in real time, including position, energy and task load information, and obtains the machine operation state index Ztzs; Step 4: The task allocation module associates the obtained machine operation status index Ztzs with the preset task list, and uses relevant allocation strategies, including priority-based allocation and polling allocation, to allocate the generated task list to the underwater robot; Step 5: The monitoring module monitors the underwater robot that is performing the assigned task in real time, and provides feedback on the progress of the monitoring task and the status of the robot, and performs adaptive regulation based on the feedback results.

[0035] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A task allocation system for multiple underwater robots, characterized by: It includes data acquisition module, data processing module, status assessment module, task allocation module and monitoring module; The data acquisition module collects environmental data in real time through a number of integrated sensors to form a real-time environmental data group, and transmits it to the data processing module for processing through a communication network; The data processing module pre-processes the acquired real-time environmental data group, including data cleaning processing, data filtering processing and feature extraction, extracts environmental fluctuation environmental information, and forms a processed real-time environmental data group; The state evaluation module establishes a robot work task execution state model according to the acquired real-time environmental data group, evaluates the states of several robots in real time, including position, energy and task load information, and obtains the machine operation state index Ztzs; The task allocation module associates the acquired machine operation status index Ztzs with a preset task list, and uses relevant allocation strategies, including priority-based allocation and round-robin allocation, to allocate the generated task list to the underwater robot; The monitoring module monitors the underwater robot executing the assigned task in real time, and provides feedback on the progress of the monitoring task and the status of the robot, and performs adaptive regulation based on the feedback results.

2. The task allocation system for multiple underwater robots according to claim 1, characterized in that: The data acquisition module includes an acquisition unit and a transmission unit; The acquisition unit collects environmental data in real time through a number of integrated sensors to form a real-time environmental data group, and the sensors include sonar, camera and water quality sensor; Among them, the real-time environmental data group includes terrain and obstacle data, image and video data, water quality physical data, water quality chemical data, and water flow and pressure data; The transmission unit packages the real-time environment data group, marks the current underwater robot unique sequence information, timestamp information and machine position information, and sends it to the data processing module for preprocessing.

3. The task allocation system for multiple underwater robots according to claim 1, characterized in that: The data processing module includes a processing unit and an extraction unit; The processing unit performs preprocessing on the acquired real-time environment data group, including data cleaning processing and data filtering processing, wherein data cleaning includes using mean filtering, median filtering and Kalman filtering to clean the data, thereby removing noise in the data, and data filtering includes using the three sigma principle and box plot method to filter the data, thereby detecting and removing abnormal values; The extraction unit performs feature extraction on the preprocessed real-time environmental data group to form a real-time environmental data group processed after feature extraction, including terrain feature extraction, water quality feature extraction, water flow change feature extraction and temperature fluctuation feature extraction.

4. The task allocation system for multiple underwater robots according to claim 3 is characterized in that: The mean filtering included in data cleaning is cleaned by the following calculation formula: ； In the formula, represents the cleaned data, Ys represents the original data, represents the i-th data point after cleaning, represents the i-th original data point, k represents the half-width value of the filter window, represents the coefficient for taking the average of the data points in the window, Represents the sum of all data points within the window range; Feature extraction includes terrain feature extraction obtained through the Canny edge detection formula: ； ； In the formula, Indicates the gradient strength of the pixel point on the x-axis and y-axis. Represents the gradient value of the pixel point (x, y) on the x-axis. Represents the gradient value of the pixel point (x, y) on the y-axis. represents the gradient direction angle, Represents the inverse tangent function.

5. The task allocation system for multiple underwater robots according to claim 1, characterized in that: The state assessment module includes a modeling unit; The modeling unit performs feature selection processing based on the acquired real-time environment data set to obtain the robot's state, including the machine position , Machine Energy , Task Load and work efficiency The processed data is divided into training set and test set according to the preset ratio of 80:20, and the robot task execution state model is established using the multivariate linear regression machine learning model. The status of several robots is evaluated in real time through training, and the machine operation state index Ztzs is obtained. The underwater robot task coordination and allocation is carried out according to the machine operation state index Ztzs.

6. The task allocation system for multiple underwater robots according to claim 5, characterized in that: Machine location Obtained through the following calculation formula: ； In the formula, They represent the coordinate values ​​of robot k in three-dimensional space respectively; The machine energy Obtained through the following calculation formula: ； In the formula, represents the initial energy value of robot k, represents the energy consumed by robot k, p represents the total number of completed tasks, and q represents the qth task; The task load Obtained through the following calculation formula: ； In the formula, represents the load weight ratio value of the current task w, m represents the total number of current tasks, and w represents the wth current task; The working efficiency Obtained through the following calculation formula: ； In the formula, Indicates the total time required to complete the task.

7. The task allocation system for multiple underwater robots according to claim 1, characterized in that: The machine operation status index Ztzs is obtained by the following calculation formula: ； In the formula, represents the modular intercept term, , , and They represent the regression coefficients, Indicates the machine location, represents the machine energy, represents the task load, Indicates work efficiency, represents the error constant term.

8. The task allocation system for multiple underwater robots according to claim 1, characterized in that: The task assignment module includes an association unit; The association unit associates the acquired machine operation status index Ztzs with a preset task list, and uses relevant allocation strategies, including auction method and genetic algorithm, to allocate the generated task list to the underwater robot; Among them, the task list is allocated by the following association method, and is associated with the preset task list according to the machine operation status index Ztzs: ； In the formula, represents the task assigned to robot k, f represents the task-state association function, which is to associate the task with the robot state through predefined rules, Ztzs represents the machine operation state index, Represents a preset task list; Among them, the acquisition of f includes rule formulation, heuristic algorithms and machine learning models; Among them, the rules are formulated: ； In the formula, Indicates high priority tasks, Represents a low priority task, represents the machine operation status index of robot k, and Z represents the preset threshold of the status index.

9. The task allocation system for multiple underwater robots according to claim 1, characterized in that: The monitoring module includes a monitoring unit and a feedback unit; The monitoring unit monitors the underwater robots that perform the assigned tasks in real time, and marks and transmits the status of each underwater robot monitored in real time, including position information, energy information and task progress information; The feedback unit feeds back the real-time information acquired by the monitoring unit to adaptively adjust and record the execution of the task allocation of the underwater robot, and then updates the task progress status in real time through the feedback information.

10. A method for allocating tasks to multiple underwater robots, comprising a system for allocating tasks to multiple underwater robots as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: The data acquisition module collects environmental data in real time through a number of integrated sensors to form a real-time environmental data group, and transmits it to the data processing module for processing through a communication network; Step 2: The data processing module pre-processes the acquired real-time environmental data group, including data cleaning, data filtering and feature extraction, extracts environmental fluctuation information, and forms a processed real-time environmental data group; Step 3: The state evaluation module establishes a robot task execution state model based on the acquired real-time environmental data set, evaluates the states of several robots in real time, including position, energy and task load information, and obtains the machine operation state index Ztzs; Step 4: The task allocation module associates the obtained machine operation status index Ztzs with the preset task list, and uses relevant allocation strategies, including priority-based allocation and polling allocation, to allocate the generated task list to the underwater robot; Step 5: The monitoring module monitors the underwater robot that is performing the assigned task in real time, and provides feedback on the progress of the monitoring task and the status of the robot, and performs adaptive regulation based on the feedback results.

Images