A task and operation and maintenance collaborative scheduling system and method for intelligent farming robots

Abstract

This invention provides a task and operation / maintenance collaborative scheduling system and method for intelligent aquaculture robots, comprising: a scheduling control unit, an aquaculture robot, an automatic feeding device, a charging device, and an air shower device; the aquaculture robot, automatic feeding device, charging device, and air shower device are connected to the scheduling control unit via a wired or wireless communication network; the aquaculture robot is used to move within the work area and perform feeding and inspection tasks; the automatic feeding device is used to replenish feed for the aquaculture robot; the charging device is used to charge the aquaculture robot; the air shower device is used to clean and dry the aquaculture robot; the scheduling control unit includes a task planning module, a maintenance decision module, and an execution control module. This invention can enhance the adaptability, overall operational efficiency, and long-term operational reliability of fish aquaculture robot systems, and powerfully promotes the intelligent upgrading of factory-scale aquaculture.

Description

Technical Field

[0001] This application relates to the field of intelligent aquaculture technology, and more specifically, to a task and operation and maintenance collaborative scheduling system and method for intelligent aquaculture robots. Background Technology

[0002] The modern fish farming industry is developing towards a high-density, factory-style farming model, with an increasingly urgent need for automation and intelligence in areas such as precise feeding, water environment monitoring, and disease control. Using mobile robots to replace manual labor for automated feeding and pond inspection has become a key means of improving farming efficiency and reducing labor intensity.

[0003] However, existing fish farming robot systems often operate in isolation from their task execution and maintenance management, exhibiting static and simplistic operational strategies that are ill-suited to the specific and dynamic requirements of fish farming scenarios. Specifically, they suffer from the following limitations:

[0004] Fish feeding needs to be dynamically adjusted based on factors such as species, growth stage, water temperature, and feeding behavior. Existing systems typically set fixed feeding cycles or amounts for robots, failing to provide precise feed replenishment based on the differentiated feeding tasks they have just completed (e.g., different types and weights of feed were fed to different ponds). This can easily lead to mixed feed in the robot's hold and a mismatch between spare feed and actual needs, affecting the accuracy of subsequent feeding operations. The high temperature and humidity environment in aquaculture workshops means that after robots operate in water, water stains, feed dust, and microorganisms easily adhere to their bodies and sensors. Existing systems mostly use timed cleaning or simple trigger-based cleaning, without considering the varying levels of contamination encountered by the robot in different areas (e.g., low-oxygen areas prone to bacterial growth, feed distribution areas). Insufficient cleaning can lead to equipment corrosion and sensor malfunction, while excessive cleaning wastes energy and time. The robot's workload (e.g., travel distance, duration of operation of the feeding device under load, and continuous sensor operation time) directly affects its energy consumption. Current charging strategies are mostly based on fixed power thresholds and do not correlate with the amount of work the robot is about to perform (such as continuously inspecting multiple large ponds). This may lead to the robot running out of power midway through a task or frequent recharging trips reducing operational coverage. When deploying multiple robots in a large-scale aquaculture workshop, their task completion times may be concentrated, resulting in intense competition for resources in the maintenance area (charging stations, feeding stations, air showers) within a short period. Existing systems lack global collaborative scheduling of multi-robot task queues and maintenance resources, which can easily lead to congestion and reduce overall operational efficiency.

[0005] In summary, the operation and maintenance management of existing robotic systems for fish farming is static, passive, and isolated. It fails to deeply integrate with dynamically changing farming tasks, complex environmental factors, and multi-machine collaborative scenarios, thus restricting the further improvement of the overall efficiency and reliability of intelligent farming systems. Summary of the Invention

[0006] The present invention aims to overcome the shortcomings of the prior art and provide a task and operation and maintenance collaborative scheduling system and method for intelligent aquaculture robots, so as to solve the technical problem that the operation and maintenance management of existing fish farming robot systems is static, passive and isolated, and fails to be deeply integrated with dynamically changing aquaculture tasks, complex environmental factors and multi-machine collaborative scenarios.

[0007] In a first aspect, the present invention provides a task and operation and maintenance collaborative scheduling system for an intelligent breeding robot, comprising: a scheduling control unit, a breeding robot, an automatic feeding device, a charging device, and an air shower device; wherein the breeding robot, the automatic feeding device, the charging device, and the air shower device are connected to the scheduling control unit via a wired or wireless communication network; The aforementioned aquaculture robot is used to move within the work area and perform feeding and inspection tasks; The automatic feeding device is used to replenish feed for the breeding robot; The charging device is used to charge the breeding robot; The air shower device is used to clean and dry the breeding robot; The scheduling and control unit includes a task planning module, a maintenance decision module, and an execution control module; The task planning module is used to generate a set of work tasks, including feeding tasks and inspection tasks, based on the work intensity parameters of the breeding workshop, and to allocate the set of work tasks to the breeding robot. The maintenance decision module is used to dynamically generate a set of maintenance strategies for the breeding robot based on the content and status of the completed work tasks fed back by the breeding robot. The set of maintenance strategies includes feeding strategy, charging strategy, air shower strategy and self-inspection strategy. The execution control module is used to control the automatic feeding device, the charging device, and the air shower device to perform corresponding maintenance operations according to the maintenance strategy set after the breeding robot returns to the preset maintenance area.

[0008] Preferably, the system further includes an automatic lifting gate device deployed between the work area and the maintenance area. The automatic lifting gate device is communicatively connected to the execution control module and is used to control the lifting and lowering of the gate according to the passage command of the breeding robot.

[0009] In a second aspect, the present invention provides a method for collaborative scheduling of tasks and maintenance of intelligent farming robots, applied to the system as described in any one of the first aspects, the method comprising: Based on the workload parameters of the breeding workshop, a set of work tasks, including feeding and inspection tasks, is generated and assigned to the breeding robot. After the breeding robot completes the set of work tasks or meets the return conditions, the breeding robot is controlled to return to the preset maintenance area. Based on the content and status of the completed tasks reported by the breeding robot, a set of maintenance strategies for the breeding robot is dynamically generated. The set of maintenance strategies includes feeding strategies, charging strategies, air shower strategies, and self-inspection strategies. Within the maintenance area, the corresponding maintenance device is controlled to perform corresponding maintenance operations on the breeding robot according to the maintenance strategy set; Based on the task execution status and maintenance requirements of all the aforementioned breeding robots, the allocation priority of subsequent work tasks and the scheduling order of maintenance resources are dynamically adjusted.

[0010] Preferably, the work intensity parameters include at least one of the following: number of aquaculture ponds, fish species, and aquaculture cycle; The feeding task includes feeding type, feeding quantity, and feeding strategy information; The inspection task includes information on data collection type, data collection time, and data extraction content.

[0011] Preferably, the dynamic generation of the maintenance strategy set for the aquaculture robot includes: Based on the types and weight of feed consumed in the feeding tasks already completed by the breeding robot, determine the types and weight of feed that need to be replenished. The feeding strategy is determined based on the type and weight of the feed to be supplemented.

[0012] Preferably, the dynamic generation of the maintenance strategy set for the aquaculture robot includes: The charging capacity and charging time are determined based on the remaining battery power of the breeding robot, the estimated energy consumption of the work tasks to be performed, and the occupancy status of the equipment in the maintenance area. The charging strategy is determined based on the charging capacity and the charging time.

[0013] Preferably, the dynamic generation of the maintenance strategy set for the aquaculture robot includes: The duration and intensity of the air shower are determined based on the environmental humidity and level of contaminants encountered by the breeding robot during the inspection task. The air shower strategy is determined based on the air shower duration and the air shower intensity.

[0014] Preferably, the dynamic generation of the maintenance strategy set for the aquaculture robot includes: The depth of self-inspection content and the execution time of self-inspection are determined based on the cumulative duration of high-load tasks performed by the breeding robot or the triggering of specific abnormal events. The self-check strategy is determined based on the depth of the self-check content and the self-check execution time.

[0015] Thirdly, the present invention provides a readable medium including executable instructions, which, when executed by a processor of an electronic device, cause the electronic device to perform any of the methods described in the second aspect.

[0016] Fourthly, the present invention provides an electronic device including a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor performs the method as described in any of the second aspects.

[0017] This invention provides a task and maintenance collaborative scheduling system and method for intelligent aquaculture robots. Addressing the core problem of the disconnect between robot operation and maintenance management in fish farming scenarios, it achieves multiple technological breakthroughs by constructing an integrated intelligent collaborative scheduling system and method for task and maintenance. The system dynamically generates feeding and inspection tasks based on workload parameters such as the number of ponds, fish species, and growth cycle. Based on the actual operation content and status feedback from the robots, it makes real-time and precise decisions on personalized maintenance plans, including feeding strategies, charging strategies, air shower strategies, and self-inspection strategies. This not only achieves precise on-demand feed replenishment, predictive charging matching energy consumption and workload, and efficient cleaning based on the actual degree of environmental contamination, significantly improving resource utilization efficiency and operational continuity; but also optimizes task allocation and maintenance resource scheduling order for multi-robot systems through global monitoring and collaborative scheduling, effectively avoiding congestion in maintenance areas. This enhances the adaptability, overall operational efficiency, and long-term operational reliability of fish farming robot systems, powerfully promoting the intelligent upgrading of factory-style aquaculture.

[0018] The further effects of the aforementioned non-conventional preferred method will be explained below in conjunction with specific embodiments. Attached Figure Description

[0019] To more clearly illustrate the embodiments of the present invention or the existing technical solutions, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the task and operation and maintenance collaborative scheduling system for an intelligent breeding robot provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the composition of a scheduling control unit in a task and operation and maintenance collaborative scheduling system for an intelligent breeding robot according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a task and operation and maintenance collaborative scheduling method for an intelligent breeding robot provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0021] The attached diagram is labeled as follows: 10-Schedule and control unit, 20-Aquaculture robot, 30-Automatic feeding device, 40-Charging device, 50-Air shower device, 110-Task planning module, 120-Maintenance decision module, 130-Execution control module. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0023] The modern fish farming industry is developing towards a high-density, factory-style farming model, with an increasingly urgent need for automation and intelligence in areas such as precise feeding, water environment monitoring, and disease control. Using mobile robots to replace manual labor for automated feeding and pond inspection has become a key means of improving farming efficiency and reducing labor intensity.

[0024] However, existing fish farming robot systems often operate in isolation from their task execution and maintenance management, exhibiting static and simplistic operational strategies that are ill-suited to the specific and dynamic requirements of fish farming scenarios. Specifically, they suffer from the following limitations:

[0025] Fish feeding needs to be dynamically adjusted based on factors such as species, growth stage, water temperature, and feeding behavior. Existing systems typically set fixed feeding cycles or amounts for robots, failing to provide precise feed replenishment based on the differentiated feeding tasks they have just completed (e.g., different types and weights of feed were fed to different ponds). This can easily lead to mixed feed in the robot's hold and a mismatch between spare feed and actual needs, affecting the accuracy of subsequent feeding operations. The high temperature and humidity environment in aquaculture workshops means that after robots operate in water, water stains, feed dust, and microorganisms easily adhere to their bodies and sensors. Existing systems mostly use timed cleaning or simple trigger-based cleaning, without considering the varying levels of contamination encountered by the robot in different areas (e.g., low-oxygen areas prone to bacterial growth, feed distribution areas). Insufficient cleaning can lead to equipment corrosion and sensor malfunction, while excessive cleaning wastes energy and time. The robot's workload (e.g., travel distance, duration of operation of the feeding device under load, and continuous sensor operation time) directly affects its energy consumption. Current charging strategies are mostly based on fixed power thresholds and do not correlate with the amount of work the robot is about to perform (such as continuously inspecting multiple large ponds). This may lead to the robot running out of power midway through a task or frequent recharging trips reducing operational coverage. When deploying multiple robots in a large-scale aquaculture workshop, their task completion times may be concentrated, resulting in intense competition for resources in the maintenance area (charging stations, feeding stations, air showers) within a short period. Existing systems lack global collaborative scheduling of multi-robot task queues and maintenance resources, which can easily lead to congestion and reduce overall operational efficiency.

[0026] In summary, the operation and maintenance management of existing robotic systems for fish farming is static, passive, and isolated. It fails to deeply integrate with dynamically changing farming tasks, complex environmental factors, and multi-machine collaborative scenarios, thus restricting the further improvement of the overall efficiency and reliability of intelligent farming systems.

[0027] In view of this, the present invention provides a task and operation and maintenance collaborative scheduling system for intelligent farming robots. See also... Figure 1 The image shows a specific embodiment of a task and maintenance collaborative scheduling system for an intelligent farming robot provided by the present invention. In this embodiment, the task and maintenance collaborative scheduling system for the intelligent farming robot includes:

[0028] The system includes a scheduling control unit 10, a livestock robot 20, an automatic feeding device 30, a charging device 40, and an air shower device 50. The livestock robot 20, automatic feeding device 30, charging device 40, and air shower device 50 are connected to the scheduling control unit 10 via a wired or wireless communication network. The livestock robot 20 is used to move within the work area and perform feeding and inspection tasks. The automatic feeding device 30 is used to replenish feed for the livestock robot 20. The charging device 40 is used to charge the livestock robot 20. The air shower device 50 is used to clean and dry the livestock robot 20.

[0029] The scheduling and control unit 10 includes a task planning module 110, a maintenance decision module 120, and an execution control module 130. The task planning module 110 generates a set of work tasks, including feeding and inspection tasks, based on the workload parameters of the breeding workshop, and assigns the work task set to the breeding robot 20. The maintenance decision module 120 dynamically generates a set of maintenance strategies for the breeding robot 20 based on the content and status of completed work tasks reported by the breeding robot 20. The maintenance strategy set includes feeding strategies, charging strategies, air shower strategies, and self-inspection strategies. The execution control module 130 controls the automatic feeding device 30, charging device 40, and air shower device 50 to perform corresponding maintenance operations according to the maintenance strategy set after the breeding robot 20 returns to the preset maintenance area.

[0030] The system also includes an automatic lifting gate device deployed between the work area and the maintenance area. The automatic lifting gate device is communicatively connected to the execution control module 130 and is used to control the lifting and lowering of the gate according to the passage command of the breeding robot 20.

[0031] Specifically, the scheduling and control unit 10 is the control center of this system, and is typically deployed on a local server or cloud platform in the breeding workshop. For example... Figure 2 As shown, it integrates three key functional modules: a task planning module 110, a maintenance decision module 120, and an execution control module 130. The core function of the task planning module 110 is to generate a specific, executable set of work tasks based on input workload parameters. Work workload parameters are a comprehensive set of inputs, including at least the number of aquaculture ponds, the species of fish being farmed, and their current aquaculture cycle. This module incorporates or links aquaculture knowledge models and algorithms, enabling it to transform these parameters into precise operational instructions. For example, for bass in their fattening stage, the algorithm calculates the precise daily feeding amount and matches it with "fattening sinking feed" (feeding type), while simultaneously generating the operational instruction of "slowly and evenly spreading along the pond edge" (feeding strategy). For water quality monitoring, it plans patrol tasks requiring the collection of "dissolved oxygen, ammonia nitrogen content, and water surface video images" (data acquisition type), and specifies the continuous collection time at each monitoring point. Finally, this module packages these instructions into a structured "work task set" and dynamically distributes them to each aquaculture robot 20 via a communication network.

[0032] The maintenance decision-making module 120 works closely with the task planning module 110, continuously receiving data packets from the aquaculture robot 20 that are deeply linked to the content and status of completed tasks. This data includes not only quantitative results such as "5 kg of type A feed consumed" and "battery remaining power reduced to 40%", but also environmental contact information such as "high humidity and feed dust adhesion detected by the robot's sensors in area 3". The core innovation of this module lies in its internal dynamic decision-making logic. Instead of using fixed rules, it generates a highly personalized set of maintenance strategies in real time based on a multi-factor, adaptive analysis model. This strategy set is a combination of feeding, charging, air shower, and self-checking strategies. For example, its feeding strategy generator directly and accurately deduces the type and weight of feed to be replenished based on the type and weight of feed consumed reported by the robot, ensuring "quantitative replenishment based on consumption." Its charging strategy generator is more complex, comprehensively considering the robot's current remaining battery power, the estimated energy consumption model of the next stage task issued by the task planning module 110, and the occupancy status of charging piles in the maintenance area obtained in real time by the execution control module 130. This allows it to calculate an optimal charging capacity and charging time scheme that balances charging speed and overall system efficiency, achieving predictive charging. This strategy generation mechanism ensures a strong correlation between maintenance activities and actual workload and real-time system resource status.

[0033] The execution control module 130 is the final executor and coordinator of system commands. This module is activated when the livestock robot 20 returns to the preset maintenance area according to the commands. It is responsible for parsing and accurately executing the maintenance strategy set issued by the maintenance decision module 120. Its workflow is coordinated: First, it sends a command to the automatic lifting gate device via the communication network to open a passage for the robot; then, it controls the robotic arm or feeding mechanism of the automatic feeding device 30 to replenish the robot's hopper with feed according to the type and weight specified in the feeding strategy; next, it guides the robot to park in the designated idle charging pile and sends a command to start charging, while monitoring the charging process; during charging intervals or after charging is completed, it activates the air shower device 50 to perform targeted cleaning of the robot according to the air shower duration and intensity settings in the air shower strategy. For the self-check strategy, it issues a self-check program command to the robot. This module ensures a seamless and reliable transition from intelligent decision-making to physical actions.

[0034] The livestock farming robot 20 is the system's mobile operation terminal. Its core function is defined as autonomously moving within the work area of ​​the livestock farming workshop and precisely executing feeding and inspection tasks issued by the scheduling and control unit 10. The livestock farming robot 20 can be equipped with a feed bin, a precision feeding mechanism, environmental sensors (such as water quality probes and cameras), and a navigation system. It is a unit that directly interacts with the farmed animals and the environment.

[0035] The automatic feeding device 30, charging device 40, and air shower device 50 are specialized support equipment fixed within the maintenance area. The automatic feeding device 30 is an intelligent storage and conveying system capable of storing various feeds and distributing them precisely according to instructions; the charging device 40 is a wireless or wired charging station; and the air shower device 50 is a cleaning device with adjustable airflow and timing. Together, they constitute a "one-stop" logistical support base for the livestock robot 20, receiving and responding to the drive of the execution control module 130 to complete the material, energy, and cleaning maintenance of the robot.

[0036] Through the closed-loop collaboration of the aforementioned components, the entire system achieves a complete intelligent process, from intelligent planning of aquaculture tasks, execution of robot operations, real-time perception of operational status, to dynamic generation and execution of personalized operation and maintenance strategies. In the specific scenario of fish farming, it significantly improves resource utilization efficiency, operational continuity, and the level of system management sophistication.

[0037] This invention also provides a method for collaborative scheduling of tasks and maintenance for intelligent farming robots. See also... Figure 3 The image shows a specific embodiment of a task and maintenance collaborative scheduling method for an intelligent farming robot provided by the present invention. This embodiment of the method is applied to... Figures 1-2 The system's technical solution is essentially the same as the above embodiments, and the corresponding descriptions in the above embodiments also apply to this embodiment. The method includes:

[0038] Step 101: Based on the workload parameters of the breeding workshop, generate and assign a set of work tasks, including feeding and inspection tasks, to the breeding robot; Specifically, in this embodiment, the workload parameter refers to the set of input variables that quantify the workshop production load, obtained from the aquaculture management system or set by the operator. Its core parameters include at least: the number of aquaculture ponds in active operation mode, the specific fish species raised in each pond (e.g., bass, grouper), and the specific growth stage or aquaculture cycle of the fish species (e.g., fry stage, fattening stage). The feeding task is a structured operational instruction, defined by three key pieces of information: feeding type (referring to the specific category of feed, such as a certain type of extruded feed), feeding amount (the amount fed per feeding by weight or volume), and feeding strategy (referring to the specific feeding behavior pattern, such as uniform spreading, fixed-point feeding, slow feeding). Patrol tasks are another type of structured operational instruction, defined by three key information elements: data acquisition type (referring to the physical or chemical parameters to be collected, such as dissolved oxygen, temperature, ammonia nitrogen concentration, and video images), data acquisition time (the duration of continuous collection at each monitoring point), and data extraction content (referring to the key information to be analyzed from the raw data, such as abnormal fish activity index and water quality parameter exceeding limit alarms). The work task set is generated based on the above work intensity parameters, through calculations using built-in aquaculture decision-making models (such as feeding calculation models and inspection cycle models), and contains one or more feeding and patrol tasks that can be assigned to specific execution individuals.

[0039] Step 102: After the breeding robot completes the work task set or meets the return conditions, control the breeding robot to return to the preset maintenance area; Furthermore, completing the work task set means that the farming robot has executed all assigned sub-tasks according to instructions. Meeting the return condition is a preset trigger logic, typically referring to a critical point during task execution where the robot's own state (such as battery power below a safety threshold, insufficient feed in the bin, or equipment self-test error) reaches a point where operation must be interrupted and the robot must return for maintenance. The preset maintenance area is a physically designated area within the workshop specifically for centralized maintenance of the robot, containing various maintenance devices required for subsequent steps. Controlling the farming robot's return means that the scheduling control unit sends navigation commands to the farming robot via a wireless communication network, guiding it to autonomously travel along the optimal path to the maintenance area.

[0040] Step 103: Based on the content and status of the completed tasks reported by the breeding robot, dynamically generate a set of maintenance strategies for the breeding robot. The set of maintenance strategies includes feeding strategies, charging strategies, air shower strategies, and self-inspection strategies. Furthermore, this step is the core of the intelligent operation and maintenance of this invention. The content and status of the completed tasks are datasets fed back by the aquaculture robot and deeply bound to its specific operational history. The corresponding content refers to the specific details of the completed tasks, such as "25 kg of type A feed was fed to ponds 1-5". The status includes changes in its own status caused by task execution (such as battery power dropping from 80% to 50%) and the perceived environmental status (such as high humidity and feed dust adhesion detected in pond area 3). Based on this feedback, the system dynamically generates a set of maintenance strategies for that specific robot.

[0041] Feed replenishment strategy generation: The system extracts information on the types and weights of feed consumed from the feedback data. Through simple reverse mapping, it directly and accurately determines the types and weights of feed that need to be replenished. This ensures that the replenishment operation perfectly matches the actual consumption in the previous work cycle, achieving precise logistical support based on consumption.

[0042] Charging strategy generation: The system comprehensively considers the remaining battery power (current energy state), the estimated energy consumption of the tasks to be performed (based on the task planning module's calculation of the next stage of the task), and the occupancy status of equipment within the maintenance area (such as whether charging piles are idle or require queuing). Through built-in energy management algorithms, the system jointly optimizes the charging capacity (target power) and time (estimated charging duration or the start time of charging) to maximize the utilization rate of charging facilities and the robot's attendance rate while meeting the needs of subsequent operations.

[0043] Air Shower Strategy Generation: This strategy is based on the robot's historical interactions with the environment during inspection tasks. The system dynamically determines the air shower duration and intensity by matching the feedback environmental humidity and contamination level (which can be quantified and graded using sensor data) with a pre-defined cleaning rule library. For example, standard cleaning is used for robots that only encounter normal high-humidity environments, while a high-intensity, long-duration deep cleaning mode is activated for robots reporting a "high contamination level."

[0044] Self-check strategy generation: This strategy aims to achieve predictive maintenance. Triggering conditions are divided into two categories: based on cumulative load, "the cumulative duration of high-load tasks performed by the animal husbandry robot" (such as the duration of continuous heavy-load feeding operations), or based on events, "triggering specific abnormal events" (such as drive motor overheating alarms or navigation module positioning drift). Depending on the different triggering conditions, the system determines differentiated self-check content depth (such as rapid visual inspection or in-depth motor performance diagnostics) and self-check execution time (such as execution during charging intervals or immediate execution).

[0045] Step 104: Within the maintenance area, control the corresponding maintenance device to perform corresponding maintenance operations on the breeding robot according to the maintenance strategy set; Furthermore, in this step, the corresponding maintenance devices specifically refer to the physical equipment deployed within the maintenance area that corresponds one-to-one with each strategy in the maintenance strategy set, namely, automatic feeding devices, charging devices, and air shower devices. Executing corresponding maintenance operations according to the maintenance strategy set means that the scheduling control unit (specifically the execution control module) parses the generated maintenance strategy set, converting each parameterized instruction (such as adding 5 kg of feed A, charging to 80% capacity, and strong air shower for 120 seconds) into a series of control signals that can drive the aforementioned devices. It then coordinates these devices to perform feeding, charging, and cleaning operations on the livestock robot located at the maintenance station in an orderly or parallel manner. This step is the key execution stage for translating intelligent decisions into tangible maintenance results.

[0046] Step 105: Based on the task execution status and maintenance requirements of all breeding robots, dynamically adjust the allocation priority of subsequent work tasks and the scheduling order of maintenance resources.

[0047] Furthermore, this step demonstrates the global optimization capability of this invention in multi-robot collaborative operation scenarios. The task execution status and maintenance requirements of all farming robots are a global monitoring view at the system level, covering the real-time location, operation progress, battery level, and potential or triggered maintenance requirements of each farming robot calculated according to the logic in step 103. Dynamically adjusting the allocation priority of subsequent work tasks means that when the task planning module allocates new tasks, it not only considers the production needs of farming but also comprehensively considers the estimated available time of each robot (e.g., robots that are charging need to wait for them to finish charging), prioritizing the allocation of tasks to robots that can be deployed immediately or have the shortest waiting time. Dynamically adjusting the scheduling order of maintenance resources means that when multiple robots request maintenance simultaneously and resources (e.g., a single air shower device) conflict, the maintenance decision or collaborative scheduling module will reorder the maintenance queue according to the urgency of each robot's maintenance needs, task priority, and other rules. This step effectively resolves resource competition, smooths system load, and maximizes the overall operational throughput of the multi-robot system through system-level feedback and proactive scheduling.

[0048] The following describes this embodiment with specific application examples.

[0049] This embodiment can be applied to an indoor recirculating aquaculture workshop with 12 aquaculture ponds, in which sea bass and grouper at different growth stages are cultured together.

[0050] The task planning module in the scheduling and control unit (a server deployed in the workshop monitoring center) is activated. The module reads or receives workload parameters from the workshop management system, including: the number of active aquaculture ponds (12), the fish species (bass / grouper) in each pond, and their current aquaculture cycle (e.g., bass in the fattening stage, grouper in the juvenile stage). Based on these parameters, the task planning module uses a built-in aquaculture model to generate a set of phased work tasks for the day. For example:

[0051] Feeding Task 1: Feed “Fattening Pellet Feed A” to ponds 1-6 (bass) at a rate of 5 kg per pond, using a slow and even spreading strategy on the water surface.

[0052] Feeding Task 2: Feed “Fry Extruded Feed B” to ponds 7-12 (grouper) at a rate of 1.5 kg per pond, using a fixed-point, small-volume, frequent feeding strategy.

[0053] Patrol Task: Conduct a patrol to collect water quality data from all 12 ponds. Data collection types include pond-side video images (for observing fish activity) and specific point measurements of water temperature and dissolved oxygen. Each measurement should last for 2 minutes, and key information such as abnormal fish aggregation and dissolved oxygen levels below the threshold must be extracted. Subsequently, the task planning module will assign this task set to two aquaculture robots, numbered R1 and R2.

[0054] The aquaculture robots R1 and R2 receive the assigned task instructions through a communication network (in this embodiment, industrial Wi-Fi can be used), autonomously navigate into the work area (i.e., the passageway next to the aquaculture pond), and begin to perform the task.

[0055] Robot R1 performs feeding task 1 and part of the inspection task. Robot R2 performs feeding task 2 and the remaining inspection task. During task execution, the robots automatically record key data. After task completion, the robots package the completed tasks and their status and send them back to the scheduling control unit. The feedback data package may include, for example:

[0056] R1: "Feed A has been fed to pools 1-6, consuming a total of 30 kg; battery power remaining is 45%; average ambient humidity along the patrol route is 92%; high levels of feed dust were detected in the area of ​​pool 4."

[0057] R2: "Feeding of feed B to pools 7-12 has been completed, consuming a total of 9 kg; battery power remaining is 60%; no special waste alarm has been triggered."

[0058] The maintenance decision module of the scheduling and control unit receives the above feedback information in real time and immediately starts the logic for generating personalized maintenance strategies for each robot.

[0059] Maintenance strategy set for R1: Feed replenishment strategy: Based on the consumption of 30 kg of feed A, generate the instruction "Replenish 30 kg of feed A".

[0060] Charging strategy: Based on its current 45% battery level, the estimated energy consumption of the next stage of the task, and the current availability of the charging device, a plan is calculated to "charge to 85%, estimated time 45 minutes".

[0061] Air shower strategy: Based on the high humidity environment and the state of "high feed dust adhesion", generate the instruction of "high intensity air shower, duration 180 seconds".

[0062] Self-check strategy: Because it has just completed a heavy feeding task, it generates an instruction to "perform a quick diagnosis of the feeding motor and transmission mechanism before charging (self-check time 30 seconds)".

[0063] Maintenance strategy set for R2: Supplementation strategy: Supplement with 9 kg of feed B.

[0064] Charging strategy: With high battery level and light task load, generate a plan to "charge to 80%, estimated time 25 minutes".

[0065] Air shower strategy: Generate the instruction "Standard intensity air shower, duration 120 seconds".

[0066] Self-check strategy: There are currently no conditions to trigger a deep self-check, so a command to "only perform a basic system self-check" is generated.

[0067] During the autonomous return of robots R1 and R2 to the maintenance area according to instructions, the execution control module coordinates the opening of the automatic lifting door device. After the robots enter the maintenance area, the execution control module controls each device to perform its functions in an orderly manner according to the maintenance strategy set generated above.

[0068] First, the automatic feeding device replenishes R1 and R2 with the corresponding type and weight of feed. Then, R1 and R2 are guided to idle charging units for charging, and R1 is triggered to perform a designated rapid self-check. During or after charging, according to a strategy, the air shower device cleans and dries R1 and R2 with varying intensities and durations. Throughout the process, the execution control module ensures smooth operation of each maintenance procedure and efficient resource utilization, avoiding conflicts.

[0069] If a third robot, R3, is about to finish its task and request maintenance, but only one air shower unit in the maintenance area is currently occupied by R1 and requires a considerable amount of time, the maintenance decision module can detect this resource contention. It may dynamically adjust its strategy: appropriately advance or postpone R2's air shower task, or generate a temporary instruction for R3 to "delay return and first execute a low-priority additional inspection task," thereby smoothing the maintenance load and optimizing the overall operational efficiency of the multi-robot system.

[0070] As can be seen from the above technical solutions, the beneficial effects of this embodiment are: it not only achieves precise on-demand feed replenishment, predictive charging that matches energy consumption with workload, and efficient cleaning based on the actual degree of environmental contamination, significantly improving resource utilization efficiency and operational continuity; but also optimizes task allocation and maintenance resource scheduling order of multi-robot systems through global monitoring and collaborative scheduling, effectively avoiding congestion in maintenance areas. This enhances the adaptive capabilities, overall operational efficiency, and long-term operational reliability of the fish farming robot system, powerfully promoting the intelligent upgrading of factory-scale aquaculture.

[0071] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include main memory, such as high-speed random-access memory (RAM), or it may also include non-volatile memory, such as at least one disk storage device. Of course, the electronic device may also include other hardware required for other services.

[0072] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. Buses can be categorized as address buses, data buses, and other types. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0073] Memory is used to store instructions for execution. Specifically, instructions for execution are computer programs that can be executed. Memory can include main memory and non-volatile memory, and it provides the processor with execution instructions and data.

[0074] In one possible implementation, the processor reads the corresponding execution instructions from non-volatile memory into main memory and then executes them. Alternatively, it can obtain the corresponding execution instructions from other devices to form a task and operation and maintenance collaborative scheduling system for the intelligent farming robot at the logical level. The processor executes the execution instructions stored in the memory to implement the task and operation and maintenance collaborative scheduling method for the intelligent farming robot provided in any embodiment of the present invention.

[0075] The above is as described in the present invention. Figure 1 The method for executing a task and operation and maintenance collaborative scheduling system for an intelligent aquaculture robot provided in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed through integrated logic circuits in the processor's hardware or through software instructions. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor.

[0076] The steps of the method disclosed in the embodiments of this invention can be directly manifested as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0077] This invention also proposes a readable medium storing execution instructions. When these instructions are executed by the processor of an electronic device, the device can perform a task and maintenance collaborative scheduling method for an intelligent aquaculture robot provided in any embodiment of this invention, specifically for executing, for example... Figure 3 The method shown.

[0078] The electronic devices in the foregoing embodiments may be computers.

[0079] Those skilled in the art will understand that embodiments of the present invention can be provided as methods or computer program products. Therefore, the present invention can be implemented in a completely hardware embodiment, a completely software embodiment, or a combination of software and hardware.

[0080] The various embodiments in this invention are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0081] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0082] The above are merely embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A task and operation and maintenance collaborative scheduling system for an intelligent farming robot, characterized in that, include: The system includes a scheduling and control unit, a breeding robot, an automatic feeding device, a charging device, and an air shower device; the breeding robot, the automatic feeding device, the charging device, and the air shower device are connected to the scheduling and control unit via a wired or wireless communication network. The aforementioned aquaculture robot is used to move within the work area and perform feeding and inspection tasks; The automatic feeding device is used to replenish feed for the breeding robot; The charging device is used to charge the breeding robot; The air shower device is used to clean and dry the breeding robot; The scheduling and control unit includes a task planning module, a maintenance decision module, and an execution control module; The task planning module is used to generate a set of work tasks, including feeding tasks and inspection tasks, based on the work intensity parameters of the breeding workshop, and to allocate the set of work tasks to the breeding robot. The maintenance decision module is used to dynamically generate a set of maintenance strategies for the breeding robot based on the content and status of the completed work tasks fed back by the breeding robot. The set of maintenance strategies includes feeding strategy, charging strategy, air shower strategy and self-inspection strategy. The execution control module is used to control the automatic feeding device, the charging device, and the air shower device to perform corresponding maintenance operations according to the maintenance strategy set after the breeding robot returns to the preset maintenance area.

2. The system according to claim 1, characterized in that, The system also includes an automatic lifting gate device deployed between the work area and the maintenance area. The automatic lifting gate device is communicatively connected to the execution control module and is used to control the lifting and lowering of the gate according to the passage command of the breeding robot.

3. A method for collaborative scheduling of tasks and operations of an intelligent farming robot, applied to the system as described in any one of claims 1-2, characterized in that, The method includes: Based on the workload parameters of the breeding workshop, a set of work tasks, including feeding and inspection tasks, is generated and assigned to the breeding robot. After the breeding robot completes the set of work tasks or meets the return conditions, the breeding robot is controlled to return to the preset maintenance area. Based on the content and status of the completed tasks reported by the breeding robot, a set of maintenance strategies for the breeding robot is dynamically generated. The set of maintenance strategies includes feeding strategies, charging strategies, air shower strategies, and self-inspection strategies. Within the maintenance area, the corresponding maintenance device is controlled to perform corresponding maintenance operations on the breeding robot according to the maintenance strategy set; Based on the task execution status and maintenance requirements of all the aforementioned breeding robots, the allocation priority of subsequent work tasks and the scheduling order of maintenance resources are dynamically adjusted.

4. The method according to claim 3, characterized in that, The work intensity parameters include at least one of the following: number of aquaculture ponds, fish species, and aquaculture cycle; The feeding task includes feeding type, feeding quantity, and feeding strategy information; The inspection task includes information on data collection type, data collection time, and data extraction content.

5. The method according to claim 3, characterized in that, The dynamically generated maintenance strategy set for the aquaculture robot includes: Based on the types and weight of feed consumed in the feeding tasks already completed by the breeding robot, determine the types and weight of feed that need to be replenished. The feeding strategy is determined based on the type and weight of the feed to be supplemented.

6. The method according to claim 3, characterized in that, The dynamically generated maintenance strategy set for the aquaculture robot includes: The charging capacity and charging time are determined based on the remaining battery power of the breeding robot, the estimated energy consumption of the work tasks to be performed, and the occupancy status of the equipment in the maintenance area. The charging strategy is determined based on the charging capacity and the charging time.

7. The method according to claim 3, characterized in that, The dynamically generated maintenance strategy set for the aquaculture robot includes: The duration and intensity of the air shower are determined based on the environmental humidity and level of contaminants encountered by the breeding robot during the inspection task. The air shower strategy is determined based on the air shower duration and the air shower intensity.

8. The method according to claim 3, characterized in that, The dynamically generated maintenance strategy set for the aquaculture robot includes: The depth of self-inspection content and the execution time of self-inspection are determined based on the cumulative duration of high-load tasks performed by the breeding robot or the triggering of specific abnormal events. The self-check strategy is determined based on the depth of the self-check content and the self-check execution time.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 3 to 8.

10. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 3 to 8.

Images