Motor torque control system for multifunctional garden operation device

Abstract

The invention discloses a motor torque control system for a multifunctional garden operation device, and belongs to the technical field of motor torque control. The system comprises a multi-mode sensor module which collects multi-dimensional data of environment and equipment states in real time; the dynamic environment modeling module is used for constructing and updating a working environment model in real time, identifying vegetation types, evaluating topographic features and tracking dynamic objects; the intelligent decision-making module is used for generating an optimal operation strategy by utilizing a task planner, a path optimizer and an action sequence generator based on the operation environment model and a task target; the self-adaptive safety control module is used for evaluating safety risks in the operation process in real time, dynamically generating safety constraints and carrying out intelligent safety management by utilizing a probability risk evaluation model; the precise torque execution module is used for precisely controlling the output torque of the motor so as to execute the optimal operation strategy generated by the intelligent decision module; and the man-machine interaction interface module is used for providing an intuitive visual interface and a manual control interface.

Description

Technical Field

[0001] The present application relates to the technical field of motor torque control, and more specifically, to a motor torque control system for a multifunctional gardening operation device. Background Art

[0002] In modern gardening operations, multifunctional gardening operation devices are increasingly used. Such devices usually include multiple functional modules, such as pruning, fertilizing and watering, to meet the needs of different gardening operations. However, traditional gardening operation equipment has many deficiencies in torque control, mainly manifested in poor adaptability to the working environment, weak dynamic adjustment capabilities and insufficient safety. At present, when facing complex terrain and changing environments, the equipment is often unable to monitor and adjust the output torque of the motor in real time, which affects the efficiency and safety of the operation.

[0003] With the development of sensor technology and intelligent control technology, the combination of multimodal sensors and intelligent decision-making algorithms to achieve dynamic monitoring and optimization of the gardening process has become the key to improving equipment operation efficiency. By accurately controlling the output torque of the motor, the working state of the equipment can be optimized according to the actual load and environmental changes to ensure efficient gardening operations. In addition, safety is also an important factor that cannot be ignored in gardening operations. Real-time safety risk monitoring and intelligent safety management will greatly reduce the risk of accidents during operations.

[0004] In summary, how to achieve precise control of motor torque in a multifunctional gardening operation device and dynamically adapt to complex environments and operation requirements has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In order to overcome a series of defects in the prior art, the purpose of this application is to provide a motor torque control system for a multifunctional gardening operation device, including the following modules:

[0006] The multimodal sensor module collects multi-dimensional data of the environment and device status in real time by integrating multiple sensors to achieve comprehensive environmental perception and dynamic monitoring;

[0007] Dynamic environment modeling module, which builds and updates the operating environment model in real time, identifies vegetation types, evaluates terrain features and tracks dynamic objects to support intelligent decision-making;

[0008] Intelligent decision-making module, based on the working environment model and task objectives, uses task planner, path optimizer and action sequence generator to generate the optimal working strategy to achieve efficient gardening operations;

[0009] Adaptive safety control module, which evaluates safety risks during operation in real time, dynamically generates safety constraints, and uses probabilistic risk assessment models for intelligent safety management;

[0010] Precise torque execution module, which precisely controls the output torque of the motor to execute the optimal operation strategy generated by the intelligent decision-making module to achieve efficient operation;

[0011] The human-computer interaction interface module provides an intuitive visual interface and manual control interface, supports manual operation and voice command control, and realizes efficient human-computer collaboration.

[0012] Furthermore, the multimodal sensor module includes the following components:

[0013] High-resolution camera array, which consists of multiple high-resolution cameras to achieve 360-degree visual perception and capture detailed image information of the environment;

[0014] Torque sensors are installed on key joints and actuators of the equipment to monitor the stress of each component of the equipment in real time to ensure force control and equipment safety during operation;

[0015] LiDAR scanners that quickly and accurately measure the 3D structure of the surrounding environment for terrain mapping and dynamic obstacle tracking;

[0016] Inertial measurement unit, which integrates accelerometer, gyroscope and magnetometer to monitor the attitude, orientation and motion of the device in real time, providing key data for precise navigation and stable control;

[0017] The environmental sensor group integrates a variety of environmental sensors to monitor local environmental parameters and provide a basis for plant maintenance and operation strategy adjustments.

[0018] Furthermore, the dynamic environment modeling module includes the following components:

[0019] 3D point cloud generation unit, used to generate and update high-precision 3D point cloud models in real time, providing basic spatial information for subsequent analysis and decision-making;

[0020] Vegetation identification and classification unit, used to quickly identify and classify different types of vegetation, providing accurate plant information for gardening operations;

[0021] The terrain feature analysis unit identifies and quantifies terrain undulations, slopes, and texture features based on a three-dimensional point cloud model, providing terrain information for path planning and operation strategy formulation;

[0022] Dynamic object tracking unit, which detects and tracks moving objects in the environment in real time and updates dynamic elements in the 3D point cloud model in real time;

[0023] The semantic segmentation unit performs semantic understanding and segmentation of the environment, divides the work scene into different functional areas, and provides contextual information for intelligent decision-making;

[0024] The spatiotemporal data fusion unit integrates the data from various units to build a unified, real-time updated four-dimensional operating environment model, providing a comprehensive environmental representation for the intelligent decision-making module.

[0025] Furthermore, the intelligent decision-making module includes the following components:

[0026] Task parser, which parses the high-level task instructions input by the user to convert them into specific job objectives and constraints;

[0027] Environmental status evaluator, which analyzes the operating environment model in real time, evaluates the status and characteristics of the current operating environment, and provides the latest environmental status information for the decision-making process;

[0028] The task planner generates a high-level work plan based on the work objectives and environmental status information, including task decomposition and priority sorting, to ensure the logic and efficiency of the overall operation;

[0029] The path optimizer combines the working environment model and the working plan to calculate the optimal movement path and realize the efficient navigation of the equipment in the complex garden environment;

[0030] The action sequence generator converts the optimal motion path into a specific equipment action instruction sequence to ensure accurate execution of the operation;

[0031] The strategy evaluator and adjuster monitors job execution in real time, evaluates strategy effectiveness, and dynamically adjusts decisions based on feedback to achieve adaptive optimization and continuous improvement.

[0032] Furthermore, the optimal motion path is calculated by combining the working environment model and the working plan to realize efficient navigation of the equipment in a complex garden environment, including the following steps:

[0033] Based on the 3D point cloud data and semantic segmentation information provided by the dynamic environment modeling module, a high-precision environment map is constructed. At the same time, the dynamic elements in the map are updated in real time using the data of the dynamic object tracking unit to ensure that the path planning is based on the latest environment information;

[0034] According to the operation plan generated by the intelligent decision-making module, the overall operation is broken down into a series of specific operation areas, and the operation sequence is determined according to the task priority and logical sequence;

[0035] Integrate constraints from different modules and transform them into a set of rules that the path planning algorithm can handle;

[0036] Based on the selected path planning algorithm, an initial feasible path from the starting point to the end point is generated taking into account the rule set;

[0037] Using the gradient descent method, multiple objective functions including path length, energy consumption, time and safety margin are comprehensively considered to optimize the initial feasible path until the preset optimization goal or number of iterations is reached;

[0038] A dynamic adjustment mechanism for the path is introduced to cope with unexpected situations that may be encountered during the execution process. At the same time, a feedback loop with other modules is established to continuously optimize the path planning strategy according to the actual execution situation.

[0039] Furthermore, the adaptive security control module includes the following components:

[0040] Real-time risk monitor, which continuously monitors data streams from multi-modal sensor modules to detect potential safety hazards and abnormal conditions in real time;

[0041] Probabilistic risk assessment model, which quantifies the detected risk factors based on Monte Carlo simulation and calculates the risk probability under different scenarios;

[0042] Dynamic safety constraint generator, based on risk assessment results, generates safety constraint conditions that adapt to the current environment and operating status in real time to ensure the safety of the operating process;

[0043] The emergency response policy controller presets and dynamically updates a series of emergency response plans for different levels of security risks, and quickly activates corresponding policies when high-risk situations are detected.

[0044] Furthermore, the risk probability is calculated by the following formula: Where N is the total number of simulations, that is, the number of different operation scenarios generated; P risk is the overall risk probability, which indicates the proportion of safety risks occurring in all simulation scenarios; R1, R2, ..., R n To influence the security risk in each scenario; I(S j |R1, R2, ..., R n ) indicates that in scenario S j In the process, after comprehensively considering multiple risk factors, whether a security risk has occurred.

[0045] Furthermore, the safety constraint condition S(t) is expressed as: S(t) = α·S base +(1-α)·S adj (C(t)), where S base Indicates the basic safety constraints applicable when the risk level is low; S adj(C(t)) is the safety constraint adjusted according to the current environment and operation status C(t); α is a dynamically adjusted weight coefficient that changes based on the risk probability: when P risk ≤θ1, α=1; when θ1<P risk When θ2 is less than When P risk When ≥θ2, α=0; θ1 and θ2 are the thresholds of risk assessment results, which are used to divide risk levels.

[0046] Furthermore, the precise torque execution module includes the following components:

[0047] High-precision torque sensor measures the actual torque of the motor output shaft in real time, providing accurate feedback data and laying the foundation for closed-loop control;

[0048] Adaptive PID controller, which dynamically calculates and adjusts PID parameters to generate precise control signals based on the deviation between the setpoint and actual torque feedback;

[0049] The motor driver receives the control signal and accurately adjusts the motor input current to achieve direct control of the motor output torque;

[0050] Load characteristic identifier, which identifies and predicts various load changes in gardening operations by analyzing motor parameters and environmental data in real time, so as to improve the response speed to external environmental changes;

[0051] Torque command parser converts the operation plan and equipment action command sequence generated by the intelligent decision-making module into specific torque control commands to ensure the accurate implementation of the execution strategy;

[0052] The performance monitoring and diagnostic unit continuously monitors the torque control performance, detects abnormal conditions, and provides real-time diagnosis to ensure long-term stable operation.

[0053] Furthermore, the control signal is expressed as: Where u(t) is the control signal for adjusting the motor input; e(t) is the torque error, that is, the difference between the expected torque and the actual torque; f p (e(t)) is the proportional gain function after dynamic adjustment, which is adjusted according to the current torque error e(t); f i (e(t)) is the dynamically adjusted integral gain function, taking into account the cumulative error changes and load conditions; f d (e(t)) is the dynamically adjusted differential gain function, which is used to quickly respond to the rate of change of the torque error; e(τ) represents the error value at time τ; dτ represents the time increment used in the integral calculation; de(t) represents the small change in the error e(t) at time t; t represents the current time; dt represents the time increment used in the differential calculation.

[0054] Compared with the prior art, the beneficial effects of this application are:

[0055] This application uses multimodal sensors to achieve real-time environmental perception and dynamic monitoring, combines dynamic environmental modeling and intelligent decision-making modules to generate efficient operation strategies, and introduces adaptive safety control and precise torque execution mechanisms to ensure the efficiency, safety and accuracy of the garden operation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a structural diagram of a motor torque control system for a multifunctional gardening operation device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical scheme and advantages of the implementation of the present invention clearer, the technical scheme in the embodiment of the present invention will be described in more detail below in conjunction with the drawings in the embodiment of the present invention. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of the present invention, not all of the embodiments.

[0058] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0059] The embodiments and directional terms described below with reference to the accompanying drawings are exemplary and intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0060] like Figure 1 As shown, a motor torque control system for a multifunctional gardening operation device includes the following modules:

[0061] The multimodal sensor module collects multi-dimensional data of the environment and device status in real time by integrating multiple sensors to achieve comprehensive environmental perception and dynamic monitoring;

[0062] Dynamic environment modeling module, which builds and updates the operating environment model in real time, identifies vegetation types, evaluates terrain features and tracks dynamic objects to support intelligent decision-making;

[0063] Intelligent decision-making module, based on the working environment model and task objectives, uses task planner, path optimizer and action sequence generator to generate the optimal working strategy to achieve efficient gardening operations;

[0064] Adaptive safety control module, which evaluates safety risks during operation in real time, dynamically generates safety constraints, and uses probabilistic risk assessment models for intelligent safety management;

[0065] Precise torque execution module, which precisely controls the output torque of the motor to execute the optimal operation strategy generated by the intelligent decision-making module to achieve efficient operation;

[0066] The human-computer interaction interface module provides an intuitive visual interface and manual control interface, supports manual operation and voice command control, and realizes efficient human-computer collaboration.

[0067] In this embodiment, the multimodal sensor module is a basic component of the multifunctional garden operation device, which is responsible for collecting multi-dimensional data of the environment and equipment status by integrating multiple sensors. The data acquisition capability of the multimodal sensor greatly enhances the understanding of the surrounding environment of the operation device. The data collected in real time can be used to monitor the growth status of plants, soil conditions and climate change, thereby providing a scientific basis for subsequent decision-making. In addition, through data fusion technology, this module can effectively reduce redundant data and improve the accuracy and reliability of data. Through these data, the operation device can identify and adapt to different environmental conditions, enhancing the flexibility and intelligence level of the operation. The successful implementation of this module has laid a solid foundation for the automation of garden operations.

[0068] In this embodiment, by using machine learning algorithms and computer vision technology, the dynamic environment modeling module can extract key information in a complex environment, thereby generating an accurate environmental model. Real-time environmental modeling ensures that the operating device can adapt to changing operating conditions. For example, when the vegetation type or terrain features change, the module can quickly update the model to ensure the effectiveness of the operating strategy. At the same time, through dynamic object tracking technology, moving objects in the operating area can be monitored in real time to avoid potential conflicts and damage. This module provides the necessary background information for intelligent decision-making, making garden operations more accurate and efficient. By comprehensively analyzing environmental factors, the dynamic environment modeling module can provide a solid foundation for subsequent intelligent decision-making and ensure the smooth progress of the operating process.

[0069] In this embodiment, the intelligent decision-making module is the core part of the entire system. Based on the dynamic environment model and the preset task objectives, the task planner, path optimizer and action sequence generator are used to generate the optimal operation strategy. The task planner determines the most suitable operation task based on real-time data analysis, while the path optimizer calculates the optimal operation path based on environmental information and equipment status to reduce operation time and resource consumption. In addition, the action sequence generator can generate specific execution action sequences based on the planned tasks and paths to achieve efficient gardening operations. This module uses artificial intelligence and optimization algorithms to ensure the intelligence and flexibility of the operation strategy, and can be dynamically adjusted according to environmental changes and operation requirements, greatly improving operation efficiency and safety. Through real-time decision-making capabilities, the intelligent decision-making module not only improves the automation level of the operation, but also enables the operation device to respond flexibly in a changing environment, bringing revolutionary changes to gardening operations.

[0070] In this embodiment, the adaptive safety control module plays a vital role in the garden operation process. Its main function is to evaluate the safety risks in the operation process in real time and dynamically generate safety constraints. The module uses a probabilistic risk assessment model to continuously monitor the working environment and identify potential safety hazards, such as obstacles, dynamic personnel or animals. By analyzing real-time data, the module can generate intelligent safety management strategies to ensure that the operating device follows safety standards when performing various tasks. For example, when approaching an area with people or animals, the module will automatically reduce the speed of the equipment or issue a warning to avoid accidents. The existence of this module greatly improves the safety of the operation process, provides reliable protection for the operator and the surrounding environment, and reduces the risk of accidents caused by equipment failure or human error.

[0071] In this embodiment, the precise torque execution module is the execution unit of the entire system, which is responsible for precisely controlling the output torque of the motor to execute the optimal operation strategy generated by the intelligent decision-making module. This module monitors the operating status of the motor in real time through a high-precision sensor to ensure that the motor outputs the required torque during operation, thereby ensuring the stability and reliability of the equipment under various operating conditions. By controlling the torque output of the motor, it is possible to fine-tune the operation intensity to adapt to different operating requirements and environmental conditions. For example, when cultivating the soil, the adjustment of the torque output can effectively prevent the equipment from over-compacting the soil and improve the quality of the operation. At the same time, precise torque control can also extend the service life of the equipment, reduce energy consumption, and improve operating efficiency. This module plays an important role in the entire garden operation and is an important guarantee for achieving efficient operation.

[0072] In this embodiment, the human-machine interaction interface module provides the operator with an intuitive visual interface and manual control interface, supports manual operation and voice command control, and realizes efficient human-machine collaboration. The module displays real-time data and operation status through a friendly user interface, allowing the operator to easily monitor the operation of the equipment and make necessary adjustments. At the same time, the implementation of the voice command control function further enhances the convenience of operation, allowing the operator to control the equipment through voice commands even when his hands are busy. The design of this module fully considers the operator's user experience, and improves work efficiency and reduces learning costs through concise and clear information display and convenient operation methods. In addition, the system's feedback mechanism enables the operator to obtain the status information of the equipment in a timely manner, ensures transparency and controllability during the operation process, and enhances the safety and reliability of the equipment.

[0073] In summary, the motor torque control system for multifunctional garden operation devices realizes efficient, safe and intelligent garden operations through the synergy of multimodal sensor module, dynamic environment modeling module, intelligent decision-making module, adaptive safety control module, precise torque execution module and human-computer interaction interface module. The innovation of these modules not only improves the operating efficiency and safety of the equipment, but also enhances its adaptability and autonomous decision-making ability in complex environments. In the future, with the continuous development of technology, this system is expected to play an important role in a wider range of garden and agricultural fields, and promote the progress and development of smart agriculture.

[0074] Furthermore, the multimodal sensor module includes the following components:

[0075] High-resolution camera array, which consists of multiple high-resolution cameras to achieve 360-degree visual perception and capture detailed image information of the environment;

[0076] Torque sensors are installed on key joints and actuators of the equipment to monitor the stress of each component of the equipment in real time to ensure force control and equipment safety during operation;

[0077] LiDAR scanners that quickly and accurately measure the 3D structure of the surrounding environment for terrain mapping and dynamic obstacle tracking;

[0078] Inertial measurement unit, which integrates accelerometer, gyroscope and magnetometer to monitor the attitude, orientation and motion of the device in real time, providing key data for precise navigation and stable control;

[0079] The environmental sensor group integrates a variety of environmental sensors to monitor local environmental parameters and provide a basis for plant maintenance and operation strategy adjustments.

[0080] In this embodiment, the high-resolution camera array captures detailed image information of the environment through the collaborative work of multiple high-resolution cameras, providing rich visual data for subsequent environmental analysis and decision-making. High-resolution cameras can clearly identify the type of vegetation, health status and environmental characteristics of its surroundings, and support complex visual analysis, such as vegetation coverage, pest and disease monitoring, and growth assessment. Due to its wide viewing angle coverage, the camera array can flexibly respond to different lighting conditions, provide real-time image information for the equipment's autonomous navigation and obstacle detection, and ensure safety and efficiency during the operation process. In addition, image data can also be fused with other sensor data to form a more comprehensive environmental perception system, thereby optimizing the overall strategy of garden operations.

[0081] In this embodiment, the role of the torque sensor is not limited to providing real-time torque data, but more importantly, it ensures force control and equipment safety during the operation. In gardening operations, each movement of the equipment requires precise force application. The torque sensor can provide necessary feedback information to ensure that the equipment applies appropriate force when performing operations such as soil cultivation and plant pruning to avoid damage to plants. In addition, the torque sensor can also monitor the working status of the equipment, prevent safety accidents caused by overload or mechanical failure, and ensure that the equipment operates in the best condition through real-time data collection and analysis, thereby improving work efficiency and safety.

[0082] In this embodiment, the LiDAR scanner can generate high-precision terrain maps and environmental models through laser emission and reception technology. The rapid measurement capability of LiDAR enables it to effectively track obstacles in a dynamic operating environment, provide real-time environmental information for the equipment, and ensure safe operation. In gardening operations, LiDAR can not only be used for terrain mapping, but also to identify and avoid potential obstacles such as pedestrians, animals, or other equipment. This efficient obstacle detection capability greatly improves the adaptability of the equipment in complex environments, and also provides important basic data for subsequent adjustments to operating strategies. In addition, the three-dimensional model generated by LiDAR can be fused with other sensor data to improve the accuracy and reliability of environmental perception.

[0083] In this embodiment, the inertial measurement unit (IMU) is an advanced sensor module that integrates an accelerometer, a gyroscope, and a magnetometer, which is responsible for real-time monitoring of the device's attitude, direction, and motion state. This module provides key data for the precise navigation and stable control of the device, ensuring that the device operates smoothly on complex terrain. In gardening operations, the use of IMU can improve the positioning accuracy of the equipment in different operating environments, ensuring that each movement complies with the preset path and operating strategy. For example, when the device is operating on a slope or uneven ground, the IMU can provide real-time feedback on attitude changes, helping the device to automatically adjust its posture to maintain balance and stability. The introduction of this component enables the device to have self-correction capabilities during the operation process, which not only improves the efficiency of the operation, but also enhances the safety and reliability of the equipment.

[0084] In this embodiment, the environmental sensor group is another key component of the multimodal sensor module, which integrates a variety of environmental sensors to monitor local environmental parameters. The comprehensive application of these sensors provides an important basis for plant maintenance and operation strategy adjustment. For example, through the soil moisture sensor, the equipment can monitor the moisture status of the soil in real time to determine whether irrigation or fertilization is needed. Temperature and humidity sensors can monitor climate change and help the equipment adjust the operation plan in time to optimize the growth environment of plants. The data of the environmental sensor group not only helps to improve the accuracy of gardening operations, but also realizes intelligent management and promotes the realization of sustainable development goals. In addition, environmental data can also be fused and analyzed with data from other modules to further improve operation efficiency and effectiveness.

[0085] In summary, the multimodal sensor module provides comprehensive and accurate environmental perception capabilities for the multifunctional garden operation device through the synergy of high-resolution camera array, torque sensor, lidar scanner, inertial measurement unit and environmental sensor group. These components perform their respective functions and provide a rich information basis for the intelligent decision-making module through real-time data collection and analysis, ensuring the efficiency, safety and intelligence of garden operations.

[0086] Furthermore, the dynamic environment modeling module includes the following components:

[0087] 3D point cloud generation unit, used to generate and update high-precision 3D point cloud models in real time, providing basic spatial information for subsequent analysis and decision-making;

[0088] Vegetation identification and classification unit, used to quickly identify and classify different types of vegetation, providing accurate plant information for gardening operations;

[0089] The terrain feature analysis unit identifies and quantifies terrain undulations, slopes, and texture features based on a three-dimensional point cloud model, providing terrain information for path planning and operation strategy formulation;

[0090] Dynamic object tracking unit, which detects and tracks moving objects in the environment in real time and updates dynamic elements in the 3D point cloud model in real time;

[0091] The semantic segmentation unit performs semantic understanding and segmentation of the environment, divides the work scene into different functional areas, and provides contextual information for intelligent decision-making;

[0092] The spatiotemporal data fusion unit integrates the data from various units to build a unified, real-time updated four-dimensional operating environment model, providing a comprehensive environmental representation for the intelligent decision-making module.

[0093] In this embodiment, the three-dimensional point cloud generation unit is one of the core components of the dynamic environment modeling module, and its main function is to generate and update high-precision three-dimensional point cloud models in real time. The unit captures the spatial information of the surrounding environment through the combination of laser radar and other sensors, and converts it into point cloud data to form a three-dimensional environmental model. This high-precision three-dimensional point cloud model provides basic spatial information for subsequent analysis and decision-making, and supports complex spatial analysis tasks such as obstacle detection, path planning, and boundary definition of the working area. Through continuously updated point cloud data, it can dynamically reflect changes in the environment and ensure that emergencies can be responded to in a timely manner when performing garden operations. In addition, the application of the three-dimensional point cloud generation unit can improve the accuracy and efficiency of operations, reduce resource waste, and provide a scientific basis for garden management.

[0094] In this embodiment, the vegetation identification and classification unit plays a vital role in the dynamic environment modeling module, and is responsible for quickly identifying and classifying different types of vegetation. This unit uses image processing and machine learning technology to accurately identify a variety of plant types and their growth status by analyzing data from high-resolution cameras and other sensors. This function not only provides accurate plant information for gardening operations, but also provides a scientific basis for subsequent maintenance and management measures. For example, by timely identifying pest-infested vegetation, corresponding maintenance plans can be automatically triggered, such as spraying pesticides or pruning. The efficient operation of this module can significantly improve the accuracy and pertinence of gardening operations, achieve more scientific plant management, and provide support for the healthy development of garden ecology.

[0095] In this embodiment, the terrain feature analysis unit focuses on identifying and quantifying the undulations, slopes, and texture features of the terrain based on the generated three-dimensional point cloud model. By analyzing these terrain features, crucial information can be provided for path planning and operation strategy formulation. For example, the equipment can determine the best operation route based on the terrain undulations, avoid working on steep slopes or uneven ground, and reduce equipment damage and operation risks. At the same time, terrain feature analysis can also help formulate reasonable soil improvement and irrigation strategies to improve the efficiency of crop growth. The introduction of this module not only improves the safety and efficiency of operations, but also supports the goal of environmental protection, avoids operations under unsuitable terrain conditions, and thus achieves sustainable garden management.

[0096] In this embodiment, the dynamic object tracking unit is responsible for real-time detection and tracking of moving objects in the environment to ensure timely updating of dynamic elements in the three-dimensional point cloud model. This unit can use lidar, cameras and other sensor fusion technologies to accurately identify dynamic objects around it, such as pedestrians, animals or other equipment. Real-time tracking of dynamic objects not only improves safety during the operation and avoids potential collision risks, but also optimizes the operation strategy. For example, in garden pruning operations, the work plan can be adjusted according to the position of dynamic objects to ensure the continuity and efficiency of the operation. The efficient operation of this unit provides intelligent environmental perception capabilities for garden operations, enabling equipment to cope with complex working environments and improve overall operating efficiency.

[0097] In this embodiment, the semantic segmentation unit is based on machine learning and deep learning technology, and can analyze the image and point cloud data to identify the functional characteristics of different areas, such as vegetation areas, trails, open areas, and buildings. This spatial subdivision provides rich contextual information for intelligent decision-making, enabling the system to formulate corresponding operation strategies according to the characteristics of different areas. For example, in an environment with obvious vegetation areas and trail areas, watering and fertilizing can be prioritized in the vegetation areas, while the maintenance of the trails can be left to subsequent operations. The introduction of semantic segmentation has greatly improved the accuracy and efficiency of garden operations, making resource allocation and operation arrangements more scientific and reasonable.

[0098] In this embodiment, the spatiotemporal data fusion unit plays a connecting role in the dynamic environment modeling module. It integrates data from various units to build a unified, real-time updated four-dimensional operating environment model. This four-dimensional model not only contains spatial information, but also adds a time dimension to reflect the changes in the environment over time. This unit provides a comprehensive environmental representation for the intelligent decision-making module, making the decision-making process more scientific and accurate. For example, the system can predict the growth of plants by analyzing the changes in environmental parameters in different time periods, and formulate appropriate maintenance plans accordingly. Through spatiotemporal data fusion, the equipment can achieve autonomous navigation and intelligent operation in a dynamic environment, providing strong support for the realization of comprehensive intelligent garden management.

[0099] In summary, the dynamic environment modeling module provides comprehensive and accurate environmental perception and dynamic modeling capabilities for the multifunctional garden operation device through the close collaboration of the three-dimensional point cloud generation unit, vegetation recognition and classification unit, terrain feature analysis unit, dynamic object tracking unit, semantic segmentation unit and spatiotemporal data fusion unit. The effective combination of these components not only improves the safety and efficiency of garden operations, but also provides a data basis for scientific garden management. With the continuous development of intelligent technology, the dynamic environment modeling module will be further optimized to make greater contributions to the intelligent and sustainable development of future garden operations.

[0100] Furthermore, the intelligent decision-making module includes the following components:

[0101] Task parser, which parses the high-level task instructions input by the user to convert them into specific job objectives and constraints;

[0102] Environmental status evaluator, which analyzes the operating environment model in real time, evaluates the status and characteristics of the current operating environment, and provides the latest environmental status information for the decision-making process;

[0103] The task planner generates a high-level work plan based on the work objectives and environmental status information, including task decomposition and priority sorting, to ensure the logic and efficiency of the overall operation;

[0104] The path optimizer combines the working environment model and the working plan to calculate the optimal movement path and realize the efficient navigation of the equipment in the complex garden environment;

[0105] The action sequence generator converts the optimal motion path into a specific equipment action instruction sequence to ensure accurate execution of the operation;

[0106] The strategy evaluator and adjuster monitors job execution in real time, evaluates strategy effectiveness, and dynamically adjusts decisions based on feedback to achieve adaptive optimization and continuous improvement.

[0107] In this embodiment, the task parser is the core component of the intelligent decision-making module, which is responsible for parsing the high-level task instructions input by the user and converting them into specific operation goals and constraints. Through natural language processing technology, the task parser can understand the user's intentions and extract relevant operation requirements and constraints. This function greatly simplifies the interaction between the user and the system, allowing the user to input task requirements in an intuitive way. At the same time, the task parser can decompose complex task instructions into executable subtasks, providing a clear framework for subsequent decision-making and execution. By effectively connecting the user's needs with the system's capabilities, the task parser lays a solid foundation for the entire intelligent decision-making process and ensures the smooth progress of garden operations.

[0108] In this embodiment, the environmental status evaluator can update environmental information in real time by integrating data from multimodal sensors, including climate conditions, soil moisture, and plant health status. This information is crucial for formulating operation strategies. For example, when the environmental status evaluator detects impending bad weather or plant water shortage, it can automatically adjust the operation plan to prioritize emergency tasks. The introduction of the environmental status evaluator ensures the scientificity and timeliness of system decisions, enabling garden operations to respond more flexibly to changing environmental conditions and improve the safety and efficiency of operations.

[0109] In this embodiment, the task planner can dynamically adjust the order of operations based on the real-time information provided by the environmental assessor to ensure the logic and efficiency of the operations. For example, in a complex garden environment, the task planner will reasonably arrange operations such as watering, fertilizing, and pruning based on the growth status of the plants, the terrain characteristics, and the current location of the equipment to avoid waste of resources and improve the operation effect. In addition, the task planner can also generate alternative plans to deal with potential emergencies to ensure the continuity and efficiency of the entire operation process. Its intelligent task planning function greatly improves the flexibility and responsiveness of garden operations.

[0110] In this embodiment, the path optimizer uses advanced algorithms, such as the A* algorithm or the Dijkstra algorithm, to analyze terrain features and obstacle information to generate a safe and efficient driving path. The operation of the path optimizer not only takes into account the shortest path, but also evaluates the terrain undulations, obstacle locations, and the dynamic state of the equipment to ensure the stability and safety of the equipment during operation. For example, when the equipment needs to cross different types of ground, the path optimizer can select the most suitable driving route to reduce the risk of equipment failure and accidents. Through precise path planning, the path optimizer provides strong support for the intelligent navigation and efficient operation of the equipment.

[0111] In this embodiment, the action sequence generator analyzes the motion path generated by the path optimizer to refine the specific instructions for each motion step, including speed, steering angle, and operation. The introduction of the action sequence generator enables the device to efficiently perform tasks according to the predetermined motion trajectory and operation plan, avoiding operational errors caused by unclear instructions. In addition, the generated instruction sequence can be updated in real time to adapt to changes in the dynamic environment, thereby ensuring the flexibility and adaptability of the operation. The accuracy and reliability of the action sequence generator provide guarantees for the smooth implementation of garden operations and promote the development of intelligent operations.

[0112] In this embodiment, the strategy evaluation and adjuster is an indispensable component of the intelligent decision-making module, which is responsible for real-time monitoring of job execution, evaluating the effectiveness of the strategy, and dynamically adjusting the decision based on feedback. This component evaluates the effectiveness of the current strategy by collecting real-time data during the operation, such as equipment operating status, operation progress, and environmental changes. This real-time feedback mechanism enables the system to perform adaptive optimization according to actual conditions and adjust the operation strategy in a timely manner to improve operation efficiency and quality. For example, if it is monitored that a certain operation strategy does not achieve the expected effect, the strategy evaluation and adjuster can automatically adjust the execution order or method of subsequent tasks to ensure the realization of the ultimate goal. By introducing an adaptive adjustment mechanism, the module can achieve continuous improvement and promote the development of garden operations towards intelligence and efficiency.

[0113] In summary, the intelligent decision-making module provides efficient and intelligent decision support for the multifunctional garden operation device through the close cooperation of the task parser, environmental state evaluator, task planner, path optimizer, action sequence generator and strategy evaluation and adjuster. The synergy of these components ensures the logic, flexibility and adaptability of garden operations, laying a solid foundation for efficient and accurate garden management.

[0114] Furthermore, the optimal motion path is calculated by combining the working environment model and the working plan to realize efficient navigation of the equipment in a complex garden environment, including the following steps:

[0115] Based on the 3D point cloud data and semantic segmentation information provided by the dynamic environment modeling module, a high-precision environment map is constructed. At the same time, the dynamic elements in the map are updated in real time using the data of the dynamic object tracking unit to ensure that the path planning is based on the latest environment information;

[0116] According to the operation plan generated by the intelligent decision-making module, the overall operation is broken down into a series of specific operation areas, and the operation sequence is determined according to the task priority and logical sequence;

[0117] Integrate constraints from different modules and transform them into a set of rules that the path planning algorithm can handle;

[0118] Based on the selected path planning algorithm, an initial feasible path from the starting point to the end point is generated taking into account the rule set;

[0119] Using the gradient descent method, multiple objective functions including path length, energy consumption, time and safety margin are comprehensively considered to optimize the initial feasible path until the preset optimization goal or number of iterations is reached;

[0120] A dynamic adjustment mechanism for the path is introduced to cope with unexpected situations that may be encountered during the execution process. At the same time, a feedback loop with other modules is established to continuously optimize the path planning strategy according to the actual execution situation.

[0121] Through the above steps, the path optimizer can achieve efficient navigation in complex garden environments. From building a high-precision environmental map based on 3D point cloud data to dynamically adjusting the path planning strategy, the entire process not only ensures the logic and efficiency of the operation, but also maximizes safety. This intelligent path planning and optimization method provides a solid foundation for the efficient operation of multifunctional garden operation devices, enabling them to respond flexibly to various complex environmental conditions, and promoting the intelligent and efficient development of garden operations.

[0122] Furthermore, the adaptive security control module includes the following components:

[0123] Real-time risk monitor, which continuously monitors data streams from multi-modal sensor modules to detect potential safety hazards and abnormal conditions in real time;

[0124] Probabilistic risk assessment model, which quantifies the detected risk factors based on Monte Carlo simulation and calculates the risk probability under different scenarios;

[0125] Dynamic safety constraint generator, based on risk assessment results, generates safety constraint conditions that adapt to the current environment and operating status in real time to ensure the safety of the operating process;

[0126] The emergency response policy controller presets and dynamically updates a series of emergency response plans for different levels of security risks, and quickly activates corresponding policies when high-risk situations are detected.

[0127] In this embodiment, the real-time risk monitor continuously monitors the data stream from the multimodal sensor module to detect potential safety hazards and abnormal conditions in real time. By integrating information from multiple sensors, such as high-resolution cameras, lidars, and environmental sensors, the real-time risk monitor can provide comprehensive environmental monitoring capabilities. It can not only identify static obstacles, but also track the movement trajectory of dynamic objects, thereby identifying potential threats that may cause safety accidents. For example, if the monitor detects that a person or other moving object accidentally enters the working area, it will immediately issue an alarm and take corresponding measures. This real-time monitoring capability provides important safety protection for gardening operations, allowing operators to respond quickly in abnormal situations, thereby reducing the probability of accidents.

[0128] In this embodiment, the risk factors detected by the real-time risk monitor will be input into the probabilistic risk assessment model, which performs quantitative analysis on the detected risks based on Monte Carlo simulation. Monte Carlo simulation can generate risk probability distributions under different scenarios through multiple random sampling and calculations of risk factors. This process enables the system to evaluate the probability of occurrence of potential safety hazards under specific conditions. For example, in the presence of complex environmental factors (such as wind, humidity, etc.) and multiple dynamic obstacles, the probabilistic risk assessment model can accurately calculate the possible safety risks in different scenarios and help operators formulate reasonable safety measures. This quantitative analysis not only enhances the scientific nature of safety control, but also makes the decision-making process more transparent and credible, ensuring the efficient and safe conduct of gardening operations.

[0129] In this embodiment, the dynamic safety constraint generator can generate safety constraints that adapt to the current environment and operating status in real time. By analyzing the real-time monitoring data and risk assessment results, the dynamic safety constraint generator can automatically adjust the operating parameters of the equipment, such as reducing the movement speed, limiting the operating area, or increasing the safety distance. Such dynamic adjustments ensure the safety of the equipment in an uncertain environment and reduce the potential risk of accidents. For example, if the presence of personnel in a certain operating area is detected, the corresponding safety constraints can be automatically generated to ensure that the equipment operates within a safe range. This ability to generate and adjust safety constraints in real time enables the adaptive safety control module to flexibly respond to various complex operating scenarios and improve the overall safety level of gardening operations.

[0130] In this embodiment, the key to the emergency response strategy is that it can dynamically update and adjust the response strategy for different levels of security risks. By analyzing historical data and risk assessment results, the emergency response strategy can formulate corresponding response plans for different risk scenarios, such as stopping equipment operation, evacuating operators, or sounding alarms. In addition, the strategy also supports continuous optimization of response plans based on real-time conditions, making emergency responses faster and more effective. This flexibility and real-time performance enable the equipment to respond quickly to emergencies, minimize accident risks, and protect the safety of operators.

[0131] In summary, the adaptive safety control module provides comprehensive safety protection for gardening operations through the collaborative work of components such as real-time risk monitor, probabilistic risk assessment model, dynamic safety constraint generator and emergency response strategy. The real-time monitoring capability ensures the timely discovery of potential risks, the probabilistic assessment provides a scientific basis for safety decision-making, the dynamically generated safety constraints improve the flexibility of operations, and the emergency response strategy ensures a rapid response in crisis situations. Through these intelligent means, the module not only improves the safety of gardening operations, but also enhances the adaptability of equipment in complex and uncertain environments, and promotes the development of gardening operations in a more efficient and safer direction.

[0132] Furthermore, the risk probability is calculated by the following formula: Where N is the total number of simulations, that is, the number of different operation scenarios generated; P risk is the overall risk probability, which indicates the proportion of safety risks occurring in all simulation scenarios; R1, R2, ..., R n To influence the security risk in each scenario; I(S j |R1, R2, ..., R n ) indicates that in scenario S j In the adaptive safety control module, after comprehensively considering multiple risk factors, whether a safety risk has occurred. The calculation of risk probability is a crucial component of the adaptive safety control module, which provides an important quantitative basis for safety decision-making. By simulating different operating scenarios, potential safety risks can be identified and evaluated, thereby effectively improving the safety of gardening operations. Such a dynamic evaluation mechanism can flexibly adapt to the ever-changing operating environment and ensure safety and reliability during the operation process.

[0133] Furthermore, the safety constraint condition S(t) is expressed as: S(t) = α·S base +(1-α)·S adj (C(t)), where S base Indicates the basic safety constraints applicable when the risk level is low; S adj(C(t)) is the safety constraint adjusted according to the current environment and operation status C(t); α is a dynamically adjusted weight coefficient that changes based on the risk probability: when P risk ≤θ1, α=1; when θ1<P risk When θ2 is less than When P risk When ≥θ2, α=0; θ1 and θ2 are the thresholds of risk assessment results, which are used to divide risk levels. By dynamically adjusting the safety constraint condition S(t), combining the basic safety constraint with the adjustment constraint of the current environmental state, a higher level of safety assurance can be achieved. This mechanism not only improves the flexibility and adaptability of operations, but also ensures the safety of operations under various environments and risk conditions, and ultimately achieves the goal of intelligent gardening operations.

[0134] Furthermore, the precise torque execution module includes the following components:

[0135] High-precision torque sensor measures the actual torque of the motor output shaft in real time, providing accurate feedback data and laying the foundation for closed-loop control;

[0136] Adaptive PID controller, which dynamically calculates and adjusts PID parameters to generate precise control signals based on the deviation between the setpoint and actual torque feedback;

[0137] The motor driver receives the control signal and accurately adjusts the motor input current to achieve direct control of the motor output torque;

[0138] Load characteristic identifier, which identifies and predicts various load changes in gardening operations by analyzing motor parameters and environmental data in real time, so as to improve the response speed to external environmental changes;

[0139] Torque command parser converts the operation plan and equipment action command sequence generated by the intelligent decision-making module into specific torque control commands to ensure the accurate implementation of the execution strategy;

[0140] The performance monitoring and diagnostic unit continuously monitors the torque control performance, detects abnormal conditions, and provides real-time diagnosis to ensure long-term stable operation.

[0141] The precise torque execution module builds an efficient closed-loop control system by integrating components such as high-precision torque sensor, adaptive PID controller, motor driver, load characteristic identifier, torque command parser and performance monitoring and diagnostic unit. This mechanism can monitor and adjust the output torque of the motor in real time to ensure the safety and efficiency of gardening operations under various complex conditions. Through this dynamic adjustment mechanism, gardening operation devices can achieve precise control, improve operation quality and efficiency, and promote the progress and development of intelligent gardening operations.

[0142] Furthermore, the control signal is expressed as: Where u(t) is the control signal for adjusting the motor input; e(t) is the torque error, that is, the difference between the expected torque and the actual torque; f p (e(t)) is the proportional gain function after dynamic adjustment, which is adjusted according to the current torque error e(t); f i (e(t)) is the dynamically adjusted integral gain function, taking into account the cumulative error changes and load conditions; f d (e(t)) is the dynamically adjusted differential gain function, which is used to quickly respond to the rate of change of the torque error; e(τ) represents the error value at time τ; dτ represents the time increment used in the integral calculation; de(t) represents the small change in the error e(t) at time t; t represents the current time; dt represents the time increment used in the differential calculation. Through the above formula, the control signal u(t) can flexibly adjust the input of the motor to ensure that the output torque meets the operating requirements. The dynamically adjusted proportional, integral and differential gain functions enable the control system to quickly respond to changing operating conditions and environmental factors, providing precise torque control. This adaptive control mechanism is an important guarantee for achieving efficient gardening operations, and can cope with changing workloads and external conditions to ensure stable operation of the equipment.

[0143] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A motor torque control system for a multifunctional gardening operation device, characterized in that: Includes the following modules: The multimodal sensor module collects multi-dimensional data of the environment and device status in real time by integrating multiple sensors to achieve comprehensive environmental perception and dynamic monitoring; Dynamic environment modeling module, which builds and updates the operating environment model in real time, identifies vegetation types, evaluates terrain features and tracks dynamic objects to support intelligent decision-making; Intelligent decision-making module, based on the working environment model and task objectives, uses task planner, path optimizer and action sequence generator to generate the optimal working strategy to achieve efficient gardening operations; Adaptive safety control module, which evaluates safety risks during operation in real time, dynamically generates safety constraints, and uses probabilistic risk assessment models for intelligent safety management; Precise torque execution module, which precisely controls the output torque of the motor to execute the optimal operation strategy generated by the intelligent decision-making module to achieve efficient operation; The human-computer interaction interface module provides an intuitive visual interface and manual control interface, supports manual operation and voice command control, and realizes efficient human-computer collaboration.

2. A motor torque control system for a multifunctional gardening operation device according to claim 1, characterized in that: The multimodal sensor module includes the following components: High-resolution camera array, which consists of multiple high-resolution cameras to achieve 360-degree visual perception and capture detailed image information of the environment; Torque sensors are installed on key joints and actuators of the equipment to monitor the stress of each component of the equipment in real time to ensure force control and equipment safety during operation; LiDAR scanners that quickly and accurately measure the 3D structure of the surrounding environment for terrain mapping and dynamic obstacle tracking; Inertial measurement unit, which integrates accelerometer, gyroscope and magnetometer to monitor the attitude, orientation and motion of the device in real time, providing key data for precise navigation and stable control; The environmental sensor group integrates a variety of environmental sensors to monitor local environmental parameters and provide a basis for plant maintenance and operation strategy adjustments.

3. The motor torque control system for a multifunctional gardening operation device according to claim 1, characterized in that: The dynamic environment modeling module includes the following components: 3D point cloud generation unit, used to generate and update high-precision 3D point cloud models in real time, providing basic spatial information for subsequent analysis and decision-making; Vegetation identification and classification unit, used to quickly identify and classify different types of vegetation, providing accurate plant information for gardening operations; The terrain feature analysis unit identifies and quantifies terrain undulations, slopes, and texture features based on a three-dimensional point cloud model, providing terrain information for path planning and operation strategy formulation; Dynamic object tracking unit, which detects and tracks moving objects in the environment in real time and updates dynamic elements in the 3D point cloud model in real time; The semantic segmentation unit performs semantic understanding and segmentation of the environment, divides the work scene into different functional areas, and provides contextual information for intelligent decision-making; The spatiotemporal data fusion unit integrates the data from various units to build a unified, real-time updated four-dimensional operating environment model, providing a comprehensive environmental representation for the intelligent decision-making module.

4. The motor torque control system for a multifunctional gardening operation device according to claim 1, characterized in that: The intelligent decision-making module includes the following components: Task parser, which parses the high-level task instructions input by the user to convert them into specific job objectives and constraints; Environmental status evaluator, which analyzes the operating environment model in real time, evaluates the status and characteristics of the current operating environment, and provides the latest environmental status information for the decision-making process; The task planner generates a high-level work plan based on the work objectives and environmental status information, including task decomposition and priority sorting, to ensure the logic and efficiency of the overall operation; The path optimizer combines the working environment model and the working plan to calculate the optimal movement path and realize the efficient navigation of the equipment in the complex garden environment; The action sequence generator converts the optimal motion path into a specific equipment action instruction sequence to ensure accurate execution of the operation; The strategy evaluator and adjuster monitors job execution in real time, evaluates strategy effectiveness, and dynamically adjusts decisions based on feedback to achieve adaptive optimization and continuous improvement.

5. The motor torque control system for a multifunctional gardening operation device according to claim 4, characterized in that: Combining the working environment model and the working plan, the optimal motion path is calculated to achieve efficient navigation of the equipment in a complex garden environment, including the following steps: Based on the 3D point cloud data and semantic segmentation information provided by the dynamic environment modeling module, a high-precision environment map is constructed. At the same time, the dynamic elements in the map are updated in real time using the data of the dynamic object tracking unit to ensure that the path planning is based on the latest environment information; According to the operation plan generated by the intelligent decision-making module, the overall operation is broken down into a series of specific operation areas, and the operation sequence is determined according to the task priority and logical sequence; Integrate constraints from different modules and transform them into a set of rules that the path planning algorithm can handle; Based on the selected path planning algorithm, an initial feasible path from the starting point to the end point is generated taking into account the rule set; Using the gradient descent method, multiple objective functions including path length, energy consumption, time and safety margin are comprehensively considered to optimize the initial feasible path until the preset optimization goal or number of iterations is reached; A dynamic adjustment mechanism for the path is introduced to cope with unexpected situations that may be encountered during the execution process. At the same time, a feedback loop with other modules is established to continuously optimize the path planning strategy according to the actual execution situation.

6. The motor torque control system for a multifunctional gardening operation device according to claim 1, characterized in that: The adaptive safety control module includes the following components: Real-time risk monitor, which continuously monitors data streams from multi-modal sensor modules to detect potential safety hazards and abnormal conditions in real time; Probabilistic risk assessment model, which quantifies the detected risk factors based on Monte Carlo simulation and calculates the risk probability under different scenarios; Dynamic safety constraint generator, based on risk assessment results, generates safety constraint conditions that adapt to the current environment and operating status in real time to ensure the safety of the operating process; The emergency response policy controller presets and dynamically updates a series of emergency response plans for different levels of security risks, and quickly activates corresponding policies when high-risk situations are detected.

7. A motor torque control system for a multifunctional gardening operation device according to claim 6, characterized in that: The risk probability is calculated by the following formula: Where N is the total number of simulations, that is, the number of different operation scenarios generated; P risk is the overall risk probability, which indicates the proportion of safety risks occurring in all simulation scenarios; R1, R2, ..., R n To influence the security risk in each scenario; I(S j |R1, R2, ..., R n ) indicates that in scenario S j In the process, after comprehensively considering multiple risk factors, whether a security risk has occurred.

8. The motor torque control system for a multifunctional gardening operation device according to claim 6, characterized in that: The safety constraint condition S(t) is expressed as: S(t) = α·S base +(1-α)·S adj (C(t)), where S base Indicates the basic safety constraints applicable when the risk level is low; S adj (C(t)) is the safety constraint adjusted according to the current environment and operation status C(t); α is a dynamically adjusted weight coefficient that changes based on the risk probability: when P risk ≤θ1, α=1; when θ1<P risk When θ2 is less than When P risk When ≥θ2, α=0; θ1 and θ2 are the thresholds of risk assessment results, which are used to divide risk levels.

9. The motor torque control system for a multifunctional gardening operation device according to claim 1, characterized in that: The precision torque actuator module includes the following components: High-precision torque sensor measures the actual torque of the motor output shaft in real time, providing accurate feedback data and laying the foundation for closed-loop control; Adaptive PID controller, which dynamically calculates and adjusts PID parameters to generate precise control signals based on the deviation between the setpoint and actual torque feedback; The motor driver receives the control signal and accurately adjusts the motor input current to achieve direct control of the motor output torque; Load characteristic identifier, which identifies and predicts various load changes in gardening operations by analyzing motor parameters and environmental data in real time, so as to improve the response speed to external environmental changes; Torque command parser converts the operation plan and equipment action command sequence generated by the intelligent decision-making module into specific torque control commands to ensure the accurate implementation of the execution strategy; The performance monitoring and diagnostic unit continuously monitors the torque control performance, detects abnormal conditions, and provides real-time diagnosis to ensure long-term stable operation.

10. The motor torque control system for a multifunctional gardening operation device according to claim 9, characterized in that: The control signal is expressed as: Where u(t) is the control signal for adjusting the motor input; e(t) is the torque error, that is, the difference between the expected torque and the actual torque; f p (e(t)) is the proportional gain function after dynamic adjustment, which is adjusted according to the current torque error e(t); f i (e(t)) is the dynamically adjusted integral gain function, taking into account the cumulative error changes and load conditions; f d (e(t)) is the dynamically adjusted differential gain function, which is used to quickly respond to the rate of change of the torque error; e(τ) represents the error value at time τ; dτ represents the time increment used in the integral calculation; de(t) represents the small change in the error e(t) at time t; t represents the current time; dt represents the time increment used in the differential calculation.

Images