CN119696459A

CN119696459A - A motor torque control system for a multifunctional gardening operation device

Info

Publication number: CN119696459A
Application number: CN202411827104.XA
Authority: CN
Inventors: 于晓
Original assignee: Linyi Garden Sanitation Support Service Center
Current assignee: Linyi Garden Sanitation Support Service Center
Priority date: 2024-12-12
Filing date: 2024-12-12
Publication date: 2025-03-25

Abstract

The present application discloses a motor torque control system for a multifunctional garden operation device, which belongs to the technical field of motor torque control. The system includes: a multimodal sensor module, which collects multi-dimensional data of the environment and equipment status in real time; a dynamic environment modeling module, which builds and updates the operation environment model in real time, identifies vegetation types, evaluates terrain features and tracks dynamic objects; an intelligent decision-making module, which generates the optimal operation strategy based on the operation environment model and task objectives using a task planner, a path optimizer and an action sequence generator; an adaptive safety control module, which evaluates the safety risks in the operation process in real time, dynamically generates safety constraints, and uses a probabilistic risk assessment model for intelligent safety management; a precise torque execution module, which accurately controls the output torque of the motor to execute the optimal operation strategy generated by the intelligent decision-making module; and a human-computer interaction interface module, which provides an intuitive visual interface and a manual control interface.

Description

Motor torque control system for multifunctional garden operation device

Technical Field

The application relates to the technical field of motor torque control, in particular to a motor torque control system for a multifunctional garden operation device.

Background

In modern gardening operations, the use of multifunctional gardening operations devices is increasing, such devices generally comprising various functional modules, such as pruning, fertilizing and watering, etc., to meet the needs of different gardening operations. However, the conventional garden working equipment has various disadvantages in torque control, mainly manifested by poor adaptability to working environment, weak dynamic adjustment capability and insufficient safety. At present, when equipment faces complex terrains and changeable environments, the output torque of a motor cannot be monitored and adjusted in real time, so that the operation efficiency and the safety are affected.

Along with the development of sensor technology and intelligent control technology, the combination of a multi-mode sensor and an intelligent decision algorithm realizes the dynamic monitoring and optimization of the garden operation process, and becomes a key for improving the operation efficiency of equipment. Through the output torque of accurate control motor, can be according to actual load and environmental change, optimize the operating condition of equipment, ensure the high-efficient of gardens operation and go on. In addition, the safety is also a non-negligible important factor in garden operation, and real-time safety risk monitoring and intelligent safety management greatly reduce accident risks in the operation process.

In summary, how to realize accurate control of motor torque in a multifunctional garden working device and dynamically adapt to complex environments and working requirements has become a technical problem to be solved.

Disclosure of Invention

In order to overcome the drawbacks of the prior art, an object of the present application is to provide a motor torque control system for a multifunctional garden working device, comprising the following modules:

The multi-mode sensor module is used for collecting multi-dimensional data of the environment and the equipment state in real time through integrating various sensors so as to realize comprehensive environment sensing and dynamic monitoring;

the dynamic environment modeling module builds and updates an operation environment model in real time, identifies vegetation types, evaluates terrain features and tracks dynamic objects so as to support intelligent decision-making;

The intelligent decision module is used for generating an optimal operation strategy by using a task planner, a path optimizer and an action sequence generator based on the operation environment model and the task target so as to realize efficient garden operation;

The self-adaptive safety control module is used for evaluating the safety risk in the operation process in real time, dynamically generating safety constraint and carrying out intelligent safety management by utilizing the probability risk evaluation model;

the accurate torque executing module is used for accurately controlling the output torque of the motor so as to execute the optimal operation strategy generated by the intelligent decision module and realize efficient operation;

and the man-machine interaction interface module provides an intuitive visual interface and a manual control interface, supports manual operation and voice command control, and realizes efficient man-machine cooperation.

Further, the multi-modal sensor module includes the following components:

the high-resolution camera array consists of a plurality of high-resolution cameras, realizes 360-degree omnibearing visual perception and is used for capturing detailed image information of the environment;

the moment sensor is arranged on a key joint point and an actuator of the equipment, monitors stress conditions of all parts of the equipment in real time, and ensures force control and equipment safety in the operation process;

The laser radar scanner is used for rapidly and accurately measuring the three-dimensional structure of the surrounding environment and is used for topographic surveying and mapping and dynamic obstacle tracking;

The inertial measurement unit integrates an accelerometer, a gyroscope and a magnetometer, monitors the gesture, the direction and the motion state of equipment in real time, and provides key data for accurate navigation and stable control;

The environmental sensor group integrates various environmental sensors, monitors local environmental parameters and provides basis for plant maintenance and operation strategy adjustment.

Further, the dynamic environment modeling module includes the following components:

The three-dimensional point cloud generating unit is used for generating and updating the high-precision three-dimensional point cloud model in real time and providing basic space information for subsequent analysis and decision;

The vegetation identification and classification unit is used for rapidly identifying and classifying different types of vegetation and providing accurate plant information for garden operation;

the terrain feature analysis unit is used for identifying and quantifying terrain fluctuation, gradient and texture features based on the three-dimensional point cloud model and providing terrain information for path planning and operation strategy formulation;

the dynamic object tracking unit detects and tracks a moving object in the environment in real time and updates dynamic elements in the three-dimensional point cloud model in real time;

the semantic segmentation unit is used for carrying out semantic understanding and segmentation on the environment, dividing a working scene into different functional areas and providing context information for intelligent decision-making;

And the space-time data fusion unit integrates data from each unit, builds a unified and real-time updated four-dimensional operation environment model and provides comprehensive environment representation for the intelligent decision module.

Further, the intelligent decision module comprises the following components:

The task analyzer analyzes the high-level task instruction input by the user to convert the high-level task instruction into a specific job target and constraint conditions;

The environment state evaluator analyzes the operation environment model in real time, evaluates the state and the characteristics of the current operation environment and provides the latest environment state information for the decision process;

The task planner generates a high-level operation plan based on the operation target and the environment state information, wherein the task plan comprises task decomposition and priority ordering, and the logic and the efficiency of the whole operation are ensured;

The path optimizer is used for calculating an optimal motion path by combining the operation environment model and the operation plan, so that the equipment can efficiently navigate in the complex garden environment;

The action sequence generator converts the optimal motion path into a specific equipment action instruction sequence, so as to ensure the accurate execution of the operation;

and the strategy evaluation and adjustment device is used for monitoring the execution condition of the operation in real time, evaluating the strategy effect, dynamically adjusting the decision according to feedback and realizing self-adaptive optimization and continuous improvement.

Furthermore, by combining the operation environment model and the operation plan, the optimal motion path is calculated, and the efficient navigation of the equipment in the complex garden environment is realized, and the method comprises the following steps:

based on the three-dimensional point cloud data and semantic segmentation information provided by the dynamic environment modeling module, constructing a high-precision environment map, and simultaneously, utilizing the data of the dynamic object tracking unit to update dynamic elements in the map in real time so as to ensure that path planning is based on the latest environment information;

decomposing the whole operation into a series of specific operation areas according to the operation plan generated by the intelligent decision-making module, and determining the operation sequence according to the task priority and the logic sequence;

Integrating constraint conditions from different modules and converting the constraint conditions into a rule set which can be processed by a path planning algorithm;

Based on the selected path planning algorithm, generating an initial feasible path from the start point to the end point under consideration of the rule set;

Using a gradient descent method, comprehensively considering a plurality of objective functions including path length, energy consumption, time and safety margin, and optimizing an initial feasible path until a preset optimization target or iteration number is reached;

And introducing a dynamic adjustment mechanism of the path to cope with unexpected situations possibly encountered in the execution process, simultaneously establishing feedback loops with other modules, and continuously optimizing a path planning strategy according to the actual execution situation.

Further, the adaptive security control module includes the following components:

The real-time risk monitor is used for continuously monitoring the data flow from the multi-mode sensor module and detecting potential safety hazards and abnormal conditions in real time;

the probability risk assessment model is used for carrying out quantitative analysis on the detected risk factors based on Monte Carlo simulation, and calculating the risk probabilities under different situations;

The dynamic safety constraint generator generates safety constraint conditions suitable for the current environment and the operation state in real time according to the risk assessment result, so that the safety of the operation process is ensured;

The emergency response strategy device presets and dynamically updates a series of emergency response schemes for coping with different levels of security risks, and rapidly activates corresponding strategies when high risk conditions are detected.

Further, the risk probability is calculated by the following formula: Wherein, N is the total number of simulations, i.e. the number of different job scenarios generated, P _risk is the total risk probability, which indicates the proportion of security risks occurring in all the simulated scenarios, R ₁,R₂,...,R_n is the security risk affecting each scenario, and I (S _j∣R₁,R₂,...,R_n) indicates whether the security risk occurs or not after comprehensively considering a plurality of risk factors in scenario S _j.

Further, the safety constraint condition S (t) is expressed as S (t) =α·s _base+(1-α)·S_adj (C (t)), where S _base represents a basic safety constraint applicable when the risk level is low, S _adj (C (t)) is a safety constraint adjusted according to the current environment and the working state C (t), α is a dynamically adjusted weight coefficient, and changes based on the risk probability that when P _risk≤θ₁, α=1, when θ ₁＜P_risk＜θ₂,When P _risk≥θ₂, α=0, θ ₁、θ₂ is a threshold value of the risk assessment result, and is used for classifying risk levels.

Further, the precision torque executive module comprises the following components:

The high-precision torque sensor is used for measuring the actual torque of the motor output shaft in real time, providing accurate feedback data and providing a basis for closed-loop control;

The self-adaptive PID controller dynamically calculates and adjusts PID parameters according to the deviation between the set value and the actual torque feedback so as to generate an accurate control signal;

The motor driver receives the control signal and accurately adjusts the input current of the motor to realize direct control of the output torque of the motor;

the load characteristic identifier is used for identifying and predicting various load changes in the garden operation by analyzing the motor parameters and the environment data in real time so as to improve the response speed to the external environment changes;

the torque command analyzer converts the operation plan and the equipment action command sequence generated by the intelligent decision module into specific torque control commands, so as to ensure the accurate implementation of the execution strategy;

And the performance monitoring and diagnosing unit is used for continuously monitoring the torque control performance, detecting abnormal conditions and providing real-time diagnosis to ensure long-term stable operation.

Further, the control signal is expressed as: Wherein u (t) is a control signal input by the regulating motor, e (t) is a torque error, namely a difference value between a desired torque and an actual torque, f _p (e (t)) is a proportional gain function after dynamic regulation, regulation is carried out according to the current torque error e (t), f _i (e (t)) is an integral gain function after dynamic regulation, and considering cumulative error change and load conditions, f _d (e (t)) is a differential gain function after dynamic regulation and is used for rapidly responding to the change rate of the torque error, e (tau) represents an error value of time tau, dtau represents a time increment used in integral calculation, de (t) represents a tiny change amount of the error e (t) at the moment t, t represents the current time, and dt represents a time increment used in differential calculation.

Compared with the prior art, the application has the beneficial effects that:

According to the application, real-time environment sensing and dynamic monitoring are realized through the multi-mode sensor, a dynamic environment modeling and intelligent decision module is combined to generate a high-efficiency operation strategy, and meanwhile, a self-adaptive safety control and accurate torque execution mechanism is introduced to ensure the high efficiency, safety and accuracy of a garden operation process.

Drawings

Fig. 1 is a block diagram of a motor torque control system for a multifunctional garden working device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention become more apparent, the technical solutions in the embodiments of the present invention will be described in more detail below with reference to the accompanying drawings in the embodiments of the present invention. In the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The described embodiments are some, but not all, embodiments of the invention.

All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The embodiments described below, together with the words of orientation, are exemplary and intended to explain the invention and should not be taken as limiting the invention.

As shown in fig. 1, a motor torque control system for a multifunctional garden working device includes the following modules:

In this embodiment, the multi-mode sensor module is a basic component of the multifunctional garden working device, and is responsible for collecting multi-dimensional data of the environment and the equipment state by integrating various sensors. The data acquisition capability of the multi-mode sensor greatly improves the understanding of the working device to the surrounding environment. The data collected in real time can be used for monitoring plant growth state, soil condition and climate change, so that scientific basis is provided for subsequent decisions. In addition, through the data fusion technology, the module can effectively reduce redundant data and improve the accuracy and reliability of the data. Through the data, the operation device can identify and adapt to different environmental conditions, and the flexibility and the intelligent level of operation are enhanced. Successful implementation of the module lays a solid foundation for automation of garden operations.

In this embodiment, by applying a machine learning algorithm and a computer vision technique, the dynamic environment modeling module can extract key information in a complex environment, thereby generating an accurate environment model. Real-time environmental modeling ensures that the working device is able to adapt to changing working conditions. For example, when vegetation types or terrain features change, the module can quickly update the model, ensuring the effectiveness of the work strategy. Meanwhile, through a dynamic object tracking technology, moving objects in a working area can be monitored in real time, and potential collision and damage are avoided. The module provides necessary background information for intelligent decision making, so that the gardening operation can be more accurate and efficient. By comprehensively analyzing environmental factors, the dynamic environment modeling module can provide a solid foundation for subsequent intelligent decisions, and smooth operation process is ensured.

In this embodiment, the intelligent decision module is a core part of the whole system, and generates an optimal operation strategy by using a task planner, a path optimizer and an action sequence generator based on a dynamic environment model and a preset task target. The task planner determines the most suitable job task according to real-time data analysis, and the path optimizer calculates the optimal job path based on the environment information and the equipment state so as to reduce the job time and the resource consumption. In addition, the action sequence generator can generate a specific execution action sequence according to the planned task and path so as to realize efficient garden operation. The module uses artificial intelligence and an optimization algorithm, ensures the intelligence and flexibility of an operation strategy, can be dynamically adjusted according to environmental changes and operation demands, and greatly improves the operation efficiency and the safety. Through the real-time decision making capability, the intelligent decision making module not only improves the automation level of the operation, but also enables the operation device to flexibly cope with the variable environment, thereby bringing revolutionary changes to the garden operation.

In this embodiment, the adaptive security control module plays a vital role in the garden operation process, and its main function is to evaluate the security risk in the operation process in real time and dynamically generate security constraints. The module utilizes a probability risk assessment model to continuously monitor the operation environment and identify potential safety hazards, such as barriers, dynamic personnel or animals and the like. By analyzing the real-time data, the module can generate an intelligent safety management strategy to ensure that the operation device complies with safety standards when performing various tasks. For example, when approaching a person or animal, the module may automatically slow down the device or alert, thereby avoiding the occurrence of accidents. The safety of the operation process is greatly improved by the aid of the module, reliable protection is provided for operators and surrounding environments, and accident risks caused by equipment faults or human errors are reduced.

In this embodiment, the precise torque execution module is an execution unit of the whole system and is responsible for precisely controlling the output torque of the motor so as to execute the optimal operation strategy generated by the intelligent decision module. The module monitors the running state of the motor in real time through the high-precision sensor, and ensures that the motor outputs required torque in the working process, thereby ensuring the stability and reliability of the equipment under various working conditions. By controlling the torque output of the motor, the operation intensity can be finely adjusted, and the motor is suitable for different operation demands and environmental conditions. For example, when soil cultivation is performed, the torque output can be adjusted to effectively prevent excessive compaction of soil by the equipment and improve the working quality. Meanwhile, the service life of the equipment can be prolonged, the energy consumption can be reduced, and the operation efficiency can be improved by accurate torque control. The module plays an important role in the whole garden operation and is an important guarantee for realizing high-efficiency operation.

In this embodiment, the man-machine interaction interface module provides an intuitive visual interface and a manual control interface for an operator, supports manual operation and voice command control, and realizes efficient man-machine cooperation. The module displays real-time data and operation states through a friendly user interface, so that an operator can easily monitor the running condition of equipment and carry out necessary adjustment. Meanwhile, the implementation of the voice command control function further enhances the convenience of operation, and allows an operator to control the device through voice commands under the condition that both hands are busy. The module fully considers the use experience of operators, improves the operation efficiency and reduces the learning cost through concise and clear information display and convenient operation modes. In addition, the feedback mechanism of the system enables an operator to acquire the state information of the equipment in time, ensures the transparency and the controllability in the operation process, and enhances the safety and the reliability of the equipment.

In summary, the motor torque control system for the multifunctional garden working device realizes efficient, safe and intelligent garden working through the synergistic effect of the multi-modal sensor module, the dynamic environment modeling module, the intelligent decision module, the self-adaptive safety control module, the accurate torque execution module and the man-machine interaction interface module. The innovation of the modules not only improves the operation efficiency and the safety of the equipment, but also enhances the adaptability and the autonomous decision making capability of the equipment in a complex environment. In the future, with the continuous development of technology, the system is expected to play an important role in the wider garden and agriculture fields, and promote the progress and development of intelligent agriculture.

Further, the multi-modal sensor module includes the following components:

In this embodiment, the high-resolution camera array captures detailed image information of the environment through cooperative work of a plurality of high-resolution cameras, and provides abundant visual data for subsequent environmental analysis and decision. The high-resolution camera can clearly identify the type, health state and surrounding environmental characteristics of vegetation, and support complex visual analysis such as vegetation coverage, pest and disease damage monitoring and growth condition assessment. Because of the wide visual angle coverage, the camera array can flexibly cope with different illumination conditions, provide real-time image information for autonomous navigation and obstacle detection of equipment, and ensure the safety and high efficiency in the operation process. In addition, the image data can be fused with other sensor data to form a more comprehensive environment perception system, so that the overall strategy of garden operation is optimized.

In this embodiment, the torque sensor is not limited to providing real-time torque data, but rather ensures force control and equipment safety during operation. In garden operation, each action of the equipment needs accurate force application, and the moment sensor can provide necessary feedback information, so that the equipment can apply proper force when performing soil cultivation, plant pruning and other operations, and damage to plants is avoided. In addition, the moment sensor can also monitor the working state of the equipment, prevent the safety accident caused by overload or mechanical failure, and ensure the equipment to operate in the optimal state through the acquisition and analysis of real-time data, thereby improving the working efficiency and the safety.

In this embodiment, the lidar scanner can generate a high-precision topographic map and an environmental model by a laser transmitting and receiving technique. The rapid measurement capability of the laser radar enables the laser radar to effectively track obstacles in a dynamic working environment, provide real-time environmental information for equipment, and ensure safe operation. In garden operations, lidar may be used not only for topographic mapping, but also to identify and avoid potential obstacles, such as pedestrians, animals, or other equipment. The high-efficiency obstacle detection capability greatly improves the adaptability of the equipment in a complex environment, and simultaneously provides important basic data for subsequent operation strategy adjustment. In addition, the three-dimensional model generated by the laser radar can be fused with other sensor data, and the accuracy and reliability of environment perception are improved.

In this embodiment, the Inertial Measurement Unit (IMU) is an advanced sensor module integrating an accelerometer, a gyroscope and a magnetometer, and is responsible for monitoring the posture, direction and motion state of the device in real time. The module provides key data for accurate navigation and stable control of equipment, and ensures that the equipment stably operates on complex terrains. In garden operation, the use of the IMU can improve the positioning precision of the equipment in different operation environments, and ensure that each movement can accord with a preset path and operation strategy. For example, when the device is working on hillside or uneven ground, the IMU can feed back the attitude changes in real time, helping the device to automatically adjust its attitude to maintain balance and stability. The introduction of the assembly ensures that the equipment has self-correction capability in the operation process, thereby not only improving the operation efficiency, but also enhancing the safety and reliability of the equipment.

In this embodiment, the environmental sensor group is another key component of the multi-modal sensor module, and multiple environmental sensors are integrated to monitor local environmental parameters. The comprehensive application of the sensors provides important basis for plant maintenance and operation strategy adjustment. For example, by means of a soil moisture sensor, the device can monitor the moisture status of the soil in real time, thereby determining whether irrigation or fertilization is required. The temperature and humidity sensors can monitor climate change, and help equipment to timely adjust operation plans so as to optimize the growth environment of plants. The data of the environmental sensor group not only contributes to improving the precision of garden operation, but also can realize intelligent management and promote the realization of sustainable development targets. In addition, the environmental data can be fused with the data of other modules for analysis, so that the operation efficiency and the effect are further improved.

In summary, the multi-mode sensor module provides comprehensive and accurate environment sensing capability for the multifunctional garden operation device through the synergistic effect of the high-resolution camera array, the moment sensor, the laser radar scanner, the inertia measurement unit and the environment sensor group. The components perform their own functions, and provide a rich information basis for the intelligent decision module through real-time data acquisition and analysis, so that the high efficiency, safety and intellectualization of garden operation are ensured.

In this embodiment, the three-dimensional point cloud generating unit is one of core components of the dynamic environment modeling module, and its main function is to generate and update a high-precision three-dimensional point cloud model in real time. The unit captures the spatial information of the surrounding environment through the combination of the laser radar and other sensors, and converts the spatial information into point cloud data, so that a three-dimensional environment model is formed. The 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 a working area. The change of the environment can be dynamically reflected through continuously updated point cloud data, so that the emergency can be timely dealt with when the garden operation is executed. In addition, the application of the three-dimensional point cloud generating unit can improve the accuracy and efficiency of the operation, reduce the resource waste and provide scientific basis for garden management.

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. The unit can accurately identify various plant types and growth states thereof by analyzing data from high-resolution cameras and other sensors by using image processing and machine learning techniques. The function not only provides accurate plant information for garden operation, but also provides scientific basis for subsequent maintenance and management measures. For example, by identifying pest vegetation in a timely manner, a corresponding maintenance schedule, such as spraying pesticides or pruning, may be automatically triggered. The efficient operation of the module can obviously improve the precision and pertinence of garden operation, realize more scientific plant management and provide support for healthy development of garden ecology.

In this embodiment, the terrain feature analysis unit focuses on identifying and quantifying the relief, gradient, and texture features of the terrain based on the generated three-dimensional point cloud model. By analyzing these topographical features, vital information can be provided for path planning and job strategy formulation. For example, the equipment can determine the optimal operation route according to the relief situation of the terrain, avoid operating on steep slopes or uneven ground, and reduce equipment damage and operation risks. Meanwhile, the topography characteristic analysis can help to formulate a reasonable soil improvement and irrigation strategy so as to improve the efficiency of crop growth. The module is introduced to improve the safety and efficiency of operation, support the aim of environmental protection, and avoid operation under unsuitable terrain conditions, thereby realizing sustainable development of garden management.

In this embodiment, the dynamic object tracking unit is responsible for detecting and tracking a moving object in an environment in real time, so as to ensure the timely update of dynamic elements in the three-dimensional point cloud model. This unit can accurately identify surrounding dynamic objects such as pedestrians, animals, or other devices using lidar, camera, and other sensor fusion technologies. The real-time tracking of the dynamic object not only improves the safety in the operation process and avoids potential collision risks, but also optimizes the operation strategy. For example, in a garden trimming job, a work plan may be adjusted according to the position of a dynamic object, thereby ensuring the continuity and efficiency of the job. The efficient operation of the unit provides intelligent environment sensing capability for garden operation, so that the equipment can freely cope in a complex working environment, and the overall operation efficiency is improved.

In this embodiment, the semantic segmentation unit can analyze the image and the point cloud data based on machine learning and deep learning technologies, so as to identify functional characteristics of different areas, such as vegetation areas, footpaths, open areas, buildings, and the like. The subdivision of the space provides rich context information for intelligent decision making, so that the system can formulate corresponding operation strategies according to the characteristics of different areas. For example, in environments with significant vegetation areas and pavement areas, watering and fertilizing in the vegetation areas may be preferentially arranged, leaving the maintenance of the pavement to follow-up operations. The introduction of semantic segmentation greatly improves the accuracy and the high efficiency of garden operation, so that the resource allocation and the operation arrangement are more scientific and reasonable.

In this embodiment, the spatio-temporal data fusion unit plays a role in the dynamic environment modeling module, and integrates the data from each unit to construct a unified and real-time updated four-dimensional operation environment model. The four-dimensional model not only contains space information, but also adds a time dimension, and reflects the change of the environment along with time. The unit provides comprehensive environmental representation for the intelligent decision module, so that the decision process is more scientific and accurate. For example, the system can predict the growth of plants by analyzing the change of environmental parameters in different time periods and make a proper maintenance plan according to the growth. Through space-time data fusion, the device can realize autonomous navigation and intelligent operation in a dynamic environment, and provides powerful support for realizing comprehensive intelligent garden management.

In summary, the dynamic environment modeling module provides comprehensive and accurate environment sensing and dynamic modeling capability for the multifunctional garden operation device through the close cooperation of the three-dimensional point cloud generating unit, the vegetation identification and classification unit, the terrain feature analysis unit, the dynamic object tracking unit, the semantic segmentation unit and the space-time data fusion unit. The effective combination of these components not only promotes the safety and efficiency of garden operation, but also provides a data base for scientific garden management. With the continuous development of the intelligent technology, the dynamic environment modeling module is further optimized, and makes a greater contribution to the intelligent and sustainable development of the future garden operation.

Further, the intelligent decision module comprises the following components:

In this embodiment, the task analyzer is a core component of the intelligent decision module, and is responsible for analyzing the advanced task instruction input by the user and converting the advanced task instruction into a specific job target and constraint condition. Through natural language processing technology, the task analyzer can understand the intention of a user and extract relevant job requirements and limiting factors. This functionality greatly simplifies the interaction between the user and the system, allowing the user to enter task demands in an intuitive manner. Meanwhile, the task analyzer can decompose complex task instructions into executable subtasks, and a clear framework is provided for subsequent decision making and execution. By effectively interfacing the needs of the user with the capabilities of the system, the task analyzer lays a solid foundation for the whole intelligent decision process and ensures smooth progress of garden operations.

In this embodiment, the environmental state estimator can update environmental information including climate conditions, soil humidity, plant health states, etc. in real time by integrating data from the multi-modal sensor. Such information is critical to the formulation of a work strategy, for example, when the environmental condition evaluator detects imminent severe weather or a plant water deficiency, the work plan may be automatically adjusted to prioritize emergency tasks. The scientificity and timeliness of system decisions are ensured by the introduction of the environment state estimator, so that the garden operation can be more flexible to cope with changing environment conditions, and the safety and efficiency of the operation are improved.

In this embodiment, the task planner can dynamically adjust the job sequence according to the real-time information provided by the environment evaluator, so as to ensure the logic and efficiency of the job. For example, in a complex garden environment, the task planner can reasonably arrange operations such as watering, fertilizing, trimming and the like according to the growth state of plants, the terrain characteristics and the current position of equipment, so as to avoid resource waste and improve the operation effect. In addition, the mission planner can also generate alternatives to cope with potential emergencies, ensuring continuity and efficiency of the whole job process. The intelligent task planning function of the system greatly improves flexibility and response capability of garden operation.

In this embodiment, the path optimizer analyzes the terrain features and the obstacle information by using an advanced algorithm, such as an a-algorithm or Dijkstra algorithm, and generates a safe and efficient travel path. The operation of the path optimizer not only considers the shortest path, but also evaluates the topography fluctuation, the obstacle position and the dynamic state of the equipment, thereby ensuring the stability and the safety of the equipment in the operation process. For example, when the equipment needs to traverse different types of ground, the path optimizer can select the most appropriate travel route, reducing the risk of equipment failure and accidents. Through accurate path planning, the path optimizer provides powerful support for intelligent navigation and efficient operation of equipment.

In this embodiment, the motion sequence generator refines specific instructions of each motion step, including speed, steering angle, and operation of the job, by analyzing the motion path generated by the path optimizer. The action sequence generator is introduced, so that the equipment can efficiently execute tasks according to a preset motion track and a preset operation plan, and misoperation caused by ambiguous instructions is avoided. In addition, the generated instruction sequence can be updated in real time to adapt to the change of dynamic environment, so that the flexibility and adaptability of the operation are ensured. The accuracy and the reliability of the action sequence generator provide guarantee for smooth implementation of garden operation, and promote development of intelligent operation.

In this embodiment, the policy evaluation and adjuster is an indispensable component in the intelligent decision module, and is responsible for monitoring the execution of the job in real time, evaluating the policy effect, and dynamically adjusting the decision according to feedback. The component evaluates the validity of the current policy by collecting real-time data during the operation, such as equipment operating status, job progress, and environmental changes. The real-time feedback mechanism enables the system to perform self-adaptive optimization according to actual conditions, and timely adjusts the operation strategy so as to improve the operation efficiency and quality. For example, if it is monitored that a certain job policy does not achieve the desired effect, the policy evaluation and adjustment device may automatically adjust the execution sequence or method of the subsequent tasks to ensure achievement of the final objective. By introducing the self-adaptive adjustment mechanism, the module can realize continuous improvement and promote the development of garden operation to intellectualization and high efficiency.

In summary, the intelligent decision module provides efficient and intelligent decision support for the multifunctional garden operation device through the tight cooperation of the task analyzer, the environment state estimator, the task planner, the path optimizer, the action sequence generator and the strategy estimation and adjustment device. The cooperation of the components ensures the logic, flexibility and adaptability of the garden operation, and lays a solid foundation for realizing efficient and accurate garden management.

Through the steps, the path optimizer can realize efficient navigation in a complex garden environment. From constructing a high-precision environment map based on three-dimensional point cloud data to dynamically adjusting a path planning strategy, the whole process ensures the logic and high efficiency of the operation and improves the safety to the greatest extent. The intelligent path planning and optimizing method provides a solid foundation for the efficient operation of the multifunctional garden operation device, so that the intelligent path planning and optimizing method can flexibly cope with various complex environmental conditions, and the intelligent and efficient development of garden operation is promoted.

In this embodiment, the real-time risk monitor continuously monitors the data flow from the multimodal sensor module to detect potential safety hazards and anomalies in real time. By integrating information from multiple sensors, such as high resolution cameras, lidar, environmental sensors, etc., the real-time risk monitor is able to provide comprehensive environmental monitoring capabilities. The method can not only identify static barriers, but also track the motion trail of dynamic objects, thereby identifying potential threats possibly causing safety accidents. For example, if the monitor finds someone or other moving object accidentally entering the work area, it will immediately alert and take corresponding action. The real-time monitoring capability provides important safety guarantee for garden operation, so that operators can quickly respond under abnormal conditions, and the probability of accidents is reduced.

In this embodiment, the risk factors detected by the real-time risk monitor will be input into a probabilistic risk assessment model that quantitatively analyzes the detected risk based on Monte Carlo simulation. The Monte Carlo simulation can generate risk probability distribution under different scenes through multiple random sampling and calculation of risk factors. This process enables the system to evaluate the probability of occurrence of a potential safety hazard under certain conditions. For example, in the case of complex environmental factors (such as wind power, humidity, etc.) and multiple dynamic obstacles, the probabilistic risk assessment model can accurately calculate the security risks that may occur in different scenes, and help operators to make reasonable security measures. The quantitative analysis not only enhances the scientificity of safety control, but also enables the decision process to be more transparent and reliable, and ensures the efficient and safe performance of garden operation.

In this embodiment, the dynamic security constraint generator is capable of generating in real time security constraint conditions adapted to the current environment and the job status. By analyzing the real-time monitored data and risk assessment results, the dynamic security constraint generator may automatically adjust operating parameters of the device, such as reducing movement speed, limiting work area, or increasing security distance, etc. Such dynamic adjustment ensures the safety of the device in an uncertain environment, reducing the risk of potential accidents. For example, if personnel are detected to be present in a certain work area, corresponding safety constraints can be automatically generated to ensure that the equipment operates within a safe range. The capability of generating and adjusting the safety constraint in real time enables the self-adaptive safety control module to flexibly cope with various complex operation scenes, and improves the overall safety level of garden operation.

In this embodiment, the key of the emergency response policy device is that it can dynamically update and adjust the coping policy for security risks of different levels. By analyzing the historical data and the risk assessment results, the emergency response policer can formulate corresponding response schemes for different risk situations, such as stopping equipment operation, evacuating operators, or raising an alarm. In addition, the strategicer also supports the continuous optimization of response schemes according to real-time conditions, so that the emergency response is quicker and more effective. The flexibility and the instantaneity enable the equipment to quickly react when facing an emergency, so that the accident risk is reduced to the greatest extent and the safety of operators is protected.

In summary, the adaptive security control module provides comprehensive security for garden operations through the cooperative work of the components such as the real-time risk monitor, the probabilistic risk assessment model, the dynamic security constraint generator, the emergency response strategicer and the like. The ability to monitor in real time ensures the timely discovery of potential risks, probability assessment provides a scientific basis for safety decisions, dynamically generated safety constraints promote operational flexibility, and emergency response policers ensure rapid response in crisis situations. Through the intelligent means, the module not only improves the safety of the garden operation, but also enhances the adaptability of the equipment in complex and uncertain environments, and promotes the garden operation to develop towards a more efficient and safer direction.

Further, the risk probability is calculated by the following formula: Wherein, N is the total number of simulations, i.e. the number of different job scenarios generated, P _risk is the total risk probability, which indicates the proportion of security risks occurring in all the simulated scenarios, R ₁,R₂,...,R_n is the security risk affecting each scenario, and I (S _j∣R₁,R₂,...,R_n) indicates whether the security risk occurs or not after comprehensively considering a plurality of risk factors in scenario S _j. The calculation of the risk probability is a crucial component part in the self-adaptive safety control module, and provides important quantitative basis for safety decision. By simulating different operation scenes, potential safety risks can be identified and evaluated, and accordingly safety of garden operation is effectively improved. The dynamic evaluation mechanism can flexibly adapt to the continuously-changing working environment, and ensures the safety and reliability in the working process.

Further, the safety constraint condition S (t) is expressed as S (t) =α·s _base+(1-α)·S_adj (C (t)), where S _base represents a basic safety constraint applicable when the risk level is low, S _adj (C (t)) is a safety constraint adjusted according to the current environment and the working state C (t), α is a dynamically adjusted weight coefficient, and changes based on the risk probability that when P _risk≤θ₁, α=1, when θ ₁＜P_risk＜θ₂,When P _risk≥θ₂, α=0, θ ₁、θ₂ is a threshold value of the risk assessment result, and is used for classifying risk levels. By dynamically adjusting the safety constraint condition S (t), and combining the basic safety constraint and the adjustment constraint of the current environment state, higher-level safety guarantee can be realized. The mechanism not only improves the flexibility and adaptability of the operation, but also ensures the operation safety under various environment and risk conditions, and finally achieves the goal of intelligent garden operation.

The accurate torque execution module constructs an efficient closed-loop control system by integrating components such as a high-accuracy torque sensor, a self-adaptive PID controller, a motor driver, a load characteristic identifier, a torque command analyzer, a performance monitoring and diagnosing unit and the like. The mechanism can monitor and regulate the output torque of the motor in real time, and ensure the safety and high efficiency of garden operation under various complex conditions. Through the dynamic adjustment mechanism, the garden operation device can realize accurate control, improve the operation quality and efficiency, and promote the progress and development of intelligent garden operation.

Further, the control signal is expressed as: Wherein u (t) is a control signal input by the regulating motor, e (t) is a torque error, namely a difference value between a desired torque and an actual torque, f _p (e (t)) is a proportional gain function after dynamic regulation, regulation is carried out according to the current torque error e (t), f _i (e (t)) is an integral gain function after dynamic regulation, and considering cumulative error change and load conditions, f _d (e (t)) is a differential gain function after dynamic regulation and is used for rapidly responding to the change rate of the torque error, e (tau) represents an error value of time tau, dtau represents a time increment used in integral calculation, de (t) represents a tiny change amount of the error e (t) at the moment t, t represents the current time, and dt represents a time increment used in differential calculation. Through the formula, the control signal u (t) can flexibly adjust the input of the motor, and ensure that the output torque meets the operation requirement. The dynamically adjusted proportional, integral and derivative gain functions enable the control system to quickly respond to changing operating conditions and environmental factors, providing precise torque control. The self-adaptive control mechanism is an important guarantee for realizing efficient garden operation, and can cope with variable workload and external conditions and ensure stable operation of equipment.

Finally, it should be pointed out that the above embodiments are only intended to illustrate the technical solution of the invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that modifications may be made to the technical solutions described in the foregoing embodiments or equivalents may be substituted for some of the technical features thereof, and that such modifications or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention in essence of the corresponding technical solutions.

Claims

1. The motor torque control system for the multifunctional garden operation device is characterized by comprising the following modules:

2. The motor torque control system for a multifunctional garden work device according to claim 1, wherein the multi-modal sensor module comprises the following components:

3. The motor torque control system for a multifunctional garden work device according to claim 1, wherein the dynamic environment modeling module comprises the following components:

4. The motor torque control system for a multifunctional garden work device according to claim 1, wherein the intelligent decision module comprises the following components:

5. The motor torque control system for a multifunctional garden working device according to claim 4, wherein the optimal motion path is calculated by combining the working environment model and the working plan, and the efficient navigation of the equipment in the complex garden environment is realized, and the motor torque control system comprises the following steps:

6. The motor torque control system for a multifunctional garden work device according to claim 1, wherein the adaptive safety control module comprises the following components:

7. The motor torque control system for a multifunctional garden working device according to claim 6, wherein the risk probability is calculated by the following formula: Wherein, N is the total number of simulations, i.e. the number of different job scenarios generated, P _risk is the total risk probability, which indicates the proportion of security risks occurring in all the simulated scenarios, R ₁,R₂,...,R_n is the security risk affecting each scenario, and I (S _j∣R₁,R₂,...,R_n) indicates whether the security risk occurs or not after comprehensively considering a plurality of risk factors in scenario S _j.

8. The motor torque control system for a multifunctional garden working device according to claim 6, wherein the safety constraint condition S (t) is expressed as S (t) = α.s _base+(1-α)·S_adj (C (t)), wherein S _base is an applicable basic safety constraint when the risk level is low, S _adj (C (t)) is a safety constraint adjusted according to the current environment and the working state C (t), α is a dynamically adjusted weight coefficient, and is changed based on the risk probability that when P _risk≤θ₁, α=1, when θ ₁＜P_risk＜θ₂,When P _risk≥θ₂, α=0, θ ₁、θ₂ is a threshold value of the risk assessment result, and is used for classifying risk levels.

9. The motor torque control system for a multifunctional garden work device according to claim 1, wherein the precise torque execution module comprises the following components:

10. A motor torque control system for a multifunctional garden working device, as claimed in claim 9, characterized in that the control signal is expressed as: Wherein u (t) is a control signal input by the regulating motor, e (t) is a torque error, namely a difference value between a desired torque and an actual torque, f _p (e (t)) is a proportional gain function after dynamic regulation, regulation is carried out according to the current torque error e (t), f _i (e (t)) is an integral gain function after dynamic regulation, and considering cumulative error change and load conditions, f _d (e (t)) is a differential gain function after dynamic regulation and is used for rapidly responding to the change rate of the torque error, e (tau) represents an error value of time tau, dtau represents a time increment used in integral calculation, de (t) represents a tiny change amount of the error e (t) at the moment t, t represents the current time, and dt represents a time increment used in differential calculation.