A robotic arm control method and system for livestock status monitoring

Abstract

The present invention relates to the technical field of robotic arm control, and particularly to a robotic arm control method and system for livestock status monitoring. The method includes the following steps: using an electronic monitoring device to obtain livestock activity images and calculating the activity distribution density of livestock species, and then, quantifying the vibration of the robotic arm based on the activity density data to estimate the stress state probability of the livestock; then, adjusting the approaching speed of the robotic arm according to the stress state probability and designing a monitoring attitude control instruction to ensure that the actions of the robotic arm match the behaviors of the livestock; finally, encoding and processing the monitoring attitude adjustment instruction, designing an automatic control program, and embedding it into the robotic arm control system to achieve precise livestock status monitoring and control. The present invention makes the robotic arm control technology more precise through the optimization of the robotic arm control technology.

Description

Technical Field

[0001] The present invention relates to the technical field of robotic arm control, and particularly to a robotic arm control method and system for livestock status monitoring. Background Art

[0002] With the gradual modernization and intelligentization of agricultural production methods, the status monitoring of livestock has become an indispensable part of modern agricultural management. Traditional livestock management relies on manual inspections and empirical judgments. This method is not only inefficient but also easily affected by human factors, making it difficult to achieve precise and efficient management. Especially in large-scale breeding environments, the deficiencies of manual management can lead to delays in detecting livestock health problems, thereby affecting breeding efficiency and animal welfare. To solve this problem, scientific and technological personnel have begun to research livestock status monitoring systems based on advanced technologies such as sensing technology, data analysis, and automation control, gradually realizing real-time, comprehensive, and accurate monitoring of livestock. As a highly flexible and precise automation device, robotic arms have been widely used in fields such as manufacturing, healthcare, and logistics. In recent years, with the rapid development of artificial intelligence technology, robotic arms have been introduced into the agricultural field for the monitoring and management of livestock status. However, traditional robotic arm control methods have problems such as insufficient adaptability of the robotic arm to environmental interference and the inability to precisely control the robotic arm. Summary of the Invention

[0003] Based on this, it is necessary to provide a robotic arm control method and system for livestock status monitoring to solve at least one of the above technical problems.

[0004] To achieve the above objective, a robotic arm control method for livestock status monitoring, the method includes the following steps:

[0005] Step S1: Monitor the activities of livestock in the livestock monitoring area through an electronic monitoring device to obtain livestock activity monitoring images; calculate the distribution density of the livestock activity monitoring images to obtain the distribution density of livestock species activities;

[0006] Step S2: Quantify the vibration of the robotic arm approaching for observation based on the distribution density of livestock species activities to obtain robotic arm approaching vibration quantification data; estimate the probability of the livestock stress state based on the robotic arm approaching vibration quantification data to obtain livestock stress state probability data;

[0007] Step S3: Match the approaching speed of the robotic arm according to the livestock stress state probability data to obtain robotic arm approaching speed matching data; design a robotic arm monitoring attitude control instruction based on the robotic arm approaching speed matching data and the livestock activity monitoring images to obtain a robotic arm monitoring attitude adjustment control instruction;

[0008] Step S4: Encoding the robotic arm monitoring attitude adjustment control instruction to obtain the robotic arm monitoring attitude adjustment encoding instruction; Designing an automated control program based on the robotic arm monitoring attitude adjustment encoding instruction to obtain the robotic arm monitoring attitude control program, and embedding the robotic arm monitoring attitude control program into the robotic arm control center to execute the robotic arm control method for livestock status monitoring.

[0009] Preferably, step S1 includes the following steps:

[0010] Step S11: Obtain the livestock monitoring area; Deploy a cross track in the livestock monitoring area. The cross track is electrically connected to the robotic arm through a servo motor, and the servo motor is used to control the movement of the robotic arm on the cross track. An electronic monitoring device is deployed on the robotic arm;

[0011] Step S12: Monitor the livestock activities in the livestock monitoring area through the electronic monitoring device to obtain the livestock activity monitoring image;

[0012] Step S13: Mark the livestock species in the livestock activity monitoring image to obtain the livestock species activity monitoring image; The livestock species include pigs, cows, and sheep;

[0013] Step S14: Calculate the distribution density of the livestock species activity monitoring image to obtain the livestock species activity distribution density.

[0014] Preferably, step S2 includes the following steps:

[0015] Step S21: Analyze the livestock movable azimuth of the livestock activity monitoring image based on the livestock species activity distribution density to obtain the livestock movable azimuth data set;

[0016] Step S22: Predict the livestock spatial movement trajectory according to the livestock movable azimuth data set and the livestock activity monitoring image to obtain the livestock spatial movement trajectory prediction data;

[0017] Step S23: Quantify the vibration of the robotic arm approaching for observation based on the livestock spatial movement trajectory prediction data to obtain the robotic arm approaching vibration quantification data;

[0018] Step S24: Estimate the probability of the livestock stress state for the robotic arm approaching vibration quantification data to obtain the livestock stress state probability data.

[0019] Preferably, step S23 includes the following steps:

[0020] Step S231: Analyze the intermittent speed change of the livestock spatial movement trajectory prediction data to obtain the livestock intermittent speed change data;

[0021] Step S232: Perform instantaneous pause inertia simulation during the robotic arm's approach observation based on the intermittent speed change data of livestock to obtain instantaneous pause inertia data;

[0022] Step S233: Conduct robotic arm jitter vector attenuation analysis on the instantaneous pause inertia data to obtain the robotic arm jitter attenuation vector;

[0023] Step S234: Calculate the periodic jitter vector difference for the robotic arm jitter attenuation vector to obtain the periodic jitter vector difference;

[0024] Step S235: Obtain the robotic arm design structure data; perform robotic arm approach observation vibration quantification based on the robotic arm design structure data, the robotic arm jitter attenuation vector, and the periodic jitter vector difference to obtain the robotic arm approach vibration quantification data.

[0025] Preferably, step S24 includes the following steps:

[0026] Step S241: Obtain the livestock-acceptable noise decibels, where the livestock-acceptable noise decibels include: pig-acceptable noise decibels, sheep-acceptable noise decibels, and cattle-acceptable noise decibels;

[0027] Step S242: Perform vibration-noise feedback matching on the robotic arm approach vibration quantification data to obtain vibration-noise feedback data;

[0028] Step S243: Calculate the instantaneous noise spectrum band difference for the vibration-noise feedback data to obtain the instantaneous noise spectrum band difference;

[0029] Step S244: Conduct noise band extreme value distribution analysis based on the instantaneous noise spectrum band difference to obtain noise band extreme value distribution data;

[0030] Step S245: Perform excessive sound pressure instantaneous aggregation analysis on the livestock-acceptable noise decibels based on the instantaneous noise spectrum band difference and the noise band extreme value distribution data to obtain excessive sound pressure instantaneous aggregation data;

[0031] Step S246: Estimate the probability of the livestock stress state for the livestock-acceptable noise decibels based on the excessive sound pressure instantaneous aggregation data to obtain livestock stress state probability data.

[0032] Preferably, step S3 includes the following steps:

[0033] Step S31: Perform robotic arm approach speed matching based on the robotic arm approach vibration quantification data and the livestock stress state probability data to obtain robotic arm approach speed matching data;

[0034] Step S32: Conduct logical error iterative testing on the robotic arm approach speed matching data to obtain logical error iterative testing data;

[0035] Step S33: Perform rate error correction on the approaching rate matching data of the robotic arm according to the logical error iterative test data to obtain the optimized approaching rate data of the robotic arm.

[0036] Step S34: Design a robotic arm monitoring attitude control instruction based on the optimized approaching rate data of the robotic arm and the livestock activity monitoring image to obtain a robotic arm monitoring attitude adjustment control instruction.

[0037] Preferably, step S33 includes the following steps:

[0038] Step S331: Perform multi-frequency error cumulative calculation on the logical error iterative test data to obtain multi-frequency error cumulative data.

[0039] Step S332: Perform interval maximum error analysis on the logical error iterative test data according to the multi-frequency error cumulative data to obtain multi-frequency maximum error interval data.

[0040] Step S333: Perform time-series linear interpolation on the multi-frequency maximum error interval data to obtain error interval time-series interpolation data.

[0041] Step S334: Perform rate error correction on the approaching rate matching data of the robotic arm according to the error interval time-series interpolation data and the multi-frequency maximum error interval data to obtain the optimized approaching rate data of the robotic arm.

[0042] Preferably, step S34 includes the following steps:

[0043] Step S341: Perform livestock activity posture decomposition processing on the livestock activity monitoring image to obtain livestock activity posture decomposition data.

[0044] Step S342: Perform dynamic analysis of the livestock's blind spot of view on the livestock activity posture decomposition data to obtain dynamic data of the livestock's blind spot of view.

[0045] Step S343: Perform robotic arm path posture control adjustment on the dynamic data of the livestock's blind spot of view according to the optimized approaching rate data of the robotic arm to obtain robotic arm path posture control adjustment data.

[0046] Step S344: Design a robotic arm monitoring attitude control instruction based on the robotic arm path posture control adjustment data to obtain a robotic arm monitoring attitude adjustment control instruction.

[0047] Preferably, step S343 includes the following steps:

[0048] Perform blind spot boundary surface fitting processing on the dynamic data of the livestock's blind spot of view to obtain blind spot boundary surface fitting data.

[0049] Perform robotic arm spatial coverage calculation on the blind area boundary surface fitting data to obtain robotic arm spatial coverage data;

[0050] Perform path point distribution retrieval processing on the blind area boundary surface fitting data based on the robotic arm spatial coverage data to obtain path point distribution data;

[0051] Perform phased motion parameter matching on the path point distribution data according to the robotic arm approaching rate optimization data to obtain robotic arm phased motion parameters;

[0052] Perform robotic arm path attitude control adjustment according to the robotic arm phased motion parameters and the path point distribution data to obtain robotic arm path attitude control adjustment data.

[0053] Preferably, the present invention also provides a robotic arm control system for livestock status monitoring, which is used to execute the robotic arm control method for livestock status monitoring as described above. The robotic arm control system for livestock status monitoring includes:

[0054] A distribution density analysis module, which is used to monitor livestock activities in the livestock monitoring area through an electronic monitoring device to obtain livestock activity monitoring images; perform distribution density calculation on the livestock activity monitoring images to obtain livestock species activity distribution density;

[0055] A stress state probability estimation module, which is used to perform robotic arm approaching observation vibration quantization based on the livestock species activity distribution density to obtain robotic arm approaching vibration quantization data; perform livestock stress state probability estimation on the robotic arm approaching vibration quantization data to obtain livestock stress state probability data;

[0056] An attitude control instruction design module, which is used to perform robotic arm approaching rate matching according to the livestock stress state probability data to obtain robotic arm approaching rate matching data; perform robotic arm monitoring attitude control instruction design based on the robotic arm approaching rate matching data and the livestock activity monitoring images to obtain robotic arm monitoring attitude adjustment control instructions;

[0057] An automatic control program design module, which is used to encode the robotic arm monitoring attitude adjustment control instructions to obtain robotic arm monitoring attitude adjustment encoding instructions; perform automatic control program design based on the robotic arm monitoring attitude adjustment encoding instructions to obtain a robotic arm monitoring attitude control program, and embed the robotic arm monitoring attitude control program into the robotic arm control center to execute the robotic arm control method for livestock status monitoring.

[0058] The beneficial effects of the present invention are as follows: By using electronic monitoring devices to monitor the livestock monitoring area in real time, it is possible to accurately obtain the activity images of livestock and calculate the distribution density of the images. This process enables the system to understand the activity conditions of different types of livestock in different areas, providing accurate basic data for subsequent steps. The calculation of the distribution density not only helps to identify the activity status of livestock but also provides early warnings of abnormal behaviors or changes in group behaviors, thus providing a scientific basis for livestock management and stress state assessment. According to the distribution density of livestock activities, through the vibration quantification data of the robotic arm, the vibration signals generated during the approach of the robotic arm to livestock can be accurately analyzed. These vibration signals are highly correlated with the stress responses of livestock. Therefore, by quantifying the vibration data and combining it with the probability estimation of the stress state of livestock, the physiological stress state of livestock can be evaluated in real time. This step effectively improves the intelligence level of the robotic arm monitoring system, enabling it to automatically adjust the control strategy according to the reactions of livestock, avoiding excessive interference or causing negative emotions. Based on the probability data of the livestock stress state, the system can automatically adjust the approach rate of the robotic arm, thereby achieving more precise monitoring and operation. This step avoids unnecessary scaring or stress reactions of the robotic arm when approaching livestock through the optimized matching of the rate. At the same time, by designing the posture control instructions in combination with the livestock activity images, the robotic arm can adjust its posture to ensure the stability and effectiveness of the monitoring process. This measure effectively improves the sensitivity and adaptability of the robotic arm operation, thus achieving the interaction with livestock and the efficient execution of the monitoring task. After encoding the robotic arm monitoring posture adjustment instructions, efficient control instructions can be formed, providing technical support for the automated operation of the robotic arm. By embedding the robotic arm control center and executing a specially designed control program, the system can respond in real time to the state changes of livestock and automatically adjust the posture and operation mode of the robotic arm. This automated control not only reduces the need for manual intervention but also improves work efficiency and accuracy, ensuring that the robotic arm can accurately and stably perform various operation tasks during livestock state monitoring, thereby achieving efficient and seamless livestock management and monitoring. Therefore, the present invention is an optimized treatment for the traditional robotic arm control method for livestock state monitoring, solving the problems of insufficient adaptability of the robotic arm to environmental interference and inability to precisely control the robotic arm in the traditional robotic arm control method for livestock state monitoring, improving the adaptability of the robotic arm to environmental interference and enhancing the precise control ability of the robotic arm. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is a schematic flowchart of the steps of a robotic arm control method for livestock state monitoring;

[0060] Figure 2 is Figure 1 a detailed implementation step flowchart of step S2 in

[0061] Figure 3 For Figure 1 a detailed implementation step flow diagram of step S3 in

[0062] The realization, functional features, and advantages of the present invention will be further described in conjunction with the embodiments and with reference to the accompanying drawings. Specific implementation manners

[0063] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those skilled in the art within the scope of the present invention without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0064] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0065] It should be understood that although terms such as "first" and "second" may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed related items.

[0066] To achieve the above object, please refer to Figures 1 to 3 , a robotic arm control method for livestock status monitoring, the method comprising the following steps:

[0067] Step S1: Monitor the livestock activities in the livestock monitoring area through an electronic monitoring device to obtain livestock activity monitoring images; calculate the distribution density of the livestock activity monitoring images to obtain the distribution density of livestock species activities;

[0068] Step S2: Quantify the vibration of the robotic arm approaching for observation based on the distribution density of livestock species activities to obtain the quantified vibration data of the robotic arm approaching; estimate the probability of the livestock stress state from the quantified vibration data of the robotic arm approaching to obtain the probability data of the livestock stress state;

[0069] Step S3: Perform robotic arm approaching speed matching based on the livestock stress state probability data to obtain robotic arm approaching speed matching data; design a robotic arm monitoring attitude control instruction based on the robotic arm approaching speed matching data and the livestock activity monitoring image to obtain a robotic arm monitoring attitude adjustment control instruction;

[0070] Step S4: Perform encoding processing on the robotic arm monitoring attitude adjustment control instruction to obtain a robotic arm monitoring attitude adjustment encoding instruction; design an automated control program based on the robotic arm monitoring attitude adjustment encoding instruction to obtain a robotic arm monitoring attitude control program, and embed the robotic arm monitoring attitude control program into the robotic arm control center to execute the robotic arm control method for livestock state monitoring.

[0071] In the embodiment of the present invention, refer to Figure 1 As shown, it is a schematic diagram of the step flow of a robotic arm control method for livestock state monitoring according to the present invention. In this example, the robotic arm control method for livestock state monitoring includes the following steps:

[0072] Step S1: Use an electronic monitoring device to monitor livestock activities in the livestock monitoring area to obtain livestock activity monitoring images; perform distribution density calculation on the livestock activity monitoring images to obtain livestock species activity distribution density;

[0073] In the embodiment of the present invention, the livestock monitoring area is monitored in real time through an electronic monitoring device. These monitoring devices include a servo motor electrically connected to the cross track and the robotic arm, and the robotic arm is controlled to move on the cross track through the servo motor. An electronic monitoring device, or a multi-sensor integration system, such as a combination of an infrared imaging camera and a conventional visible light camera, is deployed on the robotic arm. The image data obtained by the camera is used to observe the activities of the livestock in real time. After obtaining the monitoring image, image processing technology is used to analyze it. First, the livestock in the image are separated using an image segmentation algorithm, and the contour of each livestock is extracted. To improve the segmentation accuracy, a threshold-based segmentation method is adopted to separate the livestock in the image from the background, and the edge definition is further optimized through morphological operations (such as erosion and dilation). Next, the region growing method or the connected component analysis algorithm is used to judge and distinguish different species of livestock, such as pigs, cows, and sheep, etc., and they are classified and marked according to features such as color and texture. After completing the livestock species marking, the distribution density of each livestock species is calculated using a density estimation algorithm (such as kernel density estimation) to generate a livestock species activity distribution density map. This calculation can obtain the distribution density of livestock in the monitoring area by calculating the frequency of each livestock species appearing in the image and combining its spatial distribution characteristics, thereby providing basic data for the subsequent steps.

[0074] Step S2: Quantify the vibration of the robotic arm during close observation based on the activity distribution density of livestock species to obtain the vibration quantification data of the robotic arm during close approach; estimate the probability of the livestock stress state from the vibration quantification data of the robotic arm during close approach to obtain the livestock stress state probability data;

[0075] In the embodiment of the present invention, first, based on the livestock species activity distribution density data obtained in step S1, the vibration quantification process of the robotic arm during close observation is carried out. By analyzing the distribution density data, the areas with high density and low density are identified, and the observation position and direction of the robotic arm are adjusted according to this information. At this time, the sensor data acquisition system is used to monitor the relative position change between the robotic arm and the livestock in real time. Combining the movement trajectory and reaction speed of the robotic arm, the vibration amplitude and frequency generated by the robotic arm when approaching the livestock are calculated. The vibration quantification can read the vibration data when the robotic arm moves through the sensor, and perform frequency domain analysis on these vibration data using the Fourier transform (FFT) to obtain the amplitude and frequency distribution of the vibration, and then quantify the vibration data generated during the close approach of the robotic arm. Subsequently, using the above vibration data, the livestock stress state probability data is obtained. The stress state probability estimation adopts the Bayesian inference method, and by introducing the relationship between the vibration amplitude, frequency and the livestock stress response, the calculation is carried out, and finally the stress probability of the livestock in the current environment is obtained. The key to this process is to establish a mathematical model between the vibration and the stress state by analyzing the influence of the vibration of the robotic arm on different types of livestock, so as to provide a scientific basis for the subsequent adjustment of the robotic arm speed.

[0076] Step S3: Match the approaching speed of the robotic arm according to the livestock stress state probability data to obtain the approaching speed matching data of the robotic arm; design the monitoring attitude control instruction of the robotic arm based on the approaching speed matching data of the robotic arm and the livestock activity monitoring image to obtain the monitoring attitude adjustment control instruction of the robotic arm;

[0077] In the embodiment of the present invention, first, according to the livestock stress state probability data obtained in step S2, the approaching speed of the robotic arm is matched. To ensure that the movement of the robotic arm does not cause excessive stress reactions to the livestock, first, by dynamically adjusting the movement speed of the robotic arm, it is ensured that the robotic arm approaches the livestock at the most appropriate speed. The speed matching adopts an optimization algorithm, such as the gradient descent method, and adjusts the movement speed of the robotic arm in combination with the stress probability data to make it adapt to the stress reaction. The goal of speed matching is to minimize the probability of livestock stress while ensuring that the robotic arm can complete the monitoring task quickly and effectively. Next, based on the optimized speed matching data and the livestock activity monitoring images, the attitude control instructions of the robotic arm are designed. First, analyze the spatial position of the livestock in the image, combine the position and the operable space of the robotic arm, and use the inverse kinematics algorithm to calculate the optimal attitude of the robotic arm. According to these attitude data, the corresponding control instructions are designed. At this time, the control instructions will consider the joint angles of the robotic arm, the constraints of the working space, and the impact on the livestock stress state, and generate the robotic arm monitoring attitude adjustment control instructions to ensure that the robotic arm completes the monitoring task of the livestock in an appropriate attitude while minimizing unnecessary vibrations and noise interference during the movement of the robotic arm.

[0078] Step S4: Encode the robotic arm monitoring attitude adjustment control instructions to obtain the robotic arm monitoring attitude adjustment encoded instructions; design an automatic control program based on the robotic arm monitoring attitude adjustment encoded instructions to obtain the robotic arm monitoring attitude control program, and embed the robotic arm monitoring attitude control program into the robotic arm control center to execute the robotic arm control method for livestock state monitoring.

[0079] In the embodiment of the present invention, first, the robotic arm monitoring attitude adjustment control instructions are encoded. This encoding process converts the designed control instructions into a command format suitable for the robotic arm control system. Specifically, a standard control language (such as PLC programming language or robot control protocol) is used to format and encode the attitude adjustment instructions so that they can be recognized and executed by the robotic arm control system. Then, based on these encoded control instructions, an automatic control program is designed. The design of the control program is based on control algorithms, such as PID control, fuzzy control, or adaptive control, to ensure that the robotic arm can adjust its attitude according to real-time feedback to meet the requirements of livestock monitoring. During the design process, through the analysis of the kinematic model and dynamic model of the robotic arm, it is ensured that each instruction can effectively control the actions of the robotic arm, taking into account the inertia, speed limit, and working space limit of the robotic arm. After completing the design of the automatic control program, embed this program into the robotic arm control center so that the robotic arm can autonomously execute the livestock state monitoring task. This control system can automatically adjust the position, attitude, and movement speed of the robotic arm according to the real-time state of the livestock and environmental changes to ensure that the monitoring task is completed without disturbing the livestock.

[0080] Step S1 includes the following steps:

[0081] Step S11: Obtain the livestock monitoring area; deploy a cross track in the livestock monitoring area. The cross track is electrically connected to the robotic arm through a servo motor, and the robotic arm is controlled by the servo motor to move on the cross track. An electronic monitoring device is deployed on the robotic arm;

[0082] Step S12: Monitor the livestock activities in the livestock monitoring area through the electronic monitoring device to obtain livestock activity monitoring images;

[0083] Step S13: Mark the livestock species in the livestock activity monitoring images to obtain livestock species activity monitoring images; wherein the livestock species include pigs, cows, and sheep;

[0084] Step S14: Calculate the distribution density of the livestock species activity monitoring images to obtain the livestock species activity distribution density.

[0085] In the embodiments of the present invention, first, it is necessary to obtain the physical environment information of the livestock monitoring area to ensure that there is sufficient space and facilities for the robotic arm to operate in this area. This area is usually determined through environmental assessment, including ground flatness, spatial layout, and distance from surrounding obstacles, etc. Next, a cross track is deployed at an appropriate position in the livestock monitoring area. The cross track is composed of two intersecting tracks, which are respectively installed in the X-axis and Y-axis directions to enable the precise movement of the robotic arm in a two-dimensional plane. During the laying process of the track, the width, length, and material of the track must meet the load requirements of the robotic arm movement. Usually, high-strength steel or aluminum alloy materials are used to ensure that the track has sufficient stability and durability. At each end point of the cross track, a servo motor system is set up, and this motor system controls the movement of the robotic arm along the track. The selection of the servo motor needs to be determined according to the weight, movement accuracy, and movement speed requirements of the robotic arm. The motor drive system needs to ensure that the robotic arm can move smoothly and precisely along the X-axis or Y-axis direction on the track. The servo motor control system monitors the position of the robotic arm in real time through a closed-loop feedback method and adjusts the motor drive to ensure the precise positioning of the robotic arm on the track. An electronic monitoring device is installed on the robotic arm body. The device includes a high-definition camera, an infrared sensor, and other necessary image acquisition devices for monitoring and recording the activity status of livestock. The installation position of this device needs to ensure full coverage of the monitoring area to avoid any corner being overlooked. Driven by the servo motor control system, the robotic arm can be precisely positioned on the cross track, thereby realizing the full-round monitoring of the livestock area. The real-time monitoring of livestock activities is carried out through the electronic monitoring device deployed on the robotic arm. The electronic monitoring device mainly includes a high-resolution visible light camera, an infrared imaging camera, and a motion sensor. The visible light camera is used to capture images under normal illumination, while the infrared imaging camera is used to monitor livestock in low-light or night environments. The device is installed on the robotic arm, and the position of the robotic arm is precisely controlled through the servo motor system to obtain image data at different positions in the livestock monitoring area. The obtained image data needs to be processed by the data acquisition system to ensure the quality and clarity of the images. Through image processing algorithms, preliminary noise removal and contrast enhancement are performed on the images to make the livestock in the images more obvious. In addition, during the monitoring process, the temperature and humidity data of the surrounding environment also need to be monitored in real time, and the influence of environmental changes on the image quality is recorded through sensors. Through image analysis techniques (such as edge detection, contour extraction, etc.), the images are further processed to obtain the activity conditions of livestock in the monitoring area. This image data provides basic visual information for subsequent steps and can support livestock species marking and distribution density calculation. The livestock species are marked for the livestock activity monitoring images obtained in step S12. For this purpose, an image classification algorithm is used for analysis, specifically including using a convolutional neural network (CNN) based on deep learning for image feature extraction and classification.By training a multi-class classification model, the model can identify different livestock species in images, including pigs, cows, sheep, etc. During the training process, a large number of labeled livestock images are used as training data. The spatial features in the images (such as texture, shape, color, etc.) are extracted through CNN, and then the automatic classification of livestock species is achieved. Specifically, first, the input livestock activity monitoring images are preprocessed, such as scaling, standardizing, and normalizing, to ensure that the sizes of the images input into the CNN model are consistent. Then, the convolutional layer is used to perform layer-by-layer convolution operations on the images to extract local features in the images. Next, the pooling layer is used to compress the feature dimensions, and finally, the fully connected layer is used for classification output to obtain the livestock species in each region of the image. The classification results will be marked on the original monitoring images to form livestock species activity monitoring images, where each livestock is marked with the corresponding species label. To improve the marking accuracy, post-processing steps can also be adopted, such as manually correcting some areas suspected of misidentification to further ensure the accuracy of image marking. Calculate the distribution density of the livestock species activity monitoring images obtained in step S13. The specific steps include segmenting the marked images into regions, identifying the distribution of each livestock species, and calculating their spatial density within the monitoring region. For this purpose, the kernel density estimation (KDE) method is used to analyze the distribution of livestock species in the images. This method sets a kernel function (such as a Gaussian kernel) around the current position of each livestock in the image and calculates the density value of the kernel function around this point. The core idea of kernel density estimation is to estimate the livestock distribution density in each region of the image through weighted summation. Specifically, for each livestock species, first determine the spatial coordinates of each livestock, and then perform weighted summation on the region around this coordinate through the kernel density function to obtain the density value of this region. For the calculation of the entire image, kernel density estimation can be performed at each pixel point of the image to generate a density map, showing the livestock density in different regions. This process can clearly display the activity density of livestock in the monitoring region, and thus provide a basis for the subsequent motion trajectory planning and monitoring adjustment of the robotic arm. This distribution density map provides a basis for the regional division of the monitoring work of the robotic arm, enabling it to effectively avoid high-density regions or adjust the monitoring method.

[0086] Step S2 includes the following steps:

[0087] Step S21: Analyze the livestock movable azimuth of the livestock activity monitoring images based on the livestock species activity distribution density to obtain a livestock movable azimuth data set;

[0088] Step S22: Predict the livestock spatial movement trajectory based on the livestock movable azimuth data set and the livestock activity monitoring images to obtain livestock spatial movement trajectory prediction data;

[0089] Step S23: Quantify the vibration of the robotic arm approaching for observation based on the predicted data of the livestock's spatial movement trajectory to obtain the quantified vibration data of the robotic arm approaching;

[0090] Step S24: Estimate the probability of the livestock's stress state based on the quantified vibration data of the robotic arm approaching to obtain the probability data of the livestock's stress state.

[0091] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0092] Step S21: Analyze the livestock's movable azimuth of the livestock activity monitoring image based on the livestock species activity distribution density to obtain the livestock movable azimuth data set;

[0093] In the embodiment of the present invention, first, analyze the livestock's movable azimuth of the livestock activity monitoring image based on the livestock species activity distribution density data obtained in step S14. The key to this step is to identify the activity range and possible movement directions of different types of livestock in the monitoring area. By analyzing the distribution density map and using image segmentation technology to divide different density regions. The areas with higher density indicate that the livestock activities are more concentrated, while the areas with lower density are open areas with less activity. On this basis, extract the activity boundaries and trajectories of the livestock through image processing algorithms. Specifically, the threshold segmentation method can be used to separate the pixel regions showing livestock in the image, so as to determine the contour positions and activity ranges of each livestock. On this basis, use a path search algorithm based on graph theory (such as A algorithm) to predict the movement direction of livestock. A The algorithm combines heuristic search and path optimization, and can calculate the best movement direction and path according to the current distribution density of the livestock and its activity area. These path prediction results form the livestock movable azimuth data set, which records the movement directions and areas of each type of livestock in the monitoring area. The data set contains the starting positions of each livestock, the predicted movement directions and the areas it passes through, and finally forms the livestock movable azimuth data set, providing an important reference for the subsequent operation of the robotic arm.

[0094] Step S22: Predict the livestock's spatial movement trajectory based on the livestock movable azimuth data set and the livestock activity monitoring image to obtain the predicted data of the livestock's spatial movement trajectory;

[0095] In the embodiments of the present invention, first, livestock spatial movement trajectory prediction is performed based on the livestock movable azimuth data set obtained in step S21 and the livestock activity monitoring images obtained in step S12. The goal of this step is to use the known livestock movable azimuth data set, combine the historical movement trajectories of livestock and the environmental features visible in the monitoring images to predict the future movement trajectories of livestock. To this end, a trajectory prediction algorithm based on Kalman filtering is used to estimate the movement trajectories of livestock. Kalman filtering is a recursive algorithm that can dynamically update the estimated values according to the known measurement data and prediction model, and is suitable for accurate prediction under high uncertainty. In the implementation process, first, the livestock position information in the monitoring images (i.e., the coordinates of each livestock at a certain moment) and the historical trajectory data are input into the Kalman filter. Through the prediction step of the filter, the speed, acceleration, and position information of each livestock are updated. Then, according to the movement state of the livestock, the filter will generate a set of possible movement trajectories and output the movement paths of each livestock within a certain future time. To further improve the prediction accuracy, by combining with the current environmental information (such as terrain obstacles, the movement of other livestock, etc.), the state transition matrix of the Kalman filter can be adjusted to make the prediction results more in line with the changes in the actual environment. Finally, the obtained livestock spatial movement trajectory prediction data includes the path points and position coordinates that each livestock may pass through in the future time period, thus providing data support for the action planning of the robotic arm.

[0096] Step S23: Based on the livestock spatial movement trajectory prediction data, perform vibration quantization for the robotic arm approaching for observation to obtain robotic arm approaching vibration quantization data;

[0097] In the embodiment of the present invention, based on the predicted data of the livestock spatial movement trajectory obtained in step S22, the vibration of the manipulator approaching for observation is quantified. The key to this process is to quantify the vibration impact of the manipulator when performing tasks according to the relative position relationship between the movement trajectory of the livestock and the movement path of the manipulator. First, the movement trajectory and position of the manipulator are determined according to the predicted data of the livestock spatial movement trajectory. The task of the manipulator is to observe and intervene in a predetermined area, so it is necessary to calculate the distance between the manipulator and the livestock, and adjust the movement speed of the manipulator according to this distance. In order to quantify the vibration of the manipulator, an acceleration sensor and a gyroscope are installed at key parts of the manipulator to monitor the vibration of the manipulator in real time during the movement. Specifically, the acceleration data detected by the sensor is analyzed by a digital signal processing algorithm to obtain the vibration amplitude and frequency. The process of vibration quantification includes modeling the inertial force of the manipulator in motion, and calculating the vibration amount generated by the manipulator when approaching the livestock through parameters such as the mass, movement speed and path curvature of the manipulator, combined with the vibration propagation model in physics. This process requires careful adjustment of the control system of the manipulator to ensure that the manipulator maintains stable movement during the vibration quantification process. Ultimately, the quantitative data on the robot arm's approach vibration will include the vibration amplitude and frequency generated by the robot arm at different movement phases and its relative distance from the livestock.

[0098] Step S24: Estimating the livestock stress state probability based on the robot arm approach vibration quantified data to obtain livestock stress state probability data.

[0099] In the embodiments of the present invention, first, based on the robotic arm approaching vibration quantization data obtained in step S23, the probability of the livestock's stress state is estimated. The core task of this step is to deduce the probability of the livestock's stress response under different vibration states by quantifying the intensity and frequency of the vibration. The intensity of the stress response is closely related to the amplitude, frequency, and duration of the vibration. Therefore, by analyzing the amplitude changes and frequency characteristics in the vibration data, the sensitivity of the livestock to the vibration and the degree of stress response can be deduced. In this process, a logistic regression model or a naive Bayes classification algorithm can be used to establish a probability model based on the robotic arm vibration data and historical stress data. The model learns the relationship between the vibration quantization data and the livestock's stress response, and outputs the probability of the livestock's stress state under a specific vibration state. The specific operation is as follows: First, collect a large amount of experimental data, including the livestock's behavioral performance, stress response, and its physiological data (such as heart rate, respiratory rate, etc.) under different vibration conditions. Then, train a probability estimation model based on these data, and determine the probability relationship between the vibration quantization data and the stress response by the maximum likelihood estimation method. Finally, obtain the probability data of the livestock's stress state, including the stress response probability of each livestock under different vibration conditions. This data provides a basis for the subsequent intervention and adjustment of the robotic arm, ensuring that the actions of the robotic arm will not overly interfere with the livestock and avoid unnecessary stress responses.

[0100] Step S23 includes the following steps:

[0101] Step S231: Analyze the intermittent speed change of the livestock in the predicted data of the livestock's spatial movement trajectory to obtain the intermittent speed change data of the livestock;

[0102] Step S232: Perform an instantaneous pause inertia simulation when the robotic arm approaches for observation according to the intermittent speed change data of the livestock to obtain the instantaneous pause inertia data;

[0103] Step S233: Analyze the attenuation of the robotic arm jitter vector for the instantaneous pause inertia data to obtain the robotic arm jitter attenuation vector;

[0104] Step S234: Calculate the periodic jitter vector difference for the robotic arm jitter attenuation vector to obtain the periodic jitter vector difference;

[0105] Step S235: Obtain the robotic arm design structure data; perform robotic arm approaching observation vibration quantization according to the robotic arm design structure data, the robotic arm jitter attenuation vector, and the periodic jitter vector difference to obtain the robotic arm approaching vibration quantization data.

[0106] In the embodiment of the present invention, first, the intermittent speed change analysis of livestock spatial movement trajectory prediction data is carried out. By analyzing the speed data of each livestock on its predetermined trajectory, the volatility and regularity of the speed are identified. The key to this step is to judge the speed change pattern during the movement of livestock and quantify its intermittent speed change. Specifically, by performing a difference operation on the speed of each livestock in the time series, the incremental data of the speed is obtained, and then the sliding window algorithm is used to calculate the speed change rate within each window. By setting an appropriate window size, the speed change of livestock in a short period of time can be observed, and the acceleration, deceleration or pause moments during its movement can be identified. Further, the fast Fourier transform (FFT) can be used to perform frequency domain analysis on the speed data, so as to extract the frequency characteristics of speed fluctuations and identify periodic or non-periodic speed change patterns. Finally, the intermittent speed change data of livestock is obtained, including information such as the movement speed change frequency, fluctuation amplitude and change period of each livestock. This data provides an important input for the subsequent steps. Especially when the robotic arm approaches for observation, it can adjust the action strategy of the robotic arm according to the speed change of livestock to avoid unnecessary interference. Based on the intermittent speed change data of livestock obtained in step S231, the instantaneous pause inertia simulation is carried out when the robotic arm approaches for observation. The core task of this process is to simulate the inertial reaction of the robotic arm when approaching these speed change points by analyzing the speed pause or change during the movement of livestock. First, according to the movement trajectory of livestock and its speed change, the pause moment and position that the robotic arm needs to make when approaching are calculated. On this basis, using the momentum theorem in physics, by calculating the mass, speed and acceleration of the robotic arm, the inertial reaction of the robotic arm during the pause is estimated. Specifically, it is assumed that the robotic arm generates a certain speed during the approach to livestock and suddenly pauses at a certain moment. The inertial effect of the robotic arm will cause it to continue to move forward for a certain distance until it stops under the action of an external force (such as braking or friction). At this time, by analyzing the speed and mass of the robotic arm during the pause, the classical dynamic formula is used to simulate the inertial effect. By calculating the inertial effect, the inertial data during the pause of the robotic arm can be obtained, including the speed, displacement and acceleration during the pause. This data provides a theoretical basis for the subsequent vibration simulation and adjustment of the robotic arm, ensuring that the robotic arm can effectively control its inertial influence during the movement process and avoid causing additional interference to livestock. Based on the instantaneous pause inertia data obtained in step S232, the attenuation analysis of the jitter vector of the robotic arm is carried out. This step aims to simulate the jitter generated after the robotic arm pauses and evaluate the interference degree of the robotic arm to livestock by analyzing its attenuation process. First, the inertial effect generated during the instantaneous pause of the robotic arm will cause it to vibrate, and the amplitude and frequency of the vibration are related to the mass, movement state and pause time of the robotic arm.To this end, first, calculate the vibration frequency and amplitude of the robotic arm after pausing through a mathematical model, and use a simplified harmonic model to describe the vibration mode of the robotic arm. This model is based on the natural frequency of the system, the damping coefficient, as well as the mass and elastic characteristics of the robotic arm, and can accurately predict the vibration response of the robotic arm. According to the vibration data of the robotic arm, use an attenuation model (such as an exponential decay formula) to describe the attenuation process of the vibration over time. The attenuation coefficient is calculated based on the structural and material characteristics of the robotic arm and can reflect the decreasing rate of the vibration energy over time. Through simulation calculations, obtain the attenuation vector of the robotic arm vibration, and this vector characterizes the change in the vibration amplitude at different time points. Finally, obtain the jitter attenuation vector of the robotic arm, providing data support for subsequent periodic jitter analysis to ensure that the impact of the vibration on livestock is effectively controlled when the robotic arm approaches the livestock. Based on the jitter attenuation vector of the robotic arm obtained in step S233, calculate the periodic jitter vector difference. The goal of this step is to quantify the periodic changes in the robotic arm jitter and evaluate the impact of different periodic jitters on the stability of the robotic arm by calculating the periodic jitter vector difference. First, according to the attenuation vector, extract the periodic characteristics of the robotic arm vibration and analyze the vibration frequency. Through frequency domain analysis techniques such as Fourier transform, the vibration signal can be decomposed into multiple frequency components and the main vibration frequencies can be identified. On this basis, calculate the change in the vibration amplitude within each period, and use the difference calculation method to obtain the difference in the vibration vectors between different periods. Specifically, the periodic jitter vector difference evaluates the stability of the robotic arm vibration within each period by calculating the difference in the vibration amplitudes between adjacent periods. If the periodic jitter vector difference is large, it indicates that there are large fluctuations in the vibration amplitude, which will have an adverse impact on the operation accuracy of the robotic arm. Through this method, the vibration characteristics of the robotic arm at different time periods can be comprehensively understood, providing data support for further optimizing the control strategy of the robotic arm. First, obtain the robotic arm design structure data, which includes various design parameters of the robotic arm, such as structural dimensions, mass distribution, moment of inertia, etc. According to the robotic arm design data, the jitter attenuation vector obtained in step S233, and the periodic jitter vector difference obtained in step S234, perform vibration quantification for the robotic arm during close observation. During this process, the robotic arm design structure data is a key input factor. By combining it with the vibration attenuation vector and periodic vibration data, calculate the vibration response of the robotic arm under different working conditions. Specifically, based on the mass distribution and moment of inertia of the robotic arm, use a mechanical model to perform vibration quantification calculations, taking into account the external and internal forces acting on the robotic arm during movement, and deduce the vibration amplitude and frequency. At this time, by calculating the propagation path and reflection characteristics of the vibration, obtain the specific quantification data of the vibration during the robotic arm approaching process. The vibration quantification data will include important information such as vibration amplitude, frequency, duration, and the relative impact between the robotic arm and the livestock.With this data, it is possible to ensure the smooth movement of the robotic arm, avoid excessive vibrations, reduce the impact on livestock, and at the same time provide accurate parameters for subsequent robotic arm control.

[0107] Step S24 includes the following steps:

[0108] Step S241: Obtain the noise decibels acceptable to livestock, where the noise decibels acceptable to livestock include: the noise decibels acceptable to pigs, the noise decibels acceptable to sheep, and the noise decibels acceptable to cows;

[0109] Step S242: Perform vibration noise feedback matching on the vibration quantization data of the robotic arm approaching the livestock to obtain vibration noise feedback data;

[0110] Step S243: Calculate the instantaneous noise spectrum band difference of the vibration noise feedback data to obtain the instantaneous noise spectrum band difference;

[0111] Step S244: Analyze the extreme value distribution of the noise band based on the instantaneous noise spectrum band difference to obtain the extreme value distribution data of the noise band;

[0112] Step S245: Perform excessive sound pressure instantaneous aggregation analysis on the noise decibels acceptable to livestock based on the instantaneous noise spectrum band difference and the extreme value distribution data of the noise band to obtain excessive sound pressure instantaneous aggregation data;

[0113] Step S246: Estimate the probability of the livestock stress state for the noise decibels acceptable to livestock based on the excessive sound pressure instantaneous aggregation data to obtain the livestock stress state probability data.

[0114] In the embodiments of the present invention, first, the acceptable noise decibel data of different types of livestock are obtained, specifically including the noise tolerance of pigs, sheep, and cattle. To ensure the accuracy of the data, first, the basic responses of each type of livestock in a quiet environment are evaluated. A noise sensor or a sound level meter is used to monitor the responses of livestock in different environments. Through experiments, the acceptable noise thresholds of different types of livestock under various noise sources are gradually determined. First, each type of livestock is placed alone in an environment with adjustable noise, and the decibel value of the environmental noise is gradually increased, and its behavioral responses are observed. Pigs are relatively sensitive and usually show certain restlessness behaviors when the noise reaches 85 decibels. Therefore, the acceptable noise decibel for pigs is 85 decibels. Sheep begin to show slight restlessness behaviors when the noise reaches 80 decibels. Therefore, the acceptable noise decibel for sheep is 80 decibels. Cattle have a relatively high noise tolerance and usually show restlessness behaviors only when the noise reaches 90 decibels. Therefore, the acceptable noise decibel for cattle is 90 decibels. Through these experimental data, the acceptable noise decibel datasets of each type of livestock are obtained, including the noise tolerance of three types of livestock: pigs, sheep, and cattle, providing key reference data for subsequent noise interference analysis; in another embodiment, relevant literature can also be consulted to obtain the acceptable noise decibels of pigs, sheep, and cattle. First, vibration noise feedback matching is performed on the vibration quantization data when the robotic arm approaches. This step aims to match the vibration signal generated by the robotic arm when approaching livestock with the actual noise data to form vibration noise feedback data. According to the robotic arm vibration quantization data obtained in step S235, considering that the vibration generated during the movement of the robotic arm will not only affect the stability of the robotic arm itself but also produce additional noise effects. Therefore, first, the frequency components and amplitudes of the vibration signal are extracted to establish a vibration spectrum. Then, the vibration spectrum is filtered in frequency bands using high-pass and low-pass filters, and the frequency distribution of the vibration noise is divided into several main intervals: low frequency, medium frequency, and high frequency. By comparing the vibration spectrum with the acceptable noise decibels of livestock, feedback matching is performed to evaluate the degree of noise interference generated by the vibration on livestock. Specifically, a matching algorithm, such as the least squares method or the normalized cross-correlation method, is used to compare the matching degree between the robotic arm vibration spectrum and the acceptable noise threshold of livestock. Through this method, vibration noise feedback data can be obtained, which characterizes the contribution of vibration during the movement of the robotic arm to the environmental noise, thereby providing a reference for subsequent noise analysis. The instantaneous noise spectrum band difference of the vibration noise feedback data is calculated. The goal of this step is to calculate the noise spectrum difference at different time points by analyzing the spectrum band of the vibration noise feedback data. First, the vibration noise feedback data is divided into multiple time periods, and the noise signal in each time period is converted into a frequency-domain signal using the fast Fourier transform (FFT). Then, according to the frequency-domain data, different frequency components of the noise signal are identified. By calculating the difference between the noise spectrum bands of adjacent time periods, the noise spectrum band difference at each time point is obtained.The calculation method of the noise spectrum band difference is to perform differential processing on the spectral amplitudes of each time period. That is, for any two time points t1 and t2, calculate the difference in their corresponding frequency components. If the spectral difference is large, it indicates that the frequency components of the noise signal have changed significantly at this time point. Through this calculation method, the volatility of the noise spectrum can be quantified, and the frequency change pattern that causes the stress response of livestock when the robotic arm approaches can be identified. Based on the instantaneous noise spectrum band difference data obtained in step S243, an analysis of the extreme value distribution of the noise band is carried out. The purpose of the analysis of the extreme value distribution of the noise band is to evaluate the extreme value distribution of the noise spectrum fluctuations caused by the vibration of the robotic arm in different frequency bands, especially to identify the noise bands that cause the stress response of livestock. First, select multiple frequency ranges in the noise spectrum band and calculate the maximum amplitude of each frequency band in groups. By statistically analyzing the maximum noise amplitude and the occurrence frequency of each frequency band, the extreme value distribution of the noise in different frequency bands is obtained. Further, the extreme value theory model is used to analyze the extreme value distribution characteristics of the noise to determine whether the noise amplitude in each frequency band exceeds the acceptable range of livestock. For each frequency band, the potential impact on livestock can be evaluated by calculating the statistical characteristics of the noise peak in this frequency band, such as the maximum value, average value, and standard deviation. At this time, through the extreme value distribution data of the noise band, the intensity and fluctuation of the noise in different frequency bands can be clarified, providing a basis for subsequent noise control and stress state analysis. Based on the instantaneous noise spectrum band difference and the extreme value distribution data of the noise band obtained in step S243 and step S244, an analysis of the instantaneous aggregation of excessive sound pressure on the acceptable noise decibels of livestock is carried out. The goal of this analysis is to identify the aggregation effect of the noise, that is, whether the noise intensity that appears in a short period of time will generate excessive sound pressure on livestock, thus triggering a stress response. First, according to the instantaneous band difference and extreme value distribution data of each noise frequency band, calculate the sound pressure aggregation value at different time points. Specifically, by integrating the instantaneous noise spectrum band difference data, the total noise intensity of each time period is obtained, and combined with the extreme value distribution of the noise band, the excessive accumulation of sound pressure in these time periods is evaluated. By calculating the aggregation of sound pressure in each time period, the area of excessive concentration of sound pressure in a short period of time can be identified. For each time period, further compare it with the acceptable noise decibels of livestock to identify whether it exceeds the noise tolerance of livestock, and then predict the triggered stress response. Based on the instantaneous aggregation data of excessive sound pressure obtained in step S245, an estimation of the probability of the stress state of livestock on the acceptable noise decibels of livestock is carried out. The purpose of this step is to quantify the probability of the stress response of livestock under different noise intensities. First, combine the noise tolerance data of different livestock to evaluate the excessive sound pressure in each time period. If the sound pressure aggregation value in a certain time period exceeds the acceptable noise decibels of livestock, it is considered that the stress response of livestock is caused in this time period. According to the experimental data, by constructing a stress response probability model, based on the degree and duration of the excessive aggregation of noise, estimate the probability of the stress response of livestock in this time period.This probability model can be fitted and trained using statistical methods such as linear regression or logistic regression to obtain a mapping function that correlates the excessive sound pressure data with the probability of stress response. Finally, through this model, the probability of the stress state of livestock under different noise conditions can be accurately predicted, providing decision-making support for subsequent monitoring and intervention.

[0115] Step S3 includes the following steps:

[0116] Step S31: Perform robotic arm approaching rate matching based on the robotic arm approaching vibration quantization data and the livestock stress state probability data to obtain the robotic arm approaching rate matching data;

[0117] Step S32: Conduct a logical error iterative test on the robotic arm approaching rate matching data to obtain the logical error iterative test data;

[0118] Step S33: Correct the rate error of the robotic arm approaching rate matching data according to the logical error iterative test data to obtain the robotic arm approaching rate optimization data;

[0119] Step S34: Design a robotic arm monitoring attitude control instruction based on the robotic arm approaching rate optimization data and the livestock activity monitoring image to obtain the robotic arm monitoring attitude adjustment control instruction.

[0120] As an example of the present invention, referring to Figure 3 as shown, in this example, step S3 includes:

[0121] Step S31: Perform robotic arm approaching rate matching based on the robotic arm approaching vibration quantization data and the livestock stress state probability data to obtain the robotic arm approaching rate matching data;

[0122] In the embodiments of the present invention, first, the vibration quantization data of the robotic arm approaching and the livestock stress state probability data are obtained. These two data sets respectively characterize the vibration effect generated when the robotic arm moves and the probability of the stress response of the livestock caused by the vibration. Based on these data, the approaching speed matching of the robotic arm is carried out. The purpose is to minimize the impact of the vibration on the livestock stress state by adjusting the movement speed of the robotic arm. Specifically, first, according to the vibration quantization data of the robotic arm at different movement speeds, a relationship graph between the vibration amplitude and the movement speed is drawn. This graph shows that there is a certain linear or non-linear relationship between the movement speed of the robotic arm and the vibration amplitude, and a higher movement speed will result in stronger vibration. Then, combined with the livestock stress state probability data, the probability of the stress response generated by the livestock at different vibration amplitudes is identified. For example, when the vibration amplitude exceeds a certain threshold, the probability of the livestock stress state increases sharply, resulting in a stress response. Therefore, according to the relationship between the livestock stress state probability and the vibration quantization data, the movement speed of the robotic arm is adjusted to keep the vibration amplitude within the acceptable range of the livestock, thereby ensuring the comfort and safety of the livestock. Finally, the approaching speed matching data of the robotic arm is obtained.

[0123] Step S32: Perform a logical error iterative test on the approaching speed matching data of the robotic arm to obtain logical error iterative test data;

[0124] In the embodiments of the present invention, a logical error iterative test is performed on the approaching speed matching data of the robotic arm. First, the actual movement data of the robotic arm at different speeds is compared with the theoretical speed matching data to analyze the deviation between the two. For this purpose, it is necessary to continuously monitor the actual speed of the robotic arm during its movement and compare it with the optimized ideal speed. Through an error feedback control algorithm, such as a proportional-integral-derivative (PID) controller or a Kalman filter algorithm, the speed of the robotic arm is dynamically adjusted to make it closer to the ideal speed. When there is an error between the actual movement speed of the robotic arm and the preset ideal speed, the system will adjust the speed value according to the feedback information to gradually reduce the error. Through multiple iterative tests, the actual movement of the robotic arm is re-evaluated after each adjustment to ensure that the error is continuously reduced. This process continues until a predetermined error tolerance range is reached. During this process, the results of each adjustment and calculation are based on the previous error feedback to achieve higher accuracy and better matching, and logical error iterative test data is obtained. This data is used for further speed optimization to ensure that the movement speed of the robotic arm can accurately meet the actual needs at each stage.

[0125] Step S33: Perform speed error correction on the approaching speed matching data of the robotic arm according to the logical error iterative test data to obtain the optimized approaching speed data of the robotic arm;

[0126] In the embodiment of the present invention, rate error correction is performed on the approaching rate matching data of the robotic arm by using the logical error iterative test data. First, based on the error iterative data obtained in step S32, the error between the actual movement rate and the target rate of the robotic arm in each iteration is calculated. By statistically analyzing these error data, the patterns and changing trends of the rate error are identified. A correction method, such as weighted average or minimum error method, is used to correct the rate matching data of the robotic arm. For example, within each rate segment, the distribution law of the error is analyzed and its average deviation is calculated, and then the error of each rate segment is corrected to obtain more accurate rate matching data of the robotic arm. The core of rate error correction is to minimize the influence of different errors. By adjusting the parameters of rate matching, the error between it and the ideal rate is kept within the minimum range. For each set of actual movement rates of the robotic arm, fine adjustments are made according to their error values to ensure that the corrected rate is more accurate. Finally, through this correction step, the optimized approaching rate data of the robotic arm are obtained, providing more stable and reliable rate data for subsequent attitude control and motion adjustment.

[0127] Step S34: Design a robotic arm monitoring attitude control instruction based on the optimized approaching rate data of the robotic arm and the livestock activity monitoring image, and obtain a robotic arm monitoring attitude adjustment control instruction.

[0128] In the embodiment of the present invention, based on the optimized approaching rate data of the robotic arm and the livestock activity monitoring image obtained in step S33, a robotic arm monitoring attitude control instruction is designed. First, the optimized rate data of the robotic arm provides a basis for designing the monitoring attitude control instruction. During the design process, it is necessary to analyze the influence of the movement trajectory and attitude adjustment of the robotic arm on the livestock. By analyzing the livestock activity monitoring image, the position, movement and state information of the livestock are extracted. Based on these image data, the current position and activity range of the livestock are identified, and according to the optimized rate data of the robotic arm, the possible paths and postures of the robotic arm when approaching the livestock are predicted. In order to ensure that the robotic arm does not cause unnecessary stress reactions when approaching the livestock, it is necessary to adjust the monitoring attitude of the robotic arm in real time according to the activity of the livestock. For example, when the livestock is in a relatively tense state, the robotic arm should maintain a slower approaching rate and adopt a relatively gentle posture to avoid excessive vibration or sound pressure stimulation. In the design of the control instruction, these factors need to be comprehensively considered to generate an attitude adjustment plan suitable for the current livestock state, and finally obtain a robotic arm monitoring attitude adjustment control instruction. These instructions will ensure that the robotic arm is more accurate and stable during movement, while reducing interference to the livestock.

[0129] Step S33 includes the following steps:

[0130] Step S331: Perform multi-frequency error cumulative calculation on the logical error iterative test data to obtain multi-frequency error cumulative data;

[0131] Step S332: Perform interval maximum error analysis on the logical error iterative test data based on the multi-frequency error cumulative data to obtain multi-frequency maximum error interval data;

[0132] Step S333: Perform time-series linear interpolation on the multi-frequency maximum error interval data to obtain error interval time-series interpolation data;

[0133] Step S334: Perform rate error correction on the robotic arm approaching rate matching data according to the error interval time-series interpolation data and the multi-frequency maximum error interval data to obtain robotic arm approaching rate optimization data.

[0134] In the embodiments of the present invention, multi-frequency error accumulation calculation is performed on the logical error iteration test data. First, test data of multiple logical error iterations are obtained and arranged in chronological order. The data of each round of error test is usually based on a time step and can form a time series. To calculate the multi-frequency error accumulation, it is necessary to accumulate the values of each error. The specific operation is to add the error value of each round to the error value of the previous round to obtain the accumulated error. To implement this process, first, the error values of each test cycle are normalized so that the error data has the same dimension, facilitating subsequent summation calculations. By calculating the error at each time point and the accumulated error value of the previous time point, the accumulated values of all errors are gradually obtained. The accumulated error value at each time point reflects the cumulative situation of errors during that time period, forming a set of error accumulation data. This data set not only includes the time distribution of errors but also reveals the error evolution trend at different rates, helping to analyze the maximum fluctuation range of errors in the subsequent analysis. Interval maximum error analysis is performed based on the multi-frequency error accumulation data. First, it is necessary to perform time interval analysis on the multi-frequency error accumulation data. The accumulated error value at each time point can be compared with the accumulated error value of the previous time point to calculate the error change in each time interval. To perform the maximum error analysis, it is necessary to find the maximum error value in each time interval of the error accumulation data. This process involves calculating the error difference for each time period, that is, subtracting the accumulated error value of the previous time point from the accumulated error value of the current time point. In this way, the error increment of each time interval can be calculated, and the maximum error value in each interval can be identified. Then, analyze the maximum error in each time interval and record the time interval in which it occurs. Through this analysis, the multi-frequency maximum error interval data obtained shows the amplitude of error value fluctuations and the time intervals in which they occur at different time periods. This data is crucial for subsequent error correction and rate optimization because it can help accurately identify which time periods have the largest error fluctuations, thus providing an accurate basis for optimizing rate matching. Perform time-series linear interpolation on the multi-frequency maximum error interval data. First, obtain the multi-frequency maximum error interval data obtained in step S332, which includes the maximum error value and its time span in each time interval. To smooth this data and perform interpolation processing, it is necessary to first determine the interpolation time points. These time points can be selected between the time intervals of the original data to ensure the continuity and high precision of the interpolated data. Then, use the linear interpolation method to interpolate the error values between every two adjacent time points. The specific operation of linear interpolation is that for any two time points, assuming their error values are E1 and E2 and the time intervals are T1 and T2, the interpolated error value can be calculated by the following formula: , through this method, the error value at each interpolation time point can be obtained, thereby forming a smooth error value curve. The main purpose of time-series linear interpolation is to fill the gaps in the original data, making the entire error data set more refined and having a higher time resolution. The interpolated data can more accurately reflect the changing trend of the error at each time point and provide more detailed information for subsequent error correction. Perform rate error correction on the approaching rate matching data of the robotic arm according to the error interval time-series interpolated data and the multi-frequency maximum error interval data. First, obtain the error interval time-series interpolated data in step S333 and the multi-frequency maximum error interval data in step S332. These two sets of data represent the smooth changing trend of the error and the maximum fluctuation range of the error respectively. In order to perform rate error correction on the approaching rate matching data of the robotic arm, it is necessary to combine these two sets of data with the original rate matching data for error correction. The specific operation is as follows: First, calculate the rate error at each time point by comparing the relationship between the original rate matching data and the error accumulation data. Then, adjust the rate value at each time point according to the error interval time-series interpolated data and the multi-frequency maximum error interval data. The adjustment method is to calculate the correction factor according to the amplitude and time interval of the error fluctuation. This correction factor reflects the accumulation of errors within a certain time period and dynamically adjusts the rate matching data according to the maximum fluctuation range of the error. For the error at each time point, use the weighted average or minimum error optimization algorithm to gradually correct the movement rate of the robotic arm to make it closer to the target rate. Finally, obtain the optimized approaching rate data of the robotic arm. The movement of the robotic arm is adjusted to a more precise state through the rate after error correction, ensuring that the robotic arm can minimize the interference to the livestock when approaching the livestock and avoid unnecessary stress reactions caused by excessive vibration.

[0135] Step S34 includes the following steps:

[0136] Step S341: Perform livestock activity posture decomposition processing on the livestock activity monitoring image to obtain livestock activity posture decomposition data;

[0137] Step S342: Perform dynamic analysis of the blind area of the livestock's perspective on the livestock activity posture decomposition data to obtain dynamic data of the blind area of the livestock's perspective;

[0138] Step S343: Adjust the robotic arm path posture control according to the optimized approaching rate data of the robotic arm for the dynamic data of the blind area of the livestock's perspective to obtain robotic arm path posture control adjustment data;

[0139] Step S344: Design the robotic arm monitoring posture control instruction based on the robotic arm path posture control adjustment data to obtain the robotic arm monitoring posture adjustment control instruction.

[0140] In the embodiments of the present invention, the livestock activity monitoring images are processed for decomposing the livestock activity postures. First, the livestock activity monitoring image data from cameras or other image acquisition devices are obtained. These image data usually include the movement trajectories of the livestock and their specific activity postures. To effectively decompose the livestock activity postures, the images are first preprocessed to remove noise and enhance the image contrast, making the contours of the livestock clearer. During the processing, an edge detection algorithm (such as the Canny edge detection) is used to extract the contours and joint positions of the livestock in the images. Then, a pose estimation algorithm, such as the OpenPose algorithm, is used to identify the position information of each part (such as the head, limbs, torso, etc.) of the livestock through key point detection technology. These key points are connected according to different activity postures to form a skeleton graph, representing the postures of the livestock at different time points. Further, the joint positions of each skeleton graph are matched with time to obtain the time series data of the livestock activities, thus completing the decomposition of the livestock activity postures. Finally, the obtained livestock activity posture decomposition data contains the specific posture information of the livestock at different time points, including key features such as the start, duration, and movement direction of the activity, providing basic data for subsequent blind area analysis and path control. Perform dynamic analysis on the livestock blind area of the livestock activity posture decomposition data. The purpose of this step is to identify and analyze the changing rules of the blind area of the livestock during its activities, so as to effectively monitor and intervene using the blind area. According to the livestock activity posture decomposition data obtained in step S341, first, by analyzing the orientation and movement trajectories of the livestock's head and eyes, combined with its activity state, the visual field range of the livestock at each time node is deduced. Since the orientation of the livestock's head and eyes often changes during movement, its blind area is dynamically changing. To accurately describe this change, stereo vision technology and deep learning algorithms are used to analyze the three-dimensional information of the images to identify which areas are occluded and become blind areas at different time points. For example, if the livestock's head rotates rapidly or the body posture changes greatly, the size and position of the blind area will also change accordingly. Based on these analyses, dynamic area division technology is used to spatially represent the blind area as dynamic area data that changes with time, and generate livestock blind area dynamic data. Through this analysis, the position of the livestock's blind area can be accurately grasped, providing accurate data support for subsequent path adjustment and monitoring instructions. Optimize the data according to the approaching rate of the robotic arm, and perform robotic arm path posture control adjustment on the livestock blind area dynamic data. The goal of this step is to adjust the path and posture of the robotic arm by analyzing the relationship between the movement speed of the robotic arm and the dynamic change of the blind area, ensuring that the robotic arm is always within the blind area of the livestock, thus avoiding interfering with the visual perception of the livestock. First, obtain the robotic arm approaching rate optimization data that has been completed in step S333, which describes the optimal movement rate and acceleration of the robotic arm during the process of approaching the livestock.Then, based on the dynamic data of the blind spot of the livestock's perspective, it is judged whether the robotic arm has entered the visible range of the livestock. If the robotic arm enters the livestock's field of view, its movement path needs to be adjusted so that the robotic arm can be kept in the blind spot of the livestock as much as possible during the approaching process. This adjustment is achieved by re-planning the path points of the robotic arm and adjusting its posture. For example, a path planning method based on the A* algorithm is adopted. While considering the speed limit of the robotic arm, the line of sight of the livestock is avoided, so that the path of the robotic arm can be kept from being exposed to the livestock's field of view as much as possible. By adjusting the movement trajectory and speed of the robotic arm, it is ensured that the robotic arm is always in the blind spot of the livestock's perspective, thus avoiding interfering with the normal activities of the livestock. Through this path adjustment, the control adjustment data of the robotic arm path posture is obtained, and these data reflect the specific posture adjustment instructions that the robotic arm should take during the approaching process of the livestock. The robotic arm monitoring posture control instruction design is carried out based on the control adjustment data of the robotic arm path posture. The purpose of this step is to generate the final robotic arm control instruction to ensure that the robotic arm can accurately execute the path posture adjustment and maintain in the blind spot of the livestock. First, according to the control adjustment data of the robotic arm path posture obtained in step S343, combined with the current state, target position and movement rate of the robotic arm, the inverse kinematics (IK) algorithm is used to accurately calculate the angle of each joint of the robotic arm. Through this process, the target position and movement angle of each joint are calculated to ensure that each part of the robotic arm can move according to the predetermined path and posture. During the path control process, a trajectory tracking algorithm, such as the PID control algorithm, is adopted to ensure that the movement process of the robotic arm is stable and smooth, avoiding instability caused by too fast or too slow speed. Finally, according to these control parameters, the posture adjustment control instruction of the robotic arm is generated, including control parameters such as the angle change, movement speed, and acceleration of each joint, ensuring that the robotic arm can accurately execute the predetermined path and maintain the monitoring operation in the blind spot of the livestock. Through this series of steps, the generated robotic arm monitoring posture adjustment control instruction ensures that the robotic arm can efficiently and accurately complete the task during the operation, while avoiding interfering with the livestock to the greatest extent.

[0141] Step S343 includes the following steps:

[0142] Perform blind spot boundary surface fitting processing on the dynamic data of the livestock's perspective blind spot to obtain blind spot boundary surface fitting data;

[0143] Perform robotic arm space coverage calculation on the blind spot boundary surface fitting data to obtain robotic arm space coverage data;

[0144] Based on the robotic arm space coverage data, perform path point distribution retrieval processing on the blind spot boundary surface fitting data to obtain path point distribution data;

[0145] Optimize the data of the path point distribution according to the approaching speed optimization data of the robotic arm to perform phased motion parameter matching, and obtain the phased motion parameters of the robotic arm;

[0146] Adjust the path attitude control of the robotic arm according to the phased motion parameters of the robotic arm and the path point distribution data, and obtain the path attitude control adjustment data of the robotic arm.

[0147] In the embodiments of the present invention, first, the dynamic data of the blind area of the livestock's perspective is subjected to blind area boundary surface fitting processing. The main purpose of this step is to accurately describe the shape and position changes of the blind area during the livestock's activities by fitting the boundary surface of the blind area. First, obtain the dynamic data of the blind area of the livestock's perspective obtained in step S342. This data reflects the angles and positions of the livestock's activities at different time points, as well as the resulting changes in the blind area of the perspective. To perform the fitting processing, polynomial fitting or B-spline curve method is adopted. These two methods can generate smooth surfaces through a small number of data points and are suitable for describing irregular boundaries. By fitting the blind area data in three-dimensional space, the surface equation of the blind area boundary is obtained. Specifically, when operating, the coordinates of each data point in space (for example, the positions on the X, Y, and Z axes) are used as the fitting input, and the change rules of these coordinates are modeled through the surface fitting algorithm, and finally a set of mathematical functions that can describe the blind area boundary surface are generated. In this way, the obtained blind area boundary surface fitting data can accurately represent the three-dimensional shape of the dynamic perspective blind area formed by the livestock during activities, and further provide a basis for path planning and robotic arm motion adjustment. Through the calculation of the space coverage of the robotic arm for the blind area boundary surface fitting data. The generation of the robotic arm space coverage data is to ensure that its path and actions do not enter the livestock's field of view area by judging the space area that the robotic arm can cover. In this step, first, according to the working range and motion parameters of the robotic arm, determine the effective reachable space of the robotic arm, usually by calculating the intersection of the robotic arm's trajectory and the target area. To more accurately control the behavior of the robotic arm, it is necessary to combine the structural characteristics of the robotic arm (such as arm length, rotation angle, etc.) and the blind area boundary surface fitting data to analyze whether the robotic arm can enter or approach the livestock's perspective range under a specific path. If the working space of the robotic arm coincides with the blind area of the livestock, it means that the robotic arm can move in this area, thus ensuring that the task is executed without disturbing the livestock's field of view. During the calculation process of this step, spatial mapping technology is adopted to compare the reachable area of the robotic arm with the blind area boundary to obtain the robotic arm space coverage data, and clarify the motion range of the robotic arm and its relative position relationship with the blind area. In the path point distribution retrieval processing step, according to the robotic arm space coverage data, perform path point distribution retrieval on the blind area boundary surface fitting data. The purpose of this step is to ensure that the robotic arm can always stay within the blind area during the process of approaching the livestock by retrieving and distributing path points, and avoid being exposed in the livestock's field of view. First, use the robotic arm space coverage data to clarify the motion range of the robotic arm and the relative position of the blind area boundary. Next, through path planning algorithms such as the A* algorithm or Dijkstra algorithm, perform path point distribution retrieval based on the working range of the robotic arm and the blind area data.The retrieval process needs to consider the target position of the robotic arm, the blind area range, and the limiting conditions of the surrounding environment, and evenly distribute the path points in the working space of the robotic arm to ensure that the robotic arm path always remains within the blind area during movement and avoid crossing the visual range of livestock. Through this path point distribution retrieval process, path point distribution data is obtained to ensure that the path of the robotic arm movement adapts to the blind area of the livestock's vision. Perform phased motion parameter matching on the path point distribution data according to the robotic arm approaching rate optimization data. First, determine the phased parameters of the robotic arm movement according to the robotic arm approaching rate optimization data. These parameters include the speed, acceleration, interval between target points, and movement order of path points of the robotic arm. Then, combine these parameters with the path point distribution data to perform phased motion parameter matching. This process involves ensuring that the robotic arm is always in an appropriate motion state when completing the task by adjusting the time interval and movement speed between path points, so as to ensure that it always remains within the blind area during the approach to livestock. Specifically, use time segmentation and parameter adjustment algorithms (such as piecewise linear interpolation) to accurately match the motion parameters of the robotic arm between different path points, making the robotic arm movement both stable and efficient, and avoiding instability caused by too fast or too slow speed. After this step, the phased motion parameters of the robotic arm are obtained, and these data provide a motion basis for the precise control of the robotic arm. Finally, perform robotic arm path attitude control adjustment according to the robotic arm phased motion parameters and path point distribution data to obtain robotic arm path attitude control adjustment data. The purpose of this step is to ensure that it can accurately execute the task and always remain within the blind area of the livestock by optimizing the path and attitude of the robotic arm. In this step, first calculate the angle changes of each joint according to the robotic arm phased motion parameters, and adjust the attitude of the robotic arm through the inverse kinematics algorithm to adapt to the changes between different path points. At the same time, combined with the path point distribution data, use a trajectory tracking algorithm (such as the PID control algorithm) to finely control the movement of the robotic arm to ensure that the robotic arm does not deviate from the predetermined trajectory during movement and always remains within the blind area range. Finally, generate robotic arm path attitude control adjustment data, which provides control instructions such as joint angles, speeds, and accelerations required for the robotic arm to execute tasks, ensuring that the robotic arm can accurately complete the monitoring task and make the most of the blind area of the livestock's vision for monitoring operations.

[0148] The present invention also provides a robotic arm control system for livestock status monitoring, which is used to execute the robotic arm control method for livestock status monitoring as described above. The robotic arm control system for livestock status monitoring includes:

[0149] A distribution density analysis module, which is used to monitor the livestock activities in the livestock monitoring area through an electronic monitoring device to obtain livestock activity monitoring images; calculate the distribution density of the livestock activities monitoring images to obtain the distribution density of livestock species activities;

[0150] A stress state probability estimation module, which is used to quantify the vibration of the robotic arm approaching for observation based on the activity distribution density of livestock species, so as to obtain the quantified vibration data of the robotic arm approaching; estimate the probability of the livestock stress state based on the quantified vibration data of the robotic arm approaching, so as to obtain the livestock stress state probability data;

[0151] An attitude control instruction design module, which is used to match the approaching speed of the robotic arm according to the livestock stress state probability data, so as to obtain the approaching speed matching data of the robotic arm; design the robotic arm monitoring attitude control instruction based on the approaching speed matching data of the robotic arm and the livestock activity monitoring image, so as to obtain the robotic arm monitoring attitude adjustment control instruction;

[0152] An automatic control program design module, which is used to encode the robotic arm monitoring attitude adjustment control instruction to obtain the robotic arm monitoring attitude adjustment encoded instruction; design an automatic control program based on the robotic arm monitoring attitude adjustment encoded instruction to obtain the robotic arm monitoring attitude control program, and embed the robotic arm monitoring attitude control program into the robotic arm control center to execute the robotic arm control method for livestock state monitoring.

[0153] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be included in the present invention.

[0154] The above are only the specific implementation manners of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for controlling a robotic arm for livestock status monitoring, characterized in that: The following steps are involved: Step S1: monitoring livestock activities in a livestock monitoring area through electronic monitoring equipment to obtain livestock activity monitoring images; calculating the distribution density of livestock activity monitoring images to obtain livestock activity distribution density; Step S2: quantifying the vibration of the approaching robot arm observation based on the activity distribution density of livestock types, and obtaining the quantified data of the approaching robot arm vibration; The probability of livestock stress state is estimated based on the quantitative data of the mechanical arm approaching vibration, and the probability data of livestock stress state is obtained; Step S3: performing robot arm approach rate matching according to the livestock stress state probability data to obtain robot arm approach rate matching data; Based on the approach rate matching data of the robot arm and the livestock activity monitoring images, the robot arm monitoring posture control instructions are designed to obtain the robot arm monitoring posture adjustment control instructions; Step S4: Encode the robot arm monitoring posture adjustment control instruction to obtain the robot arm monitoring posture adjustment coding instruction; design an automated control program based on the robot arm monitoring posture adjustment coding instruction to obtain the robot arm monitoring posture control program, and embed the robot arm monitoring posture control program into the robot arm control center to execute the robot arm control method for livestock status monitoring.

2. The method for controlling a robotic arm for monitoring livestock status according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: obtaining a livestock monitoring area; deploying a cross track in the livestock monitoring area, the cross track and the robotic arm are electrically connected via a servo motor, the servo motor controls the robotic arm to move on the cross track, and an electronic monitoring device is deployed on the robotic arm; Step S12: monitoring livestock activities in the livestock monitoring area through electronic monitoring equipment to obtain livestock activity monitoring images; Step S13: marking the livestock types on the livestock activity monitoring image to obtain a livestock type activity monitoring image; wherein the livestock types include pigs, cattle and sheep; Step S14: Calculate the distribution density of the livestock activity monitoring images to obtain the livestock activity distribution density.

3. The method for controlling a robotic arm for monitoring livestock status according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: analyzing the movable positions of livestock on the livestock activity monitoring images based on the distribution density of livestock types and activities, and obtaining a livestock movable position data set; Step S22: predicting the livestock spatial movement trajectory based on the livestock movable position data set and the livestock activity monitoring image to obtain livestock spatial movement trajectory prediction data; Step S23: quantifying the vibration of the approaching robot arm based on the predicted data of the livestock spatial movement trajectory, and obtaining the quantified data of the vibration of the approaching robot arm; Step S24: Estimating the livestock stress state probability based on the robot arm approach vibration quantified data to obtain livestock stress state probability data.

4. The method for controlling a robotic arm for monitoring livestock status according to claim 3, characterized in that: Step S23 includes the following steps: Step S231: analyzing the livestock intermittent speed change of the livestock spatial movement trajectory prediction data to obtain the livestock intermittent speed change data; Step S232: performing an inertia simulation of the instantaneous pause when the robot arm approaches for observation according to the intermittent speed change data of the livestock, and obtaining the instantaneous pause inertia data; Step S233: performing a robot arm jitter vector attenuation analysis on the instantaneous pause inertia data to obtain a robot arm jitter attenuation vector; Step S234: calculating the periodic jitter vector difference of the robot arm jitter attenuation vector to obtain the periodic jitter vector difference; Step S235: Acquire the design structure data of the robot arm; quantify the close observation vibration of the robot arm according to the design structure data of the robot arm, the robot arm jitter attenuation vector and the periodic jitter vector difference to obtain the close observation vibration quantification data of the robot arm.

5. The method for controlling a robotic arm for monitoring livestock status according to claim 3, characterized in that: Step S24 includes the following steps: Step S241: Obtain the noise decibel acceptable to livestock, wherein the noise decibel acceptable to livestock includes: the noise decibel acceptable to pigs, the noise decibel acceptable to sheep, and the noise decibel acceptable to cattle; Step S242: performing vibration noise feedback matching on the robot arm approach vibration quantization data to obtain vibration noise feedback data; Step S243: calculating the instantaneous noise spectrum band difference on the vibration noise feedback data to obtain the instantaneous noise spectrum band difference; Step S244: performing noise band extreme value distribution analysis according to the instantaneous noise spectrum band difference to obtain noise band extreme value distribution data; Step S245: performing an excessive sound pressure instantaneous aggregation analysis on the livestock acceptable noise decibel according to the instantaneous noise spectrum band difference and the noise band extreme value distribution data, and obtaining the excessive sound pressure instantaneous aggregation data; Step S246: estimating the livestock stress state probability based on the excess sound pressure instantaneous aggregation data for the livestock acceptable noise decibels, and obtaining livestock stress state probability data.

6. The method for controlling a robotic arm for monitoring livestock status according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing robot arm approach rate matching according to the robot arm approach vibration quantification data and livestock stress state probability data to obtain robot arm approach rate matching data; Step S32: performing a logic error iteration test on the robot arm approach rate matching data to obtain logic error iteration test data; Step S33: performing rate error correction on the robot arm approach rate matching data according to the logical error iteration test data to obtain the robot arm approach rate optimization data; Step S34: Designing a robot arm monitoring posture control instruction based on the robot arm approach rate optimization data and the livestock activity monitoring image to obtain a robot arm monitoring posture adjustment control instruction.

7. The method for controlling a robotic arm for monitoring livestock status according to claim 6, characterized in that: Step S33 includes the following steps: Step S331: performing multi-frequency error accumulation calculation on the logic error iteration test data to obtain multi-frequency error accumulation data; Step S332: performing interval maximum error analysis on the logic error iteration test data according to the multi-frequency error accumulation data to obtain multi-frequency maximum error interval data; Step S333: performing time series linear interpolation on the multi-frequency maximum error interval data to obtain error interval time series interpolation data; Step S334: performing rate error correction on the robot arm approach rate matching data according to the error interval timing interpolation data and the multi-frequency maximum error interval data to obtain the robot arm approach rate optimization data.

8. The method for controlling a robotic arm for monitoring livestock status according to claim 6, characterized in that: Step S34 includes the following steps: Step S341: performing livestock activity posture decomposition processing on the livestock activity monitoring image to obtain livestock activity posture decomposition data; Step S342: Performing dynamic analysis of the livestock visual field blind area on the livestock activity posture decomposition data to obtain dynamic data of the livestock visual field blind area; Step S343: performing robot arm path posture control adjustment on the livestock visual field blind spot dynamic data according to the robot arm approach rate optimization data to obtain robot arm path posture control adjustment data; Step S344: Designing a robot arm monitoring posture control instruction based on the robot arm path posture control adjustment data to obtain a robot arm monitoring posture adjustment control instruction.

9. The method for controlling a robotic arm for monitoring livestock status according to claim 8, characterized in that: Step S343 includes the following steps: Performing blind zone boundary surface fitting processing on the dynamic data of the blind zone of the livestock visual field to obtain blind zone boundary surface fitting data; Perform robot arm space coverage calculation on the blind area boundary surface fitting data to obtain robot arm space coverage data; Based on the space coverage data of the robot arm, the blind area boundary surface fitting data is processed for path point distribution retrieval to obtain path point distribution data; According to the robot arm approach rate optimization data, the path point distribution data is matched with the staged motion parameters to obtain the staged motion parameters of the robot arm; The robot arm path posture control adjustment is performed according to the robot arm's staged motion parameters and path point distribution data to obtain the robot arm path posture control adjustment data.

10. A robotic arm control system for livestock status monitoring, characterized in that: The method for controlling a robotic arm for livestock status monitoring according to claim 1, wherein the robotic arm control system for livestock status monitoring comprises: The distribution density analysis module is used to monitor livestock activities in the livestock monitoring area through electronic monitoring equipment to obtain livestock activity monitoring images; calculate the distribution density of livestock activity monitoring images to obtain the distribution density of livestock types; A stress state probability estimation module is used to quantify the vibration of the approaching observation of the robot arm based on the activity distribution density of the livestock species to obtain the quantified data of the approaching vibration of the robot arm; and to estimate the probability of the livestock stress state based on the quantified data of the approaching vibration of the robot arm to obtain the probability data of the livestock stress state; The posture control instruction design module is used to match the approach rate of the robot arm according to the probability data of the livestock stress state, and obtain the approach rate matching data of the robot arm; the robot arm monitoring posture control instruction is designed based on the approach rate matching data of the robot arm and the livestock activity monitoring image, and the robot arm monitoring posture adjustment control instruction is obtained; The automatic control program design module is used to encode and process the robot arm monitoring posture adjustment control instructions to obtain the robot arm monitoring posture adjustment coding instructions; based on the robot arm monitoring posture adjustment coding instructions, the automatic control program is designed to obtain the robot arm monitoring posture control program, and the robot arm monitoring posture control program is embedded into the robot arm control center to execute the robot arm control method for livestock status monitoring.

Images