Intelligent inspection robot and monitoring system

Abstract

The present application provides an intelligent inspection robot and a monitoring system, which generates a three-dimensional map of an area to be inspected and an optimal inspection path through a inspection navigation module, so as to drive the intelligent inspection robot to inspect the area to be inspected according to the optimal inspection path and generate inspection data; generates environmental monitoring data through an environmental monitoring module; collects crop image data and the environmental monitoring data in real time through a pest and disease detection module, and generates pest and disease detection data and pest and disease prediction data based on a pre-trained crop pest and disease prediction model; thereby achieving accurate path navigation and autonomous obstacle avoidance, and real-time monitoring of the crop growth environment and the crop pest and disease situation, which can improve inspection efficiency and the accuracy of pest and disease detection, ensure the healthy growth of crops, and can be adapted to inspection tasks in a variety of complex agricultural operating environments.

Description

Technical Field

[0001] The present application relates to the technical field of agricultural robots, and in particular to an intelligent inspection robot and a monitoring system. Background Art

[0002] In modern agricultural production, the monitoring requirements for crop growth status and growth environment in agricultural production scenes such as farmland, orchards, and greenhouses are getting higher and higher. Although the traditional manual inspection method can achieve regular inspections of crops themselves and the environment, the limitations of this method are becoming increasingly apparent as the scale of agricultural production expands.

[0003] First, manual inspections are inefficient. Especially in large-scale agricultural production, inspections are often time-consuming and labor-intensive, making it difficult to achieve full coverage of the entire operating area.

[0004] In addition, the accuracy of manual inspections is also limited by the experience and subjective judgment of personnel, and they cannot promptly detect problems that may lead to pests and diseases, abnormal crop growth, etc.

[0005] Furthermore, in agricultural production scenarios such as farmlands and orchards, the growth environment of various crops is complex and changeable. Factors such as weather, soil moisture, and temperature may affect the quality of inspections, and manual inspections are often difficult to carry out continuously under harsh conditions.

[0006] Therefore, with the development of agricultural automation technology, intelligent inspection robots have gradually become an important tool in agricultural production. Intelligent inspection robots can monitor the growth environment and growth status of various crops in real time, detect pests and diseases in real time, and detect equipment failures in time. However, existing intelligent inspection robots have some defects, including insufficient intelligence in path planning, low accuracy in pest and disease detection, and poor adaptability in complex environments.

[0007] In order to solve the above problems, this application proposes an intelligent agricultural inspection robot system based on multi-sensor fusion technology, which can perform autonomous cruising, environmental monitoring, pest and disease detection and real-time alarm in complex agricultural environments to ensure crop health and the safety of agricultural facilities. Summary of the invention

[0008] In view of the above-mentioned shortcomings of the prior art, the purpose of the present application is to provide an intelligent inspection robot and a monitoring system to solve the problems of poor path planning ability, low pest and disease detection accuracy and poor adaptability of the existing intelligent inspection robots.

[0009] To achieve the above-mentioned purpose and other related purposes, the first aspect of the present application provides an intelligent inspection robot, which includes: a robot body, including: a walking structure, used to move the intelligent inspection robot to a specified position; an inspection navigation module, which is arranged on the robot body, and is used to collect the position information of the intelligent inspection robot, the position information and shape information of each obstacle and each crop in the current area to be inspected in real time, and generate a three-dimensional map of the area to be inspected based on the collected information, and generate an optimal inspection path based on the generated three-dimensional map and a preset inspection strategy to drive the intelligent inspection robot. The inspection robot inspects the area to be inspected according to the optimal inspection path and generates inspection data; the environmental monitoring module is arranged on the robot body and is used to collect environmental monitoring data in real time; the pest detection module is arranged on the robot body and connected to the environmental monitoring module and is used to collect multiple types of crop image data in real time, and based on the pre-trained crop pest prediction model, analyzes the pest conditions and pest risks of each crop in the area to be inspected according to the collected crop image data and the received environmental monitoring data, and generates pest detection data and pest prediction data; the wireless communication module is arranged on The robot body is connected to the inspection navigation module, the environmental monitoring module and the pest detection module, and is used to upload various types of data generated by each module to an external monitoring center for analyzing the working status, inspection progress, inspection results and inspection efficiency of the intelligent inspection robot, and remotely managing and optimizing the intelligent inspection robot; wherein the pest detection module includes: an image data acquisition unit, which is used to collect multiple types of crop image data in real time; an image data processing unit, which is connected to the image data acquisition unit, and is used to perform preprocessing operations and Data enhancement operation; a multimodal data fusion unit, connected to the image data processing unit and the environmental monitoring module, used to normalize and embed various types of crop image data and the environmental monitoring data into a multidimensional vector, and fuse them using a deep feature fusion method to generate multimodal fusion feature data; a pest and disease detection unit, connected to the multimodal data fusion unit, used to analyze the pest and disease conditions and pest and disease risks of each crop in the inspection area based on a pre-trained crop pest and disease prediction model according to the generated multimodal fusion feature data, and generate pest and disease detection data and pest and disease prediction data.

[0010] In some embodiments of the first aspect of the present application, the inspection navigation module includes: an inertial measurement unit and one or more lidar sensors, which are used to collect in real time the posture information of the intelligent inspection robot, the position information and shape information of each obstacle and each crop in the current inspection area, so as to generate a three-dimensional map of the inspection area by using multi-sensor fusion technology, and generate an optimal inspection path based on the three-dimensional map and a preset inspection strategy.

[0011] In some embodiments of the first aspect of the present application, a three-dimensional map of the area to be inspected is generated by using multi-sensor fusion technology, and based on the three-dimensional map and a preset inspection strategy, an optimal inspection path is generated, including: measuring the posture information of the intelligent inspection robot by the inertial measurement unit, scanning the current environment by the lidar sensor, measuring the distance between the intelligent inspection robot and each obstacle and each crop, and obtaining the position information and shape information of each obstacle and each crop; performing data preprocessing and point cloud matching on the obtained posture information of the intelligent inspection robot, the position information and shape information of each obstacle, and the position information and shape information of each crop, and using the extended Kalman filter positioning algorithm to locate various types of information. Data fusion is performed to generate positioning information of the intelligent robot, obstacles and crops to construct a three-dimensional map of the area to be inspected; based on the constructed three-dimensional map of the area to be inspected and a preset inspection strategy, an optimal inspection path is planned using a path planning algorithm so that the intelligent inspection robot can inspect the area to be inspected according to the optimal inspection path; during the inspection process of the intelligent inspection robot, according to the position information of the intelligent inspection robot collected in real time by the inertial measurement unit and the lidar sensor, the position information and shape information of the obstacles and crops in the current area to be inspected, a dynamic obstacle avoidance algorithm is used to dynamically adjust the optimal inspection path to dynamically avoid obstacles, and the optimal inspection path is continuously updated.

[0012] In some embodiments of the first aspect of the present application, the environmental monitoring module includes: one or more of a temperature sensor, a humidity sensor, a light sensor, a soil moisture sensor, and a soil pH sensor, which are used to collect air temperature monitoring data, air humidity monitoring data, light monitoring data, soil moisture monitoring data, and soil pH monitoring data in real time to generate environmental monitoring data.

[0013] In some embodiments of the first aspect of the present application, the image data acquisition unit includes: one or more of an RGB camera, a multispectral camera, a hyperspectral camera, and an infrared camera, which are used to respectively collect crop color image data, crop multispectral data, crop hyperspectral data, and crop infrared imaging data in real time.

[0014] In some embodiments of the first aspect of the present application, the method of training the crop pest and disease prediction model includes: collecting crop historical image data and environmental historical monitoring data, performing data preprocessing on the crop historical image data and the environmental historical monitoring data, performing feature extraction on the preprocessed data, and generating a crop historical pest and disease feature data set; splitting the crop historical pest and disease feature data set into a sample training set, a sample verification set, and a sample test set, and marking the diseased crops, the locations of the diseased crops, the types of pests and diseases suffered by the diseased crops, and the risk levels in the sample training set and the sample verification set; using the marked sample training set to train a target detection model to obtain a primary crop pest and disease prediction model. The test model is used, and the model parameters of the primary crop pest and disease prediction model are optimized and updated through the defined calculation loss function to obtain a converged crop pest and disease prediction model; the generalization ability of the crop pest and disease prediction model is verified by using the labeled sample verification set, and the model structure and hyperparameters of the crop pest and disease prediction model are optimized and updated to obtain the optimal crop pest and disease prediction model for identifying and marking the diseased crops, the locations of the diseased crops, the types of pests and diseases and the risk levels of the diseased crops in the sample test set, generating corresponding pest and disease detection data, and predicting the crops with disease risk, the locations of the crops with disease risk, the types of pests and diseases that may be suffered and the risk levels, and generating corresponding pest and disease prediction data.

[0015] In some embodiments of the first aspect of the present application, the intelligent inspection robot also includes: a fault monitoring module, which is arranged on the robot body and connected to the wireless communication module, and is used to monitor the working status, performance data and remaining power of the intelligent inspection robot in real time, and generate robot monitoring data to be sent to an external monitoring center through the wireless communication module.

[0016] In some embodiments of the first aspect of the present application, the intelligent inspection robot also includes: an alarm module, which is arranged on the robot body, connected to the environmental monitoring module, the pest and disease detection module and the fault monitoring module, and is used to identify abnormal environmental events, abnormal pest and disease events and abnormal robot failure events according to the environmental monitoring data, pest and disease detection data and robot monitoring data generated by each module, and to send corresponding alarm signals when various abnormal events occur.

[0017] In some embodiments of the first aspect of the present application, the intelligent inspection robot further includes: a power module, which is arranged on the robot body, including: an energy storage battery and a solar panel, for providing continuous power for the intelligent inspection robot; an energy management module, which is arranged on the robot body, for automatically adjusting the working mode of the intelligent inspection robot according to the remaining workload of the current inspection task and the remaining power of the intelligent inspection robot; wherein the working mode includes: a first working mode, a second working mode and a charging mode; when the remaining power of the intelligent inspection robot is greater than a preset first power threshold, the working mode is set to the first working mode, so that the intelligent inspection robot inspects the area to be inspected according to the preset inspection strategy; when the remaining power of the intelligent inspection robot is less than the preset first power threshold, the working mode is set to the second working mode, the inspection strategy is updated, and the intelligent inspection robot is made to inspect the key inspection area first; when the remaining power of the intelligent inspection robot is less than the preset second power threshold, the working mode is set to the charging mode, so that the intelligent inspection robot returns to the charging warehouse for charging; wherein, the first power threshold is greater than the second power threshold.

[0018] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides an intelligent patrol robot monitoring system, which includes: a plurality of intelligent patrol robots described in the above-mentioned embodiments, which are used to automatically patrol the area to be inspected, and generate corresponding patrol data, environmental monitoring data and pest and disease detection data and upload them to a monitoring center; a monitoring center, connected to each of the intelligent patrol robots, for analyzing the working status, patrol progress, patrol results and patrol efficiency of each of the intelligent patrol robots based on the patrol data, environmental monitoring data and pest and disease detection data generated by each of the intelligent patrol robots, and remotely managing and optimizing each of the intelligent patrol robots; a mobile terminal application end, connected to the monitoring center, for agricultural managers to monitor the working status, patrol progress and patrol results of a specified intelligent patrol robot on a mobile terminal, and remotely control the operation of the intelligent patrol robot.

[0019] As described above, the present application provides an intelligent inspection robot and monitoring system, which generates a three-dimensional map of the area to be inspected and an optimal inspection path through an inspection navigation module, so as to drive the intelligent inspection robot to inspect the area to be inspected according to the optimal inspection path and generate inspection data; collects air temperature monitoring data, air humidity monitoring data, light monitoring data, soil moisture monitoring data and soil pH monitoring data in real time through an environmental monitoring module, and generates environmental monitoring data; collects crop image data and the environmental monitoring data in real time through a pest and disease detection module, and generates pest and disease detection data and pest and disease prediction data based on a pre-trained crop pest and disease prediction model. The present application has the following beneficial effects: it realizes accurate path navigation and autonomous obstacle avoidance, and can monitor the growth environment of crops and the pest and disease conditions of crops in real time, thereby greatly improving the inspection efficiency and the accuracy of pest and disease detection, ensuring the healthy growth of crops, and can be adapted to inspection tasks in a variety of complex agricultural operating environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 Shown is a structural schematic diagram of an intelligent inspection robot in one embodiment of the present application.

[0021] Figure 2 Shown is a schematic diagram of the structure of the robot body in one embodiment of the present application.

[0022] Figure 3 Shown is a schematic diagram of a process for generating an optimal inspection path in an embodiment of the present application.

[0023] Figure 4 Shown is a schematic diagram of the process of training a crop disease and pest prediction model in one embodiment of the present application.

[0024] Figure 5 Shown is a structural schematic diagram of an intelligent inspection robot monitoring system in one embodiment of the present application. DETAILED DESCRIPTION

[0025] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0026] In order to solve the problems in the above-mentioned background technology, the present application provides an intelligent inspection robot and a monitoring system, which aims to solve the problems of poor path planning ability, low accuracy of pest and disease detection and poor adaptability of existing intelligent inspection robots, and can achieve accurate path navigation and autonomous obstacle avoidance, and monitor the growth environment of crops in real time and detect the pest and disease conditions of crops in real time, thereby improving agricultural production efficiency, reducing labor input, and ensuring the healthy growth of crops. At the same time, in order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application are further described in detail through the following embodiments and in combination with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the invention.

[0027] like Figure 1 As shown, a schematic diagram of the structure of the intelligent inspection robot in the embodiment of the present application is shown. The intelligent inspection robot in this embodiment includes: a robot body 1, an inspection navigation module 2, an environmental monitoring module 3, a disease and pest detection module 4 and a wireless communication module 5. Among them, the inspection navigation module 2, the environmental monitoring module 3, the disease and pest detection module 4 and the wireless communication module 5 are all arranged in the robot body 1, and are used to drive the robot body 1, automatically inspect the area to be inspected, and generate corresponding inspection data, environmental monitoring data and disease and pest detection data. The wireless communication module 5 is connected to the inspection navigation module 2, the environmental monitoring module 3 and the disease and pest detection module 4 respectively.

[0028] The robot body 1 is as follows Figure 2 As shown, it includes a walking structure for moving the intelligent inspection robot to an execution position to automatically perform inspection tasks and inspect the area to be inspected.

[0029] The inspection navigation module 2 is used to collect the position information of the intelligent inspection robot, the position information and shape information of each obstacle and each crop in the current area to be inspected in real time, and generate a three-dimensional map of the area to be inspected based on the collected information, and generate an optimal inspection path based on the generated three-dimensional map and a preset inspection strategy to drive the intelligent inspection robot to inspect the area to be inspected according to the optimal inspection path and generate inspection data.

[0030] In one embodiment, the inspection navigation module 2 includes: an inertial measurement unit and one or more lidar sensors, which are used to collect the position information of the intelligent inspection robot, the position information and shape information of each obstacle and each crop in the current inspection area in real time, so as to generate a three-dimensional map of the inspection area by using multi-sensor fusion technology, and generate an optimal inspection path based on the three-dimensional map and a preset inspection strategy.

[0031] Specifically, Figure 3 As shown, a method of using multi-sensor fusion technology to generate a three-dimensional map of the area to be inspected, and generating an optimal inspection path based on the three-dimensional map and a preset inspection strategy includes the following steps.

[0032] Step S201: The position information of the intelligent inspection robot is measured by the inertial measurement unit, and the current environment is scanned by the lidar sensor to measure the distance between the intelligent inspection robot and each obstacle and each crop, so as to obtain the position information and shape information of each obstacle and each crop.

[0033] Step S202: Perform data preprocessing and point cloud matching on the acquired posture information of the intelligent inspection robot, the position information and shape information of each obstacle, and the position information and shape information of each crop, and use the extended Kalman filter positioning algorithm to fuse various types of information to generate the positioning information of the intelligent robot, each obstacle and each crop, so as to construct a three-dimensional map of the area to be inspected.

[0034] Step S203: Based on the constructed three-dimensional map of the area to be inspected and the preset inspection strategy, an optimal inspection path is planned using a path planning algorithm, so that the intelligent inspection robot can inspect the area to be inspected according to the optimal inspection path.

[0035] Step S204: During the inspection process of the intelligent inspection robot, based on the posture information of the intelligent inspection robot collected in real time by the inertial measurement unit and the lidar sensor, the position information and shape information of each obstacle and each crop in the current inspection area, a dynamic obstacle avoidance algorithm is used to dynamically adjust the optimal inspection path to dynamically avoid obstacles, and the optimal inspection path is continuously updated.

[0036] In this embodiment, the preset inspection strategy includes but is not limited to: inspection cycle, scheduled inspection time, key inspection area and general inspection area. The inspection data includes but is not limited to: inspection start time, inspection end time and actual inspection path. It should be noted that the user can set the inspection strategy according to the needs, and can set multiple inspection areas with different priorities, such as: first priority inspection area, second priority inspection area and third priority inspection area.

[0037] It should be noted that the user can select specific algorithms for the path planning algorithm and the dynamic obstacle avoidance algorithm according to their needs, and this application does not make any specific limitations.

[0038] The environmental monitoring module 3 is used to collect environmental monitoring data in real time.

[0039] In one embodiment, the environmental monitoring module 3 includes: one or more of a temperature sensor, a humidity sensor, a light sensor, a soil moisture sensor, and a soil pH sensor, which are used to collect air temperature monitoring data, air humidity monitoring data, light monitoring data, soil moisture monitoring data, and soil pH monitoring data in real time to generate environmental monitoring data.

[0040] The pest and disease detection module 4 is connected to the environmental monitoring module 3, and is used to collect multiple types of crop image data in real time. Based on the pre-trained crop pest and disease prediction model, according to the collected crop image data and the environmental monitoring data generated by the environmental monitoring module 3, the pest and disease conditions and pest and disease risks of each crop in the inspection area are analyzed to generate pest and disease detection data and pest and disease prediction data.

[0041] In one embodiment, the pest detection module 4 includes: an image data acquisition unit, an image data processing unit, a multimodal data fusion unit and a pest detection unit.

[0042] The image data acquisition unit is used to collect multiple types of crop image data in real time. Specifically, the image data acquisition unit includes: one or more of an RGB camera, a multispectral camera, a hyperspectral camera, and an infrared camera, which are respectively used to collect crop color image data, crop multispectral data, crop hyperspectral data, and crop infrared imaging data in real time, so as to provide a pre-trained crop pest prediction model, and analyze the pest and disease conditions and pest and disease risks of each crop in the inspection area in combination with the environmental monitoring data, and generate pest and disease detection data and pest and disease prediction data.

[0043] The image data processing unit is connected to the image data acquisition unit and is used to perform preprocessing operations and data enhancement operations on the various types of crop image data collected, including crop color image data, crop multispectral data, crop hyperspectral data, and crop infrared imaging data. The preprocessing operations performed include operations such as translation, transposition, mirroring, rotation, scaling, and resolution reduction on the crop color image data, the crop multispectral data, the crop hyperspectral data, and the crop infrared imaging data; the image quality of the various types of crop image data can be effectively improved, noise and irrelevant changes can be reduced, and the processed crop image data of various types can be more suitable for subsequent analysis and processing tasks.

[0044] The multimodal data fusion unit is connected to the image data processing unit and the environmental monitoring module 3, and is used to normalize and embed various types of crop image data and the environmental monitoring data into a multidimensional vector, and fuse them using a deep feature fusion method to generate multimodal fusion feature data. It should be noted that the specific method of normalizing and embedding various types of crop image data and the environmental monitoring data includes: through data preprocessing technology, the environmental monitoring data is converted into a format compatible with the image data, so as to generate multimodal fusion feature data together with the image data. In addition, the deep feature fusion method includes but is not limited to: late fusion, hybrid fusion and feature-level fusion, so as to achieve deep fusion of different modal data.

[0045] The pest detection unit is connected to the multimodal data fusion unit, and is used to analyze the pest conditions and pest risks of each crop in the inspection area based on the pre-trained crop pest prediction model and the generated multimodal fusion feature data, and generate pest detection data and pest prediction data. The pest detection data includes but is not limited to: diseased crops, the location of diseased crops, the types of pests and diseases that the diseased crops suffer from, and the risk level; the pest prediction data includes but is not limited to: crops with disease risk, the location of crops with disease risk, the types of pests and diseases that may be suffered, and the risk level.

[0046] Among them, the crop disease and pest prediction model mainly uses image recognition technology and multimodal target detection technology to perform visual inspection and risk prediction on crops. It can effectively identify the disease and pest conditions of crops, classify and evaluate the types of diseases and pests on crops, and accurately predict the possible disease and pest risks.

[0047] In a preferred embodiment, the crop pest and disease prediction model includes: multiple convolutional layers and residual blocks, used to further extract deep features of the multimodal fusion feature data; a multi-scale feature fusion module, used to fuse feature maps of different scales generated by multiple convolutional layers and residual blocks to enhance the feature expression ability of the crop pest and disease prediction model; an attention mechanism module, used to focus on key areas in various types of crop image data to focus on and prioritize learning the characteristics of crops in key areas, thereby improving the recognition accuracy and prediction accuracy of the crop pest and disease prediction model for crop pests and diseases; an output layer, used to generate pest and disease detection data and pest and disease prediction data.

[0048] Specifically, the attention techniques used by the attention mechanism module include but are not limited to: channel attention, spatial attention and mixed attention, so as to enhance the recognition and prediction capabilities of the crop pest prediction model for key features. The output layer includes a decision network for comprehensively judging the type, location and severity of pests and diseases based on the output results of the multi-scale feature fusion module and the attention mechanism module, and visually displaying the generated pest and disease detection data and pest and disease prediction data to facilitate subsequent agricultural management decisions.

[0049] In one embodiment, the crop pest prediction model is trained as follows: Figure 4 As shown, the following steps are included.

[0050] Step S401: collecting crop historical image data and environmental historical monitoring data, performing data preprocessing on the crop historical image data and the environmental historical monitoring data, performing feature extraction on the preprocessed data, and generating a crop historical pest and disease feature data set.

[0051] Step S402: split the crop historical pest and disease feature data set into a sample training set, a sample verification set and a sample test set, and mark the diseased crops, the locations of the diseased crops, the types of pests and diseases suffered by the diseased crops and the risk levels in the sample training set and the sample verification set.

[0052] Step S403: using the labeled sample training set to train the target detection model, obtain a primary crop disease and pest prediction model, and optimize and update the model parameters of the primary crop disease and pest prediction model through a defined calculation loss function to obtain a converged crop disease and pest prediction model.

[0053] Step S404: Use the labeled sample verification set to verify the generalization ability of the crop pest and disease prediction model, optimize and update the model structure and hyperparameters of the crop pest and disease prediction model, and obtain the optimal crop pest and disease prediction model to identify and mark the diseased crops, the locations of the diseased crops, the types of pests and diseases and the risk levels of the diseased crops in the sample test set, generate corresponding pest and disease detection data, and predict crops with disease risks, the locations of crops with disease risks, the types of pests and diseases that may be suffered and the risk levels, and generate corresponding pest and disease prediction data.

[0054] In a preferred embodiment, the target detection model may adopt an improved YOLOX-S model. The YOLOX-S model is a small and fast network designed for fast and accurate detection scenarios. It not only maintains high detection accuracy, but also achieves fast reasoning speed. It should be noted that the type of specific target detection model can be set by the user according to needs, and this application does not limit it.

[0055] The wireless communication module 5 is used to upload various types of data generated by each module to an external monitoring center for analyzing the working status, inspection progress, inspection results and inspection efficiency of the intelligent inspection robot, and remotely manage and optimize the intelligent inspection robot.

[0056] In this embodiment, the inspection navigation module 2 uses multi-sensor fusion technology for intelligent path planning and autonomous obstacle avoidance, which can improve the adaptability of the intelligent inspection robot, making it adaptable to a variety of complex agricultural operating environments and agricultural scenes, so that it can replace manual inspection methods and adapt to large-scale agricultural production. Specifically, the inertial measurement unit and the lidar sensor perceive the surrounding environment in real time, generate a three-dimensional map, and generate the optimal inspection path through the path planning algorithm to ensure the maximization of the inspection coverage and the maximization of the inspection efficiency. At the same time, the inspection navigation module 2 adjusts the optimal inspection path in real time according to environmental changes during the movement of the intelligent inspection robot to avoid obstacles or dangerous areas. In addition, the inspection data generated by the inspection navigation module 2 can also be used to optimize the path planning algorithm, which can generate a more accurate optimal inspection path, achieve excellent autonomous navigation and obstacle avoidance capabilities, and thus efficiently perform inspection tasks in large-scale agricultural operating environments such as farmlands and orchards.

[0057] In a preferred embodiment, the crop image data collected by the visual sensor can also be combined with the shape information of each obstacle and each crop in the current inspection area collected by the inertial measurement unit and the lidar sensor to generate a more accurate three-dimensional map and optimal inspection path.

[0058] In this embodiment, the pest and disease detection module 4 integrates autonomous learning and adaptive optimization functions, and adopts a multimodal target detection algorithm to effectively identify diseased crops and the types and risk levels of the pests and diseases they suffer. In addition, by learning the correlation between environmental monitoring data, such as air temperature, air humidity, light, soil moisture, and soil pH, and crop images and pests and diseases, the disease risk of crops is predicted through changes in crop image data and environmental changes, so that agricultural managers can take corresponding measures in advance for prevention, avoid large-scale pests and diseases, and reduce losses caused by pests and diseases. In addition, the collected data, including crop image data, environmental monitoring data, and generated pest and disease detection data, can also be used as sample training data to continue iterative training and optimize the crop pest and disease prediction model, so as to further improve the accuracy of crop pest and disease detection and prediction during the inspection process.

[0059] In one embodiment, the intelligent inspection robot further includes: a fault monitoring module 6. The fault monitoring module 6 is disposed on the robot body 1 and connected to the wireless communication module 5, and is used to monitor the working status, performance data and remaining power of the intelligent inspection robot in real time, and generate robot monitoring data to be sent to an external monitoring center through the wireless communication module 5.

[0060] Therefore, the intelligent inspection robot can upload the inspection data generated by the inspection navigation module 2, the environmental monitoring data generated by the environmental monitoring module 3, the pest detection data generated by the pest detection module 4, and the robot monitoring data generated by the fault monitoring module 6 to an external monitoring center through the wireless communication module 5, so as to analyze the working status, inspection progress, inspection results and inspection efficiency of the intelligent inspection robot, and remotely manage and optimize the intelligent inspection robot.

[0061] In one embodiment, the intelligent inspection robot further includes: an alarm module 7. The alarm module 7 is arranged on the robot body 1, connected to the environment monitoring module 3, the pest detection module 4 and the fault monitoring module 6, and is used to identify environmental abnormal events, pest abnormal events and robot fault abnormal events according to the environment monitoring data, pest detection data and robot monitoring data generated by each module, and send corresponding alarm signals when various abnormal events occur. Preferably, different types of alarm signals can be generated based on different environmental abnormal events, pest abnormal events and robot fault abnormal events, so that when agricultural managers receive the specified type of alarm signal, they can quickly distinguish the type of abnormal event and take corresponding solutions in time to avoid greater danger or loss.

[0062] In one embodiment, the intelligent inspection robot further includes: a power module and an energy management module (not shown) disposed on the robot body 1 .

[0063] The power module includes: an energy storage battery and a solar panel, which are used to provide continuous power for the intelligent inspection robot. In this embodiment, the intelligent inspection robot can obtain auxiliary energy through the solar panel, thereby effectively extending its working time and ensuring the smooth completion of the inspection work.

[0064] The energy management module is used to automatically adjust the working mode of the intelligent inspection robot according to the remaining workload of the current inspection task and the remaining power of the intelligent inspection robot. Wherein, the working modes include: a first working mode, a second working mode and a charging mode. When the remaining power of the intelligent inspection robot is greater than the preset first power threshold, the working mode is set to the first working mode, so that the intelligent inspection robot inspects the area to be inspected according to the preset inspection strategy; when the remaining power of the intelligent inspection robot is less than the preset first power threshold, the working mode is set to the second working mode, the inspection strategy is updated, and the intelligent inspection robot is given priority to inspect the key inspection areas, so as to complete the inspection task first, and return to the charging warehouse for charging after the task is completed; when the remaining power of the intelligent inspection robot is less than the preset second power threshold, the working mode is set to the charging mode, so that the intelligent inspection robot returns to the charging warehouse for charging; wherein, the first power threshold is greater than the second power threshold.

[0065] In this embodiment, the power module and the energy management module of the intelligent inspection robot described in this application are designed mainly based on the low-power design principle. The electronic components used in other modules are also low-power electronic components, and optimized software algorithms are used, which can greatly reduce unnecessary calculations and communications and reduce energy consumption.

[0066] In summary, it should be understood that the intelligent inspection robot described in the present application adopts a modular design and can be freely combined and replaced according to specific application scenarios. For example, according to the application scenario, you can choose to add or remove a fault monitoring module, an alarm module or an energy management module; add or remove a certain type of sensor in the environmental monitoring module. As a result, the intelligent inspection robot has high flexibility, and it will be more convenient to maintain and upgrade. One of the modules or sensor units can be maintained separately, thereby reducing the maintenance cost of the robot.

[0067] In order to better describe the working mode and applicable scenarios of the intelligent inspection robot, the present application provides the following specific embodiments to further illustrate that the intelligent inspection robot can flexibly adapt to inspection work in different agricultural places such as farmland, orchards, greenhouses, etc.

[0068] Embodiment 1: An intelligent inspection robot for field crops.

[0069] In the production process of field crops, inspection work mainly involves environmental monitoring and pest detection. In this embodiment, the intelligent inspection robot includes: a robot body, an inspection navigation module, an environmental monitoring module, a pest detection module, an alarm module and a wireless communication module. The inspection navigation module can autonomously cruise between farmlands by carrying GPS and laser radar sensors; the environmental monitoring module monitors environmental parameters such as air temperature, air humidity, light and soil moisture in real time by carrying a variety of environmental sensors; the pest detection module identifies crop pest conditions and pest risks by carrying visual sensors and combining the monitored environmental parameters.

[0070] The working method of the intelligent inspection robot includes: determining the optimal inspection route in the field through the inspection navigation module, and during the inspection process, collecting key parameters of the crop growth environment in real time through the environmental monitoring module, and transmitting them to the external monitoring center through the wireless communication module; identifying environmental abnormal events through the alarm module, and if an environmental abnormal event is detected (such as low soil moisture or abnormal temperature), immediately sending a corresponding alarm signal through the alarm module to remind farm managers to take corresponding measures; identifying disease spots or pests on crop leaves through the visual sensor carried by the pest and disease detection module, and classifying and assessing the risk level. If a serious pest and disease situation is detected, the intelligent inspection robot will send a corresponding alarm signal according to the alarm module and record the location of the infected area so that farm managers can take corresponding measures later.

[0071] Embodiment 2: An intelligent inspection robot for use in an orchard.

[0072] The inspection tasks in the orchard mainly include tree growth monitoring and fruit pest detection. In this embodiment, the intelligent inspection robot includes: a robot body, an inspection navigation module, an environmental monitoring module, a pest detection module, an alarm module, and a wireless communication module. The pest detection module is equipped with a high-precision visual sensor and a spectrum analyzer, and can move flexibly between fruit trees to detect the growth status of fruit trees and the health status of fruits.

[0073] The working method of the intelligent inspection robot includes: planning the optimal inspection route of the orchard through the inspection navigation module, and adjusting the optimal inspection path in real time according to the distribution of fruit trees; during the inspection process, the pest and disease detection module uses a spectrometer to detect disease spots or signs of pests on the surface of the fruit, and combines visual sensors to evaluate the growth status of the trees; if the fruit is found to have pests or diseases or the tree is growing abnormally, a corresponding alarm signal is sent out through the alarm module, and the specific location and abnormal situation are recorded for reference by the orchard manager and the adoption of corresponding measures.

[0074] Embodiment 3: An intelligent inspection robot for a greenhouse.

[0075] In a greenhouse, the growth environment of crops needs to be precisely controlled, and any changes in environmental parameters may have a significant impact on the growth of crops. In this embodiment, the intelligent inspection robot includes: a robot body, an inspection navigation module, an environmental monitoring module, a pest detection module, an alarm module, and a wireless communication module. The environmental monitoring module can monitor the environmental parameters of the greenhouse in real time by integrating temperature and humidity sensors, carbon dioxide sensors, and light sensors.

[0076] The working method of the intelligent inspection robot includes: generating a three-dimensional map of the greenhouse through the inspection navigation module, and performing path planning according to the layout in the greenhouse to generate an optimal inspection path; during the patrol process, collecting data such as air temperature, air humidity, carbon dioxide concentration and light intensity in the greenhouse through the environmental monitoring module, and analyzing in real time to generate environmental monitoring data; if it is found that the environmental parameters exceed the set threshold range, the intelligent inspection robot will immediately send out a corresponding alarm signal through the alarm module, and upload the environmental monitoring data to an external monitoring center so that the manager can adjust the environmental parameters of the greenhouse.

[0077] Embodiment 4: An intelligent inspection robot for vineyards.

[0078] The inspection task of the vineyard mainly involves the growth status and pest detection of grapevines. In this embodiment, the intelligent inspection robot includes: a robot body, an inspection navigation module, an environmental monitoring module, a pest detection module, an alarm module and a wireless communication module. The pest detection module can move flexibly among the grapevines by carrying a visual sensor and a spectrum analyzer to detect the health status of the grapevines and the maturity of the fruit. The visual sensor is a high-precision camera.

[0079] The working method of the intelligent inspection robot includes: planning the optimal inspection path of the vineyard through the inspection navigation module, and adjusting the optimal inspection path in real time according to the distribution of grapevines; during the inspection process, the pest and disease detection module uses a camera and a spectrum analyzer to detect the leaves and fruits of the grapevines, generates pest and disease detection data to be uploaded to an external monitoring center through the wireless communication module, and identifies signs of pests and diseases or nutritional deficiencies; if an abnormality is found, the intelligent inspection robot will send a corresponding alarm signal through the alarm module, so that the manager can take corresponding measures in time, and the manager can also judge the health status and pest and disease situation of the grapevines based on the pest and disease detection data transmitted to the monitoring center.

[0080] In the embodiments of the present application, words such as "first" and "second" are used to distinguish the same or similar items with substantially the same functions and effects. For example, the first XX and the second XX are only used to distinguish different XXs, and do not limit their order. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0081] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" represent examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0082] In the embodiments of the present application, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple.

[0083] like Figure 5 , which shows a schematic diagram of the structure of an intelligent inspection robot monitoring system 500 in an embodiment of the present application. The intelligent inspection robot monitoring system 500 includes: a plurality of intelligent inspection robots 501, a monitoring center 502 and a mobile terminal application 503.

[0084] The intelligent inspection robot 501, such as the intelligent inspection robot provided in the above embodiments, is used to automatically inspect the area to be inspected, and generate corresponding inspection data, environmental monitoring data, and pest and disease detection data and upload them to the monitoring center 502. The inspection data includes but is not limited to: the inspection start time, the inspection end time, and the actual inspection path; the environmental monitoring data includes but is not limited to: air temperature monitoring data, air humidity monitoring data, light monitoring data, and soil humidity monitoring data; the pest and disease detection data includes but is not limited to: diseased crops, the location of diseased crops, the types of diseases and pests suffered by diseased crops, and the risk level.

[0085] The monitoring center 502 is connected to each of the intelligent inspection robots 501, and is used to analyze the working status, inspection progress, inspection results and inspection efficiency of each of the intelligent inspection robots 501 based on the inspection data, environmental monitoring data and pest and disease detection data generated by each of the intelligent inspection robots 501, and remotely manage and optimize each of the intelligent inspection robots 501.

[0086] In a specific embodiment, after the monitoring center 502 obtains the inspection data, environmental monitoring data and pest detection data generated by each intelligent inspection robot 501, it can obtain inspection experience based on these data and analyze the performance of each intelligent inspection robot 501, such as analyzing the actual inspection path, obstacle avoidance ability, collected crop-related data and the accuracy of predicted crop detection data of each intelligent inspection robot 501. And it can learn from these experiences, re-input the obtained inspection data, environmental monitoring data and pest detection data into the inspection navigation module, the environmental monitoring module and the pest detection module, optimize the performance of each module, such as optimizing the path planning algorithm, dynamic obstacle avoidance algorithm and the crop pest prediction model, so that each intelligent inspection robot 501 can better complete the inspection task, more accurately identify the pest situation of crops and environmental abnormal events, etc., improve the inspection efficiency of each intelligent inspection robot 501, and ensure the efficient and safe agricultural production. In addition, the monitoring center 502 can also analyze crop growth data under different climatic conditions based on the collected data, so as to be used for long-term agricultural research and production optimization, and help agricultural managers adjust planting strategies to improve crop yields and quality.

[0087] The mobile terminal application end 503 is connected to the monitoring center 502, and is used for the agricultural manager to monitor the working status, inspection progress and inspection results of the designated intelligent inspection robot 501 on the mobile terminal, and remotely control the operation of the intelligent inspection robot 501. Therefore, the agricultural manager can view the inspection data, environmental monitoring data, pest detection data, and the working status, remaining power, inspection progress and inspection results of the intelligent inspection robot 501 obtained by the designated intelligent inspection robot 501 in real time through a mobile terminal, such as a mobile phone or a computer terminal, so as to control the operation of the intelligent inspection robot 501, including adjusting its working mode, making it prioritize the inspection of key inspection areas, or directly return to the charging warehouse for charging, etc., to achieve intelligent management and remote management of each intelligent inspection robot 501.

[0088] It should be understood that the specific process of each module executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0089] It should also be understood that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0090] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0091] In summary, the present application provides an intelligent inspection robot and monitoring system, which generates a three-dimensional map of the area to be inspected and an optimal inspection path through an inspection navigation module, so as to drive the intelligent inspection robot to inspect the area to be inspected according to the optimal inspection path and generate inspection data; collects air temperature monitoring data, air humidity monitoring data, light monitoring data, soil moisture monitoring data and soil pH monitoring data in real time through an environmental monitoring module, and generates environmental monitoring data; collects crop image data and the environmental monitoring data in real time through a pest and disease detection module, and generates pest and disease detection data and pest and disease prediction data based on a pre-trained crop pest and disease prediction model. The present application has the following beneficial effects: it realizes accurate path navigation and autonomous obstacle avoidance, and can monitor the growth environment of crops and the pest and disease conditions of crops in real time, thereby greatly improving the inspection efficiency and the accuracy of pest and disease detection, ensuring the healthy growth of crops, and can adapt to inspection tasks in a variety of complex agricultural operating environments.

[0092] Therefore, the present application effectively overcomes various shortcomings in the prior art and has high industrial utilization value.

[0093] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. An intelligent inspection robot, characterized in that: include: The robot body includes: a walking structure for moving the intelligent inspection robot to a designated position; The inspection navigation module is arranged on the robot body, and includes: an inertial measurement unit and a laser radar sensor, which is used to collect the position information of the intelligent inspection robot, the position information and shape information of each obstacle and each crop in the current inspection area in real time, and generate a three-dimensional map of the inspection area based on the collected information by using multi-sensor fusion technology, and generate an optimal inspection path based on the generated three-dimensional map and the preset inspection strategy, so as to drive the intelligent inspection robot to inspect the inspection area according to the optimal inspection path and generate inspection data; wherein the preset inspection strategy includes: inspection cycle, scheduled inspection time, key inspection area and general inspection area; An environmental monitoring module is provided on the robot body and is used to collect environmental monitoring data in real time; wherein the environmental monitoring module includes: a temperature sensor, a humidity sensor, a light sensor, a soil moisture sensor and a soil pH sensor, which are respectively used to collect air temperature monitoring data, air humidity monitoring data, light monitoring data, soil moisture monitoring data and soil pH monitoring data in real time to generate environmental monitoring data; A pest and disease detection module is provided on the robot body and connected to the environmental monitoring module, and is used to collect multiple types of crop image data in real time, and based on a pre-trained crop pest and disease prediction model, analyzes the pest and disease conditions and pest and disease risks of each crop in the inspection area according to the collected crop image data and the received environmental monitoring data, and generates pest and disease detection data and pest and disease prediction data; A wireless communication module, which is arranged on the robot body, connected to the inspection navigation module, the environmental monitoring module and the pest detection module, and is used to upload various data generated by each module to an external monitoring center, so as to analyze the working status, inspection progress, inspection results and inspection efficiency of the intelligent inspection robot, and remotely manage and optimize the intelligent inspection robot; The pest and disease detection module includes: an image data acquisition unit, which is used to collect multiple types of crop image data in real time; an image data processing unit, which is connected to the image data acquisition unit and is used to perform preprocessing operations and data enhancement operations on the collected crop image data of each type; a multimodal data fusion unit, which is connected to the image data processing unit and the environmental monitoring module, and is used to normalize and embed the crop image data of each type and the environmental monitoring data into a multidimensional vector, and fuse them using a deep feature fusion method to generate multimodal fusion feature data; a pest and disease detection unit, which is connected to the multimodal data fusion unit and is used to analyze the pest and disease conditions and pest and disease risks of each crop in the inspection area based on a pre-trained crop pest and disease prediction model and the generated multimodal fusion feature data, and generate pest and disease detection data and pest and disease prediction data; Among them, the crop pest and disease prediction model includes: multiple convolutional layers and residual blocks, which are used to further extract deep features of the multimodal fusion feature data; a multi-scale feature fusion module, which is used to fuse feature maps of different scales generated by multiple convolutional layers and residual blocks to enhance the feature expression ability of the crop pest and disease prediction model; an attention mechanism module, which is used to focus on key areas in various types of crop image data to focus on and prioritize the characteristics of crops in key areas; an output layer, which is used to generate pest and disease detection data and pest and disease prediction data.

2. The intelligent inspection robot according to claim 1, characterized in that: The multi-sensor fusion technology is used to generate a three-dimensional map of the area to be inspected, and based on the three-dimensional map and the preset inspection strategy, the optimal inspection path is generated in the following ways: The inertial measurement unit is used to measure the position and posture information of the intelligent inspection robot, and the laser radar sensor is used to scan the current environment to measure the distance between the intelligent inspection robot and each obstacle and each crop, so as to obtain the position information and shape information of each obstacle and each crop; The obtained posture information of the intelligent inspection robot, the position information and shape information of each obstacle, and the position information and shape information of each crop are subjected to data preprocessing and point cloud matching, and various types of information are fused using an extended Kalman filter positioning algorithm to generate positioning information of the intelligent inspection robot, each obstacle, and each crop, so as to construct a three-dimensional map of the area to be inspected; Based on the constructed three-dimensional map of the area to be inspected and the preset inspection strategy, an optimal inspection path is planned using a path planning algorithm, so that the intelligent inspection robot can inspect the area to be inspected according to the optimal inspection path; During the inspection process of the intelligent inspection robot, a dynamic obstacle avoidance algorithm is used to dynamically adjust the optimal inspection path based on the posture information of the intelligent inspection robot collected in real time by the inertial measurement unit and the lidar sensor, the position information and shape information of each obstacle and each crop in the current inspection area, so as to dynamically avoid obstacles and continuously update the optimal inspection path.

3. The intelligent inspection robot according to claim 1, characterized in that: The image data acquisition unit includes: one or more of an RGB camera, a multispectral camera, a hyperspectral camera and an infrared camera, which are respectively used to collect crop color image data, crop multispectral data, crop hyperspectral data and crop infrared imaging data in real time.

4. The intelligent inspection robot according to claim 1, characterized in that: Methods for training the crop pest and disease prediction model include: Collecting crop historical image data and environmental historical monitoring data, performing data preprocessing on the crop historical image data and the environmental historical monitoring data, performing feature extraction on the preprocessed data, and generating a crop historical pest and disease feature data set; Splitting the crop historical pest and disease feature data set into a sample training set, a sample verification set, and a sample test set, and marking the diseased crops, the locations of the diseased crops, the types of pests and diseases suffered by the diseased crops, and the risk levels in the sample training set and the sample verification set; Using the labeled sample training set to train the target detection model, obtain a primary crop disease and insect pest prediction model, and optimize and update the model parameters of the primary crop disease and insect pest prediction model through a defined calculation loss function to obtain a converged crop disease and insect pest prediction model; The generalization ability of the crop pest and disease prediction model is verified by using the labeled sample verification set, and the model structure and hyperparameters of the crop pest and disease prediction model are optimized and updated to obtain the optimal crop pest and disease prediction model for identifying and marking diseased crops, the locations of diseased crops, the types of diseases and pests suffered by diseased crops and the risk levels in the sample test set, generating corresponding disease and pest detection data, and predicting crops with disease risks, the locations of crops with disease risks, the types of diseases and pests that may be suffered and the risk levels, and generating corresponding disease and pest prediction data.

5. The intelligent inspection robot according to claim 1, characterized in that: Also includes: A fault monitoring module is arranged on the robot body and connected to the wireless communication module, and is used to monitor the working status, performance data and remaining power of the intelligent inspection robot in real time, and generate robot monitoring data to be sent to an external monitoring center through the wireless communication module.

6. The intelligent inspection robot according to claim 5, characterized in that: Also includes: An alarm module is arranged on the robot body, connected to the environment monitoring module, the pest detection module and the fault monitoring module, and is used to identify abnormal environmental events, abnormal pest events and abnormal robot fault events according to the environment monitoring data, pest detection data and robot monitoring data generated by each module, and to send corresponding alarm signals when various abnormal events occur.

7. The intelligent inspection robot according to claim 1, characterized in that: Also includes: A power module, arranged on the robot body, includes: an energy storage battery and a solar panel, for providing continuous power for the intelligent inspection robot; An energy management module, disposed on the robot body, for automatically adjusting the working mode of the intelligent inspection robot according to the remaining workload of the current inspection task and the remaining power of the intelligent inspection robot; Wherein, the working modes include: a first working mode, a second working mode and a charging mode; When the remaining power of the intelligent inspection robot is greater than a preset first power threshold, the working mode is set to the first working mode, so that the intelligent inspection robot inspects the area to be inspected according to the preset inspection strategy; when the remaining power of the intelligent inspection robot is less than the preset first power threshold, the working mode is set to the second working mode, the inspection strategy is updated, and the intelligent inspection robot prioritizes inspecting key inspection areas; when the remaining power of the intelligent inspection robot is less than the preset second power threshold, the working mode is set to the charging mode, so that the intelligent inspection robot returns to the charging warehouse for charging; wherein, the first power threshold is greater than the second power threshold.

8. An intelligent inspection robot monitoring system, characterized in that: include: A plurality of intelligent inspection robots as described in any one of claims 1 to 7, used for automatically inspecting the area to be inspected, and generating corresponding inspection data, environmental monitoring data, and pest and disease detection data and uploading them to a monitoring center; A monitoring center connected to each of the intelligent inspection robots, for analyzing the working status, inspection progress, inspection results and inspection efficiency of each of the intelligent inspection robots based on the inspection data, environmental monitoring data and pest detection data generated by each of the intelligent inspection robots, and remotely managing and optimizing each of the intelligent inspection robots; The mobile terminal application end is connected to the monitoring center and is used by agricultural managers to monitor the working status, inspection progress and inspection results of the designated intelligent inspection robot on the mobile terminal, and remotely control the operation of the intelligent inspection robot.

Images