Cooperative weed control method, device and medium
By predicting weed growth rate, collecting spectral characteristics, and adjusting laser power, the problem of multiple weeding robots not working together was solved, achieving efficient and eco-friendly weeding results.
Patent Information
- Application Number
- CN202410940411.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-15
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-07-15
AI Technical Summary
In existing technologies, multiple weeding robots fail to work effectively together when weeding large areas, affecting weeding efficiency and potentially damaging the farmland ecosystem.
By acquiring farmland data to predict weed growth rates, linking multiple weeding robots, collecting weed distribution areas, and adjusting laser power based on spectral characteristics, we can achieve coordinated movement and weeding path planning among robots, and optimize weeding strategies in real time.
It enables collaborative work among multiple weeding robots, improving weeding efficiency while maximizing the protection of the farmland ecological environment, thus achieving intelligent and efficient weeding.
Smart Images

Figure CN118476528B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a collaborative weed control method, device and medium. Background Art
[0002] With the development of science and technology, weeding robots are applied in people's lives, and lasers are used to weed. At this time, in a larger area, multiple weeding robots are needed to work together. The larger area is divided into multiple sub-areas, and each sub-area is respectively arranged with a weeding robot. However, based on one weeding robot for one sub-area, and performing separate weeding work in one sub-area, in the prior art, multiple weeding robots perform separate weeding according to a preset path, and do not work in coordination, which affects the coordinated weeding mode between the multiple weeding robots. Summary of the invention
[0003] The embodiments of the present application provide a control method, device and medium for collaborative weeding, thereby optimizing the weeding strategy in real time at least to a certain extent, and monitoring the weeding effects of multiple weeding robots along corresponding weeding paths in real time, thereby ensuring a collaborative weeding mode between multiple weeding robots, and being able to protect the ecological environment of farmland to the greatest extent while ensuring weeding efficiency, thereby realizing intelligent and efficient weeding.
[0004] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.
[0005] According to one aspect of an embodiment of the present application, a control method for collaborative weeding is provided, which is applied to a weeding robot. The control method for collaborative weeding includes:
[0006] Acquire multiple farmland data, and predict the growth rate of weeds based on the multiple farmland data;
[0007] If the growth rate of the weeds reaches a preset growth rate, multiple weeding robots are associated and the distribution area of the weeds is collected;
[0008] Triggering the coordinated movement of multiple weeding robots based on the distribution area of weeds, and defining corresponding weeding paths according to the multiple weeding robots;
[0009] When the weeding robot is weeding along the corresponding weeding path, the spectral characteristics of the weeds are collected, and the laser power of the weeding robot is adjusted according to the spectral characteristics of the weeds;
[0010] The weeding effect of the weeding robot under the corresponding laser power is collected, and the weeding strategy is optimized according to the weeding effect and environmental changes.
[0011] Optionally, the acquiring of a plurality of farmland data and predicting the growth rate of weeds based on the plurality of farmland data includes:
[0012] Locate the fields that are being treated by multiple weeding robots;
[0013] Building an online collection model based on the farmland;
[0014] In the online collection model, multiple farmland data corresponding to the farmland are collected in real time, and the multiple farmland data include temperature, humidity, light intensity, soil parameters, average height of crops, and leaf area of crops;
[0015] Predicting the growth rate of weeds based on multiple farmland data and a weed growth rate prediction model;
[0016] Among them, the weed growth rate prediction model is as follows:
[0017] WG = alpha1 × f1(T, H, L) + alpha2 × f2(SH, pH, N) + alpha3 × f3(G, LA)
[0018] At this time, WG represents the growth rate of weeds; T, H, L represent the temperature, humidity and light intensity in the meteorological data respectively; SH, pH, N represent soil parameters, including soil moisture, pH value and nutrient content; G and LA represent the average height and leaf area of crops; f1, f2, f3 are functions of the influence of meteorological data, soil conditions and crop growth status on the growth rate of weeds; alpha1, alpha2, alpha3 are weight coefficients.
[0019] Optionally, if the growth rate of the weeds reaches a preset growth rate, a plurality of weeding robots are associated and the distribution area of the weeds is collected, including:
[0020] Compare the growth rate of weeds to a preset growth rate:
[0021] If the growth rate of weeds reaches a preset growth rate, multiple weeding robots are associated;
[0022] Based on multiple weeding robots collecting weeds along the farmland and forming multiple weed images;
[0023] The distribution area of weeds is determined based on a plurality of weed images.
[0024] Optionally, triggering the coordinated movement of multiple weeding robots based on the distribution area of weeds, and defining corresponding weeding paths according to the multiple weeding robots, includes:
[0025] Determine the distribution area of weeds and divide the distribution area of weeds into multiple sub-areas;
[0026] Establishing a collaborative weeding working relationship based on the multiple weeding robots, and performing collaborative movements between the multiple weeding robots based on the collaborative weeding working relationship;
[0027] Obtaining locations of multiple sub-areas and multiple weeding robots;
[0028] The weeding path planning is triggered based on the locations of the multiple sub-areas and the multiple weeding robots, and the weeding paths that each weeding robot is responsible for are corresponding.
[0029] Optionally, when the weeding robot is weeding along the corresponding weeding path, collecting the spectral characteristics of the weeds, and adjusting the laser power of the weeding robot according to the spectral characteristics of the weeds, includes:
[0030] When the weeding robot weeds along the corresponding weeding path, spectral data of the weeds is collected;
[0031] defining spectral characteristics of weeds based on spectral data of the weeds;
[0032] Adjust the laser power of the weeding robot according to the spectral characteristics of the weeds;
[0033] Among them, the automatic adjustment model of laser power is as follows:
[0034] P = beta1 × g1(Sw) + beta2 × g2(Sc); lambda = beta3 × h1(Sw) +beta4 × h2(Sc)
[0035] At this time, P represents laser power; lambda represents the wavelength of the laser; Sw and Sc represent the spectral characteristics of weeds and crops respectively; g1, g2, h1, h2 represent the mapping function from spectral characteristics to laser parameters; beta1, beta2, beta3, beta4 represent weight coefficients.
[0036] Optionally, collecting the weeding effect of the weeding robot at the corresponding laser power and optimizing the weeding strategy according to the weeding effect and environmental changes include:
[0037] Collect the weeding effect of the weeding robot under the corresponding laser power;
[0038] Freeze the weed control effect and the environmental changes corresponding to the current weed control effect;
[0039] Optimize weed control strategies based on weed control effects and environmental changes.
[0040] Optionally, the collecting of the weeding effect of the weeding robot at the corresponding laser power and optimizing the weeding strategy according to the weeding effect and environmental changes also includes:
[0041] The weed control strategy optimization model is as follows:
[0042] S_new = S_old + eta × grad_S R(S_old, F, E)
[0043] At this time, S_new and S_old represent the updated weeding strategy and the weeding strategy before the update respectively; eta represents the learning rate; grad_SR represents the gradient of the reward function with respect to the strategy S; F represents the feedback of the operation effect; and E represents the environmental parameters.
[0044] Optionally, the collaborative weed control method further comprises:
[0045] Collect data on weed control operations and environmental parameters during the weed control strategy;
[0046] Correlate data from weeding operations with environmental parameters;
[0047] Define ecological impact scores based on weed control data, environmental parameters, and evaluation functions;
[0048] Among them, the assessment model of ecological impact is as follows:
[0049] I = integral l(D, E) dE
[0050] Here, I represents the ecological impact score; D represents the operation data; E represents the environmental parameters; l represents the evaluation function; and integral represents the integral.
[0051] According to one aspect of an embodiment of the present application, a coordinated weed control device is provided, comprising:
[0052] An acquisition module, used for acquiring a plurality of farmland data and predicting the growth rate of weeds based on the plurality of farmland data;
[0053] An association module, used to associate multiple weeding robots and collect the distribution area of the weeds if the growth rate of the weeds reaches a preset growth rate;
[0054] A collaborative module, used to trigger collaborative movement among multiple weeding robots based on the distribution area of weeds, and define corresponding weeding paths according to the multiple weeding robots;
[0055] A control module, used for collecting spectral characteristics of weeds when the weeding robot is weeding along a corresponding weeding path, and adjusting the laser power of the weeding robot according to the spectral characteristics of the weeds;
[0056] The weeding strategy module is used to collect the weeding effect of the weeding robot under the corresponding laser power, and optimize the weeding strategy according to the weeding effect and environmental changes.
[0057] According to one aspect of an embodiment of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the control method of collaborative weeding as described in the above embodiment is implemented.
[0058] According to one aspect of an embodiment of the present application, a weeding robot is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the control method of collaborative weeding as described in the above embodiments.
[0059] According to one aspect of an embodiment of the present application, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the control method of cooperative weeding provided in the above embodiment.
[0060] In the technical solutions provided in some embodiments of the present application, multiple farmland data are obtained, and the growth rate of weeds is predicted based on the multiple farmland data; if the growth rate of the weeds reaches a preset growth rate, multiple weeding robots are associated, and the distribution area of the weeds is collected; based on the distribution area of the weeds, the coordinated movement between the multiple weeding robots is triggered, and corresponding weeding paths are defined according to the multiple weeding robots; when the weeding robots weed along the corresponding weeding paths, the spectral characteristics of the weeds are collected, and the laser power of the weeding robots is adjusted according to the spectral characteristics of the weeds; the weeding effect of the weeding robot at the corresponding laser power is collected, and the weeding strategy is optimized according to the weeding effect and environmental changes, so as to optimize the weeding strategy in real time, and monitor the weeding effect of multiple weeding robots along the corresponding weeding paths in real time, thereby ensuring the coordinated weeding mode between the multiple weeding robots, which can maximize the protection of the farmland ecological environment while ensuring the weeding efficiency, thereby realizing intelligent weeding and efficient weeding.
[0061] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:
[0063] Figure 1 A schematic flow chart of a collaborative weed control method according to an embodiment of the present application is shown;
[0064] Figure 2 Shows Figure 1 Schematic diagram of the process of step S110;
[0065] Figure 3 Shows Figure 1 Schematic diagram of the process of step S120;
[0066] Figure 4 Shows Figure 1 Schematic diagram of the process of step S130;
[0067] Figure 5 Shows Figure 1 Schematic diagram of the process of step S140;
[0068] Figure 6 Shows Figure 1 Schematic diagram of the process of step S150;
[0069] Figure 7 A block diagram of a control device for cooperative weeding according to an embodiment of the present application is shown;
[0070] Figure 8 A schematic diagram of the structure of a computer system suitable for implementing the weeding robot according to the embodiment of the present application is shown. DETAILED DESCRIPTION
[0071] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.
[0072] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.
[0073] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0074] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.
[0075] Figure 1 A schematic flow chart of a control method for cooperative weeding according to an embodiment of the present application is shown. The method can be applied to a weeding robot. In the embodiment of the present application, a weeding robot is used as an example for illustration.
[0076] refer to Figures 1 to 8 The collaborative weeding control method includes at least steps S110 to S150, which are described in detail as follows (the method is applied to a weeding robot as an example):
[0077] Step S110, acquiring a plurality of farmland data, and predicting the growth rate of weeds based on the plurality of farmland data;
[0078] Step S120: if the growth rate of the weeds reaches a preset growth rate, multiple weeding robots are associated and the distribution area of the weeds is collected;
[0079] Step S130: triggering coordinated movement among multiple weeding robots based on the distribution area of weeds, and defining corresponding weeding paths according to the multiple weeding robots;
[0080] Step S140: when the weeding robot is weeding along the corresponding weeding path, the spectral characteristics of the weeds are collected, and the laser power of the weeding robot is adjusted according to the spectral characteristics of the weeds;
[0081] Step S150: collecting the weeding effect of the weeding robot under the corresponding laser power, and optimizing the weeding strategy according to the weeding effect and environmental changes.
[0082] At this time, multiple farmland data are obtained, and the growth rate of weeds is predicted based on the multiple farmland data; if the growth rate of weeds reaches the preset growth rate, multiple weeding robots are associated, and the distribution area of weeds is collected; based on the distribution area of weeds, the coordinated movement between multiple weeding robots is triggered, and corresponding weeding paths are defined according to the multiple weeding robots; when the weeding robot weeds along the corresponding weeding path, the spectral characteristics of the weeds are collected, and the laser power of the weeding robot is adjusted according to the spectral characteristics of the weeds; the weeding effect of the weeding robot at the corresponding laser power is collected, and the weeding strategy is optimized according to the weeding effect and environmental changes, so as to optimize the weeding strategy in real time, and monitor the weeding effect of multiple weeding robots along the corresponding weeding path in real time, so as to ensure the coordinated weeding mode between multiple weeding robots, which can protect the ecological environment of farmland to the maximum extent while ensuring the weeding efficiency, thereby realizing intelligent weeding and efficient weeding.
[0083] refer to Figure 2 In step S110, a plurality of farmland data are acquired, and the growth rate of weeds is predicted based on the plurality of farmland data.
[0084] In an embodiment of the present application, multiple farmland data are collected based on the farmland to facilitate data processing of the multiple farmland data, thereby predicting the growth rate of weeds based on the multiple farmland data, so as to define the growth rate of weeds, thereby controlling the growth rate of weeds and triggering collaborative work between multiple weeding robots.
[0085] Step S111, locating the farmland to be processed by multiple weeding robots;
[0086] Step S112: constructing an online acquisition model based on the farmland;
[0087] Step S113: In the online collection model, multiple farmland data corresponding to the farmland are collected in real time, and the multiple farmland data include temperature, humidity, light intensity, soil parameters, average height of crops, and leaf area of crops;
[0088] Step S114: predicting the growth rate of weeds based on multiple farmland data and a weed growth rate prediction model;
[0089] In an embodiment of the present application, the farmland processed by multiple weeding robots is located, and targeted management and control is carried out on the farmland. At this time, an online collection model is constructed based on the farmland to facilitate data collection of the farmland. Therefore, in the online collection model, multiple farmland data corresponding to the farmland are collected in real time. The multiple farmland data include temperature, humidity, light intensity, soil parameters, average height of crops, and leaf area of crops. Temperature, humidity, light intensity, soil parameters, average height of crops, and leaf area of crops are introduced to control temperature, humidity, light intensity, soil parameters, average height of crops, and leaf area of crops.
[0090] Furthermore, the weed growth rate is predicted based on multiple farmland data and a weed growth rate prediction model, which makes full use of temperature, humidity, light intensity, soil parameters, average height of crops, and leaf area of crops. At the same time, the weed growth rate prediction model is trained based on multiple previous farmland data and weed growth rates.
[0091] Among them, the weed growth rate prediction model is as follows:
[0092] WG = alpha1 × f1(T, H, L) + alpha2 × f2(SH, pH, N) + alpha3 × f3(G, LA)
[0093] At this time, WG represents the growth rate of weeds; T, H, L represent the temperature, humidity and light intensity in the meteorological data respectively; SH, pH, N represent soil parameters, including soil moisture, pH value and nutrient content; G and LA represent the average height and leaf area of crops; f1, f2, f3 are functions of the influence of meteorological data, soil conditions and crop growth status on the growth rate of weeds; alpha1, alpha2, alpha3 are weight coefficients.
[0094] Therefore, the invention innovatively introduced the Ecological Perception Module (EPDIM), which uses multi-source data (including meteorological data, soil conditions, crop growth status, etc.) for comprehensive analysis and predicts the growth dynamics of weeds through intelligent algorithms. Compared with the traditional single data source and simple model, the EPDIM module can more accurately predict the growth trend of weeds by comprehensively considering multiple factors, providing a scientific basis for weed control strategies. For example, in the process of analyzing farmland environmental data, the EPDIM module not only considers meteorological factors (such as temperature, humidity, light intensity) and soil factors (such as soil moisture, pH value, and nutrient content), but also combines crop growth status (such as average height and leaf area of crops) and the principle of ecological balance, and accurately predicts the growth trend of weeds through comprehensive analysis by intelligent algorithms.
[0095] refer to Figure 3In step S120, if the growth rate of the weeds reaches a preset growth rate, multiple weeding robots are associated and the distribution area of the weeds is collected.
[0096] In an embodiment of the present application, the growth rate of weeds is compared with a preset growth rate, so as to facilitate the comparison of the growth rate of weeds with the preset growth rate. Therefore, if the growth rate of weeds reaches the preset growth rate, multiple weeding robots are associated and the distribution area of weeds is collected. At the same time, the present invention aims to achieve efficient and accurate identification and positioning of weeds by combining machine vision technology and ecological perception data. By adopting advanced image processing algorithms, machine learning models and laser scanning technology, the accuracy of weed identification and the accuracy of positioning can be effectively improved, thereby reducing accidental damage to crops and improving the efficiency of weeding operations.
[0097] Step S121, comparing the growth rate of weeds with a preset growth rate;
[0098] Step S122: if the growth rate of the weeds reaches a preset growth rate, multiple weeding robots are associated;
[0099] Step S123: multiple weeding robots collect weeds along the farmland and form multiple weed images;
[0100] Step S124: determining the distribution area of weeds according to the multiple weed images.
[0101] In an embodiment of the present application, the growth rate of weeds is compared with a preset growth rate. If the growth rate of weeds reaches the preset growth rate, multiple weeding robots are associated, so that a coordinated response is made to the multiple weeding robots to trigger the operation of the multiple weeding robots. At this time, weeds are collected along the farmland based on the multiple weeding robots, and multiple weed images are formed; the distribution area of the weeds is determined based on the multiple weed images, so as to further process the distribution area of the weeds. Therefore, the traversal of the farmland by multiple weeding robots is fully utilized to collect multiple weed images, and the distribution area of the weeds is formed based on the multiple weed images.
[0102] refer to Figure 4 In step S130, the coordinated movement among the multiple weeding robots is triggered based on the distribution area of the weeds, and corresponding weeding paths are defined according to the multiple weeding robots.
[0103] The specific steps are as follows:
[0104] Step S131, freeze the distribution area of weeds, and divide the distribution area of weeds into multiple sub-areas;
[0105] Step S132: establishing a collaborative weeding working relationship based on the multiple weeding robots, and performing collaborative movement between the multiple weeding robots based on the collaborative weeding working relationship;
[0106] Step S133, obtaining the locations of multiple sub-areas and multiple weeding robots;
[0107] Step S134: triggering weeding path planning based on the multiple sub-areas and the locations of the multiple weeding robots, and corresponding weeding paths that each weeding robot is responsible for.
[0108] In an embodiment of the present application, the distribution area of weeds is fixed and divided into multiple sub-areas to facilitate collaborative management of the multiple sub-areas, and multiple weeding robots are introduced into the multiple sub-areas. At this time, a collaborative weeding working relationship is established based on the multiple weeding robots, and collaborative movement is performed between the multiple weeding robots based on the collaborative weeding working relationship.
[0109] At the same time, the locations of multiple sub-areas and multiple weeding robots are obtained; based on the locations of the multiple sub-areas and multiple weeding robots, weeding path planning is triggered, and corresponding weeding paths are corresponding to the weeding paths that each weeding robot is responsible for.
[0110] Therefore, the present invention adopts a collaborative multi-robot navigation and operation platform (CMRNP), realizes real-time positioning and precise navigation of robots through the Beidou navigation system, and realizes collaborative operation between robots using ground wireless communication technology. Compared with the traditional single robot operation mode, CMRNP can realize real-time position synchronization and task allocation between multiple robots, maximize the operation efficiency and reduce the damage of machinery to crops. For example, in the CMRNP system, each robot is accurately positioned through the Beidou navigation system, and uses ground wireless communication technology for real-time data transmission and task scheduling, which can collaboratively complete tasks such as weed identification, positioning and laser weeding, and realize more efficient and accurate weeding operations.
[0111] Laser technology is used to accurately locate and kill weeds while minimizing the impact on surrounding crops and the environment. The key to this technology is the ability to automatically adjust the power and wavelength of the laser according to the spectral characteristics of weeds and crops to achieve efficient and precise weed control.
[0112] refer to Figure 5 In step S140, when the weeding robot is weeding along the corresponding weeding path, the spectral characteristics of the weeds are collected, and the laser power of the weeding robot is adjusted according to the spectral characteristics of the weeds.
[0113] The specific steps are as follows:
[0114] Step S141, when the weeding robot is weeding along the corresponding weeding path, collecting spectral data of the weeds;
[0115] Step S142, defining the spectral characteristics of the weeds based on the spectral data of the weeds;
[0116] Step S143: adjusting the laser power of the weeding robot according to the spectral characteristics of the weeds.
[0117] In an embodiment of the present application, when the weeding robot is weeding along the corresponding weeding path, spectral data of the weeds is collected to facilitate the collection of spectral data of the weeds, thereby freezing the spectral data of the weeds, so as to define the spectral characteristics of the weeds based on the spectral data of the weeds, thereby introducing the spectral characteristics of the weeds, and then adjusting the laser power of the weeding robot according to the spectral characteristics of the weeds, thereby achieving adaptive adjustment of the laser power of the weeding robot and ensuring targeted laser weeding of weeds.
[0118] At this time, the present invention proposes an eco-friendly precision weed control technology (EFPWT), which uses new laser technology to automatically adjust the wavelength and power according to the spectral characteristics of weeds and crops, and uses biodegradable materials as auxiliary materials to reduce the impact on the environment. Compared with traditional laser weed control technology, EFPWT can dynamically adjust laser parameters according to the spectral characteristics of weeds and crops, improving the accuracy and environmental friendliness of weed control. For example, in the EFPWT system, according to the spectral characteristics of weeds and crops, a specially designed laser emitting device is used to automatically adjust the laser parameters to achieve accurate positioning and removal of weeds, while reducing the impact on the surrounding environment.
[0119] Among them, the automatic adjustment model of laser power is as follows:
[0120] P = beta1 × g1(Sw) + beta2 × g2(Sc); lambda = beta3 × h1(Sw) +beta4 × h2(Sc)
[0121] At this time, P represents laser power; lambda represents the wavelength of the laser; Sw and Sc represent the spectral characteristics of weeds and crops respectively; g1, g2, h1, h2 represent the mapping function from spectral characteristics to laser parameters; beta1, beta2, beta3, beta4 represent weight coefficients.
[0122] The differences in spectral characteristics between weeds and crops are used to guide the execution of laser weed control. Since different plants have different reflection and absorption characteristics of light, these differences can be identified through spectral analysis technology. By accurately measuring the spectral characteristics of weeds and crops, the system can automatically adjust the power and wavelength of the laser to specifically destroy the photosynthesis system or other key physiological structures of the weeds, thereby achieving the purpose of weed control.
[0123] The laser power is adjusted to ensure that the laser energy is sufficient to destroy weed tissue without causing irreversible damage to crops and soil. Too high a power may harm crops or cause soil overheating, while too low a power may not effectively remove weeds. The choice of laser wavelength takes into account the differences in spectral characteristics. Different wavelengths of light have different penetration and absorption capabilities for plant tissue. Selecting the most suitable wavelength can maximize the efficiency and accuracy of weed control.
[0124] At this time, the weeding robot first scans the vegetation in the farmland through the spectral analysis instrument carried by it to collect spectral data of weeds and crops. Then, based on the collected data, the above formula is used to calculate the optimal laser parameters, and then the output power and wavelength of the laser equipment are adjusted to accurately weed the identified weeds.
[0125] refer to Figure 6 In step S150, the weeding effect of the weeding robot under the corresponding laser power is collected, and the weeding strategy is optimized according to the weeding effect and environmental changes.
[0126] The specific steps are as follows:
[0127] Step S151, collecting the weeding effect of the weeding robot under the corresponding laser power;
[0128] Step S152, freezing the weeding effect and the environmental changes corresponding to the current weeding effect;
[0129] Step S153: Optimize the weeding strategy according to the weeding effect and environmental changes.
[0130] In an embodiment of the present application, the weeding effect of the weeding robot under the corresponding laser power is collected, and the weeding effect is managed and controlled, so as to freeze the weeding effect and the environmental changes corresponding to the current weeding effect, so as to trigger the optimization of the weeding strategy according to the environmental changes, thereby regulating the weeding strategy and realizing the adaptive regulation of the weeding strategy.
[0131] At the same time, the collecting of the weeding effect of the weeding robot at the corresponding laser power and optimizing the weeding strategy according to the weeding effect and environmental changes also include:
[0132] The weed control strategy optimization model is as follows:
[0133] S_new = S_old + eta × grad_S R(S_old, F, E)
[0134] At this time, S_new and S_old represent the updated weeding strategy and the weeding strategy before the update respectively; eta represents the learning rate; grad_SR represents the gradient of the reward function with respect to the strategy S; F represents the feedback of the operation effect; and E represents the environmental parameters.
[0135] At this time, the self-learning and optimization decision engine is introduced. The self-learning and optimization decision engine (SLODE) is a key component for continuously optimizing weeding strategies in the intelligent ecological collaborative weeding system (IECWS). By introducing machine learning, especially reinforcement learning technology, SLODE can automatically adjust weeding strategies based on past operation results and environmental changes to ensure maximum weeding efficiency while reducing damage to crops and adverse effects on the environment.
[0136] By continuously learning and adjusting, the system can automatically discover and apply the most effective weed control strategy. Reinforcement learning plays a central role in this process, enabling the system to optimize itself based on past experience and environmental feedback.
[0137] In practical applications, SLODE first defines a clear reward function R, which can comprehensively consider factors such as weed control effect, crop damage and environmental impact to quantify the overall performance of a weed control strategy. For example, the reward function may give a higher reward value to a strategy with high weed control efficiency, low crop damage and low environmental impact.
[0138] As the system runs, SLODE collects operational feedback F (such as weeding completion, crop damage, etc.) and environmental parameters E (such as weather conditions, soil moisture, etc.). These data are used to calculate the value of the reward function R to evaluate the performance of the current weeding strategy S_old.
[0139] By calculating the gradient grad_SR of the reward function with respect to the strategy S, SLODE can determine how to adjust the strategy to improve the reward function value, that is, find the direction to optimize the effect. The learning rate eta determines the step size of this adjustment.
[0140] By repeating this process, SLODE can gradually optimize the weed control strategy to achieve higher weed control efficiency and lower environmental impact. This self-learning and optimization capability enables IECWS to not only adapt to various complex farmland environments, but also continuously improve its working efficiency and environmental friendliness over time.
[0141] In short, SLODE uses reinforcement learning technology to enable IECWS to autonomously learn and optimize its weed control strategy, thereby ensuring weed control efficiency while minimizing adverse effects on crops and the environment, and achieving truly intelligent and precise agricultural management.
[0142] In addition, the collaborative weeding control method further includes: collecting weeding operation data and environmental parameters during the weeding strategy; associating the weeding operation data and environmental parameters; defining an ecological impact score based on the weeding operation data, environmental parameters and evaluation function; wherein the ecological impact evaluation model is as follows:
[0143] I = integral l(D, E) dE
[0144] Here, I represents the ecological impact score; D represents the operation data; E represents the environmental parameters; l represents the evaluation function; and integral represents the integral.
[0145] At this time, the ecological collaborative feedback system is introduced.
[0146] The Ecological Collaborative Feedback System (ECFS) plays a vital role in the Intelligent Ecological Collaborative Weeding System (IECWS), which aims to evaluate the comprehensive impact of weeding operations on farmland ecology and provide feedback to optimize future operation strategies. By comprehensively evaluating the farmland environment after the operation, ECFS can monitor and guide agricultural activities to promote ecological balance and sustainable development.
[0147] ECFS collects and analyzes weed control data (D) and environmental parameters (E), and uses an evaluation function (l) to calculate an ecological impact score (I). This process includes not only direct operational effects, such as weed control efficiency and crop damage, but also the impact of operations on environmental factors such as soil quality, water resources, and biodiversity.
[0148] The design of the evaluation function (l) is the core of ECFS, which needs to be able to accurately reflect the impact of different operation strategies on the ecosystem. This usually requires interdisciplinary knowledge, including ecology, agricultural science, environmental science, etc., to ensure the comprehensiveness and accuracy of the evaluation. The environmental parameters (E) in the function may include soil moisture, pH value, organic matter content, biodiversity indicators, etc. These parameters can comprehensively reflect the ecological status of the farmland.
[0149] By calculating I, ECFS can provide agricultural producers with a quantitative and comprehensive ecological impact assessment to help them understand the impact of current weed control strategies on the ecological environment. This score can be used as a basis for adjusting agricultural practices and improving operational strategies, with the goal of minimizing negative impacts on the environment and promoting ecological balance while ensuring agricultural production efficiency.
[0150] The implementation of ECFS, especially the calculation of ecological impact scores, has prompted the formulation of weed control strategies to pay more attention to eco-friendly and sustainable principles. Over time, through continuous data collection and analysis, ECFS can help agricultural producers gradually optimize their operation strategies and achieve a win-win situation for production efficiency and ecological protection. In addition, ECFS can also provide valuable data and insights for agricultural scientific research, supporting the development and promotion of sustainable agricultural technologies.
[0151] In short, the Ecological Collaborative Feedback System (ECFS) evaluates the impact of weeding operations on farmland ecosystems by comprehensively considering operation data and environmental parameters, providing scientific decision support for agricultural production. This system not only helps to improve weeding efficiency and crop yields, but more importantly, promotes the health and sustainable development of agricultural ecosystems.
[0152] Therefore, a closed-loop feedback system is formed: from the collection and analysis of environmental data (EPDIM), to precise navigation and collaborative operations (CMRNP), to environmentally friendly weeding operations (EFPWT), and continuous improvement of weeding strategies through learning and optimization (SLODE), and finally to improve the eco-friendliness of the system by evaluating the impact of operations on the ecology (ECFS). Each step depends on the output of the previous step and provides input for the next step, ensuring the efficient operation of IECWS and the protection of the ecological environment.
[0153] Compared with the prior art, in the technical solutions provided in some embodiments of the present application, multiple farmland data are obtained, and the growth rate of weeds is predicted based on the multiple farmland data; if the growth rate of the weeds reaches a preset growth rate, multiple weeding robots are associated, and the distribution area of the weeds is collected; based on the distribution area of the weeds, the coordinated movement between the multiple weeding robots is triggered, and corresponding weeding paths are defined according to the multiple weeding robots; when the weeding robots weed along the corresponding weeding paths, the spectral characteristics of the weeds are collected, and the laser power of the weeding robots is adjusted according to the spectral characteristics of the weeds; the weeding effect of the weeding robot at the corresponding laser power is collected, and the weeding strategy is optimized according to the weeding effect and environmental changes, so as to optimize the weeding strategy in real time, and monitor the weeding effect of multiple weeding robots along the corresponding weeding paths in real time, thereby ensuring the coordinated weeding mode between the multiple weeding robots, which can maximize the protection of the farmland ecological environment while ensuring the weeding efficiency, thereby realizing intelligent weeding and efficient weeding.
[0154] The present invention adopts comprehensive intelligent technology, including ecological perception and data integration module, collaborative multi-robot navigation and operation platform, self-learning and optimization decision engine, etc. Compared with traditional single technical means, it has a higher level of intelligence and comprehensive advantages. For example, compared with single machine vision technology, the present invention can realize real-time perception and comprehensive analysis of farmland environment by combining multi-source data and intelligent algorithms, thereby improving the accuracy and efficiency of weed identification; at the same time, the application of collaborative multi-robot navigation and operation platform can realize real-time collaborative operation between multiple robots, maximizing the operation efficiency and reducing the damage of machinery to crops.
[0155] The present invention focuses on eco-friendliness and sustainable development. Through the ecological perception and data integration module and the ecological synergistic feedback system, it can achieve the protection of farmland ecosystems and the safety of crops, and minimize the pollution of chemical herbicides to the environment. For example, by comprehensively evaluating the impact of weeding operations on farmland ecology, scientific decision-making support is provided for agricultural producers, promoting the sustainable development of agricultural production.
[0156] The following describes an embodiment of the device of the present application, which can be used to implement the collaborative weed control method in the above embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the collaborative weed control method in the above embodiment of the present application.
[0157] Figure 7 A block diagram of a coordinated weed control device according to an embodiment of the present application is shown.
[0158] Reference Figure 7 As shown, a cooperative weed control device according to an embodiment of the present application includes:
[0159] An acquisition module 210 is used to acquire a plurality of farmland data and predict the growth rate of weeds based on the plurality of farmland data;
[0160] An association module 220 is used to associate multiple weeding robots and collect the distribution area of the weeds if the growth rate of the weeds reaches a preset growth rate;
[0161] A coordination module 230, for triggering coordinated movement between multiple weeding robots based on the distribution area of weeds, and defining corresponding weeding paths according to the multiple weeding robots;
[0162] A control module 240 is used to collect the spectral characteristics of weeds when the weeding robot is weeding along the corresponding weeding path, and adjust the laser power of the weeding robot according to the spectral characteristics of the weeds;
[0163] The weeding strategy module 250 is used to collect the weeding effect of the weeding robot under the corresponding laser power, and optimize the weeding strategy according to the weeding effect and environmental changes.
[0164] Figure 8 A schematic diagram of the structure of a computer system suitable for implementing the weeding robot according to the embodiment of the present application is shown.
[0165] It should be noted that Figure 8 The computer system of the lawn mowing robot shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0166] like Figure 8 As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.
[0167] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.
[0168] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 309, and / or installed from a removable medium 311. When the computer program is executed by a central processing unit (CPU) 301, various functions defined in the system of the present application are executed.
[0169] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier, which carries a computer-readable computer program. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0170] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0171] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.
[0172] As another aspect, the present application also provides a computer-readable medium, which may be included in the weeding robot described in the above embodiment; or may exist independently without being assembled into the weeding robot. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the weeding robot, the weeding robot implements the method described in the above embodiment.
[0173] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.
[0174] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation method of the present application.
[0175] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.
[0176] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A method for controlling synergistic weed control, It is characterized in that Applied to a weeding robot, the control method for collaborative weeding includes: Acquire a plurality of farmland data, and predict the growth rate of weeds based on the plurality of farmland data; If the growth rate of the weeds reaches a preset growth rate, a plurality of the weeding robots are associated and the distribution areas of the weeds are collected; triggering coordinated movement among the plurality of weeding robots based on the distribution area of the weeds, and defining corresponding weeding paths according to the plurality of weeding robots; When the weeding robot is weeding along the corresponding weeding path, collecting the spectral characteristics of the weeds, and adjusting the laser power of the weeding robot according to the spectral characteristics of the weeds; Collecting the weeding effect of the weeding robot under the corresponding laser power, and optimizing the weeding strategy according to the weeding effect and environmental changes; The acquiring of a plurality of farmland data and predicting the growth rate of weeds based on the plurality of farmland data comprises: Positioning the farmland to be processed by a plurality of said weeding robots; constructing an online collection model based on the farmland; In the online collection model, the plurality of farmland data corresponding to the farmland are collected in real time, and the plurality of farmland data include temperature, humidity, light intensity, soil parameters, average height of crops, and leaf area of crops; Predicting the growth rate of the weeds based on the plurality of farmland data and a weed growth rate prediction model; Wherein, the weed growth rate prediction model is as follows: WG = alpha1 × f1(T, H, L) + alpha2 × f2(SH, pH, N) + alpha3 × f3(G, LA); At this time, WG represents the growth rate of weeds; T, H, L represent the temperature, humidity and light intensity in the meteorological data respectively; SH, pH, N represent soil parameters, including soil moisture, pH value and nutrient content; G, LA represent the average height and leaf area of crops; f1, f2, f3 are functions of the influence of meteorological data, soil conditions and crop growth status on the growth rate of weeds; alpha1, alpha2, alpha3 are weight coefficients; The triggering of the coordinated movement between the plurality of weeding robots based on the distribution area of the weeds, and defining corresponding weeding paths according to the plurality of weeding robots, comprises: Determining the distribution area of the weeds, and dividing the distribution area of the weeds into a plurality of sub-areas; Establishing a collaborative weeding working relationship based on the plurality of said weeding robots, and performing collaborative movements among the plurality of said weeding robots based on the collaborative weeding working relationship; Acquire multiple sub-areas and multiple locations of the weeding robots; The weeding path planning is triggered based on the locations of the multiple sub-areas and the multiple weeding robots, and the weeding paths that each of the weeding robots is responsible for are corresponding.
2. The method according to claim 1, It is characterized in that If the growth rate of the weeds reaches a preset growth rate, a plurality of the weeding robots are associated and the distribution areas of the weeds are collected, including: The growth rate of the weed is compared to a preset growth rate: If the growth rate of the weeds reaches the preset growth rate, then associating a plurality of the weeding robots; Based on the plurality of weeding robots, weeds are collected along the farmland, and a plurality of weed images are formed; The distribution area of the weeds is determined according to the multiple weed images.
3. The method according to claim 1, It is characterized in that When the weeding robot weeds along the corresponding weeding path, the spectral characteristics of the weeds are collected, and the laser power of the weeding robot is adjusted according to the spectral characteristics of the weeds, including: When the weeding robot is weeding along the corresponding weeding path, collecting spectral data of the weeds; defining spectral characteristics of the weeds based on spectral data of the weeds; adjusting the laser power of the weeding robot according to the spectral characteristics of the weeds; The automatic adjustment model of the laser power is as follows: P = beta1 × g1(Sw) + beta2 × g2(Sc); lambda = beta3 × h1(Sw) + beta4× h2(Sc); At this time, P represents laser power; lambda represents the wavelength of the laser; Sw and Sc represent the spectral characteristics of weeds and crops respectively; g1, g2, h1, h2 represent the mapping function from spectral characteristics to laser parameters; beta1, beta2, beta3, beta4 represent weight coefficients.
4. The method according to claim 3, It is characterized in that The collecting of the weeding effect of the weeding robot at the corresponding laser power and optimizing the weeding strategy according to the weeding effect and environmental changes include: Collecting the weeding effect of the weeding robot under the corresponding laser power; Freeze the weed control effect and the environmental changes corresponding to the current weed control effect; The weed control strategy is optimized according to the weed control effect and the environmental changes.
5. The method according to claim 1, It is characterized in that The collecting of the weeding effect of the weeding robot at the corresponding laser power and optimizing the weeding strategy according to the weeding effect and environmental changes also includes: The weed control strategy optimization model is as follows: S_new = S_old + eta × grad_S R(S_old, F, E); At this time, S_new and S_old represent the updated weeding strategy and the weeding strategy before the update respectively; eta represents the learning rate; grad_SR represents the gradient of the reward function with respect to the strategy S; F represents the feedback of the operation effect; and E represents the environmental parameters.
6. The method according to claim 1, It is characterized in that Also includes: During the implementation of the weed control strategy, collecting weed control operation data and environmental parameters; Associating the data of the weeding operation with the environmental parameters; defining an ecological impact score based on the data of the weeding operation, the environmental parameters, and an evaluation function; Among them, the assessment model of ecological impact is as follows: I = integral l(D, E) dE; Here, I represents the ecological impact score; D represents the operation data; E represents the environmental parameters; l represents the evaluation function; and integral represents the integral.
7. A collaborative weed control device for implementing the collaborative weed control method according to any one of claims 1 to 6, It is characterized in that include: An acquisition module, used for acquiring a plurality of farmland data, and predicting the growth rate of weeds based on the plurality of farmland data; an association module, configured to associate a plurality of weeding robots and collect distribution areas of the weeds if the growth rate of the weeds reaches a preset growth rate; A coordination module, configured to trigger coordinated movement between the plurality of the weeding robots based on the distribution area of the weeds, and define corresponding weeding paths according to the plurality of the weeding robots; a control module, used for collecting the spectral characteristics of the weeds when the weeding robot is weeding along the corresponding weeding path, and adjusting the laser power of the weeding robot according to the spectral characteristics of the weeds; A weeding strategy module, used to collect the weeding effect of the weeding robot under the corresponding laser power, and optimize the weeding strategy according to the weeding effect and environmental changes; The acquisition module is also used for: Positioning the farmland to be processed by a plurality of said weeding robots; constructing an online collection model based on the farmland; In the online collection model, the plurality of farmland data corresponding to the farmland are collected in real time, and the plurality of farmland data include temperature, humidity, light intensity, soil parameters, average height of crops, and leaf area of crops; Predicting the growth rate of the weeds based on the plurality of farmland data and a weed growth rate prediction model; Wherein, the weed growth rate prediction model is as follows: WG = alpha1 × f1(T, H, L) + alpha2 × f2(SH, pH, N) + alpha3 × f3(G, LA); At this time, WG represents the growth rate of weeds; T, H, L represent the temperature, humidity and light intensity in the meteorological data respectively; SH, pH, N represent soil parameters, including soil moisture, pH value and nutrient content; G, LA represent the average height and leaf area of crops; f1, f2, f3 are functions of the influence of meteorological data, soil conditions and crop growth status on the growth rate of weeds; alpha1, alpha2, alpha3 are weight coefficients; The collaboration module is also used to: Determining the distribution area of the weeds, and dividing the distribution area of the weeds into a plurality of sub-areas; Establishing a collaborative weeding working relationship based on the plurality of said weeding robots, and performing collaborative movements among the plurality of said weeding robots based on the collaborative weeding working relationship; Acquire multiple sub-areas and multiple locations of the weeding robots; The weeding path planning is triggered based on the locations of the multiple sub-areas and the multiple weeding robots, and the weeding paths that each of the weeding robots is responsible for are corresponding.
8. A computer readable medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the coordinated weed control method according to any one of claims 1 to 6 is implemented.
