A control method and device of a harvesting robot, an electronic device, and a storage medium

Abstract

This invention relates to the field of wetland plant harvesting technology, and more particularly to a control method, device, electronic equipment, and storage medium for a harvesting robot. The harvesting robot control method provided in this application calculates the target cutting position of the harvesting robot's cutting blades based on the current distance of the harvesting robot relative to the surface of the filler material in the modular wetland. It also calculates the target cutting speed of the harvesting robot by combining the actual plant type and density in the modular wetland system. The method harvests the plants by synchronously controlling the lifting mechanism and the drive mechanism. Thus, through intelligent sensing and collaborative control, precise, efficient, and adaptive harvesting is achieved, significantly reducing human intervention, improving work quality and wetland maintenance efficiency, while avoiding damage to the substrate or plant roots.

Description

Technical Field

[0001] This invention relates to the field of wetland plant harvesting technology, and in particular to a control method, device, electronic equipment, and storage medium for a harvesting robot. Background Technology

[0002] Constructed wetlands, as a green and low-cost ecological wastewater treatment technology, have been widely used globally. Through a complex ecosystem of soil, plants, and microorganisms, they efficiently degrade pollutants, achieving natural water purification. Aquatic plants (such as reeds, cattails, and wild rice) are the core component of this system, playing a crucial role. However, the growth of constructed wetland plants exhibits significant seasonality and cyclicality. Every autumn and winter, a large amount of the above-ground parts wither and die. If these fallen plants are not promptly and effectively removed, they decompose in the water, releasing nutrients such as nitrogen and phosphorus back into the water, causing secondary pollution. In severe cases, this can even lead to system failure. The rotting plant debris mixed with sediment can exacerbate blockage of the wetland substrate layer, altering the designed hydraulic flow pattern, creating short-circuit flows, and reducing treatment efficiency.

[0003] Currently, the maintenance of plants in most constructed wetlands (mainly harvesting) still relies heavily on traditional manual labor. Operators must wear heavy waterproof clothing and use simple tools such as sickles and lawnmowers in muddy and slippery environments to harvest, collect, transport, and centrally process the plants. This results in high labor costs, reduced operational efficiency, and the potential for damage to the wetland ecosystem if maintenance is not timely. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a control method, device, electronic device, and storage medium for a harvesting robot.

[0005] In a first aspect, embodiments of the present invention provide a control method for a harvesting robot. The method is applied to a control unit of a wetland system. The wetland system includes a modular wetland, a harvesting robot mounted on a ring beam along its outer edge, a drive mechanism for driving the harvesting robot to move along the ring beam, a lifting mechanism for controlling the raising and lowering of harvesting blades connected to the harvesting robot, and a distance measuring mechanism for measuring distance. The drive mechanism, the lifting mechanism, and the distance measuring mechanism are electrically connected to the control unit. The method includes: The current distance of the harvesting robot relative to the surface of the filler material in the modular wetland is obtained through a ranging mechanism; Based on the current distance and a preset cutting height threshold, the target cutting position of the harvesting robot's cutting blades is calculated; at the same time, based on the plant types and plant density in the modular wetland, the target cutting speed of the harvesting robot is determined. The lifting and driving mechanisms are controlled synchronously to enable the harvesting robot to move at the target speed to the target cutting position to harvest the plants.

[0006] In addition to the first aspect, the bottom of the harvesting robot is also equipped with a vision sensor, which is connected to the control unit; The steps for calculating the target cutting position of the harvesting robot's cutting blades based on the current distance and a preset cutting height threshold include: Acquire images of plant stems captured by a visual sensor; Plant stem images are processed to identify and determine the canopy height and stem density distribution of the plant. The target cutting position is dynamically calculated by combining the current distance, the preset cutting height threshold, and the identified canopy height.

[0007] In conjunction with the first aspect, the steps for dynamically calculating the target cutting position, based on the current distance, the preset cutting height threshold, and the identified canopy height, include: Calculate using the following formula:

[0008] in, For the target cutting position, Current distance, For canopy height, For preset cutting height threshold, This is an adaptive coefficient adjusted based on the stem density distribution.

[0009] In conjunction with the first aspect, the steps for determining the target cutting speed of the harvesting robot based on the plant types and density within the modular wetland include: Acquire images of the plant canopy from a visual sensor; Plant canopy images are processed to identify plant types and current stem density. Based on a preset mapping relationship, obtain the stem strength coefficient and toughness coefficient corresponding to the plant type; Real-time monitoring of the load current of the drive motor of the harvesting blades; The current stalk density, stalk strength coefficient, toughness coefficient, and load current are input into a preset speed decision model. The optimization objective is to minimize the energy consumption per unit distance for harvesting while satisfying the constraint of cutting success rate, and the target cutting speed is output.

[0010] Combining the first aspect, the steps of inputting the current stalk density, stalk strength coefficient, toughness coefficient, and load current into a preset speed decision model, with the optimization objective of minimizing harvesting energy consumption per unit distance under the constraint of satisfying the cutting success rate, and outputting the target cutting speed, include: Calculate the overall resistance coefficient of the current vegetation based on the stem strength coefficient, toughness coefficient, and current stem density; The weight of the comprehensive resistance coefficient is dynamically adjusted based on the ratio of the load current to the rated load current. The weighted comprehensive resistance coefficient, current stalk density, and load current are input into the pre-trained energy consumption optimization model. Under the premise of satisfying the cutting success rate constraint, the constrained optimization algorithm is used to solve the multi-objective optimization function to calculate the optimal speed. The preferred speed is smoothed by motion processing and combined with the maximum acceleration threshold of the harvesting robot to output the final target cutting speed.

[0011] In conjunction with the first aspect, the harvesting robot has multiple sets of harvesting blades; the method also includes: Obtain the cutting success rate of the front set of harvesting blades; If the cutting success rate is less than the preset cutting success threshold; Control the operation of the current lifting mechanism corresponding to the current harvesting blade.

[0012] In addition to the first aspect, the harvesting robot is also equipped with a storage plate, which is set at an angle upwards along the outer side to the inner side of the modular wetland.

[0013] Secondly, this application also provides a control device for a harvesting robot. The device is applied to the control unit of a wetland system. The wetland system includes a modular wetland, a harvesting robot mounted on its outer ring beam, a drive mechanism for driving the harvesting robot to move along the ring beam, a lifting mechanism for controlling the raising and lowering of the harvesting blades connected to the harvesting robot, and a distance measuring mechanism for measuring distance. The drive mechanism, lifting mechanism, and distance measuring mechanism are electrically connected to the control unit. The device includes: The acquisition module is used to obtain the current distance of the harvesting robot relative to the surface of the filler material in the modular wetland through a ranging mechanism; The calculation module is used to calculate the target cutting position of the harvesting robot's cutting blades based on the current distance and a preset cutting height threshold; at the same time, it determines the target cutting speed of the harvesting robot based on the plant types and plant density in the modular wetland. The control module is used to synchronously control the operation of the lifting mechanism and the drive mechanism, so that the harvesting robot can move at the target speed to the target cutting position to harvest the plants to be harvested.

[0014] Thirdly, this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor runs the computer program to cause the electronic device to perform the methods described above.

[0015] Fourthly, this application provides a readable storage medium storing computer program instructions, which, when read and executed by a processor, perform the above-described method.

[0016] The embodiments of the present invention bring the following beneficial effects: This application provides a control method, device, electronic device, and storage medium for a harvesting robot. The method is applied to the control unit of a wetland system. The wetland system includes a modular wetland, a harvesting robot mounted on its outer ring beam, a drive mechanism for driving the harvesting robot to move along the ring beam, a lifting mechanism for controlling the raising and lowering of the harvesting blades connected to the harvesting robot, and a distance measuring mechanism for measuring distance. The drive mechanism, lifting mechanism, and distance measuring mechanism are electrically connected to the control unit. The method includes: obtaining the current distance of the harvesting robot relative to the surface of the filler material in the modular wetland through the distance measuring mechanism; calculating the target cutting position of the harvesting robot's harvesting blades based on the current distance and a preset cutting height threshold; simultaneously determining the target cutting speed of the harvesting robot based on the plant type and plant density in the modular wetland; and synchronously controlling the operation of the lifting mechanism and the drive mechanism so that the harvesting robot moves at the target speed to the target cutting position to harvest the plants.

[0017] The harvesting robot control method provided in this application calculates the target cutting position of the harvesting robot's cutting blades based on the current distance of the harvesting robot relative to the surface of the filler material in the modular wetland. It also calculates the target cutting speed of the harvesting robot by combining the actual plant type and density in the modular wetland system. The method then synchronously controls the lifting mechanism and the drive mechanism to harvest the plants. Through intelligent sensing and collaborative control, precise, efficient, and adaptive harvesting is achieved, significantly reducing human intervention, improving work quality and wetland maintenance efficiency, while avoiding damage to the substrate or plant roots.

[0018] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating the control method for a harvesting robot provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the control device for a harvesting robot provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the electronic device structure provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of a wetland system provided in an embodiment of the present invention.

[0022] Figure label: 1-Modular wetland, 2-Ring beam, 3-Harvesting robot, 4-Lifting mechanism, 5-Harvesting blades; 10 - Acquisition module, 20 - Calculation module, 30 - Control module; 130 - Processor, 131 - Memory, 132 - Bus, 133 - Communication interface. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] To facilitate understanding of this embodiment, the application scenarios and design concepts of this application embodiment will be briefly introduced below.

[0025] Wetlands have soft foundations and poor load-bearing capacity, making it easy for heavy terrestrial farmland harvesting equipment to get stuck and unable to move forward; uneven distribution of plant species and densities prevents operation in a fixed harvesting pattern; changes in water level affect harvesting height, making it difficult for existing terrestrial farmland harvesting equipment to flexibly adapt to different harvesting heights.

[0026] Based on this, embodiments of this application provide a control method, device, electronic device, and storage medium for a harvesting robot.

[0027] Example 1 This application provides a control method for a harvesting robot, which is applied to the control unit of a wetland system, such as... Figure 4 The wetland system shown includes a modular wetland 1, a harvesting robot 3 mounted on its outer ring beam 2, a drive mechanism (not shown) for moving the harvesting robot 3 along the ring beam 2, a lifting mechanism 4 for controlling the raising and lowering of the harvesting blades connected to the harvesting robot, and a distance measuring mechanism (not shown). The drive mechanism, lifting mechanism 4, and distance measuring mechanism are electrically connected to a control unit (not shown). The direction of movement of the harvesting robot 3 (i.e., the harvesting direction) is shown by the arrow.

[0028] In this embodiment, the wetland system includes at least one modular wetland 1, which can be connected in series or in parallel. Aquatic plants (such as reeds and cattails) in the modular wetlands 1 play a crucial role in water purification. Every winter or after the plants wither, they need to be harvested promptly to prevent the release of pollutants from decay and to promote new growth the following year. Traditional manual harvesting methods are labor-intensive and inefficient, while existing automated harvesting equipment is mostly designed for terrestrial farmland and is ill-suited to the unique environment of constructed wetlands.

[0029] Combination Figure 1 As shown, the method includes: S110, through the ranging mechanism, obtains the current distance of the harvesting robot 3 relative to the surface of the filler material inside the modular wetland 1.

[0030] S120, based on the current distance and the preset cutting height threshold, calculate the target cutting position of the harvesting robot 3's harvesting blade 5; at the same time, based on the plant type and plant density in the modular wetland 1, determine the target cutting speed of the harvesting robot 3.

[0031] S130, synchronously control the lifting mechanism 4 and the drive mechanism to operate, so that the harvesting robot 3 moves at the target speed to the target cutting position to harvest the plants to be harvested.

[0032] In this application, the harvesting robot 3 is mounted on the ring beam 2 of the modular wetland 1. The harvesting blade 5 is extended into the modular wetland 1 through a telescopic mechanism. When the robot moves along the ring beam 2 driven by the drive mechanism, it drives the harvesting blade 5 to move in the direction of the harvesting robot 3 to harvest plants. The method of suspending the harvesting blade 5 is used instead of placing the harvesting robot 3 in the modular wetland 1. The lifting mechanism 4 is controlled by obtaining the current distance of the filler surface in the modular wetland 1 to adjust the target position of the harvesting blade 5. The cutting speed is also adjusted according to the plant type and plant density in the modular wetland 1, so as to harvest plants efficiently and reliably, which is conducive to realizing the large-scale, unmanned operation and maintenance of large wetland groups.

[0033] In step S110, the distance measuring mechanism is located at the bottom of the harvesting robot 3 to obtain the current distance value of the harvesting robot 3 relative to the surface of the filler material in the modular wetland 1 below in real time. The distance measuring mechanism can be a laser rangefinder or an ultrasonic sensor. A laser rangefinder calculates the distance by emitting a laser beam and measuring the time it takes for the laser to travel from emission to reflection. It has good directionality, is not easily affected by the surrounding environment, can effectively penetrate the gaps in plant stems, directly measure the distance to the filler material or water surface, and has high resolution, capable of detecting very small distance changes. An ultrasonic sensor calculates the distance by emitting an ultrasonic beam and measuring the time it takes for the sound wave to travel from emission to return. It is unaffected by light, color, or transparency, and has a large measurement range. It is understood that both of the above methods can be implemented; however, considering the high requirement for cutting height accuracy, a laser rangefinder is selected in this application.

[0034] Preferably, this application can also improve detection accuracy through multi-sensor fusion, such as installing two or more laser rangefinders arranged horizontally. The control system takes the average or median of multiple sensors, which can effectively filter out abnormal values ​​caused by a single laser beam hitting an inclined plant stem; or, a redundant scheme of "laser rangefinder and ultrasonic sensor" can be adopted. Under normal circumstances, laser data is used, and when the system detects abnormal laser data (such as in dense fog or heavy rain), it automatically switches to the calibrated ultrasonic sensor for conservative operation or alarm.

[0035] Preferably, the ranging mechanism of this application is provided with a protective cover to prevent direct rain and dust pollution.

[0036] Preferably, the ranging mechanism of this application is also connected to an automatic cleaning device (such as a miniature wiper or air blower) to periodically measure the ranging mechanism under the control of the control unit.

[0037] Since the surface of the wetland base within modular wetland 1 may be uneven, step S120 determines the specific position to which the cutting tool should descend by calculating the difference between the current distance value of the filler surface within modular wetland 1 and the preset plant cutting height threshold. The distance between the remaining plant rootstock length and the wetland surface at this position is the preset plant cutting height threshold. For example, if the current distance is 1.5m and the preset plant cutting height threshold is 0.6m, the harvesting tool 5 is moved downwards by 1.5 - 0.6 = 0.9m. After cutting the plant, the distance between the remaining plant rootstock and the wetland surface is 0.6m. The height of the harvesting tool 5 is adjusted before harvesting each row of plants to ensure a uniform height of remaining plant rootstock after harvesting. Understandably, the ranging mechanism continuously measures, and the control unit performs closed-loop control of the lifting mechanism 4 based on the real-time updated current distance value, dynamically fine-tuning the height of the harvesting tool 5 to address any minor undulations on the filler surface and ensure a constant cutting height.

[0038] Simultaneously, in step S120, the control unit determines the target moving speed of the harvesting robot 3 based on pre-stored or real-time acquired information on plant types and density distribution within the modular wetland 1. This is because plant type determines the toughness of the stems (e.g., reeds are tougher than cattails, requiring a reduced cutting speed), and plant density determines the harvesting load per unit area (higher density necessitates a reduced moving speed to ensure thorough cutting).

[0039] In this way, the moving speed is intelligently adjusted according to different plant types and densities, which optimizes harvesting efficiency while ensuring cutting quality (no pulling and neat cut surfaces) and avoids energy waste or incomplete cutting caused by a single speed.

[0040] Subsequently, step S130 synchronously controls the operation of the lifting mechanism 4 and the drive mechanism, ensuring the continuity and stability of the harvesting operation and improving the automation and reliability of the entire system. Specifically, a command is sent to the lifting mechanism 4 to drive the harvesting blade 5 to descend to the calculated target cutting position; a command is sent to the drive mechanism to cause the harvesting robot 3 to move along the ring beam 2 at the determined target cutting speed. In this way, the harvesting blade 5 harvests the plants flat and efficiently at a preset height and at a speed synchronized with the robot's movement.

[0041] In addition to the first aspect, the bottom of the harvesting robot 3 is also equipped with a vision sensor, which is connected to the control unit.

[0042] In step S120, based on the current distance and a preset cutting height threshold, the target cutting position of the harvesting robot 3's harvesting blade 5 is calculated, specifically including: S121, acquire the plant stem image collected by the visual sensor.

[0043] Images of plant stems in front of or below are captured by vision sensors (such as high-definition cameras, multispectral cameras, or depth cameras) installed on the harvesting robot 3. Understandably, the images contain a wealth of biological information, such as the height, density, and health status of the plants.

[0044] In this embodiment, along the moving direction of the harvesting robot 3, a vision sensor is positioned in front of the harvesting area to detect the plant conditions in advance in the area to be harvested.

[0045] As a preferred option, supplementary lighting (such as LED light strips) is also installed at the bottom of the harvesting robot 3 to ensure that clear and stable images can be obtained under different lighting conditions.

[0046] S122, perform recognition processing on plant stem images to determine the canopy height and stem density distribution of the plant.

[0047] The control unit runs a specific image recognition algorithm to process and analyze the image acquired in step S121. It can segment plants and background (soil / water surface) by analyzing the color and texture differences in the image, and then calculate the average height or highest point of the vegetation area to identify the canopy height. At the same time, it can identify each individual stem based on a machine learning object detection model to accurately calculate the density. A simpler method is to estimate the relative density by calculating the percentage of vegetation pixels in the image, thereby obtaining the stem density distribution.

[0048] S123, combining the current distance, the preset cutting height threshold, and the identified canopy height, dynamically calculates the target cutting position.

[0049] In conjunction with the first aspect, step S123 includes: Calculate using the following formula:

[0050] in, For the target cutting position, Current distance, For canopy height, For preset cutting height threshold, This is an adaptive coefficient adjusted based on the aforementioned stem density distribution.

[0051] In this embodiment, the preset value will not be used continuously. Instead, it dynamically calculates the cut height based on the obtained plant information. Specifically, if the plant grows abnormally tall ( Much larger Harvesting too much material at once may overload the machine. In this case, the system may decide to harvest only a portion in the first round and wait for the second round. Conversely, if the plants are very short, the machine may stop operating.

[0052] Understandably, the control unit also stores the stem density distribution and adaptive coefficients. The mapping relationship is established so that, after identifying the stem density distribution in step S122, the corresponding adaptive coefficient is found based on the mapping relationship. The system dynamically calculates the target cutting position while taking into account the stem density distribution. Understandably, high-density areas experience greater cutting resistance and load; to protect the tool and motor, the system may decide to "cut shallower," reducing the instantaneous cutting depth. It is a positive coefficient; conversely, in low-density areas, resistance is low and load is low, so normal planning can proceed. Harvesting can be carried out, and to maintain uniformity, the cuts can be made "deeper" to increase the instantaneous cutting volume. It is a negative coefficient.

[0053] Subsequently, the absolute distance to the ground was measured using a rangefinder. This allows us to calculate the absolute target position of the tool, thus enabling us to... Taking into account the terrain undulations, and through and It takes into account crop growth conditions to generate highly intelligent final execution instructions.

[0054] In conjunction with the first aspect, step S120 determines the target cutting speed of the harvesting robot 3 based on the plant type and density within the modular wetland 1, specifically including: S124, acquire plant canopy images collected by the visual sensor.

[0055] S125 performs identification processing on plant canopy images to determine plant type and current stem density.

[0056] Understandably, different plants have unique leaf morphology, inflorescence, and canopy structure. Machine learning models (such as convolutional neural networks, CNNs) are used to identify plant species (e.g., reeds, cattails, sweet flag, etc.) in images. Simultaneously, current stem density is analyzed and identified using image analysis techniques similar to those in step S122.

[0057] S126, based on a preset mapping relationship, obtain the stem strength coefficient and toughness coefficient corresponding to the plant type.

[0058] Understandably, the control unit also stores the correspondence between plant type and stem strength coefficient and toughness coefficient. After the plant type has been identified in step S125, the stem strength coefficient and toughness coefficient are obtained by looking up the mapping relationship, thereby converting the plant type into quantifiable physical parameters that affect cutting resistance.

[0059] The stem strength coefficient represents the stem's resistance to compression and bending (unit: MPa). Understandably, the higher the stem strength, the greater the force required to cut the plant.

[0060] The stem toughness coefficient indicates the stem's ability to absorb energy before breaking. Understandably, plants with high toughness are not easily cut and are prone to "pulling," requiring sharper tools or slower cutting speeds.

[0061] S127 monitors the load current of the drive motor of the harvesting blade 5 in real time.

[0062] Understandably, the motor's load current is directly proportional to its output torque, and torque directly reflects the real-time cutting resistance. Increased current means greater cutting resistance (encountering denser, thicker, and tougher plants), while decreased current means less cutting resistance. The load current value of the motor driving the harvesting blade 5 is collected in real time by a current sensor to reflect the actual state of the cutting process.

[0063] S128 inputs the current stalk density, stalk strength coefficient, toughness coefficient and load current into the preset speed decision model, and outputs the target cutting speed with the optimization objective of minimizing the energy consumption per unit distance for harvesting under the constraint of satisfying the cutting success rate.

[0064] All the above information is input into a preset speed decision model, which calculates an optimal target cutting speed. The current stalk density is used to predict the harvest yield, the stalk strength coefficient to predict the cutting difficulty, the toughness coefficient to predict the quality risk of the cut (such as tearing), and the load current to reflect the real-time cutting resistance. By adding the constraint "cutting success rate > threshold," the speed cannot be too fast, otherwise it will lead to incomplete cutting, tearing the stalks instead of severing them, thus affecting plant regeneration and harvest quality. The cutting speed is calculated, and then "minimizing energy consumption per unit distance" is used as the optimization objective. In each control cycle, the speed is continuously fine-tuned to find the optimal solution that minimizes (motor power / forward speed), i.e., the energy consumption per unit distance, while satisfying the cutting success rate constraint.

[0065] In conjunction with the first aspect, step S128 includes: S1281, calculate the overall resistance coefficient of the current vegetation based on the stem strength coefficient, toughness coefficient and current stem density.

[0066] By integrating plant characteristic parameters from different dimensions (strength, toughness, density) into a single, quantifiable index, the harvesting difficulty in the area ahead can be predicted.

[0067] S1282 dynamically adjusts the weight of the comprehensive resistance coefficient based on the ratio of load current to rated load current.

[0068] The load factor is obtained based on the ratio of the load current to the rated load current.

[0069] If the load factor is very high (e.g., >0.9), it indicates that the actual resistance is much greater than the visually predicted resistance (the harvesting difficulty is underestimated). In this case, the system should reduce its confidence in the predicted harvesting difficulty (i.e., reduce its weight) and rely more on the real-time feedback of the load current. If the load rate is low and stable, it indicates that the prediction is accurate. In this case, the weight of harvesting difficulty can be increased, allowing the system to respond more proactively based on the field of vision ahead.

[0070] This outputs a weighting factor α (0 < α < 1), and then calculates the weighted comprehensive drag coefficient for online self-correction, thereby improving its robustness in unknown or changing environments.

[0071] S1283 inputs the weighted comprehensive resistance coefficient, current stalk density and load current into the pre-trained energy consumption optimization model. Under the premise of satisfying the cutting success rate constraint, the constrained optimization algorithm is used to solve the multi-objective optimization function to calculate the optimal speed.

[0072] Understandably, the pre-trained energy consumption optimization model, given input parameters (weighted comprehensive resistance coefficient, current stalk density, and load current), outputs the cutting success probability and energy consumption per unit distance corresponding to different speeds. Subsequently, a constrained optimization algorithm is used to solve the problem with the goal of minimizing energy consumption per unit distance and the constraint that the cutting success rate is higher than a threshold, in order to calculate the theoretically optimal "preferred speed".

[0073] S1284 performs motion smoothing on the preferred speed and, combined with the maximum acceleration threshold of the harvesting robot 3, outputs the final target cutting speed.

[0074] The "preferred speed" time series obtained in step S1283 is filtered or planned, for example, by using a low-pass filter to smooth the speed command; or more advancedly, by using an acceleration limiter. This ensures that the rate of change (acceleration) of the smoothed speed command does not exceed the maximum acceleration threshold that the robot platform can withstand, thus guaranteeing operational safety. This generates a smooth, continuous, and physically achievable "target cutting speed" command, which is then sent to the drive mechanism.

[0075] In conjunction with the first aspect, the harvesting blades 5 on the harvesting robot 3 are in multiple sets; the method also includes: S210, obtain the cutting success rate of the front harvesting blades 5.

[0076] In this embodiment, a camera mechanism is also installed at the bottom of the harvesting robot 3, positioned behind the harvesting blades 5 along the direction of movement of the harvesting robot 3, for capturing images of the harvested area. This camera mechanism is connected to the control unit to transmit the captured images. An image recognition algorithm is used to analyze whether the cut surface of the stalk is smooth, and whether there are any tears or pulls, thereby statistically calculating the cutting success rate.

[0077] S220, if the cutting success rate is less than the preset cutting success threshold.

[0078] At this point, it indicates that the previous set of blades failed to effectively complete the harvesting task. The system determines that the current working conditions (such as extremely tough plants, extremely high density, or slight wear of the blades) have exceeded expectations and intervention is necessary.

[0079] S230, control the operation of the current lifting mechanism 4 corresponding to the current harvesting blade 5.

[0080] At this point, if the front set of blades causes "missed cuts" or "tears" due to excessive cutting height, in order to correct the problems left by the front set of blades and ensure the overall harvesting quality, the control unit sends an adjustment command to the lifting mechanism 4 to which the current harvesting blade 5 (i.e. the next set of blades) belongs, to control the rear set of blades to descend to a lower position to ensure that the stalk is completely cut off.

[0081] In this way, even if the performance of the front set of tools deteriorates due to wear, dulling, or other reasons, the system can compensate through the rear set of tools, allowing the robot to continue to complete the work without immediate failure, thus improving the task completion rate.

[0082] Preferably, if the lifting mechanism 4 can adjust the pitch angle of the harvesting blade 5, the cutting can be performed at a more optimized angle by finely adjusting the pitch angle of the harvesting blade 5.

[0083] In conjunction with the first aspect, the harvesting robot 3 is also connected to a storage plate, which is inclined upward along the outer side to the inner side of the modular wetland 1.

[0084] The system includes at least one collection board, which is installed at an angle upwards and inwards along the outer side of the modular wetland 1. When the robot moves, the stems and leaves cut by the harvesting blades 5 fall onto the collection board located beside it. Because the board surface is inclined, the material slides along the lower end of the board surface under its own gravity. Traditionally, after harvesting, plant residues fall into the water and decompose, potentially releasing pollutants and affecting water quality in the short term. This application uses the collection board to quickly remove the residues from the water and collect them in one place (usually on the shore or a centralized collection point), minimizing the residence time and coverage area of ​​plant residues in the wetland and reducing secondary disturbance and pollution risks to the wetland ecosystem.

[0085] Preferably, the receiving plate can be connected to a simple vibration motor (electrically connected to the control unit). When the control unit detects that the material has high moisture content and is prone to sticking, it can briefly start vibration to prevent wet material from clogging the receiving plate and ensure smooth conveying.

[0086] As an alternative, a weight sensor can be installed at the collection end of the collection plate to estimate the yield of the harvested material and provide the robot with a feedback signal that "the collection plate is full and needs to be cleaned". It can even be linked to notify logistics personnel to transfer the material.

[0087] Secondly, this application embodiment also provides a control device for a harvesting robot 3. The device is applied to the control unit of a wetland system. The wetland system includes a modular wetland 1, a harvesting robot 3 mounted on its outer ring beam 2, a drive mechanism for driving the harvesting robot 3 to move along the ring beam 2, a lifting mechanism 4 for controlling the lifting and lowering of the harvesting blades 5 connected to the harvesting robot 3, and a distance measuring mechanism for measuring distance. The drive mechanism, the lifting mechanism 4, and the distance measuring mechanism are electrically connected to the control unit. Combination Figure 2 As shown, the device includes: an acquisition module 10, a calculation module 20, and a control module 30.

[0088] The acquisition module 10 is used to acquire the current distance of the harvesting robot 3 relative to the surface of the filler material inside the modular wetland 1 through the ranging mechanism.

[0089] The calculation module 20 is used to calculate the target cutting position of the harvesting robot 3's harvesting blade 5 based on the current distance and the preset cutting height threshold; at the same time, it determines the target cutting speed of the harvesting robot 3 based on the plant type and plant density in the modular wetland 1.

[0090] The control module 30 is used to synchronously control the operation of the lifting mechanism 4 and the drive mechanism, so that the harvesting robot 3 moves at the target speed to the target cutting position to harvest the plants to be harvested.

[0091] Thirdly, embodiments of this application provide an electronic device, combined with Figure 3 As shown, the electronic device includes a memory 131 and a processor 130. The memory 131 stores a computer program, and the processor 130 runs the computer program to make the electronic device perform the above-described method.

[0092] Furthermore, combined Figure 3 The electronic device shown also includes a bus 132 and a communication interface 133, with the processor 130, the communication interface 133 and the memory 131 connected via the bus 132.

[0093] The memory 131 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 133 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 132 may be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0094] Processor 130 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 130 or by instructions in software form. Processor 130 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 131, and processor 130 reads the information in memory 131 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0095] Fourthly, embodiments of this application provide a readable storage medium storing computer program instructions, which are read and executed by a processor to perform the above-described method.

[0096] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and apparatus described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0097] Furthermore, in the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0098] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0099] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0100] Finally, it should be noted that the above embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A control method for a harvesting robot, characterized in that, The method is applied to a control unit of a wetland system, which includes a modular wetland, a harvesting robot mounted on a ring beam along its outer edge, a drive mechanism for driving the harvesting robot to move along the ring beam, a lifting mechanism for controlling the raising and lowering of harvesting blades connected to the harvesting robot, and a distance measuring mechanism for measuring distance. The drive mechanism, the lifting mechanism, and the distance measuring mechanism are electrically connected to the control unit. A vision sensor is also provided at the bottom of the harvesting robot, and the vision sensor is connected to the control unit. The method includes: The current distance of the harvesting robot relative to the surface of the modular wetland filler is obtained through the ranging mechanism. Based on the current distance and a preset cutting height threshold, the target cutting position of the harvesting robot's cutting blades is calculated; simultaneously, based on the plant type and density within the modular wetland, the target cutting speed of the harvesting robot is determined. The lifting mechanism and the drive mechanism are synchronously controlled to enable the harvesting robot to move at a target speed and harvest the plants to be harvested at the target cutting position; The step of calculating the target cutting position of the harvesting robot's cutting blade based on the current distance and a preset cutting height threshold includes: Acquire images of plant stems captured by the visual sensor; The plant stem images are processed for identification to determine the canopy height and stem density distribution of the plant; Combining the current distance, the preset cutting height threshold, and the identified canopy height, the target cutting position is calculated using the following formula: in, For the target cutting position, Current distance, For canopy height, For preset cutting height threshold, This is an adaptive coefficient adjusted based on the aforementioned stem density distribution.

2. The method according to claim 1, characterized in that, The step of determining the target cutting speed of the harvesting robot based on the plant types and density within the modular wetland includes: Acquire images of the plant canopy from a visual sensor; The plant canopy image is processed for identification to determine the plant type and the current stem density of the plant; Based on a preset mapping relationship, obtain the stem strength coefficient and toughness coefficient corresponding to the plant type; Real-time monitoring of the load current of the drive motor of the harvesting blade; The current stalk density, stalk strength coefficient, toughness coefficient, and load current are input into a preset speed decision model. The optimization objective is to minimize the energy consumption per unit distance for harvesting while satisfying the constraint of cutting success rate, and the target cutting speed is output.

3. The method according to claim 2, characterized in that, The steps of inputting the current stalk density, stalk strength coefficient, toughness coefficient, and load current into a preset speed decision model, and optimizing to minimize energy consumption per unit distance for harvesting under the constraint of cutting success rate, and outputting the target cutting speed, include: Calculate the overall resistance coefficient of the current vegetation based on the stem strength coefficient, the toughness coefficient, and the current stem density; The weight of the comprehensive resistance coefficient is dynamically adjusted based on the ratio of the load current to the rated load current. The weighted comprehensive resistance coefficient, the current stalk density, and the load current are input into the pre-trained energy consumption optimization model. Under the premise of satisfying the cutting success rate constraint, the constrained optimization algorithm is used to solve the multi-objective optimization function to calculate the optimal speed. The preferred speed is smoothed by motion processing and combined with the maximum acceleration threshold of the harvesting robot to output the final target cutting speed.

4. The method according to claim 1, characterized in that, The harvesting robot has multiple sets of harvesting blades; The method further includes: Obtain the cutting success rate of the front set of harvesting blades; If the cutting success rate is less than the preset cutting success threshold; Control the operation of the current lifting mechanism corresponding to the current harvesting blade.

5. The method according to claim 1, characterized in that, The harvesting robot is also connected to a storage plate, which is inclined upwards along the outer side to the inner side of the modular wetland.

6. A control device for a harvesting robot, characterized in that, The device is applied to a control unit of a wetland system, the wetland system including a modular wetland, a harvesting robot mounted on a ring beam along its outer edge, a drive mechanism for driving the harvesting robot to move along the ring beam, a lifting mechanism for controlling the raising and lowering of harvesting blades connected to the harvesting robot, and a distance measuring mechanism for measuring distance; the drive mechanism, the lifting mechanism, and the distance measuring mechanism are electrically connected to the control unit; the device is used to perform the method as described in any one of claims 1-5; The device includes: The acquisition module is used to acquire the current distance of the harvesting robot relative to the surface of the modular wetland filler through the ranging mechanism; The calculation module is used to calculate the target cutting position of the harvesting robot's cutting blades based on the current distance and a preset cutting height threshold; at the same time, it determines the target cutting speed of the harvesting robot based on the plant type and density in the modular wetland. The control module is used to synchronously control the operation of the lifting mechanism and the drive mechanism so that the harvesting robot moves at the target cutting position at the target speed to harvest the plants to be harvested.

7. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program and the processor running the computer program to cause the electronic device to perform the method of any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores computer program instructions, which, when read and executed by a processor, perform the method described in any one of claims 1 to 5.

Images