A multi-legged robot for ecological restoration of high-steep slopes and its control method

Abstract

The present invention relates to the technical field of ecological restoration equipment, in particular to a multi-legged robot for ecological reconstruction of high-steep slopes, which comprises a bracket. Eight groups of walking mechanisms are arranged on the bracket. Each walking mechanism includes an upper limb, a lower limb and a ground-gripping component. One end of the upper limb is provided with a first double-shaft drive motor, and the output end of the first double-shaft drive motor is cooperatively connected with the bracket. One end of the lower limb is provided with a second double-shaft drive motor, and the output end of the second double-shaft drive motor is cooperatively connected with the other end of the upper limb. The other end of the lower limb is provided with a telescopic cylinder, the output end of the telescopic cylinder is cooperatively connected with one end of a telescopic rod, and the other end of the telescopic rod is cooperatively connected with the ground-gripping component. This robot takes into account stability, mobility, spraying function, safety and expandability.

Description

Technical Field

[0001] The present invention relates to the technical field of ecological restoration equipment, and particularly to a multi-legged robot for ecological reconstruction of high-steep slopes. Background Art

[0002] The thick-layer substrate spraying technology has been widely applied to slope greening and soil conservation projects in fields such as highways, railways, water conservancy and hydropower, and mines, playing an important role in improving environmental quality and promoting ecological restoration. However, there are still some problems in the actual application process: (1) The thick-layer substrate spraying equipment currently on the market is mainly vehicle-mounted or tractor-mounted, and its mobility and operability on high-steep slopes are limited. For difficult-to-reach areas, traditional equipment may not be able to perform effective spraying. (2) The operation efficiency of traditional spraying equipment on high-steep slopes may be limited. Adjusting the spraying distance, spraying angle and spraying particle size may reduce the operation efficiency and increase the operation time. (3) There may be safety hazards in performing spraying operations on high-steep slopes. Operators need to carry and operate equipment on complex terrains, and accidents are likely to occur. (4) The existing spraying equipment has low automation and intelligence levels, resulting in low engineering quality after spraying operations. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a multi-legged robot for ecological reconstruction of high-steep slopes.

[0004] The technical solution adopted by the present invention to achieve the above object is as follows:

[0005] The present invention discloses a multi-legged robot for ecological reconstruction of high-steep slopes in a first aspect, including a bracket, on which eight groups of walking mechanisms are provided. Each walking mechanism includes an upper limb, a lower limb and a ground-gripping component. One end of the upper limb is provided with a first double-shaft drive motor, and the output end of the first double-shaft drive motor is cooperatively connected with the bracket. One end of the lower limb is provided with a second double-shaft drive motor, and the output end of the second double-shaft drive motor is cooperatively connected with the other end of the upper limb. The other end of the lower limb is provided with a telescopic cylinder, and the output end of the telescopic cylinder is cooperatively connected with one end of a telescopic rod, and the other end of the telescopic rod is cooperatively connected with the ground-gripping component;

[0006] A spraying system is provided on the bracket. The spraying system includes a substrate storage tank, a nozzle and a spraying manipulator. The nozzle is arranged at the end of the spraying manipulator. A spray pipe is fixedly connected to the spraying manipulator, and one end of the spray pipe is connected to the substrate storage tank, and the other end of the spray pipe is connected to the nozzle. A feeding pump is arranged on the spray pipe;

[0007] The multi-legged robot further includes a controller, a data processor, a communication antenna and a storage battery.

[0008] Preferably, in a preferred embodiment of the present invention, the ground gripping assembly includes a support shaft, a first mounting block is provided at one end of the support shaft, a second mounting block is provided at the other end, a plurality of groups of electric telescopic rods are circumferentially arranged on the first mounting block, a plurality of ground claws are circumferentially hinged on the second mounting block, and the telescopic end of the electric telescopic rod is hinged to the ground claw.

[0009] Preferably, in a preferred embodiment of the present invention, the multi-legged robot further includes a camera and a plurality of sensors, and the sensors include one or more combinations of a position sensor, a temperature sensor, a wind sensor, a humidity sensor, and a wind direction sensor.

[0010] Preferably, in a preferred embodiment of the present invention, a thin film pressure sensor is provided on the ground claw, and photoelectric sensors are provided on both the upper limb and the lower limb.

[0011] A second aspect of the present invention discloses a control method for a multi-legged robot for ecological reconstruction of high-steep slopes, which is applied to any one of the multi-legged robots for ecological reconstruction of high-steep slopes, and includes the following steps:

[0012] Obtain an image of the slope to be sprayed, obtain a three-dimensional model diagram of the area to be sprayed based on the image of the slope to be sprayed, obtain the preset spraying thickness information of the base material, and generate an optimal spraying path based on the preset spraying thickness information and the three-dimensional model diagram of the area to be sprayed;

[0013] Based on the optimal spraying path, divide the area to be sprayed into several sub-spraying areas, control the multi-legged robot to spray the base material on each sub-spraying area in sequence according to the optimal spraying path. When spraying on a certain sub-spraying area is completed, obtain the image information of the previous sub-spraying area, and identify the image information of the previous sub-spraying area to obtain a first identification result or a second identification result;

[0014] If the identification result is the first identification result, it means that there is no spraying defect in the previous sub-spraying area after spraying. At this time, continue to execute the spraying instruction to spray the next sub-spraying area;

[0015] If the identification result is the second identification result, it means that there is a spraying defect in the previous sub-spraying area after spraying. At this time, stop executing the spraying instruction, generate a repair instruction, and repair the spraying defect area of the previous sub-spraying area based on the repair instruction;

[0016] After repairing the spraying defect area of the previous sub-spraying area, continue to execute the spraying instruction to spray the next sub-spraying area.

[0017] Preferably, in a preferred embodiment of the present invention, an image of the slope to be sprayed is obtained, a three-dimensional model diagram of the area to be sprayed is obtained based on the image of the slope to be sprayed, the preset spraying thickness information of the base material is obtained, and an optimal spraying path is generated based on the preset spraying thickness information and the three-dimensional model diagram of the area to be sprayed, specifically as follows:

[0018] An image of the slope to be sprayed is obtained, the image of the slope to be sprayed is filtered and image-enhanced to obtain a processed image, and the processed image is subjected to feature matching processing to obtain a number of feature points in the area to be sprayed;

[0019] Any one of the feature points is selected as the construction origin, a three-dimensional space coordinate system is constructed based on the construction origin, and the positional relationship between the remaining feature points and the construction origin is obtained. Based on the positional relationship, the remaining feature points are imported into the three-dimensional space coordinate system;

[0020] The coordinate value information of the feature points in the three-dimensional space coordinate system is obtained, and a three-dimensional model diagram of the area to be sprayed is constructed based on the coordinate value information;

[0021] The preset spraying thickness information of the base material is obtained, and the preset spraying thickness information and the three-dimensional model diagram of the area to be sprayed are imported into the ant colony algorithm for repeated construction to generate a number of spraying paths, and the path values corresponding to each spraying path are obtained;

[0022] A first sequence list is constructed, and the path values corresponding to each spraying path are imported into the first sequence list for sorting by size. After the sorting is completed, the shortest path value is extracted from the first sequence list, the spraying path corresponding to the shortest path value is marked as the optimal spraying path, and the optimal spraying path is output.

[0023] Preferably, in a preferred embodiment of the present invention, the image information of the previous sub-spraying area is identified to obtain a first identification result or a second identification result, specifically as follows:

[0024] The spraying defect image information that may occur when the multi-legged robot works under various historical spraying environment parameters is obtained through the big data network;

[0025] A database is constructed, and the spraying defect image information that may occur when the multi-legged robot works under various historical spraying environment parameters is imported into the database to obtain a characteristic database;

[0026] The real-time spraying environment parameters of the multi-legged robot are obtained, and the similarity between the real-time spraying environment parameters and each historical spraying environment parameter is calculated through the associated information entropy metric to obtain a plurality of similarities;

[0027] Construct a second sequence list, import multiple said similarity degrees into the second sequence list for sorting by size. After the sorting is completed, extract the maximum similarity degree from the second sequence list, use the historical spraying environment parameters corresponding to the maximum similarity degree as the filtered historical spraying environment parameters, and filter the spraying defect image information in the characteristic database based on the filtered historical spraying environment parameters to obtain the filtered spraying defect image information.

[0028] Preferably, in a preferred embodiment of the present invention, the following steps are further included:

[0029] Construct an identification model based on a convolutional neural network, and import the filtered spraying defect image information into the identification model for training to obtain a trained identification model;

[0030] Import the image information of the previous sub-spraying area into the identification model, and calculate the pairing rates between the image information of the previous sub-spraying area and each filtered spraying defect image information through the grey relational analysis method to obtain multiple pairing rates;

[0031] Construct a third sequence list, import multiple said pairing rates into the third sequence list for sorting by size. After the sorting is completed, extract the maximum pairing rate from the third sequence list; compare the maximum pairing rate with a preset pairing rate to obtain a pairing rate deviation value;

[0032] Judge whether the pairing rate deviation value is greater than a preset threshold. If it is greater, generate a first identification result; if it is not greater, generate a second identification result.

[0033] Preferably, in a preferred embodiment of the present invention, generate a repair instruction, and repair the spraying defect area of the previous sub-spraying area based on the repair instruction. Specifically:

[0034] Obtain the image information of the previous sub-spraying area, construct a three-dimensional model diagram of the previous sub-spraying area based on the image information of the previous sub-spraying area, and extract the three-dimensional model diagram of the spraying defect in the sub-spraying area from the three-dimensional model diagram of the previous sub-spraying area;

[0035] Conduct finite element analysis on the three-dimensional model diagram of the spraying defect to obtain the real-time internal stress of the spraying defect, obtain the material properties of the substrate, and obtain the real-time bonding strength of the previous sub-spraying area based on the real-time internal stress and the material properties, and compare the real-time bonding strength with a preset bonding strength;

[0036] If the real-time bonding strength is greater than the preset bonding strength, obtain the volume value of the spraying defect in the previous sub-spraying area from the three-dimensional model diagram of the spraying defect;

[0037] Generate a first repair volume value based on the volume value of the spraying defect, output the first repair volume value, and control the multi-legged robot to perform spraying repair on the spraying defect in the previous sub-spraying area based on the first repair volume value.

[0038] Preferably, in a preferred embodiment of the present invention, the following steps are further included:

[0039] If the real-time bonding strength is not greater than the preset bonding strength, obtain the difference between the real-time bonding strength and the preset bonding strength to get the bonding strength difference, and determine the spraying thickness and spraying width of the base material required to repair the spraying defect based on the bonding strength difference and the material properties;

[0040] Generate a second repair volume value based on the spraying thickness, spraying width, and volume value of the spraying defect;

[0041] Perform simulated spraying repair on the spraying defect in the previous sub-spraying area based on the second repair volume value to obtain a three-dimensional model diagram of the previous sub-spraying area after simulated repair; extract from the three-dimensional model diagram of the previous sub-spraying area after simulated repair the three-dimensional model diagram of the spraying defect area in this sub-spraying area after simulated repair;

[0042] Perform finite element analysis on the three-dimensional model diagram of the spraying defect area in the sub-spraying area after simulated repair to obtain the actual internal stress after the spraying defect is repaired, and obtain the actual bonding strength of the previous sub-spraying area after simulated repair based on the actual internal stress and the material properties; compare the actual bonding strength with the preset bonding strength;

[0043] If the actual bonding strength is greater than the preset bonding strength, output the second repair volume value, and control the multi-legged robot to perform spraying repair on the spraying defect in the previous sub-spraying area based on the second repair volume value.

[0044] The present invention solves the technical defects existing in the background art, and the present invention has the following beneficial effects: This robot takes into account stability, mobility, spraying function, safety, and expandability. By adopting a multi-legged design, an efficient spraying system, and an autonomous spraying function, it can achieve vegetation restoration on high-steep slopes under harsh terrain conditions, and can create a stable structure on rocky slopes that can allow plants to grow and develop without the planting substrate being washed away and damaged. Description of the Drawings

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0046] Figure 1 It is a schematic diagram of the first three-dimensional structure of this robot;

[0047] Figure 2 It is a schematic diagram of the second three-dimensional structure of this robot;

[0048] Figure 3 It is a schematic diagram of the ground-catching component structure;

[0049] Figure 4 It is a method flowchart of a control method for a multi-legged robot for ecological reconstruction of high-steep slopes;

[0050] The description of the reference numerals is as follows: 101, bracket; 102, upper limb; 103, lower limb; 104, ground-catching component; 105, first double-axis drive motor; 106, second double-axis drive motor; 107, telescopic cylinder; 108, telescopic rod; 109, support shaft; 201, first mounting block; 202, second mounting block; 203, electric telescopic rod; 204, ground claw; 205, base material storage tank; 206, nozzle; 207, spraying manipulator; 208, spray pipe. Detailed implementation manners

[0051] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific implementation manners. These drawings are all simplified schematic diagrams, only illustrating the basic structure of the present invention in a schematic manner. Therefore, they only show the components related to the present invention. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0052] In the description of the present application, it should be understood that the orientation or positional relationships indicated by the terms "center", "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings. These are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as limiting the protection scope of the present application. In addition, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Therefore, the features defined with "first", "second", etc. may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, the meaning of "a plurality" is two or more.

[0053] In the description of the present application, it should be noted that unless otherwise clearly specified and limited, the terms "mounted", "connected", "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood through specific circumstances.

[0054] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. The preferred embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0055] As Figure 1 、 2 shown, a first aspect of the present invention discloses a multi-legged robot for high-steep slope ecological restoration, including a bracket 101. Eight groups of walking mechanisms are arranged on the bracket 101. The walking mechanism includes an upper limb 102, a lower limb 103 and a ground-gripping component 104. One end of the upper limb 102 is provided with a first double-axis drive motor 105, and the output end of the first double-axis drive motor 105 is cooperatively connected with the bracket 101. One end of the lower limb 103 is provided with a second double-axis drive motor 106, and the output end of the second double-axis drive motor 106 is cooperatively connected with the other end of the upper limb 102. The other end of the lower limb 103 is provided with a telescopic cylinder 107, the output end of the telescopic cylinder 107 is cooperatively connected with one end of a telescopic rod 108, and the other end of the telescopic rod 108 is cooperatively connected with the ground-gripping component 104.

[0056] It should be noted that this robot has eight legs and feet, which can provide good stability and grip on different types of terrains. It can more effectively disperse the weight and reduce the pressure on the ground. In addition, the gait of the robot can be adjusted according to different terrains to adapt to complex terrains such as high and steep slopes. And in order to enable the robot to move flexibly on high and steep slopes, each leg is designed with an upper limb 102 and a lower limb 103. The upper limb 102 and the lower limb 103 are driven by a double-axis drive motor, which can achieve precise control and multi-degree-of-freedom rotation. Each upper limb 102 and lower limb 103 can rotate within a certain range, providing sufficient freedom of movement for the robot. The design of the upper limb 102 and the lower limb 103 also includes an encoder for real-time monitoring of the joint angle, so that the robot control system can adjust the leg posture according to the terrain, enabling the robot to have a larger range of motion and better adaptability, and achieving high-precision angle control.

[0057] In addition, it should be noted that in order to adapt to different terrains and high and steep slopes, the legs of the robot have a certain telescopic ability. By adjusting the rotation angle of the upper limb 102 and the lower limb 103, the robot can extend and retract the leg length to adapt to different ground height differences. In addition, by adjusting the relative telescopic height of the telescopic cylinders 107 on each walking mechanism, it can adapt to irregular terrains and improve the flexibility of the robot.

[0058] As Figure 3 shown, the ground-gripping component 104 includes a support shaft 109. One end of the support shaft 109 is provided with a first mounting block 201, and the other end is provided with a second mounting block 202. A number of groups of electric telescopic rods 203 are arranged circumferentially on the first mounting block 201. A number of ground claws 204 are hinged circumferentially on the second mounting block 202, and the telescopic end of the electric telescopic rod 203 is hinged to the ground claw 204.

[0059] It should be noted that in order to maintain stability on complex terrains, the robot is designed with a ground claw 204 structure with strong grip. This helps to provide stable support and good grip on different terrains such as soft soil, slippery surfaces, and stones. The ground claw 204 is a hook-like structure. The ground claws 204 on each ground-gripping component 104 are driven by independent electric telescopic rods 203 to help the robot grasp rocks or other irregular objects on high and steep slopes, thereby improving the grip and stability.

[0060] A spraying system is provided on the bracket 101. The spraying system includes a base material storage tank 205, a nozzle 206, and a spraying manipulator 207. The nozzle 206 is provided at the end of the spraying manipulator 207. A spray pipe 208 is fixedly connected to the spraying manipulator 207. One end of the spray pipe 208 is connected to the base material storage tank 205, and the other end of the spray pipe 208 is connected to the nozzle 206. A feeding pump is provided on the spray pipe 208.

[0061] The multi-legged robot further includes a controller, a data processor, a communication antenna, and a storage battery.

[0062] It should be noted that the base material storage tank 205 is made of a light and corrosion-resistant material, such as stainless steel or plastic. The capacity of the tank body is determined according to actual application requirements and can be replaced or upgraded as needed. The spraying manipulator 207 is a six-axis linkage manipulator. The six-axis linkage manipulator is a conventional existing technology, and its structure and control principle will not be described in detail here. When spraying the base material on the slope to be sprayed, the feeding pump is controlled to start, so that the base material stored in the base material storage tank 205 is pumped along the spray pipe 208 to the nozzle by the feeding pump, and then the base material will be sprayed out of the nozzle. During this process, the six-axis linkage manipulator and the traveling mechanism can move in coordination according to a preset program to drive the nozzle to spray the base material along a preset path.

[0063] The multi-legged robot further includes a camera and several sensors. The sensors include one or more combinations of a position sensor, a temperature sensor, a wind sensor, a humidity sensor, and a wind direction sensor.

[0064] It should be noted that the spraying environment parameter data can be collected by the sensors installed on the multi-legged robot. By analyzing these data, the spraying environment parameters can be monitored in real time to adjust the spraying parameters of the spraying system, improving the spraying accuracy and reliability; and the working state of the robot can be monitored in real time to discover potential problems in advance and perform maintenance.

[0065] A thin film pressure sensor is provided on the ground claw 204, and photoelectric sensors are provided on both the upper limb 102 and the lower limb 103.

[0066] It should be noted that force photoelectric sensors and thin film pressure sensors are installed on the legs of the robot to monitor the force and position of the legs in real time. This information will be transmitted to the control system of the robot for real-time adjustment of the leg posture to adapt to different terrains.

[0067] In summary, this robot takes into account stability, mobility, spraying function, safety, and expandability. By adopting a multi-legged design, an efficient spraying system, and an autonomous spraying function, vegetation restoration on high-steep slopes can be achieved under harsh terrain conditions.

[0068] On the other hand, the present invention discloses a control method for a multi-legged robot for ecological reconstruction of high-steep slopes, which is applied to any one of the multi-legged robots for ecological reconstruction of high-steep slopes as Figure 4 shown, and includes the following steps:

[0069] S102: Obtain an image of the slope to be sprayed, obtain a three-dimensional model diagram of the area to be sprayed based on the image of the slope to be sprayed, obtain the preset spraying thickness information of the base material, and generate an optimal spraying path based on the preset spraying thickness information and the three-dimensional model diagram of the area to be sprayed;

[0070] S104: Divide the area to be sprayed into several sub-spraying areas based on the optimal spraying path, control the multi-legged robot to spray the base material on each sub-spraying area in sequence according to the optimal spraying path. When spraying on a certain sub-spraying area is completed, obtain the image information of the previous sub-spraying area, and identify the image information of the previous sub-spraying area to obtain a first identification result or a second identification result;

[0071] S106: If the identification result is the first identification result, it means that there is no spraying defect after spraying on the previous sub-spraying area. At this time, continue to execute the spraying instruction to spray the next sub-spraying area;

[0072] S108: If the identification result is the second identification result, it means that there is a spraying defect after spraying on the previous sub-spraying area. At this time, stop executing the spraying instruction, generate a repair instruction, and repair the spraying defect area of the previous sub-spraying area based on the repair instruction;

[0073] S110: After repairing the spraying defect area of the previous sub-spraying area, continue to execute the spraying instruction to spray the next sub-spraying area.

[0074] It should be noted that the basic principle of the thick-layer base material spraying technology is to lay anchor components such as galvanized wire meshes and iron plates in advance on the high-steep slopes to be repaired, configure special base materials with organic matter, compound fertilizers, adhesives, water retention agents, water, etc., and then spray the base materials evenly into the anchor component areas of the rocky slopes according to the designed thickness. Under the fixing action of the anchor components, the base materials will further solidify to form a soil structure nutrient layer conducive to the continuous growth of plants. After water and fertilizer maintenance, plant seeds germinate and grow, and natural succession occurs, so as to achieve the purposes of rapid greening of rocky slopes, ecological system restoration and slope protection. The core of the thick-layer base material spraying technology is to create a porous and stable structure on the rocky slope that can allow plants to grow and develop while the planting substrate is not washed away.

[0075] It should be noted that before spraying the substrate on the slope to be sprayed, first, the image of the slope to be sprayed is obtained through the camera on the multi-legged robot, and then the position area of the anchor (i.e., the area to be sprayed) is determined according to the image information, and then the optimal spraying path is planned. Then, the multi-legged robot is controlled to spray the substrate on the area to be sprayed of the slope to be sprayed according to the optimal spraying path. Since the area to be sprayed is a porous grid structure and the single working range of the multi-legged robot is limited, the area to be sprayed needs to be divided into several sub-spraying areas so that the multi-legged robot can spray more smoothly.

[0076] In addition, it should be noted that during the process of the multi-legged robot spraying the substrate, when a certain sub-spraying area is sprayed, the substrate in the previous sub-spraying area has solidified. At this time, it is necessary to detect the spraying defects in the previous sub-spraying area to determine whether there are spraying defects such as depressions, cracks, and fissures in the previous sub-spraying area. This is because of the influence of environmental parameter factors. After the substrate solidifies, the substrate in the previous sub-spraying area may have spraying defects such as cracks and depressions. For example, when the environmental temperature is too high, spraying cracks are likely to occur after the substrate solidifies. If there are spraying defects in the solidified substrate, the bonding strength of the solidified substrate will be weakened, and the stability of the solidified substrate will be reduced, resulting in serious cracking or even collapse of the substrate during subsequent use (especially under continuous scouring by rainwater), thus causing the substrate to lose its original function and making the ecological restoration project fail. Therefore, when a certain sub-spraying area is sprayed, it is necessary to detect the spraying defects in the previous sub-spraying area. If there are spraying defects in the previous sub-spraying area, it is necessary to control the multi-legged robot to repair the spraying defects to ensure the stability of the substrate and create a stable structure on the rocky slope that can allow plants to grow and develop without the planting substrate being scoured and damaged.

[0077] In an embodiment of the present invention, the image of the slope to be sprayed is obtained, a three-dimensional model diagram of the area to be sprayed is obtained based on the image of the slope to be sprayed, the preset spraying thickness information of the substrate is obtained, and the optimal spraying path is generated based on the preset spraying thickness information and the three-dimensional model diagram of the area to be sprayed. Specifically:

[0078] The image of the slope to be sprayed is obtained, the image of the slope to be sprayed is filtered and image-enhanced to obtain a processed image, and the processed image is subjected to feature matching processing to obtain several feature points of the area to be sprayed;

[0079] Any one of the feature points is selected as the construction origin, a three-dimensional space coordinate system is constructed based on the construction origin, and the position relationship between the remaining feature points and the construction origin is obtained. Based on the position relationship, the remaining feature points are imported into the three-dimensional space coordinate system;

[0080] Obtain the coordinate value information of the feature points in the three-dimensional space coordinate system, and construct a three-dimensional model diagram of the area to be sprayed based on the coordinate value information;

[0081] Obtain the preset spraying thickness information of the base material, import the preset spraying thickness information and the three-dimensional model diagram of the area to be sprayed into the ant colony algorithm for repeated construction, generate several spraying paths, and obtain the path values corresponding to each spraying path;

[0082] Construct a first list, import the path values corresponding to each spraying path into the first list for sorting by size. After the sorting is completed, extract the shortest path value from the first list, mark the spraying path corresponding to the shortest path value as the optimal spraying path, and output the optimal spraying path.

[0083] It should be noted that the image of the slope to be sprayed is processed by image processing methods such as median filtering and image enhancement to obtain the processed image. Then, feature matching is performed on the processed image to match the feature points of the anchor bolts pre-installed on the slope (i.e., the feature points of the area to be sprayed). And the coordinate value information of each feature point in the three-dimensional space is accurately obtained by constructing a coordinate system. Then, according to the obtained coordinate value information, a three-dimensional model diagram of the anchor bolts installed on the slope (i.e., the three-dimensional model diagram of the area to be sprayed) is constructed through three-dimensional modeling software such as SolidWorks, UG, and Proe. And the optimal spraying path is obtained according to the preset spraying thickness information and the three-dimensional model diagram of the area to be sprayed, so as to control the multi-legged robot to spray the base material on the slope according to the optimal spraying path. The preset spraying thickness information is designed and specified in advance by the designer. By this method, the spraying path matching the on-site environment can be generated according to the actual installation situation of the anchor bolts, thereby eliminating the phenomenon that the installation error of the anchor bolts affects the spraying accuracy of the multi-legged robot, realizing automatic and intelligent operation, improving the working accuracy of the multi-legged robot and the reliability of the project; it can automatically plan the optimal spraying path, and further improve the working efficiency of the multi-legged robot.

[0084] In an embodiment of the present invention, the image information of the previous sub-spraying area is identified to obtain a first identification result or a second identification result. Specifically:

[0085] Obtain the spraying defect image information that may occur when the multi-legged robot works under various historical spraying environment parameters through the big data network;

[0086] Construct a database, and import the spraying defect image information that may occur when the multi-legged robot works under various historical spraying environment parameters into the database to obtain a characteristic database;

[0087] Obtain the real-time spraying environment parameters of the multi-legged robot, calculate the similarity between the real-time spraying environment parameters and each historical spraying environment parameter through the associated information entropy metric, and obtain multiple similarities;

[0088] Construct a second sequence list, import the multiple similarities into the second sequence list for sorting by size. After the sorting is completed, extract the maximum similarity from the second sequence list, use the historical spraying environment parameter corresponding to the maximum similarity as the filtered historical spraying environment parameter, and filter the spraying defect image information in the characteristic database based on the filtered historical spraying environment parameter to obtain the filtered spraying defect image information.

[0089] It should be noted that when the multi-legged robot is performing spraying work, different environmental parameters will cause different spraying defects. For example, when the on-site environmental temperature is too high, spraying cracks will appear in the base material; when the wind force is too large, uneven spraying will occur, resulting in spraying depression defects. First, obtain the spraying defect image information that will occur when the multi-legged robot works under each historical spraying environment parameter through the big data network, so as to obtain the characteristic database. When the multi-legged robot is spraying, the real-time spraying environment parameters of the site can be obtained through the environmental parameter monitoring sensors set on the multi-legged robot, such as obtaining the on-site temperature through the temperature sensor. Then, pair and filter the real-time spraying environment parameters of the site with the historical spraying environment parameters to obtain the filtered spraying defect image information. Through this method, the real-time spraying environment parameters of the multi-legged robot at the real-time work site can be matched with the historical spraying environment parameters, so as to match the historical spraying environment parameter with the highest similarity to the real-time spraying environment parameter. Then, through the historical spraying environment parameter with the highest similarity, the spraying defects that will occur when the multi-legged robot is spraying at the current work site can be determined, and the corresponding spraying defect image information can be obtained. On the one hand, it can improve the recognition effect of the multi-legged robot on the spraying defects of the on-site base material, and on the other hand, it can improve the recognition speed when the multi-legged robot recognizes the spraying defects of the on-site base material. For example, if the spraying site environment temperature of the multi-legged robot is too high and the on-site wind force is not high, the possible spraying defect that may occur after the base material solidifies is spraying cracks, and it is almost impossible to have spraying depressions. Therefore, at this time, only need to screen out all the spraying defect images of spraying cracks in the characteristic database as the filtered spraying defect image information. In this way, the image matching amount of the next step can be reduced, thereby improving the matching speed, reducing the computing amount of the system, and improving the robustness of the system.

[0090] In an embodiment of the present invention, the following steps are further included:

[0091] Construct an identification model based on a convolutional neural network, and import the filtered image information of the spraying defect into the identification model for training to obtain a trained identification model;

[0092] Import the image information of the previous sub-spraying area into the identification model, and calculate the pairing rate between the image information of the previous sub-spraying area and the image information of each filtered spraying defect through the grey relational analysis method to obtain multiple pairing rates;

[0093] Construct a third sequence list, import the multiple pairing rates into the third sequence list for sorting by size, and after the sorting is completed, extract the maximum pairing rate from the third sequence list; compare the maximum pairing rate with a preset pairing rate to obtain a pairing rate deviation value;

[0094] Judge whether the pairing rate deviation value is greater than a preset threshold. If it is greater, generate a first identification result; if it is not greater, generate a second identification result.

[0095] It should be noted that when the pairing rate deviation value is greater than the preset threshold, it means that there is no spraying defect after spraying in the previous sub-spraying area. At this time, continue to execute the spraying instruction to spray the next sub-spraying area, and generate a first identification result at this time; when the pairing rate deviation value is not greater than the preset threshold, it means that the image information of the previous sub-spraying area is highly similar to a certain spraying defect image in the identification model, indicating that there is a spraying defect after spraying in the previous sub-spraying area. At this time, stop executing the spraying instruction and generate a repair instruction, and repair the spraying defect area of the previous sub-spraying area based on the repair instruction. Through this method, the matching speed of image matching can be improved, the system operation amount can be reduced, and it can be quickly matched and identified whether there is a spraying defect in the base material after spraying.

[0096] In an embodiment of the present invention, generating a repair instruction and repairing the spraying defect area of the previous sub-spraying area based on the repair instruction specifically includes:

[0097] Obtain the image information of the previous sub-spraying area, construct a three-dimensional model diagram of the previous sub-spraying area based on the image information of the previous sub-spraying area, and extract the three-dimensional model diagram of the spraying defect in the sub-spraying area from the three-dimensional model diagram of the previous sub-spraying area;

[0098] Conduct finite element analysis on the three-dimensional model diagram of the spraying defect to obtain the real-time internal stress of the spraying defect, obtain the material properties of the base material, obtain the real-time bonding strength of the previous sub-spraying area based on the real-time internal stress and the material properties, and compare the real-time bonding strength with the preset bonding strength;

[0099] If the real-time bonding strength is greater than the preset bonding strength, obtain the volume value of the spraying defect in the previous sub-spraying area from the three-dimensional model diagram of the spraying defect;

[0100] Generate a first repair volume value based on the volume value of the spraying defect, output the first repair volume value, and control the multi-legged robot to perform spraying repair on the spraying defect in the previous sub-spraying area based on the first repair volume value.

[0101] It should be noted that if a spraying defect is identified in the previous sub-spraying area, the spraying defect needs to be repaired at this time. Specifically, obtain the image information of the previous sub-spraying area, perform feature matching on the image information to obtain multiple feature matching points and their corresponding coordinate information, then construct a three-dimensional model diagram of the previous sub-spraying area through three-dimensional modeling software, and extract the three-dimensional model diagram of the spraying defect from the three-dimensional model diagram, and then perform finite element analysis on the three-dimensional model diagram of the spraying defect to obtain the real-time internal stress of the spraying defect, so as to obtain the real-time bonding strength of the previous sub-spraying area according to the real-time internal stress and the material properties, where the material properties are the composition formula materials of the base material and the dosage of each formula material. The preset bonding strength is the strength value obtained when there is a spraying defect and the defect concentration of the spraying defect is within the allowable range, and this strength value is determined and analyzed in advance by the designer. If the real-time bonding strength is greater than the preset bonding strength, it can be explained at this time that the internal stress value of the spraying defect existing in this sub-spraying area is not large, the spraying defect existing in this sub-spraying area has little influence on the bonding strength of the base material, and the bonding strength of the base material is also greater than the preset bonding strength, indicating that the stability of the base material in this sub-spraying area is relatively high, indicating that the base material in this sub-spraying area will not spontaneously cause a collapse, and the possibility of its occurrence of collapse is relatively low. At this time, preventive repair is performed on the spraying defect existing in this sub-spraying area. At this time, only need to fill the spraying defect existing in this sub-spraying area to achieve the role of preventive repair, and further avoid the spraying defect existing in this sub-spraying area from further expanding under the scouring of subsequent rainwater, resulting in the instability of the base material and the occurrence of a collapse phenomenon. Through this method, on the premise of determining that the stability of the base material meets the preset requirements, the usage amount of the base material during repair can be minimized as much as possible, the resource utilization rate can be improved, and the area where defects exist in the base material can be prevented from being further scoured and corroded, and there is no need to repair it later, which simplifies the repair process and reduces the later repair cost.

[0102] In an embodiment of the present invention, the following steps are further included:

[0103] If the real-time bonding strength is not greater than the preset bonding strength, obtain the difference between the real-time bonding strength and the preset bonding strength to get the bonding strength difference, and determine the spraying thickness and spraying width of the base material required to repair the spraying defect based on the bonding strength difference and the material properties;

[0104] Generate a second repair volume value based on the spraying thickness, spraying width, and the volume value of the spraying defect;

[0105] Perform simulated spraying repair on the spraying defect in the previous sub-spraying area based on the second repair volume value to obtain a three-dimensional model diagram of the previous sub-spraying area after simulated repair; extract the three-dimensional model diagram of the spraying defect area in this sub-spraying area after simulated repair from the three-dimensional model diagram after simulated repair;

[0106] Perform finite element analysis on the three-dimensional model diagram of the spraying defect area in the sub-spraying area after simulated repair to obtain the actual internal stress after the spraying defect is repaired, and obtain the actual bonding strength of the previous sub-spraying area after simulated repair based on the actual internal stress and the material properties; compare the actual bonding strength with the preset bonding strength;

[0107] If the actual bonding strength is greater than the preset bonding strength, output the second repair volume value, and control the multi-legged robot to perform spraying repair on the spraying defect in the previous sub-spraying area based on the second repair volume value.

[0108] It should be noted that if the real-time bonding strength is not greater than the preset bonding strength, it can be explained at this time that the internal stress value of the spraying defect existing in this sub-spraying area is too large, and the spraying defect existing in this sub-spraying area has a greater impact on the bonding strength of the base material, indicating that the stability of the base material in this sub-spraying area is poor, indicating that the base material in this sub-spraying area will spontaneously cause a collapse, and the possibility of its occurrence of collapse is relatively high. At this time, a substantial repair is carried out on the spraying defect existing in this sub-spraying area. At this time, not only the spraying defect existing in this sub-spraying area needs to be filled, but also the base material for spraying repair needs to be sprayed in the area near the spraying defect to improve the bonding strength of the base material near the spraying defect, so as to avoid the further expansion and cracking of the spraying defect due to excessive internal stress, thereby avoiding the collapse of the base material, and thus achieving the effect of substantial repair.

[0109] It should be noted that when there is a spraying defect in a certain sub-spraying area, the effective cross-sectional area of the substrate at this area will change. And under the action of the internal stress of the spraying defect, it will cause a large difference in the bonding strength between the substrate and the preset bonding strength. Based on this bonding strength and the material properties of the substrate, the spraying thickness and spraying width of the substrate required to repair the spraying defect are determined. For example, the greater the difference in bonding strength, the greater the spraying thickness and spraying width of the substrate required to repair the spraying defect. Then, a second repair volume is generated based on the spraying thickness, spraying width, and the volume value of the spraying defect. After determining the second repair volume, a three-dimensional simulation software is used to simulate and spray the spraying defect in the sub-spraying area, so as to simulate a model diagram after spraying the spraying defect in this sub-spraying area through the three-dimensional simulation software, and analyze the actual bonding strength of this sub-spraying area after simulation repair from the three-dimensional simulation software. If the actual bonding strength is greater than the preset bonding strength, it means that after spraying the spraying defect in this sub-spraying area, the bonding strength of this area is qualified and the stability of this area after spraying repair is qualified. At this time, the second repair volume value is output, and based on the second repair volume value, a multi-legged robot is controlled to spray and repair the spraying defect in the previous sub-spraying area. If the actual bonding strength is not greater than the preset bonding strength, it means that the difference between the actual bonding strength and the preset bonding strength is calculated at this time, and then the value of the additional repair volume is calculated to ensure that after repairing the spraying defect in this sub-spraying area, the bonding strength of the substrate is greater than the preset bonding strength to ensure the stability of the substrate. To sum up, through this method, the volume value of the substrate required for spraying and repairing defects can be automatically generated to ensure the stability of the substrate, so as to create a stable structure on the rocky slope that can allow plants to grow and develop while the planting substrate is not washed away and damaged.

[0110] In addition, the control method of the multi-legged robot for ecological restoration of high-steep slopes further includes the following steps:

[0111] Construct an evaluation system for the repaired substrate;

[0112] Obtain the three-dimensional model diagram of the sprayed defect area in the currently repaired sub-spraying area after simulation repair, and determine the evaluation index based on the three-dimensional model diagram of the sprayed defect area in the sub-spraying area after simulation repair;

[0113] Obtain the image information of the repaired substrate, construct the three-dimensional model diagram of the repaired substrate based on the image information of the repaired substrate, and use the three-dimensional model diagram of the repaired substrate as the evaluation object;

[0114] Import the evaluation object and evaluation indicators into the evaluation system, obtain the evaluation scores of the evaluation object and evaluation indicators through the analytic hierarchy process, and obtain the weight value of the evaluation object based on the evaluation scores;

[0115] Judge whether the weight value is within the preset weight value range; if the weight value is within the preset weight value range, continue to execute the spraying instruction to spray the next sub-spraying area; if not, mark the area corresponding to the repaired base material as an abnormal area, and analyze the faulty equipment based on the abnormal area.

[0116] It should be noted that if the weight value is within the preset weight value range, it indicates that the repair effect of the spraying defect is good, and at this time, it indicates that the repair of the spraying defect is successful; if the weight value is not within the preset weight value range, it indicates that the repair effect of the spraying defect is poor, and there are abnormal phenomena such as deformation, cracking, and non-compliance with dimensions in the repaired area, indicating that the multi-legged robot may have malfunctioned. Through this method, the repair effect of the repaired spraying defect is evaluated to ensure the reliability of the base material after repair.

[0117] In addition, analyzing the faulty equipment based on the abnormal area is specifically as follows:

[0118] If the weight value is not within the preset weight value range, obtain the repair working parameters when the multi-legged robot sprays and repairs the spraying defect in the sub-spraying area;

[0119] Obtain the three-dimensional model diagram of the repaired base material, associate the sub-devices of the multi-legged robot based on the three-dimensional model diagram of the repaired base material, and generate relevant text;

[0120] Obtain the correlation degree between the relevant text and the repair working parameters through the cross-impact analysis method, and obtain the sub-devices that may malfunction when the multi-legged robot sprays and repairs the spraying defect in the sub-spraying area based on the correlation degree;

[0121] Import the sub-devices that may malfunction into the Markov model for random deduction to obtain the finally malfunctioned sub-devices, generate a fault report based on the finally malfunctioned sub-devices, and output the fault report.

[0122] It should be noted that after the spraying defect is repaired by the multi-legged robot, there are abnormal phenomena such as deformation, cracking, and non-compliance with dimensions in the repaired area. At this time, it can be explained that the sub-devices of the multi-legged robot have malfunctioned. If there is a deformation phenomenon, it indicates that the nozzle may have malfunctioned. Through this method, the sub-devices that malfunction can be quickly analyzed according to the repair abnormal situation.

[0123] In addition, the control method of the multi-legged robot for ecological reconstruction of high-steep slopes further includes the following steps:

[0124] Obtain the power loss rate per unit time of the multi-legged robot under different working environment combinations through the big data network;

[0125] Construct a power loss prediction model based on the deep learning network, and import the power loss rate per unit time of the multi-legged robot under different working environment combinations into the power loss prediction model for training to obtain a trained power loss prediction model;

[0126] After the multi-legged robot finishes spraying a certain slope to be sprayed, obtain the position information of the next slope to be sprayed, and obtain the current position information of the multi-legged robot;

[0127] Import the position information of the next slope to be sprayed and the current position information of the multi-legged robot into the particle swarm algorithm for repeated construction to obtain multiple moving paths, and obtain the environmental parameter information corresponding to the multiple moving paths;

[0128] Import the environmental parameter information corresponding to the multiple moving paths into the trained power loss prediction model to obtain the power loss amounts corresponding to the multiple moving paths;

[0129] Construct a sorting table, import the power loss amounts corresponding to the multiple moving paths into the sorting table for sorting to obtain the minimum power loss amount, obtain the moving path corresponding to the minimum power loss amount, mark the moving path corresponding to the minimum power loss amount as the optimal moving path, and output the optimal moving path to control the multi-legged robot to move to the next slope to be sprayed according to the optimal moving path.

[0130] It should be noted that the power loss rates of the multi-legged robot at different temperatures are inconsistent. For example, the power loss rate of the multi-legged robot in a low-temperature environment is relatively large. After the multi-legged robot finishes spraying a certain slope to be sprayed, the multi-legged robot needs to move to the next slope to be sprayed. Through this method, the moving path with the lowest energy consumption can be planned to increase the single working time of the multi-legged robot and improve the working efficiency.

[0131] The above is inspired by the ideal embodiments of the present invention, and the description is relatively specific and detailed. However, it should not be construed as a limitation to the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present invention, several deformations and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent should be subject to the appended claims.

Claims

1. A control method for a multi-legged robot used for ecological reconstruction of high-steep slopes, characterized in that: The multi-legged robot includes a bracket, on which eight groups of walking mechanisms are arranged. Each walking mechanism includes an upper limb, a lower limb and a ground-gripping component. One end of the upper limb is provided with a first double-axis drive motor, and the output end of the first double-axis drive motor is connected to the bracket in a matching manner. One end of the lower limb is provided with a second double-axis drive motor, and the output end of the second double-axis drive motor is connected to the other end of the upper limb in a matching manner. The other end of the lower limb is provided with a telescopic cylinder, and the output end of the telescopic cylinder is connected to one end of a telescopic rod in a matching manner. The other end of the telescopic rod is connected to the ground-gripping component in a matching manner; A spraying system is arranged on the bracket. The spraying system includes a base material storage tank, a nozzle and a spraying manipulator. The nozzle is arranged at the end of the spraying manipulator. A spray pipe is fixedly connected to the spraying manipulator, and one end of the spray pipe is connected to the base material storage tank, and the other end of the spray pipe is connected to the nozzle. A feeding pump is arranged on the spray pipe; The multi-legged robot further includes a controller, a data processor, a communication antenna and a storage battery; The control method includes: Obtaining an image of the slope to be sprayed, obtaining a three-dimensional model diagram of the area to be sprayed based on the image of the slope to be sprayed, obtaining the preset spraying thickness information of the base material, and generating an optimal spraying path based on the preset spraying thickness information and the three-dimensional model diagram of the area to be sprayed; Dividing the area to be sprayed into several sub-spraying areas based on the optimal spraying path, controlling the multi-legged robot to spray the base material on each sub-spraying area in turn according to the optimal spraying path. When a certain sub-spraying area is sprayed, obtaining the image information of the previous sub-spraying area, and identifying the image information of the previous sub-spraying area to obtain a first identification result or a second identification result; If the identification result is the first identification result, it indicates that there is no spraying defect in the previous sub-spraying area after spraying. At this time, continue to execute the spraying instruction to spray the next sub-spraying area; If the identification result is the second identification result, it indicates that there is a spraying defect in the previous sub-spraying area after spraying. At this time, stop executing the spraying instruction and generate a repair instruction, and repair the spraying defect area of the previous sub-spraying area based on the repair instruction; After the spraying defect area of the previous sub-spraying area is repaired, continue to execute the spraying instruction to spray the next sub-spraying area.

2. The control method of a multi-legged robot for ecological reconstruction of high-steep slopes according to claim 1, characterized in that, The ground-gripping component includes a support shaft. One end of the support shaft is provided with a first mounting block, and the other end is provided with a second mounting block. A plurality of groups of electric telescopic rods are arranged along the circumference of the first mounting block. A plurality of ground claws are hinged along the circumference of the second mounting block, and the telescopic ends of the electric telescopic rods are hinged to the ground claws.

3. The control method of a multi-legged robot for ecological reconstruction of high-steep slopes according to claim 1, characterized in that, The multi-legged robot further includes a camera and several sensors. The sensors include one or more combinations of a position sensor, a temperature sensor, a wind sensor, a humidity sensor, and a wind direction sensor.

4. The control method of a multi-legged robot for ecological reconstruction of high-steep slopes according to claim 2, characterized in that, A thin-film pressure sensor is arranged on the ground claw, and photoelectric sensors are arranged on both the upper limb and the lower limb.

5. The control method of a multi-legged robot for ecological restoration of high-steep slopes according to claim 1, characterized in that, Obtain an image of the slope to be sprayed, obtain a 3D model diagram of the area to be sprayed based on the image of the slope to be sprayed, obtain the preset spraying thickness information of the substrate, and generate an optimal spraying path based on the preset spraying thickness information and the 3D model diagram of the area to be sprayed. Specifically: Obtain an image of the slope to be sprayed, perform filtering and image enhancement processing on the image of the slope to be sprayed to obtain a processed image, and perform feature matching processing on the processed image to obtain several feature points of the area to be sprayed; Select any one of the feature points as the construction origin, construct a three-dimensional space coordinate system based on the construction origin, obtain the positional relationship between the remaining feature points and the construction origin, and import the remaining feature points into the three-dimensional space coordinate system based on the positional relationship; Obtain the coordinate value information of the feature points in the three-dimensional space coordinate system, and construct a 3D model diagram of the area to be sprayed based on the coordinate value information; Obtain the preset spraying thickness information of the substrate, import the preset spraying thickness information and the 3D model diagram of the area to be sprayed into the ant colony algorithm for repeated construction, generate several spraying paths, and obtain the path values corresponding to each spraying path; Construct a first sequence list, import the path values corresponding to each spraying path into the first sequence list for size sorting. After the sorting is completed, extract the shortest path value from the first sequence list, mark the spraying path corresponding to the shortest path value as the optimal spraying path, and output the optimal spraying path.

6. The control method of a multi-legged robot for ecological restoration of high-steep slopes according to claim 1, characterized in that, Identify the image information of the previous sub-spraying area to obtain a first identification result or a second identification result. Specifically: Obtain the spraying defect image information that may occur when the multi-legged robot works under various historical spraying environment parameters through the big data network; Construct a database, and import the spraying defect image information that may occur when the multi-legged robot works under various historical spraying environment parameters into the database to obtain a characteristic database; Obtain the real-time spraying environment parameters of the multi-legged robot, calculate the similarity between the real-time spraying environment parameters and each historical spraying environment parameter through the associated information entropy metric to obtain multiple similarities; Construct a second sequence list, import the multiple similarities into the second sequence list for size sorting. After the sorting is completed, extract the maximum similarity from the second sequence list, use the historical spraying environment parameter corresponding to the maximum similarity as the filtered historical spraying environment parameter, and filter the spraying defect image information in the characteristic database based on the filtered historical spraying environment parameter to obtain the filtered spraying defect image information.

7. The control method of a multi-legged robot for ecological reconstruction of high-steep slopes according to claim 6, characterized in that, It also includes the following steps: Construct an identification model based on the convolutional neural network, and import the filtered spraying defect image information into the identification model for training to obtain a trained identification model; Import the image information of the previous sub-spraying area into the identification model, and calculate the pairing rate between the image information of the previous sub-spraying area and each filtered spraying defect image information through the grey relational analysis method to obtain multiple pairing rates; Construct a third sequence list, import multiple said pairing rates into the third sequence list for sorting by size, and after the sorting is completed, extract the maximum pairing rate from the third sequence list; compare the maximum pairing rate with a preset pairing rate to obtain a pairing rate deviation value; Judge whether the pairing rate deviation value is greater than a preset threshold, and if it is greater, generate a first recognition result; If it is not greater, generate a second recognition result.

8. The control method of a multi-legged robot for ecological reconstruction of high-steep slopes according to claim 1, characterized in that, Generate a repair instruction, and repair the spraying defect area of the previous sub-spraying area based on the repair instruction. Specifically: Obtain the image information of the previous sub-spraying area, construct a three-dimensional model diagram of the previous sub-spraying area based on the image information of the previous sub-spraying area, and extract the three-dimensional model diagram of the spraying defect in the sub-spraying area from the three-dimensional model diagram of the previous sub-spraying area; Conduct a finite element analysis on the three-dimensional model diagram of the spraying defect to obtain the real-time internal stress of the spraying defect, obtain the material properties of the substrate, and obtain the real-time bonding strength of the previous sub-spraying area based on the real-time internal stress and the material properties, and compare the real-time bonding strength with a preset bonding strength; If the real-time bonding strength is greater than the preset bonding strength, obtain the volume value of the spraying defect in the previous sub-spraying area from the three-dimensional model diagram of the spraying defect; Generate a first repair volume value based on the volume value of the spraying defect, output the first repair volume value, and control a multi-legged robot to perform spraying repair on the spraying defect in the previous sub-spraying area based on the first repair volume value.

9. The control method of a multi-legged robot for ecological reconstruction of high-steep slopes according to claim 8, wherein, It further includes the following steps: If the real-time bonding strength is not greater than the preset bonding strength, obtain the difference between the real-time bonding strength and the preset bonding strength to obtain a bonding strength difference, and determine the spraying thickness and spraying width of the substrate required to repair the spraying defect based on the bonding strength difference and the material properties; Generate a second repair volume value based on the spraying thickness, spraying width, and the volume value of the spraying defect; Perform simulated spraying repair on the spraying defect in the previous sub-spraying area based on the second repair volume value to obtain a three-dimensional model diagram of the previous sub-spraying area after simulated repair; Extract the three-dimensional model diagram of the spraying defect area in the sub-spraying area after simulated repair from the three-dimensional model diagram after simulated repair; Conduct a finite element analysis on the three-dimensional model diagram of the spraying defect area in the sub-spraying area after simulated repair to obtain the actual internal stress after the spraying defect is repaired, and obtain the actual bonding strength of the previous sub-spraying area after simulated repair based on the actual internal stress and the material properties; Compare the actual bonding strength with the preset bonding strength; If the actual bonding strength is greater than the preset bonding strength, output the second repair volume value, and control a multi-legged robot to perform spraying repair on the spraying defect in the previous sub-spraying area based on the second repair volume value.

Images