Intelligent remote control method and system for crane

Abstract

The invention relates to the technical field of crane control, in particular to an intelligent remote control method and system for a crane, and the method comprises the steps: obtaining a road image in front of the crane, calculating the fluctuation vector of each pixel point in the road image, and obtaining a road bump map; inputting the initial control instruction, the road bump map and the hoisting state into the trained evaluation model to obtain a shaking degree, constructing control loss, and updating the initial control instruction by using a gradient descent method; and updating the initial control instruction for multiple times until the control loss is smaller than a preset value to obtain a target control instruction, and controlling the crane according to the target control instruction. According to the technical scheme, accurate control over the crane can be achieved in combination with the road condition of the driving path.

Description

Technical Field

[0001] The present application relates to the field of crane control technology, and in particular to an intelligent remote control method and system for a crane. Background Art

[0002] As a tool for transporting goods, cranes have played a huge role in industrial construction and other fields. During the operation of the crane, it is often necessary to lift heavy objects and move them to a designated location. During the movement of the crane, the lifted heavy objects will swing, which will not only affect the precise placement of the lifted heavy objects during the lifting process, but also pose safety hazards such as collision and falling. Therefore, there are high requirements for suppressing the swing of the lifted heavy objects during the movement of the crane.

[0003] At present, a patent application document with application publication number CN118495359A discloses a crane motion control method, device, equipment and readable storage medium, wherein the method includes: when receiving an operation task, dividing the crane's travel path into multiple sub-paths according to the trolley position, the truck position, the target position and the protection area; under anti-sway conditions, based on the S-curve speed control principle, the anti-sway parameters of the trolley and the truck are calculated according to the trolley position, the truck position and the end point of the current sub-path; the trolley and the truck are controlled to move according to the anti-sway parameters of the trolley and the truck; during the movement process, determining whether to merge the sub-paths according to the conditions of each sub-path and the conditions of the trolley and the truck reaching the end point; if merged, recalculating the anti-sway parameters according to the merged path, and adjusting the movement of the trolley and / or the truck according to the recalculated anti-sway parameters.

[0004] The above method uses the S-curve speed control principle to determine the anti-sway parameters, and controls the driving state of the crane on the driving path according to the anti-sway parameters. However, the road conditions of the driving path directly affect the driving state of the crane. If the road conditions of the driving path are ignored, precise control of the crane cannot be achieved. Summary of the invention

[0005] In order to solve the technical problem that it is impossible to achieve precise control of a crane, the present application provides an intelligent remote control method and system for a crane, which can achieve precise control of the crane in combination with the road conditions of the driving path.

[0006] In a first aspect, the present application provides an intelligent remote control method for a crane, the control method comprising: obtaining a road image in front of the crane, calculating the pixel value difference between a pixel point in the road image and each neighboring pixel point, and taking the maximum pixel value difference as the modulus length, constructing an undulation vector pointing from the pixel point to the neighboring pixel point corresponding to the maximum pixel value difference, and obtaining a road bump map; inputting the initial control instruction, the road bump map and the lifting state into a trained evaluation model to obtain the degree of shaking, constructing the control loss, and using the gradient descent method to update the initial control instruction, the initial control instruction including the driving direction and the driving speed, and the lifting state. The states include lifting height and lifting weight; the control loss is positively correlated with the degree of shaking and negatively correlated with the driving speed; the initial control instruction is updated multiple times until the target control instruction is obtained when the control loss is less than a preset value, and the crane is controlled with the target control instruction; the training method of the evaluation model includes: deploying an inertial sensor on the crane hook; collecting a road bump map and control instructions executed under the lifting state to obtain training samples, and using the indication of the inertial sensor after executing the control instruction as a shaking label; inputting the training sample into the evaluation model, and training the evaluation model based on the mean square error loss function between the output result and the shaking label.

[0007] During the crane operation, the road image in front of the crane is collected, the pixel value difference between the pixel point in the road image and each neighboring pixel point is calculated, and the maximum pixel value difference is used as the modulus length to construct an undulation vector from the pixel point to the neighboring pixel point corresponding to the maximum pixel value difference, and a road bump map is obtained. The road bump map can accurately reflect the changes and change directions of road characteristics at various positions in the road in front of the crane, and provide a data basis for the subsequent precise control of the crane; the initial control instructions, the road bump map and the lifting state are input into the trained evaluation model to obtain the degree of shaking, where the initial control instructions include the driving speed and the driving direction; the control loss is constructed based on the degree of shaking and the driving speed, and the control loss is positively correlated with the degree of shaking and negatively correlated with the driving speed; the initial control instructions are updated using the gradient descent method until the control loss is less than the preset value to obtain the target control instruction, and the crane is controlled by the target control instruction, while ensuring the stability of the hoisted object, the working efficiency of the crane is guaranteed, and the precise control of the crane is achieved.

[0008] Preferably, the road image is a grayscale image or a depth image.

[0009] Preferably, before obtaining the road bump map, the control method further comprises: calculating the mode of pixel values ​​of each pixel point in the road image; and subtracting the mode of pixel values ​​from the pixel value of each pixel point in the road image to obtain a preprocessed road image.

[0010] The mode of the pixel value is the pixel value of the flat area in the road in front of the crane. The pixel value in the road image after preprocessing is the difference between each pixel point and the pixel value of the flat area, which enhances the road undulation characteristics and improves the accuracy of the road bump map.

[0011] Preferably, the evaluation model includes a convolution sub-model and a regression sub-model, the convolution sub-model is used to extract image features of the road bump map, and the regression sub-model is used to regress the multidimensional data consisting of image features, initial control instructions and lifting status to the degree of shaking.

[0012] Preferably, the control loss is: , For the degree of shaking, The maximum safe driving speed is is the driving speed in the initial control instruction.

[0013] The control loss takes into account the degree of shaking and the driving speed in the initial control command. The smaller it is, the more stable the hoisted object is. The smaller it is, the closer the driving speed in the initial control instruction is to the maximum safe driving speed, that is, the higher the working efficiency of the crane is and the smaller the control loss is; the control loss can reflect the stability of the hoisted object and the working efficiency of the crane at the same time.

[0014] Preferably, the updating of the initial control instruction by using the gradient descent method comprises: performing back propagation on the evaluation model to obtain the gradient value of each control parameter in the initial control instruction; The update process is: , is the control parameter before updating , is the update coefficient, For control parameters The gradient value of is the updated control parameter .

[0015] Preferably, Update coefficient in update for: , is the initial update coefficient, and Respectively Second and The control loss of the update, is the minimum update coefficient, is the hyperbolic tangent function.

[0016] Too large an update coefficient will result in the updated control parameters Skip the global optimal solution and make the updated control parameters It is impossible to achieve the best control effect; if the update coefficient is too small, the control parameters will be The update speed is slow and the real-time control cannot be guaranteed. Therefore, the update coefficient is adaptively adjusted according to the change of control loss during the update process. The value of can improve the control effect while ensuring the real-time control.

[0017] Preferably, after controlling the crane with the target control instruction, the control method further includes: in response to the indication of the inertial sensor being greater than the indication threshold, taking the road bump map, the lifting state and the target control instruction as a group of new training samples, and taking the indication of the inertial sensor as the shaking label of the new training samples; and training the evaluation model based on the new training samples.

[0018] Whether the evaluation model can accurately predict the degree of shaking of the hoisted object directly affects the control effect of the target control instruction; after controlling the crane with the target control instruction, if the indication of the inertial sensor is greater than the indication threshold, it means that the target control instruction cannot achieve the expected control effect. At this time, the evaluation model is further trained to ensure the control effect of the target control instruction at all times.

[0019] In a second aspect of the present application, there is also provided an intelligent remote control system for a crane, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an intelligent remote control method for a crane according to the first aspect of the present application is implemented.

[0020] The technical solution of this application has the following beneficial technical effects: During the crane operation, the road image in front of the crane is collected, the pixel value difference between the pixel point in the road image and each neighboring pixel point is calculated, and the maximum pixel value difference is used as the modulus length to construct an undulation vector from the pixel point to the neighboring pixel point corresponding to the maximum pixel value difference, and a road bump map is obtained. The road bump map can accurately reflect the changes and change directions of road characteristics at various positions in the road in front of the crane, and provide a data basis for the subsequent precise control of the crane; the initial control instructions, the road bump map and the lifting state are input into the trained evaluation model to obtain the degree of shaking, where the initial control instructions include the driving speed and the driving direction; the control loss is constructed based on the degree of shaking and the driving speed, and the control loss is positively correlated with the degree of shaking and negatively correlated with the driving speed; the initial control instructions are updated using the gradient descent method until the control loss is less than the preset value to obtain the target control instruction, and the crane is controlled by the target control instruction, while ensuring the stability of the hoisted object, the working efficiency of the crane is guaranteed, and the precise control of the crane is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easy to understand. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 is a flow chart of an intelligent remote control method for a crane according to an embodiment of the present application; Figure 2 It is a structural block diagram of an intelligent remote control system for a crane according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0023] It should be understood that when the terms "first", "second", etc. are used in the claims, specification and drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0024] According to a first aspect of the present application, the present application provides an intelligent remote control method for a crane. Figure 1 FIG. 1 is a flow chart of an intelligent remote control method for a crane according to an embodiment of the present application. Figure 1 As shown, the intelligent remote control method of the crane includes steps S101 to S103, which are described in detail below.

[0025] S101, obtaining a road image in front of the crane, calculating the pixel value difference between a pixel point in the road image and each neighboring pixel point, and using the maximum pixel value difference as the modulus length, constructing an undulation vector pointing from the pixel point to the neighboring pixel point corresponding to the maximum pixel value difference, and obtaining a road bump map.

[0026] In one embodiment, an image acquisition device is deployed in front of the crane to acquire the road image in front of the crane. The image acquisition device may be an RGB camera or a depth camera; when the image acquisition device is an RGB camera, the road image is a grayscale image, and the pixel value of each pixel in the road image is a grayscale value; when the image acquisition device is a depth camera, the road image is a depth image, and the pixel value of each pixel in the road image is a depth value. In other words, the road image is a grayscale image or a depth image.

[0027] The pixel value of each pixel point in the road image can reflect the road information, and the pixel value difference between the pixel points can reflect the change of the road information, and further reflect the degree of bumpiness at each position in the road. In order to accurately measure the impact of the bumpiness at each position in the road in front of the crane on the driving state of the crane, before obtaining the road bumpiness map, the control method further includes: calculating the mode of the pixel values ​​of each pixel point in the road image; subtracting the mode of the pixel value from the pixel value of each pixel point in the road image to obtain a preprocessed road image.

[0028] The mode of the pixel value is the pixel value of the flat area in the road in front of the crane, and the pixel value in the road image after preprocessing is the difference between each pixel point and the pixel value of the flat area, which enhances the road undulation characteristics.

[0029] For the pixel points in the road image , whose neighborhood pixels are pixel points centered, and other pixels within a rectangular frame of a preset size, where the preset size can be 3×3, 5×5, or 7×7, and this application does not limit this. Calculate pixel points The pixel value difference with each neighboring pixel point, pixel point With neighboring pixels The pixel value difference satisfy , Pixel The pixel value of Pixel Neighborhood pixels Pixel value; draw from pixel point The vector pointing to the neighborhood pixel point corresponding to the maximum pixel value difference, and the vector modulus length is the maximum pixel value difference, and the pixel point is obtained. The fluctuation vector of the pixel point The maximum change with each neighborhood pixel, and the direction of change.

[0030] In this way, calculating the fluctuation vector of each pixel point in the road image can accurately reflect the changes and directions of road characteristics at each location in the road in front of the crane, providing a data basis for the subsequent precise control of the crane.

[0031] S102, input the initial control instructions, road bump map and lifting status into the trained evaluation model to obtain the degree of shaking, construct the control loss, and use the gradient descent method to update the initial control instructions. The initial control instructions include the driving direction and the driving speed, and the lifting status includes the lifting height and the lifting weight. The control loss is positively correlated with the degree of shaking and negatively correlated with the driving speed.

[0032] In one embodiment, the evaluation model is used to evaluate the shaking degree of the hoisted object during the travel of the crane. The input of the evaluation model is the initial control instruction, the road bump map and the hoisting state, and the output is the shaking degree of the hoisted object. Specifically, the evaluation model includes a convolution sub-model and a regression sub-model. The convolution sub-model is used to extract the image features of the road bump map, and the regression sub-model is used to regress the multi-dimensional data composed of the image features, the initial control instruction and the hoisting state to the shaking degree.

[0033] Among them, the convolution sub-model can adopt existing convolutional neural networks such as ResNet, ShuffleNet, VGGNet, etc.; the regression sub-model can adopt a fully connected neural network.

[0034] In order to enable the evaluation model to accurately predict the degree of sway of the hoisted object, it is necessary to collect training samples to train the evaluation model. Specifically, the training method of the evaluation model includes: deploying an inertial sensor on the crane hook; collecting road bump maps and control instructions executed in the hoisting state to obtain training samples, and using the readings of the inertial sensor after executing the control instructions as sway labels; inputting the training samples into the evaluation model, and training the evaluation model based on the mean square error loss function between the output results and the sway labels.

[0035] Among them, the inertial sensor can detect the acceleration and angular velocity of the hook, thereby determining the movement of the hook. The larger the value of the inertial sensor, the greater the acceleration and angular velocity of the hook, and the greater the degree of shaking of the hoisted object on the hook.

[0036] During the historical operation of the crane, the lifting status of the crane, the road bump map of the road ahead and the control instructions executed by the crane are collected to obtain a group of training samples. After the crane executes the control instruction, the reading of the inertial sensor is used as a shake label. The shake label can characterize the degree of shake of the lifted object after the control instruction is executed under the road bump map and the lifting status.

[0037] In the process of training the evaluation model based on the mean square error loss function between the output result and the shaking label, the evaluation model is continuously updated until the mean square error loss function between the output result and the shaking label is less than the loss threshold, and the trained evaluation model is obtained. The loss threshold is 0.001.

[0038] After the trained evaluation model is obtained, the lifting state, the road bump map obtained in step S101, and the initial control instruction are input into the trained evaluation model to obtain the shaking degree of the lifted object after executing the initial control instruction. The initial control instruction is the result of random initialization.

[0039] In one embodiment, in order to ensure the stability of the hoisted object and the working efficiency of the crane, the shaking degree and the driving speed in the initial control instruction need to be comprehensively considered when constructing the control loss. Specifically, the control loss is: , For the degree of shaking, The maximum safe driving speed is is the driving speed in the initial control instruction.

[0040] The smaller the shaking, the more stable the hoisted object is. The smaller it is, the closer the driving speed in the initial control instruction is to the maximum safe driving speed, that is, the higher the working efficiency of the crane; the smaller the control loss at this time.

[0041] In one embodiment, the use of the gradient descent method to update the initial control instruction includes: back-propagating the evaluation model to obtain the gradient value of each control parameter in the initial control instruction; The update process is: , is the control parameter before updating , is the update coefficient, For control parameters The gradient value of is the updated control parameter The control parameter is the driving direction or the driving speed; the update coefficient The value of is 0.01.

[0042] In other embodiments, too large an update coefficient may result in the updated control parameters Skip the global optimal solution and make the updated control parameters It is impossible to achieve the best control effect; if the update coefficient is too small, the control parameters will be The update speed is slow and the real-time control cannot be guaranteed. Therefore, the update coefficient is adaptively adjusted according to the change of control loss during the update process. The value of can improve the control effect while ensuring the real-time control. Update coefficient in update for: , is the initial update coefficient, and Respectively Second and The control loss of the update, is the minimum update coefficient, is the hyperbolic tangent function. Minimum update coefficient The value of is 0.01; the initial update coefficient The value of is 1.

[0043] Understandably, Indicates The change in control loss in the update, The smaller it is, the closer each control parameter is to the global optimal solution. In this case, reduce the update coefficient The value of can avoid the updated control parameters from skipping the global optimal solution and ensure the control effect of the updated control parameters.

[0044] In this way, a new initial control instruction is updated in the direction of reducing control loss using the gradient descent method. The updated initial control instruction can reduce the control loss, that is, reduce the shaking degree of the hoisted object while ensuring the driving speed.

[0045] S103, updating the initial control instruction multiple times until the control loss is less than a preset value to obtain the target control instruction, and controlling the crane with the target control instruction.

[0046] In one embodiment, after completing the update of the initial control instruction once, step S102 is executed again to update the initial control instruction; the initial control instruction is updated multiple times until the control loss is less than a preset value, indicating that the initial control instruction at this time can meet the control requirements of the crane, and the initial control instruction at this time is used as the target control instruction to realize the control of the crane.

[0047] In this way, combined with the road conditions in front of the crane, the crane can be precisely controlled, ensuring the stability of the hoisted object while ensuring the crane's working efficiency.

[0048] In other embodiments, the evaluation model can evaluate the degree of shaking of the hoisted object after executing the initial control instruction, and use this to calculate the gradient value of each control parameter in the initial control instruction, and then update the initial control instruction. Therefore, whether the evaluation model can accurately predict the degree of shaking of the hoisted object directly affects the control effect of the target control instruction. After controlling the crane with the target control instruction, if the indication of the inertial sensor is greater than the indication threshold, it means that the target control instruction cannot achieve the expected control effect. At this time, the evaluation model needs to be further trained to ensure the control effect of the target control instruction at all times. Among them, the indication threshold is 1.

[0049] Specifically, after controlling the crane with the target control instruction, the control method also includes: in response to the indication of the inertial sensor being greater than the indication threshold, taking the road bump map, the lifting state and the target control instruction as a group of new training samples, and taking the indication of the inertial sensor as the shaking label of the new training samples; training the evaluation model based on the new training samples.

[0050] The technical principle and implementation details of the intelligent remote control method for the crane of the present application are introduced above through specific embodiments. During the operation of the crane, the road image in front of the crane is collected, the pixel value difference between the pixel point in the road image and each neighboring pixel point is calculated, and the maximum value of the pixel value difference is used as the modulus length to construct an undulation vector from the pixel point to the neighboring pixel point corresponding to the maximum value of the pixel value difference, and a road bump map is obtained. The road bump map can accurately reflect the changes and change directions of road characteristics at various positions in the road in front of the crane, and provide a data basis for the subsequent precise control of the crane; the initial control instruction, the road bump map and the lifting state are input into the trained evaluation model to obtain the degree of shaking, wherein the initial control instruction includes the driving speed and the driving direction; the control loss is constructed with the degree of shaking and the driving speed, and the control loss is positively correlated with the degree of shaking and negatively correlated with the driving speed; the initial control instruction is updated by the gradient descent method until the control loss is less than the preset value to obtain the target control instruction, and the crane is controlled by the target control instruction, while ensuring the stability of the hoisted object, the working efficiency of the crane is guaranteed, and the precise control of the crane is realized.

[0051] According to the second aspect of the present application, the present application also provides an intelligent remote control system for a crane. Figure 2 1 is a structural block diagram of an intelligent remote control system for a crane according to an embodiment of the present application. Figure 2 As shown, the system 50 includes a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an intelligent remote control method for a crane according to the first aspect of the present application is implemented. The system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, whose settings and functions are known in the art, and therefore will not be described in detail here.

[0052] In the present application, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in this application may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0053] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0054] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. An intelligent remote control method for a crane, characterized in that: The control method comprises: Obtain the road image in front of the crane, calculate the pixel value difference between the pixel point in the road image and each neighboring pixel point, and use the maximum pixel value difference as the modulus length to construct an ups and downs vector pointing from the pixel point to the neighboring pixel point corresponding to the maximum pixel value difference, and obtain a road bump map; Input the initial control instruction, the road bump map and the lifting state into the trained evaluation model to obtain the shaking degree, construct the control loss, and use the gradient descent method to update the initial control instruction, the initial control instruction includes the driving direction and the driving speed, and the lifting state includes the lifting height and the lifting weight. The control loss is positively correlated with the shaking degree and negatively correlated with the driving speed; The initial control instruction is updated multiple times until the control loss is less than a preset value, and the target control instruction is obtained, and the crane is controlled with the target control instruction; The training method of the evaluation model includes: deploying inertial sensors on the crane hook; collecting road bump maps and control instructions executed under the lifting state to obtain training samples, and using the readings of the inertial sensors after executing the control instructions as shaking labels; inputting the training samples into the evaluation model, and training the evaluation model based on the mean square error loss function between the output results and the shaking labels.

2. The intelligent remote control method for a crane according to claim 1, characterized in that: The road image is a grayscale image or a depth image.

3. The intelligent remote control method for a crane according to claim 1, characterized in that: Before obtaining the road bump map, the control method further includes: Calculate the mode of pixel values ​​of each pixel point in the road image; The pixel value mode is subtracted from the pixel value of each pixel point in the road image to obtain a preprocessed road image.

4. The intelligent remote control method for a crane according to claim 1, characterized in that: The evaluation model includes a convolution sub-model and a regression sub-model. The convolution sub-model is used to extract image features of the road bump map, and the regression sub-model is used to regress multidimensional data consisting of image features, initial control instructions and lifting status to the degree of shaking.

5. The intelligent remote control method for a crane according to claim 1, characterized in that: The control loss is: , For the degree of shaking, The maximum safe driving speed is is the driving speed in the initial control instruction.

6. The intelligent remote control method for a crane according to claim 1, characterized in that: The use of the gradient descent method to update the initial control instruction includes: Back-propagate the evaluation model to obtain the gradient value of each control parameter in the initial control instruction; Control parameters The update process is: , is the control parameter before updating , is the update coefficient, For control parameters The gradient value of is the updated control parameter .

7. The intelligent remote control method for a crane according to claim 6, characterized in that: No. Update coefficient in update for: , is the initial update coefficient, and Respectively Second and The control loss of the update, is the minimum update coefficient, is the hyperbolic tangent function.

8. An intelligent remote control method for a crane according to any one of claims 1 to 7, characterized in that: After controlling the crane with the target control instruction, the control method further includes: In response to an indication of the inertial sensor being greater than an indication threshold, taking the road bump map, the lifting state, and the target control instruction as a group of newly added training samples, and taking the indication of the inertial sensor as a shaking label of the newly added training samples; The evaluation model is trained based on the newly added training samples.

9. An intelligent remote control system for a crane, characterized in that: The invention comprises a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an intelligent remote control method for a crane according to any one of claims 1 to 8 is implemented.

Images