A method, system, computer equipment, and storage medium for controlling the end effector position of a large hydraulic robotic arm.

Abstract

A method for controlling the end effector position of a large hydraulic robotic arm includes the following steps: acquiring the joint values ​​of the hydraulic robotic arm and recording them as the current joint values, where n is the number of joints in the hydraulic robotic arm; determining the first end effector target parameters of the hydraulic robotic arm; obtaining the second end effector target parameters based on the current joint values ​​and the first end effector target parameters through a first Jacobian iteration and a first error compensation; updating the joint values ​​of the hydraulic robotic arm and recording them as dynamic joint values; obtaining the end effector position error based on the second end effector target parameters and the dynamic joint values ​​through a second Jacobian iteration and a second error compensation; generating optimized control parameters based on the end effector position error; and controlling the hydraulic robotic arm based on the optimized control parameters. This invention performs two corrections to the end effector position of the hydraulic robotic arm based on two Jacobian iterations, thereby effectively improving the control accuracy of the end effector position of the hydraulic robotic arm.

Description

Technical Field

[0001] This invention relates to the field of hydraulic robotic arm control technology, specifically to a method, system, computer equipment, and storage medium for controlling the end position of a large hydraulic robotic arm. Background Technology

[0002] A hydraulic robotic arm is a type of robotic arm driven by hydraulic principles, enabling high-precision, high-speed, and highly flexible movement. Its working principle utilizes the pressure of a hydraulic engine to move each joint of the robotic arm through the action of hydraulic cylinders, hydraulic pipes, and hydraulic valves, thereby achieving the purpose of moving the robotic arm. A hydraulic robotic arm mainly consists of multiple joints. During the movement of the end effector, all joints need to participate. However, due to factors such as its own weight and material strength, the position of the end effector is difficult to precisely reach the target location. This is especially true for large hydraulic robotic arms, which have more joints and larger dimensions, amplifying the negative effects of various factors, particularly causing different deformations at different joints, making it even more difficult to control the end effector position.

[0003] In existing technologies, the actual position of the hydraulic manipulator's end effector is mainly calculated based on the combination of joint values ​​using forward kinematics error compensation. However, this method cannot completely solve the positioning deviation problem between the end effector position and the expected target point. This forward kinematics positioning error, which is known in magnitude but cannot be compensated for, becomes the main factor affecting the accuracy of inverse kinematics. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method, system, computer equipment, and storage medium for controlling the end position of a large hydraulic robotic arm. Based on two Jacobi iterations, the end position of the hydraulic robotic arm is corrected twice, and then through two error compensations, the position of the hydraulic robotic arm can be made close enough to the target position, thereby effectively improving the control accuracy of the end position of the hydraulic robotic arm.

[0005] To achieve the above objectives, the specific solution adopted by the present invention is as follows: a method for controlling the end position of a large hydraulic robotic arm, comprising the following steps:

[0006] Obtain the joint values ​​of the hydraulic robotic arm and record them as the current joint values. Where n is the number of joints in the hydraulic manipulator; determine the first end-effector target parameters of the hydraulic manipulator;

[0007] Based on current joint values The second final target parameter is obtained by sequentially performing the first Jacobian iteration and the first error compensation on the first final target parameter;

[0008] Update the joint values ​​of the hydraulic robotic arm and record them as dynamic joint values.

[0009] Based on the second end target parameters and dynamic joint values The end position error is obtained by sequentially performing a second Jacobi iteration and a second error compensation.

[0010] Optimized control parameters are generated based on the end-effector position error, and the hydraulic robotic arm is controlled based on these optimized control parameters.

[0011] As a further optimization of the aforementioned method for controlling the end effector position of a large hydraulic robotic arm: the first end effector target parameter includes the first end effector target position. and the first end target pose

[0012] Based on current joint values The methods for obtaining the second final target parameter by sequentially performing the first Jacobian iteration and the first error compensation on the first final target parameter include:

[0013] pose of the first end target and current joint value The first inverse joint value is obtained by performing the first Jacobi iteration. For the first inverse joint value The theoretical position of the first end is obtained by performing a forward DH solution.

[0014] The theoretical position of the first end is determined using a pre-trained error compensation model. The first error compensation amount is obtained by performing compensation. And based on the first error compensation amount and the theoretical position of the first end Calculate the position of the second terminal target For the current joint value Update to obtain dynamic joint values And the pose of the first end target The second end target pose is obtained by updating.

[0015] Second terminal target location Second end target pose This constitutes the second terminal target parameters.

[0016] As a further optimization of the aforementioned method for controlling the end position of a large hydraulic robotic arm: based on the first error compensation amount and the theoretical position of the first end Calculate the position of the second terminal target The methods include:

[0017] Based on the first error compensation amount and the theoretical position of the first end The actual position of the first end was calculated.

[0018] Based on the actual position of the first end and the first terminal target location Calculate the first end position error

[0019] Based on the first terminal target location and the first end position error Calculate the position of the second terminal target

[0020] As a further optimization of the aforementioned method for controlling the end effector position of a large hydraulic robotic arm: based on the second end effector target parameters and dynamic joint values... The methods for obtaining the end position error through a second Jacobi iteration and a second error compensation include:

[0021] For the second end target pose and dynamic joint values The second Jacobi iteration yields the joint values ​​of the second inverse solution. For the second inverse joint value DH cleaning is used to obtain the theoretical location of the second end.

[0022] The theoretical position of the second end is determined using a pre-trained error compensation model. The second error compensation amount is obtained by performing compensation. And based on the second error compensation amount Theoretical position of the second end Calculate the actual position of the second end

[0023] Based on the first terminal target location Second end actual position Calculate the end position error

[0024]

[0025] As a further optimization of the aforementioned method for controlling the end effector position of a large hydraulic robotic arm, the method for training the error compensation model includes:

[0026] Obtain the joint values ​​and end-effector position error of the hydraulic robotic arm, and construct a dataset;

[0027] The dataset is divided into a training set and a validation set;

[0028] The neural network model is used as the basis, and the training set is used for training.

[0029] After training is complete, the trained neural network model is validated using a validation set. If the validation passes, an error compensation model is output; otherwise, training is repeated.

[0030] A large hydraulic robotic arm end-effector position control system includes:

[0031] The data acquisition module is used to acquire the joint values ​​and first end-effector target parameters of the hydraulic robotic arm;

[0032] The data processing module is used to process data based on the current joint value. The first end target parameter and the first Jacobian iteration and the first error compensation are sequentially processed, and then the second end target parameter and dynamic joint value are applied. It then undergoes a second Jacobi iteration and a second error compensation.

[0033] The data output module is used to output optimized control parameters.

[0034] Computer equipment, including:

[0035] Memory, which stores computer programs;

[0036] A processor is used to read the computer program to implement the above-described method for controlling the end position of a large hydraulic robotic arm.

[0037] A storage medium for storing a computer program that, when executed, implements a method for controlling the end position of a large hydraulic robotic arm as described above.

[0038] Beneficial effects: This invention performs two corrections to the end-effector position of the hydraulic robotic arm based on two Jacobi iterations. Through two error compensations, the position of the hydraulic robotic arm can be made sufficiently close to the target position, thereby effectively improving the control accuracy of the end-effector position. Especially for large hydraulic robotic arms, it can effectively solve the problem of end-effector position error caused by material deformation. Attached Figure Description

[0039] Figure 1 This is a flowchart of the present invention;

[0040] Figure 2 This is a comparison chart of the control results in the X-axis direction during the experiment of a specific implementation method;

[0041] Figure 3This is a comparison chart of the control results in the Y-axis direction during the experiment of a specific implementation method;

[0042] Figure 4 This is a comparison chart of the control results in the Z-axis direction during the experiment of a specific implementation method. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] like Figure 1 As shown, a method for controlling the end position of a large hydraulic robotic arm includes S1 to S6.

[0045] S1. Obtain the joint values ​​of the hydraulic robotic arm and record them as the current joint values. Where n is the number of joints in the hydraulic robotic arm.

[0046] S2. Determine the first end-effector target parameters of the hydraulic robotic arm. The first end-effector target parameters include the first end-effector position. and the first end target pose

[0047] S3, Based on current joint values The second end-target parameters are obtained by sequentially performing the first Jacobian iteration and the first error compensation with the first end-target parameters. Based on the current joint values... The methods for obtaining the second final target parameter by sequentially performing the first Jacobian iteration and the first error compensation on the first final target parameter include:

[0048] S31. Assess the pose of the first end target. and current joint value The first inverse joint value is obtained by performing the first Jacobi iteration.

[0049] S32, For the first inverse solution joint value The theoretical position of the first end is obtained by performing a forward DH solution.

[0050] S33. Using a pre-trained error compensation model to determine the theoretical position of the first end. The first error compensation amount is obtained by performing compensation. And based on the first error compensation amount and the theoretical position of the first end Calculate the position of the second terminal target

[0051] S34, Current joint value Update to obtain dynamic joint values And the pose of the first end target The second end target pose is obtained by updating.

[0052] S35, Second Terminal Target Location Second end target pose The second terminal target parameters are composed of the first error compensation amount. and the theoretical position of the first end Calculate the position of the second terminal target The methods include S351 to S353.

[0053] S351, Based on the first error compensation amount and the theoretical position of the first end The actual position of the first end was calculated.

[0054]

[0055] S352, Based on the actual position of the first end and the first terminal target location Calculate the first end position error

[0056]

[0057] S353, Based on the location of the first terminal target and the first end position error Calculate the position of the second terminal target

[0058]

[0059] S4. Update the joint values ​​of the hydraulic robotic arm and record them as dynamic joint values.

[0060] S5. Based on the second end target parameters and dynamic joint values The end-effector position error is obtained through a second Jacobi iteration and a second error compensation. This is based on the second end-effector target parameters and dynamic joint values. The methods for obtaining the end position error through a second Jacobi iteration and a second error compensation include:

[0061] S51, Position the second end target and dynamic joint values The second Jacobi iteration yields the joint values ​​of the second inverse solution.

[0062] S52, Regarding the second inverse solution joint value DH cleaning is used to obtain the theoretical location of the second end.

[0063] S53. Using a pre-trained error compensation model to determine the theoretical position of the second end. The second error compensation amount is obtained by performing compensation. And based on the second error compensation amount Theoretical position of the second end Calculate the actual position of the second end

[0064]

[0065] S54, Based on the location of the first terminal target Second end actual position Calculate the end position error

[0066] S6. Generate optimized control parameters based on the end position error, and control the hydraulic robotic arm based on the optimized control parameters.

[0067] This invention uses a double Jacobi iteration to correct the end-effector position of a hydraulic robotic arm twice, and then compensates for the errors twice to ensure that the position of the hydraulic robotic arm is close enough to the target position, thereby effectively improving the control accuracy of the end-effector position. Especially for large hydraulic robotic arms, it can effectively solve the problem of end-effector position error caused by material deformation.

[0068] To verify the effectiveness of the invention, an experiment was conducted using the rock-drilling robotic arm of a G3Zi rock-drilling rig manufactured by Henan Gengli Engineering Equipment Co., Ltd. as the controlled object. The experimental results are as follows: Figure 2-4 As shown, in Figure 2-4 In this paper, the invention is marked as a target-corrected double Jacobian iteration, and compared with the traditional single Jacobian iteration technique. It can be seen that the invention achieves more precise control of the end position of the hydraulic robotic arm in the XYZ directions.

[0069] In this invention, the error compensation model employs a neural network model, such as a BP neural network model, which is existing technology and its structure and specific operating principle will not be elaborated here. Based on this, the method for training the error compensation model is as follows.

[0070] First, the joint values ​​and end-effector position errors of the hydraulic robotic arm are obtained, and a dataset is constructed.

[0071] Secondly, the dataset is divided into a training set and a validation set.

[0072] Then, the neural network model was used as the basis for training using the training set.

[0073] Finally, after training is complete, the trained neural network model is validated using a validation set. If the validation passes, an error compensation model is output; otherwise, training is repeated.

[0074] The present invention also provides a large hydraulic robotic arm end-effector position control system, including a data acquisition module, a data processing module and a data output module.

[0075] The data acquisition module is used to acquire the joint values ​​and first end-effector target parameters of the hydraulic robotic arm;

[0076] The data processing module is used to process data based on the current joint value. The first end target parameter and the first Jacobian iteration and the first error compensation are sequentially processed, and then the second end target parameter and dynamic joint value are applied. It then undergoes a second Jacobi iteration and a second error compensation.

[0077] The data output module is used to output optimized control parameters.

[0078] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or modules may be electrical, mechanical, or other forms.

[0079] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0080] The present invention further provides a computer device, including a memory and a processor.

[0081] A memory that stores computer programs.

[0082] A processor is used to read the computer program to implement the above-described method for controlling the end position of a large hydraulic robotic arm.

[0083] Finally, the present invention provides a storage medium for storing a computer program that, when executed, implements the above-described method for controlling the end position of a large hydraulic robotic arm.

[0084] The memory, as a carrier of resources, can be a read-only memory, random access memory, disk, or optical disk, etc. The resources stored on it can include the operating system, computer programs, etc., and the storage method can be temporary or permanent storage. The operating system is used to manage and control the various hardware devices and computer programs on the electronic device, and can be Windows Server, Netware, Unix, Linux, etc. In addition to including computer programs capable of performing the adaptive emotion regulation method based on personalized reconfigurable music disclosed in any of the foregoing embodiments, the computer programs may further include computer programs capable of performing other specific tasks. The processor can be a general-purpose processor product based on architectures such as x86, IA64, RISC, MIPS, and ARM.

[0085] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling the end-effector position of a large hydraulic robotic arm, characterized in that, Includes the following steps: Obtain the joint values ​​of the hydraulic robotic arm and record them as the current joint values. Where n is the number of joints in the hydraulic robotic arm; Determine the first end-effector target parameters of the hydraulic robotic arm; the first end-effector target parameters include the first end-effector target position. and the first end target pose Based on current joint values The second final target parameter is obtained by sequentially performing the first Jacobian iteration and the first error compensation on the first final target parameter; Update the joint values ​​of the hydraulic robotic arm and record them as dynamic joint values. Based on the second end target parameters and dynamic joint values The end position error is obtained by sequentially performing a second Jacobi iteration and a second error compensation. Optimized control parameters are generated based on the end-effector position error, and the hydraulic robotic arm is controlled based on the optimized control parameters. Based on current joint values The methods for obtaining the second final target parameter by sequentially performing the first Jacobian iteration and the first error compensation on the first final target parameter include: pose of the first end target and current joint value The first inverse joint value is obtained by performing the first Jacobi iteration. For the first inverse joint value The theoretical position of the first end is obtained by performing a forward DH solution. The theoretical position of the first end is determined using a pre-trained error compensation model. The first error compensation amount is obtained by performing compensation. And based on the first error compensation amount and the theoretical position of the first end Calculate the position of the second terminal target For the current joint value Update to obtain dynamic joint values And the pose of the first end target The second end target pose is obtained by updating. Second terminal target location Second end target pose This constitutes the second terminal target parameters.

2. The method for controlling the end position of a large hydraulic robotic arm as described in claim 1, characterized in that, Based on the first error compensation amount and the theoretical position of the first end Calculate the position of the second terminal target The methods include: Based on the first error compensation amount and the theoretical position of the first end The actual position of the first end was calculated. Based on the actual position of the first end and the first terminal target location Calculate the first end position error Based on the first terminal target location and the first end position error Calculate the position of the second terminal target 3. The method for controlling the end position of a large hydraulic robotic arm as described in claim 2, characterized in that, Based on the second end target parameters and dynamic joint values The methods for obtaining the end position error through a second Jacobi iteration and a second error compensation include: For the second end target pose and dynamic joint values The second Jacobi iteration yields the joint values ​​of the second inverse solution. For the second inverse joint value DH cleaning is used to obtain the theoretical location of the second end. The theoretical position of the second end is determined using a pre-trained error compensation model. The second error compensation amount is obtained by performing compensation. And based on the second error compensation amount Theoretical position of the second end Calculate the actual position of the second end Based on the first terminal target location Second end actual position Calculate the end position error 4. The method for controlling the end position of a large hydraulic robotic arm as described in claim 3, characterized in that, The method for training the error compensation model includes: Obtain the joint values ​​and end-effector position error of the hydraulic robotic arm, and construct a dataset; The dataset is divided into a training set and a validation set; The neural network model is used as the basis, and the training set is used for training. After training is complete, the trained neural network model is validated using a validation set. If the validation passes, an error compensation model is output; otherwise, training is repeated.

5. A position control system for the end effector of a large hydraulic robotic arm, characterized in that, include: The data acquisition module is used to acquire the joint values ​​and first end-effector target parameters of the hydraulic robotic arm; The data processing module is used to process data based on the current joint value. The first end target parameter and the first Jacobian iteration and the first error compensation are sequentially processed, and then the second end target parameter and dynamic joint value are applied. After a second Jacobi iteration and a second error compensation, the first terminal target parameters include the first terminal target position. and the first end target pose Based on current joint values The method for obtaining the second end target parameters by sequentially performing the first Jacobian iteration and the first error compensation on the first end target parameters includes: [The text abruptly ends here, likely due to an incomplete sentence or a formatting error.] and current joint value The first inverse joint value is obtained by performing the first Jacobi iteration. For the first inverse joint value The theoretical position of the first end is obtained by performing a forward DH solution. The theoretical position of the first end is determined using a pre-trained error compensation model. The first error compensation amount is obtained by performing compensation. And based on the first error compensation amount and the theoretical position of the first end Calculate the position of the second terminal target For the current joint value Update to obtain dynamic joint values And the pose of the first end target The second end target pose is obtained by updating. Second terminal target location Second end target pose The second terminal target parameters are formed; The data output module is used to output optimized control parameters.

6. A computer device, characterized in that, include: Memory, which stores computer programs; A processor is configured to read the computer program to implement a method for controlling the end position of a large hydraulic robotic arm as described in any one of claims 1-4.

7. A storage medium, characterized in that, Used to store a computer program, which, when executed, implements a method for controlling the end position of a large hydraulic robotic arm as described in any one of claims 1-4.

Images