Composite positioning method, system, device, product and medium of heavy-load mobile platform

Abstract

This invention relates to the field of displacement control, providing a composite positioning method, system, device, product, and medium for heavy-duty mobile platforms. The method includes constructing a pose estimation sub-model, calculating the likelihood of the sub-model, obtaining the confidence probability of the sub-model based on the likelihood, obtaining the pose estimate of the sub-model, calculating the platform pose estimate based on the sub-model pose estimate and the confidence probability of the sub-model, obtaining control input based on the platform pose estimate, obtaining the derivative of the model state vector through the control input, obtaining feedforward commands based on the derivative of the model state vector, determining the platform control device, inputting the feedforward commands into the platform control device, and obtaining disturbance estimation through observation, calculating disturbance compensation based on the disturbance estimation, calculating current control parameters based on historical parameters, and generating feedback control parameters for the platform control device through the disturbance compensation and the current control parameters. This invention can complete the positioning of heavy-duty mobile platforms.

Description

Technical Field

[0001] This invention relates to the field of displacement control technology, and in particular to composite positioning methods, systems, equipment, products and media for heavy-duty mobile platforms. Background Technology

[0002] Heavy-duty hydraulic presses, 10,000-ton free forging hydraulic presses, and large presses are usually equipped with movable worktables to support molds or workpieces and to switch positions during loading, unloading, mold changing, and processing preparation stages.

[0003] In high-precision positioning scenarios for mobile worktables with rated loads of no less than 500 tons, existing technologies still have shortcomings: large inertia and wide-range load variations cause the equivalent inertia and friction parameters to drift with the working conditions, and fixed proportional-integral-derivative control parameters are difficult to balance the accuracy of high-speed coarse motion and end-effector fine motion; high-frequency processing of all multi-source data increases the computational load of real-time control; disturbances such as heavy-load guide rail deflection, friction conversion, and hydraulic fluctuations are distributed in different frequency bands, and a single disturbance observer is difficult to compensate stably; complete nonlinear models have high accuracy but are difficult to directly incorporate into the real-time control cycle. Summary of the Invention

[0004] The present invention aims to at least solve one of the technical problems existing in related technologies. To this end, the present invention provides a composite positioning method, system, device, product, and medium for heavy-duty mobile platforms, achieving high-precision movement control of heavy-duty mobile platforms.

[0005] This invention provides a composite positioning method for heavy-duty mobile platforms, comprising: S1: Construct a pose estimation sub-model, calculate the sub-model likelihood of the pose estimation sub-model, and obtain the sub-model confidence probability based on the sub-model likelihood; S2: Obtain the pose estimation of the sub-model of the pose estimation sub-model, and calculate the platform pose estimation based on the pose estimation of the sub-model and the confidence probability of the sub-model; S3: Obtain control input based on platform pose estimation, obtain the derivative of model state vector through control input, and obtain feedforward command based on the derivative of model state vector; S4: Determine the platform control equipment, input the feedforward command into the platform control equipment, and observe to obtain the disturbance estimate. Calculate the disturbance compensation amount based on the disturbance estimate. S5: Obtain historical parameters of the platform control equipment, calculate the current control parameters based on the historical parameters, generate fine-tuning parameters of the platform control equipment through disturbance compensation and current control parameters, and use the fine-tuning parameters to complete the positioning of the heavy-duty mobile platform.

[0006] According to the composite positioning method for a heavy-duty mobile platform provided by the present invention, step S1 further includes: S11: Construct a pose estimation sub-model that includes a light-load low-friction model, a heavy-load high-deflection model, and a locking-stage micro-motion model; S12: Obtain the observation residuals and information covariance of the pose sub-model. Calculate the sub-model likelihood based on the observation residuals and information covariance of the pose sub-model. Obtain the sub-model confidence probability based on the sub-model likelihood.

[0007] According to the composite positioning method for a heavy-duty mobile platform provided by the present invention, in step S2, the platform pose is estimated. for: in, Let be the confidence probability of the sub-model of the i-th pose estimation sub-model at time k. Let J be the pose estimation of the sub-model of the i-th pose estimation sub-model, where J is the total number of pose estimation sub-models. For anchoring gain, For sensor monitoring data, This is the state projection matrix.

[0008] According to the composite positioning method for a heavy-duty mobile platform provided by the present invention, step S3 further includes: S31: Determine the target pose data, obtain the control input based on the platform pose estimation and the target pose data, and obtain the derivative of the model state vector through the control input; S32: Obtain the feedforward control parameters, map the feedforward control parameters to obtain the feedforward mapping coefficients, and obtain the feedforward command based on the feedforward mapping coefficients and the derivative of the model state vector.

[0009] According to the composite positioning method for a heavy-duty mobile platform provided by the present invention, in step S4, after obtaining the disturbance estimate, the state of the heavy-duty platform is obtained, the disturbance observer weight is obtained based on the heavy-duty platform state and the platform pose estimate, and the disturbance compensation amount is calculated using the disturbance observer weight and the disturbance estimate.

[0010] According to the composite positioning method for a heavy-duty mobile platform provided by the present invention, step S5 further includes: S51: Obtain the historical parameters, measure the heavy-load platform status parameters, calculate the parameter estimation uncertainty based on the historical parameters and the heavy-load platform status parameters, and calculate the current control parameters based on the parameter estimation uncertainty; S52: Generate feedback control parameters for the platform control device based on the current control parameters and disturbance compensation amount, obtain fine-tuning parameters through the feedback control parameters, and use the fine-tuning parameters to complete the positioning of the heavy-duty mobile platform.

[0011] This invention also provides a composite positioning system for heavy-duty mobile platforms, comprising: Sub-model confidence probability module: used to construct pose estimation sub-models, calculate the sub-model likelihood of pose estimation sub-models, and obtain the sub-model confidence probability based on the sub-model likelihood; Platform pose estimation module: used to obtain the pose estimation of the sub-model of the pose estimation sub-model, and to calculate the platform pose estimation based on the sub-model pose estimation and the sub-model confidence probability; Feedforward instruction module: used to obtain control input based on platform pose estimation, obtain the derivative of model state vector through control input, and obtain feedforward instructions based on the derivative of model state vector; Disturbance compensation module: used to determine the platform control equipment, input feedforward commands into the platform control equipment, observe to obtain disturbance estimates, and calculate disturbance compensation amount based on disturbance estimates; Platform feedback control module: Used to acquire historical parameters of the platform control equipment, calculate the current control parameters based on the historical parameters, generate fine-tuning parameters of the platform control equipment through disturbance compensation and the current control parameters, and use the fine-tuning parameters to complete the positioning of the heavy-duty mobile platform.

[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the composite positioning method for a heavy-duty mobile platform as described above.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the composite positioning method for a heavy-duty mobile platform as described above.

[0014] The present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, which, when executed by a computer, enable the computer to perform the steps of the composite positioning method for any of the heavy-duty mobile platforms described above.

[0015] The above-described one or more technical solutions in the embodiments of the present invention have at least one of the following technical effects: The composite positioning method, system, device, product, and medium for heavy-duty mobile platforms provided by this invention can obtain the confidence level of the pose estimation data obtained by each sub-model through the confidence probability of the sub-model. Then, the platform pose estimation is obtained by combining the results of these models. Subsequently, the feedforward command of the heavy-duty mobile platform is obtained. The disturbance compensation amount of the heavy-duty mobile platform is obtained according to the feedforward command. Finally, the feedback control parameters for controlling the heavy-duty mobile platform are obtained, so that the feedback control system of the heavy-duty platform can perform feedback control according to the real-time feedback control parameters to complete the positioning of the heavy-duty mobile platform.

[0016] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the composite positioning method for a heavy-duty mobile platform provided by the present invention.

[0019] Figure 2 This is a structural schematic diagram of the composite positioning system for a heavy-duty mobile platform provided by the present invention.

[0020] Figure 3 This is a structural schematic diagram of the composite positioning device for a heavy-duty mobile platform provided by the present invention.

[0021] Figure label: 100. Sub-model confidence probability module; 200. Platform pose estimation module; 300. Feedforward instruction module; 400. Disturbance compensation module; 500. Platform feedback control module; 810. Processor; 820. Communication interface; 830. Memory; 840. Communication bus. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention. The following embodiments are used to illustrate this invention but cannot be used to limit the scope of this invention.

[0023] In the description of the embodiments of the present invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of the present invention based on the specific circumstances.

[0024] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0025] The following is combined Figures 1 to 3 Specific embodiments of the present invention are described below. Figure 1 This is a flowchart illustrating the composite positioning method for a heavy-duty mobile platform provided by the present invention, including: S1: Construct a pose estimation sub-model, calculate the sub-model likelihood of the pose estimation sub-model, and obtain the sub-model confidence probability based on the sub-model likelihood; Furthermore, the objective of this stage is to calculate the sub-model likelihood of the pose estimation sub-model, and obtain the sub-model confidence probability based on the sub-model likelihood. Specifically, step S1 further includes: S11: Construct a pose estimation sub-model that includes a light-load low-friction model, a heavy-load high-deflection model, and a locking-stage micro-motion model; S12: Obtain the observation residuals and information covariance of the pose sub-model. Calculate the sub-model likelihood based on the observation residuals and information covariance of the pose sub-model. Obtain the sub-model confidence probability based on the sub-model likelihood.

[0026] The specific implementation method for the above steps in this embodiment is as follows: First, to address the different operating conditions of heavy-duty mobile platforms under varying loads, multiple different pose estimation sub-models need to be pre-constructed. Each pose estimation sub-model has a corresponding optimal operating condition, in which it achieves the highest accuracy in estimating the platform pose of the heavy-duty mobile platform. In this embodiment, the pose estimation sub-models include a light-load, low-friction model, a heavy-load, high-deflection model, and a locking-stage micro-motion model. These pose estimation sub-models have undergone targeted optimization of their internal structure and parameters to adapt to different operating conditions. Here, pose includes the position and attitude of the heavy-duty mobile platform.

[0027] Next, we obtain the historical data, observation residuals, and information covariance of the pose sub-model. The historical data represents the confidence probability of the pose estimation sub-model at the previous time step, characterizing the reliability of the pose estimation sub-model's assessment of the platform pose under current conditions. The observation residuals and information covariance are the observation residuals of the pose estimation sub-model under current conditions. This allows us to calculate the confidence probability of the i-th pose estimation sub-model at time k. : in, Let be the confidence probability of the i-th pose estimation sub-model obtained from the historical data of the pose sub-model at time k-1. Let be the confidence probability of the j-th pose estimation sub-model obtained from the historical data of the pose sub-model at time k-1. Let be the sub-model likelihood of the i-th pose estimation sub-model at time k. Let J be the likelihood of the j-th pose estimation sub-model at time k, and J be the total number of pose estimation sub-models. Here, the likelihood of the pose estimation sub-model can be calculated by Gaussian normalized likelihood of the observation residuals and information covariance of the pose sub-model under the current operating conditions. The observation residuals can be obtained based on the observation accuracy of the sensors measuring the parameters of the heavy-duty mobile platform, and the information covariance can be estimated based on the differences between the values ​​of the pose estimation sub-model in its optimal operating conditions and the values ​​in the current operating conditions of the heavy-duty mobile platform.

[0028] S2: Obtain the pose estimation of the sub-model of the pose estimation sub-model, and calculate the platform pose estimation based on the pose estimation of the sub-model and the confidence probability of the sub-model; Furthermore, the objective of this stage is to obtain the sub-model pose estimate, and then calculate the platform pose estimate. Specifically, in step S2, the platform pose estimate... for: in, Let be the confidence probability of the sub-model of the i-th pose estimation sub-model at time k. Let J be the pose estimation of the sub-model of the i-th pose estimation sub-model, where J is the total number of pose estimation sub-models. For anchoring gain, For sensor monitoring data, This is the state projection matrix.

[0029] The implementation method in this embodiment is as follows, based on the above steps: Here, we first need to use each pose estimation sub-model to estimate the current pose of the heavy-duty mobile platform, that is, the position and orientation of the heavy-duty mobile platform, so as to obtain the pose estimate of the sub-model of the i-th pose estimation sub-model. This allows us to calculate the platform pose estimate. : in, The anchoring gain is determined based on the multi-model fusion covariance of all pose estimation sub-models. Sensor monitoring data obtained by sensors observing the pose of a heavy-duty mobile platform. The state projection matrix is ​​predetermined.

[0030] S3: Obtain control input based on platform pose estimation, obtain the derivative of model state vector through control input, and obtain feedforward command based on the derivative of model state vector; Furthermore, the objective of this stage is to obtain the derivative of the model state vector, and then derive the feedforward instruction based on the derivative of the model state vector. Specifically, step S3 further includes: S31: Determine the target pose data, obtain the control input based on the platform pose estimation and the target pose data, and obtain the derivative of the model state vector through the control input; S32: Obtain the feedforward control parameters, map the feedforward control parameters to obtain the feedforward mapping coefficients, and obtain the feedforward command based on the feedforward mapping coefficients and the derivative of the model state vector.

[0031] The specific implementation method for the above steps in this embodiment is as follows: First, the target pose data needs to be determined, which is the desired pose data of the heavy-load mobile platform after movement. Then, the control input u of the feedback control system can be obtained based on the difference between the platform pose estimation and the target pose data, and thus the derivative of the model state vector can be obtained. : in, The first proxy parameter is updated regularly. For the second proxy parameters that are updated regularly, These are the parameters for a third agent that are updated periodically.

[0032] Subsequently, some current parameters of the feedforward control in the heavy-duty mobile platform are obtained, namely the feedforward control parameters. These feedforward control parameters are then mapped to obtain the first feedforward mapping coefficients. Second feedforward mapping coefficients The feedforward mapping coefficients are used to obtain the feedforward command. : .

[0033] S4: Determine the platform control equipment, input the feedforward command into the platform control equipment, and observe to obtain the disturbance estimate. Calculate the disturbance compensation amount based on the disturbance estimate. Furthermore, the objective of this stage is to obtain a disturbance estimate and calculate the disturbance compensation amount based on the disturbance estimate. Specifically, in step S4, after obtaining the disturbance estimate, the state of the heavy-load platform is acquired, and the disturbance observer weights are obtained based on the heavy-load platform state and the platform pose estimation. The disturbance observer weights and the disturbance estimate are then used to calculate the disturbance compensation amount.

[0034] The specific implementation method for the above steps in this embodiment is as follows: First, it is necessary to determine the platform control device that controls the movement of the heavy-duty mobile platform. After inputting feedforward commands into the platform control device, the feedforward control module within the device can perform coarse control of the heavy-duty mobile platform's movement based on these commands. Multiple sensors then observe the pose of the heavy-duty mobile platform after the coarse movement, and subsequently estimate the friction coefficient and deflection during the platform's movement, thus obtaining a disturbance estimate.

[0035] Furthermore, based on the current heavy-duty mobile platform state—that is, the load and movement state of the heavy-duty mobile platform—and the platform pose estimation, the confidence levels of different sensors when obtaining disturbance estimates can be estimated. Specifically, each sensor has a heavy-duty platform state and platform pose corresponding to the most reliable data. Thus, the confidence level of each sensor can be estimated based on the difference between the current heavy-duty platform state and platform pose estimation and the heavy-duty platform state and platform pose corresponding to the most reliable sensor data. This allows for the calculation of the disturbance observer weights for the b-th sensor. : in, Let B be the confidence level of the b-th sensor, and B be the total number of sensors. Let be the confidence level of the c-th sensor.

[0036] Finally, calculate the disturbance compensation amount. : in, This is the disturbance estimate for the b-th sensor.

[0037] S5: Obtain historical parameters of the platform control equipment, calculate the current control parameters based on the historical parameters, generate fine-tuning parameters of the platform control equipment through disturbance compensation and current control parameters, and use the fine-tuning parameters to complete the positioning of the heavy-duty mobile platform.

[0038] Furthermore, the objective of this stage is to calculate the current control parameters, thereby obtaining fine-tuning parameters, and using these fine-tuning parameters to complete the positioning of the heavy-load mobile platform. Specifically, step S5 further includes: S51: Obtain the historical parameters, measure the heavy-load platform status parameters, calculate the parameter estimation uncertainty based on the historical parameters and the heavy-load platform status parameters, and calculate the current control parameters based on the parameter estimation uncertainty; S52: Generate feedback control parameters for the platform control device based on the current control parameters and disturbance compensation amount, obtain fine-tuning parameters through the feedback control parameters, and use the fine-tuning parameters to complete the positioning of the heavy-duty mobile platform.

[0039] The specific implementation method for the above steps in this embodiment is as follows: First, it is necessary to obtain the current control parameters and parameter estimation uncertainties of the feedback control module in the platform control equipment at the previous moment, i.e., the historical parameters. Then, the current speed, acceleration, and drive pressure of the heavy-duty mobile platform are measured to obtain the heavy-duty platform state parameters. This allows for the calculation of the parameter estimation uncertainty at time t. : in, Forgetting factor, The uncertainty of parameter estimation at time t-1, Let be the parameter vector at time t, where the parameters are the state parameters of the overloaded platform, and T represents the transpose.

[0040] Then the current control parameters at time t are calculated. : in, The current control parameters at time t-1 include the current load-equivalent inertia and viscous friction parameters of the heavy-load mobile platform.

[0041] Finally, based on the current control parameters, the integral, proportional, and derivative coefficients of the feedback control module can be adjusted by comparing them with the pre-calibrated integral, proportional, and derivative coefficients under different load equivalent inertia and viscous friction parameters. Further fine-tuning of the integral, proportional, and derivative coefficients based on the disturbance compensation amount yields the feedback control parameters. These feedback control parameters are then input into the feedback control module, enabling it to obtain fine-tuning parameters for fine-tuning the heavy-load mobile platform. These fine-tuning parameters are used to further adjust the pose of the heavy-load mobile platform, thereby completing its positioning.

[0042] The composite positioning system for a heavy-duty mobile platform provided by the present invention will be described below. The composite positioning system for a heavy-duty mobile platform described below can be referred to in correspondence with the composite positioning method for a heavy-duty mobile platform described above.

[0043] Figure 2 A schematic diagram of a composite positioning system for a heavy-duty mobile platform is shown in the example. Figure 2 As shown, the composite positioning method for performing the heavy-duty mobile platform as described above includes: Sub-model confidence probability module 100: used to construct the pose estimation sub-model, calculate the sub-model likelihood of the pose estimation sub-model, and obtain the sub-model confidence probability based on the sub-model likelihood; Platform pose estimation module 200: used to obtain the pose estimation of the sub-model of the pose estimation sub-model, and to calculate the platform pose estimation based on the sub-model pose estimation and the sub-model confidence probability; Feedforward instruction module 300: used to obtain control input based on platform pose estimation, obtain the derivative of model state vector through control input, and obtain feedforward instructions based on the derivative of model state vector; Disturbance compensation module 400: used to determine the platform control equipment, input feedforward commands into the platform control equipment, observe to obtain disturbance estimates, and calculate disturbance compensation amount based on disturbance estimates; Platform feedback control module 500: Used to acquire historical parameters of the platform control equipment, calculate the current control parameters based on the historical parameters, generate fine-tuning parameters of the platform control equipment through disturbance compensation and the current control parameters, and use the fine-tuning parameters to complete the positioning of the heavy-duty mobile platform.

[0044] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 can call a computer program in the memory 830 to execute a composite positioning method for a heavy-duty mobile platform, the method including: S1: Construct a pose estimation sub-model, calculate the sub-model likelihood of the pose estimation sub-model, and obtain the sub-model confidence probability based on the sub-model likelihood; S2: Obtain the pose estimation of the sub-model of the pose estimation sub-model, and calculate the platform pose estimation based on the pose estimation of the sub-model and the confidence probability of the sub-model; S3: Obtain control input based on platform pose estimation, obtain the derivative of model state vector through control input, and obtain feedforward command based on the derivative of model state vector; S4: Determine the platform control equipment, input the feedforward command into the platform control equipment, and observe to obtain the disturbance estimate. Calculate the disturbance compensation amount based on the disturbance estimate. S5: Obtain historical parameters of the platform control equipment, calculate the current control parameters based on the historical parameters, generate fine-tuning parameters of the platform control equipment through disturbance compensation and current control parameters, and use the fine-tuning parameters to complete the positioning of the heavy-duty mobile platform.

[0045] Furthermore, when the computer program in the aforementioned memory 830 can be implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0046] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to execute the composite positioning method for a heavy-duty mobile platform provided by the above methods, the method comprising: S1: Construct a pose estimation sub-model, calculate the sub-model likelihood of the pose estimation sub-model, and obtain the sub-model confidence probability based on the sub-model likelihood; S2: Obtain the pose estimation of the sub-model of the pose estimation sub-model, and calculate the platform pose estimation based on the pose estimation of the sub-model and the confidence probability of the sub-model; S3: Obtain control input based on platform pose estimation, obtain the derivative of model state vector through control input, and obtain feedforward command based on the derivative of model state vector; S4: Determine the platform control equipment, input the feedforward command into the platform control equipment, and observe to obtain the disturbance estimate. Calculate the disturbance compensation amount based on the disturbance estimate. S5: Obtain historical parameters of the platform control equipment, calculate the current control parameters based on the historical parameters, generate fine-tuning parameters of the platform control equipment through disturbance compensation and current control parameters, and use the fine-tuning parameters to complete the positioning of the heavy-duty mobile platform.

[0047] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the composite positioning methods for the heavy-duty mobile platforms provided above, the method comprising: S1: Construct a pose estimation sub-model, calculate the sub-model likelihood of the pose estimation sub-model, and obtain the sub-model confidence probability based on the sub-model likelihood; S2: Obtain the pose estimation of the sub-model of the pose estimation sub-model, and calculate the platform pose estimation based on the pose estimation of the sub-model and the confidence probability of the sub-model; S3: Obtain control input based on platform pose estimation, obtain the derivative of model state vector through control input, and obtain feedforward command based on the derivative of model state vector; S4: Determine the platform control equipment, input the feedforward command into the platform control equipment, and observe to obtain the disturbance estimate. Calculate the disturbance compensation amount based on the disturbance estimate. S5: Obtain historical parameters of the platform control equipment, calculate the current control parameters based on the historical parameters, generate fine-tuning parameters of the platform control equipment through disturbance compensation and current control parameters, and use the fine-tuning parameters to complete the positioning of the heavy-duty mobile platform.

[0048] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A composite positioning method for a heavy-duty mobile platform, characterized in that, include: S1: Construct a pose estimation sub-model, calculate the sub-model likelihood of the pose estimation sub-model, and obtain the sub-model confidence probability based on the sub-model likelihood; S2: Obtain the pose estimation of the sub-model of the pose estimation sub-model, and calculate the platform pose estimation based on the pose estimation of the sub-model and the confidence probability of the sub-model; S3: Obtain control input based on platform pose estimation, obtain the derivative of model state vector through control input, and obtain feedforward command based on the derivative of model state vector; S4: Determine the platform control equipment, input the feedforward command into the platform control equipment, and observe to obtain the disturbance estimate. Calculate the disturbance compensation amount based on the disturbance estimate. S5: Obtain historical parameters of the platform control equipment, calculate the current control parameters based on the historical parameters, generate fine-tuning parameters of the platform control equipment through disturbance compensation and current control parameters, and use the fine-tuning parameters to complete the positioning of the heavy-duty mobile platform.

2. The composite positioning method for a heavy-duty mobile platform according to claim 1, characterized in that, Step S1 further includes: S11: Construct a pose estimation sub-model that includes a light-load low-friction model, a heavy-load high-deflection model, and a locking-stage micro-motion model; S12: Obtain the observation residuals and information covariance of the pose sub-model. Calculate the sub-model likelihood based on the observation residuals and information covariance of the pose sub-model. Obtain the sub-model confidence probability based on the sub-model likelihood.

3. The composite positioning method for a heavy-duty mobile platform according to claim 1, characterized in that, In step S2, the platform pose is estimated. for: in, Let be the confidence probability of the sub-model of the i-th pose estimation sub-model at time k. Let J be the pose estimation of the sub-model of the i-th pose estimation sub-model, where J is the total number of pose estimation sub-models. For anchoring gain, For sensor monitoring data, This is the state projection matrix.

4. The composite positioning method for a heavy-duty mobile platform according to claim 1, characterized in that, Step S3 further includes: S31: Determine the target pose data, obtain the control input based on the platform pose estimation and the target pose data, and obtain the derivative of the model state vector through the control input; S32: Obtain the feedforward control parameters, map the feedforward control parameters to obtain the feedforward mapping coefficients, and obtain the feedforward command based on the feedforward mapping coefficients and the derivative of the model state vector.

5. The composite positioning method for a heavy-duty mobile platform according to claim 1, characterized in that, In step S4, after obtaining the disturbance estimate, the heavy-load platform state is obtained, the disturbance observer weights are obtained based on the heavy-load platform state and the platform pose estimation, and the disturbance compensation amount is calculated using the disturbance observer weights and the disturbance estimate.

6. The composite positioning method for a heavy-duty mobile platform according to claim 1, characterized in that, Step S5 further includes: S51: Obtain the historical parameters, measure the heavy-load platform status parameters, calculate the parameter estimation uncertainty based on the historical parameters and the heavy-load platform status parameters, and calculate the current control parameters based on the parameter estimation uncertainty; S52: Generate feedback control parameters for the platform control device based on the current control parameters and disturbance compensation amount, obtain fine-tuning parameters through the feedback control parameters, and use the fine-tuning parameters to complete the positioning of the heavy-duty mobile platform.

7. A composite positioning system for a heavy-duty mobile platform, used to execute the composite positioning method for a heavy-duty mobile platform as described in any one of claims 1 to 6, characterized in that, include: Sub-model confidence probability module: used to construct pose estimation sub-models, calculate the sub-model likelihood of pose estimation sub-models, and obtain the sub-model confidence probability based on the sub-model likelihood; Platform pose estimation module: used to obtain the pose estimation of the sub-model of the pose estimation sub-model, and to calculate the platform pose estimation based on the sub-model pose estimation and the sub-model confidence probability; Feedforward instruction module: used to obtain control input based on platform pose estimation, obtain the derivative of model state vector through control input, and obtain feedforward instructions based on the derivative of model state vector; Disturbance compensation module: used to determine the platform control equipment, input feedforward commands into the platform control equipment, observe to obtain disturbance estimates, and calculate disturbance compensation amount based on disturbance estimates; Platform feedback control module: Used to acquire historical parameters of the platform control equipment, calculate the current control parameters based on the historical parameters, generate fine-tuning parameters of the platform control equipment through disturbance compensation and the current control parameters, and use the fine-tuning parameters to complete the positioning of the heavy-duty mobile platform.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the composite positioning method for a heavy-duty mobile platform as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the composite positioning method for a heavy-duty mobile platform as described in any one of claims 1 to 6.

10. A computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, characterized in that, When the program instructions are executed by the computer, the computer is able to perform the steps of the composite positioning method for a heavy-duty mobile platform as described in any one of claims 1 to 6.

Images