AUV (Autonomous Underwater Vehicle) visual dynamic docking PID (Proportion Integration Differentiation) parameter self-tuning method by utilizing fuzzy rule
Through fuzzy rules, the visual delay and loss rate are classified and the PID parameters are automatically tuned, which solves the problems of control lag and uncertainty in AUV visual docking, and achieves higher control accuracy and stability.
Patent Information
- Application Number
- CN202510479290.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-16
- Publication Date
- 2025-07-18
AI Technical Summary
During the AUV visual docking process, the visual delay and visual loss of the optical camera lead to control input lag and uncertainty, and the existing PID parameter control cannot effectively reduce control overshoot and steady-state static errors.
The visual delay and visual loss rate are classified using fuzzy rules, and the PID parameter self-tuning method is established. The PID parameters are automatically tuned through the fuzzy rules, the initial parameters are generated and self-tuned, and the PID parameters are adjusted using the maximum membership degree inverse fuzzy.
It effectively reduces control overshoot and steady-state static errors, and improves the control accuracy and stability of AUV visual docking.
Smart Images
Figure CN120335283A_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present application relate to the technical field of underwater dynamic docking, and particularly to a method for self-tuning PID parameters for AUV visual dynamic docking using fuzzy rules. Background Art
[0002] As a pioneer in ocean exploration, the Autonomous Underwater Vehicle (AUV) has the characteristics of small size and high flexibility. However, the energy it carries is limited. If underwater charging of the AUV can be achieved, it will greatly improve the depth and breadth of ocean exploration. The underwater docking technology is a technical prerequisite for realizing underwater charging of the AUV and is also one of the important technologies that must be deeply studied in ocean exploration and development. The target AUV carrying a visual marker and the docking AUV carrying an optical camera form a dual-AUV system. Visual docking is mainly used for end docking with a relative distance of 0 m to 15 m. Within this distance range, the optical camera has a higher recognition effect compared to acoustic devices.
[0003] During the visual docking process, the target AUV is in a stationary state or performing a uniform straight-line navigation task, and its control is relatively mature. Therefore, most of the research objects for docking control are the docking AUV. When the optical camera (visual camera) images, there are time delays such as exposure, data transmission, and image processing, and the image exposure time is dynamically adjusted, which results in a certain lag in the input obtained by the control system. In addition, the visual marker carried by the target AUV may be lost within the control period during actual perception. How to achieve the control of the docking AUV under the conditions of control input lag and loss has become a research difficulty. Summary of the Invention
[0004] In view of this, embodiments of the present application propose a method for self-tuning PID parameters for AUV visual dynamic docking using fuzzy rules, which can utilize fuzzy rules to self-tune PID control parameters under the conditions of control input delay and uncertainty caused by visual loss and visual delay, and reduce control overshoot and steady-state static error.
[0005] In a first aspect, an embodiment of the present application proposes a method for self-tuning PID parameters of AUV vision dynamic docking using fuzzy rules, which is applied to docking AUV. The method includes: establishing fuzzy rules, fuzzily classifying visual delay into three categories: low, medium, and high, and fuzzily classifying visual loss rate into three categories: low, medium, and high; wherein, visual delay consists of fixed delay and variable delay, and visual loss rate is the ratio of the number of images with parsing failure to the total number of images; inputting the current pose information of the docking AUV relative to the target AUV into a pre-constructed PID parameter self-tuning control model, and generating initial PID parameters by the control model based on the pose information; obtaining the current visual delay and current visual loss rate of the docking AUV, and performing fuzzy classification based on the fuzzy rules to obtain a fuzzy classification result; defuzzifying the fuzzy classification result according to the maximum membership degree to obtain the corresponding PID parameter change amount, and self-tuning the initial PID parameters based on the PID parameter change amount.
[0006] In some alternative embodiments, the PID parameter self-tuning control model is built through the following steps: Determine that the input of the PID parameter self-tuning control model is the pose information of the docking AUV relative to the target AUV, and the pose information of the docking AUV relative to the target AUV includes the relative position and relative distance between the docking AUV and the target AUV; Determine that the control output of the PID parameter self-tuning control model is the control quantity of the thruster, that is, use the thruster as the control output actuator of the PID parameter self-tuning control model; wherein, the thruster includes a main thruster, an auxiliary side thruster, and an auxiliary vertical thruster.
[0007] In some alternative embodiments, the visual delay is calculated by the following formula: ; ; Wherein, represents visual delay, represents fixed delay, represents variable delay, represents the time required for camera processing and transmission, represents the time consumed by the PNP image processing algorithm.
[0008] In some alternative embodiments, the fuzzily classifying the visual delay into three categories: low, medium, and high is achieved by the following formula: ; Wherein, represents low delay, represents medium delay, represents high delay, represents the control period.
[0009] In some alternative embodiments, the visual loss rate is calculated by the following formula: ; ; ; where, represents the visual loss rate, represents the number of images with parsing failures, , , respectively represent the number of images with parsing failures in the th control cycle, the th control cycle, and the th control cycle, represents the total number of images, , , respectively represent the total number of images in the th control cycle, the th control cycle, and the th control cycle.
[0010] In some alternative embodiments, the fuzzy classification of the visual loss rate into low, medium, and high categories is achieved by the following formula: ; where, represents the low loss rate, represents the medium loss rate, represents the high loss rate.
[0011] In some alternative embodiments, the PID parameters include the P parameter , the I parameter , and the D parameter . Based on the defuzzification of the fuzzy classification result according to the maximum membership degree, the corresponding change amount of the PID parameters is obtained, including: If the fuzzy classification result of the visual delay is low delay and the fuzzy classification result of the visual loss rate is low loss rate, then increase , decrease , and increase ; If the fuzzy classification result of the visual delay is low delay and the fuzzy classification result of the visual loss rate is medium loss rate, then increase , keep unchanged, and decrease ; If the fuzzy classification result of visual latency is low latency and the fuzzy classification result of visual loss rate is high loss rate, then reduce 、increase 、reduce ; If the fuzzy classification result of visual latency is medium latency and the fuzzy classification result of visual loss rate is low loss rate, then keep unchanged, increase 、increase ; If the fuzzy classification result of visual latency is medium latency and the fuzzy classification result of visual loss rate is medium loss rate, then keep unchanged, keep unchanged, keep unchanged; If the fuzzy classification result of visual latency is medium latency and the fuzzy classification result of visual loss rate is high loss rate, then reduce 、reduce 、increase ; If the fuzzy classification result of visual latency is high latency and the fuzzy classification result of visual loss rate is low loss rate, then increase 、reduce 、increase ; If the fuzzy classification result of visual latency is high latency and the fuzzy classification result of visual loss rate is medium loss rate, then reduce 、increase 、reduce ; If the fuzzy classification result of visual latency is high latency and the fuzzy classification result of visual loss rate is high loss rate, then reduce 、reduce 、increase .
[0012] An AUV vision dynamic docking PID parameter self-tuning method using fuzzy rules proposed by an embodiment of the present application first establishes fuzzy rules, and respectively fuzzily classifies the vision delay and the vision loss rate into three categories: low, medium, and high. Subsequently, the pose information of the docking AUV relative to the target AUV at present is input into a pre-constructed PID parameter self-tuning control model, and the control model generates initial PID parameters based on the pose information. Next, the current vision delay and the current vision loss rate of the docking AUV are obtained, and the two are fuzzily classified based on the fuzzy rules to obtain a fuzzy classification result. Finally, the PID parameter self-tuning control model defuzzifies the fuzzy classification result according to the maximum membership degree to obtain the corresponding PID parameter change amount, and self-tunes the initial PID parameters based on the PID parameter change amount. Considering that the vision delay and the vision loss have a lagging and uncertain impact on the docking control system, and it is impossible to accurately judge the control input during the control process, the PID parameter control with fixed parameters cannot meet the control requirements under the lagging and uncertain control input. It is necessary to design different PID parameters for different inputs. Therefore, the present application refines the classification of the vision delay and the vision loss rate, uses the control period as the benchmark for classifying the vision delay and the vision loss rate, and realizes the fuzzification of the delay and the loss rate. Then, fuzzy rules are designed according to expert experience to adjust the PID parameters. Finally, the current PID parameters are self-tuned through the maximum membership degree. Through the self-tuning of the PID parameters, it is possible to well reduce the overshoot and the steady-state control error of the control under different vision delays and vision loss rates.
[0013] In a second aspect, an embodiment of the present application proposes an AUV vision dynamic docking PID parameter self-tuning device, and the device includes: a fuzzy rule establishment module, a control model construction module, an acquisition module, and a fuzzy classification module; the fuzzy rule establishment module is used to establish fuzzy rules, fuzzily classify the vision delay into three categories: low, medium, and high, and fuzzily classify the vision loss rate into three categories: low, medium, and high, where the vision delay consists of a fixed delay and a variable delay, and the vision loss rate is the ratio of the number of images with parsing failures to the total number of images; the control model construction module is used to construct a PID parameter self-tuning control model; the acquisition module is used to acquire the pose information of the docking AUV relative to the target AUV at present, and is also used for the current vision delay and the current vision loss rate of the docking AUV; the fuzzy classification module is used to fuzzily classify the current vision delay and the current vision loss rate of the docking AUV based on the fuzzy rules to obtain a fuzzy classification result; the PID parameter self-tuning control model is used to generate initial PID parameters based on the pose information, defuzzify the fuzzy classification result according to the maximum membership degree to obtain the corresponding PID parameter change amount, and self-tune the initial PID parameters based on the PID parameter change amount.
[0014] In a third aspect, an embodiment of the present application provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, instructions executable by the at least one processor are stored in the memory, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute a method for self-tuning of PID parameters for AUV visual dynamic docking using fuzzy rules as described above.
[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above method for self-tuning of PID parameters for AUV visual dynamic docking using fuzzy rules is implemented.
[0016] It can be understood that the beneficial effects of the above second to fourth aspects can refer to the relevant descriptions in the first aspect above, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings required for use in the description of the embodiments of the present application or the related technical solutions will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0018] Figure 1 is a flowchart of a method for self-tuning of PID parameters for AUV visual dynamic docking using fuzzy rules provided in an embodiment of the present application; Figure 2 is a schematic diagram of the principle of a PID parameter self-tuning control model provided in an embodiment of the present application; Figure 3 is a schematic structural diagram of a device for self-tuning of PID parameters for AUV visual dynamic docking using fuzzy rules provided in an embodiment of the present application; Figure 4 is a schematic structural diagram of an electronic device provided in another embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will elaborate on each embodiment of the present application in conjunction with the accompanying drawings. However, those of ordinary skill in the art can understand that in each embodiment of the present application, many technical details are provided to help readers better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present application can still be implemented. The division of the following embodiments is for convenience of description and should not constitute any limitation on the specific implementation manner of the present application. The various embodiments can be combined and cross-referenced with each other on the premise of not being contradictory.
[0020] An embodiment of the present application proposes a method for self-tuning PID parameters for AUV visual dynamic docking using fuzzy rules, which is applied to docking AUVs. The following specifically describes the implementation details of a method for self-tuning PID parameters for AUV visual dynamic docking using fuzzy rules proposed in this embodiment. The following content is only implementation details provided for convenience of understanding and is not necessary for implementing this solution.
[0021] The specific process of a method for self-tuning PID parameters for AUV visual dynamic docking using fuzzy rules proposed in this embodiment can be as Figure 1 shown and includes: Step 101: Establish fuzzy rules. Fuzzily classify visual delay into three categories: low, medium, and high, and fuzzily classify visual loss rate into three categories: low, medium, and high. Among them, visual delay consists of fixed delay and variable delay, and visual loss rate is the ratio of the number of images with parsing failure to the total number of images.
[0022] In specific implementation, fuzzy rules are the basis for realizing self-tuning of PID parameters. Before actual self-tuning of PID parameters, it is necessary to first establish fuzzy rules. Since visual delay and visual loss have a lagging and uncertain impact on the docking control system, the fuzzy rules are established for visual delay and visual loss rate. Visual delay consists of fixed delay and variable delay, and visual loss rate is the ratio of the number of images with parsing failure to the total number of images. We fuzzily classify visual delay into three categories: low, medium, and high, and also fuzzily classify visual loss rate into three categories: low, medium, and high, thereby establishing the fuzzy rules.
[0023] In an example, visual delay consists of fixed delay and variable delay, and visual delay can be calculated by the following formula: ; ; where represents visual delay, represents fixed delay, represents variable delay, Indicates the time required for the processing and transmission of the camera. Indicates the time consumed by the PNP image processing algorithm.
[0024] In one example, the visual latency is classified into three categories: low, medium, and high. It is necessary to use the control period as the classification benchmark. The fuzzy classification rule of the visual latency can be expressed by the formula: ; Where, Indicates low latency. Indicates medium latency. Indicates high latency. Indicates the control period.
[0025] In one example, the visual loss rate is the ratio of the number of images with parsing failures to the total number of images. Since the image loss is somewhat accidental, we use three consecutive control periods as the reference time for image number statistics. The visual loss rate can be calculated by the following formula: ; ; ; Where, Indicates the visual loss rate. Indicates the number of images with parsing failures. , , Respectively represent the number of images with parsing failures in the th control period, the th control period, and the th control period. Indicates the total number of images. , , Respectively represent the total number of images in the th control period, the th control period, and the th control period.
[0026] In one example, the visual loss rate is classified into three categories: low, medium, and high. It is necessary to use two interval points, 0.3 and 0.6, as the classification benchmark. The fuzzy classification rule of the visual loss rate can be expressed by the formula: ; Where, Indicates low loss rate. Indicates medium loss rate. Indicates high loss rate.
[0027] It should be noted that a low visual loss rate and a low visual latency are beneficial to the control of the docking AUV, and the uncertainty during the control process is relatively small.
[0028] Step 102: Input the current pose information of the docking AUV relative to the target AUV into a pre-constructed PID parameter self-tuning control model, and the control model generates initial PID parameters based on the pose information.
[0029] In a specific implementation, when actually performing PID parameter self-tuning, the docking AUV obtains its own current pose information relative to the target AUV, inputs this pose information into the pre-constructed PID parameter self-tuning control model, and the PID parameter self-tuning control model generates initial PID parameters based on the pose information. The PID parameter self-tuning control model is deployed in the docking AUV and is called when needed.
[0030] In an example, the PID parameters include the P parameter , the I parameter and the D parameter , and the initial PID parameters generated by the PID parameter self-tuning control model based on the pose information are the initial P parameter , because the I parameter and the D parameter are both gradually determined based on the P parameter .
[0031] In an example, the PID parameter self-tuning control model is constructed through the following steps.
[0032] First, it is determined that the input of the PID parameter self-tuning control model is the pose information of the docking AUV relative to the target AUV, and the pose information of the docking AUV relative to the target AUV includes the relative position and relative distance between the docking AUV and the target AUV.
[0033] Subsequently, it is determined that the control output of the PID parameter self-tuning control model is the control quantity of the thruster, that is, the thruster is used as the control output actuator of the PID parameter self-tuning control model. Among them, the thrusters targeted by the ID parameter self-tuning control model include the main thruster, the auxiliary side thruster, and the auxiliary vertical thruster.
[0034] In an example, the working principle of the PID parameter self-tuning control model can be as Figure 2 shown.
[0035] Step 103: Obtain the current visual latency and current visual loss rate of the docking AUV, and perform fuzzy classification based on fuzzy rules to obtain a fuzzy classification result.
[0036] In a specific implementation, after the PID parameter self-tuning control model generates initial PID parameters based on the pose information, the docking AUV needs to obtain its current visual delay and visual loss rate, and perform fuzzy classification based on fuzzy rules to obtain a fuzzy classification result, which is then input into the PID parameter self-tuning control model. The fuzzy classification result specifically includes the fuzzy classification result of the visual delay and the fuzzy classification result of the visual loss rate.
[0037] Step 104: Defuzzify the fuzzy classification result according to the maximum membership degree to obtain the corresponding PID parameter variation, and perform self-tuning of the initial PID parameters based on the PID parameter variation.
[0038] In a specific implementation, after receiving the fuzzy classification result, the PID parameter self-tuning control model can defuzzify the fuzzy classification result according to the maximum membership degree to obtain the corresponding PID parameter variation, and perform self-tuning of the initial PID parameters based on the PID parameter variation. The fuzzy adaptive adjustment of the PID parameters can improve the response speed of the control when the image delay time or loss rate is low, and at the same time avoid excessive overshoot when the image delay time or loss rate is high.
[0039] In an example, the PID parameters include the P parameter 、the I parameter and the D parameter The corresponding relationship between the defuzzified fuzzy classification result according to the maximum membership degree and the PID parameter variation is shown in Table 1.
[0040] Table 1: Corresponding relationship between defuzzified fuzzy classification result according to the maximum membership degree and PID parameter variation
[0041] In this embodiment, first, it is necessary to establish fuzzy rules to fuzzily classify the visual delay and the visual loss rate into three categories: low, medium, and high. Subsequently, the pose information of the docking AUV relative to the target AUV is input into a pre-constructed PID parameter self-tuning control model, and the control model generates initial PID parameters based on the pose information. Next, the current visual delay and the current visual loss rate of the docking AUV are obtained, and they are fuzzily classified based on the fuzzy rules to obtain the fuzzy classification result. Finally, the PID parameter self-tuning control model defuzzifies the fuzzy classification result according to the maximum membership degree to obtain the corresponding PID parameter variation, and self-tunes the initial PID parameters based on the PID parameter variation. Considering that the visual delay and the visual loss have a lagging and uncertain impact on the docking control system and it is impossible to accurately judge the control input during the control process, the PID parameter control with fixed parameters cannot meet the control requirements under the lagging and uncertain control input. It is necessary to design different PID parameters for different inputs. Therefore, in this application, the visual delay and the visual loss rate are refined and classified, and the control period is used as the benchmark for classifying the visual delay and the visual loss rate to realize the fuzzification of the delay and the loss rate. Then, fuzzy rules are designed based on expert experience to adjust the PID parameters. Finally, the current PID parameters are self-tuned through the maximum membership degree. Through the self-tuning of the PID parameters, it is possible to well reduce the overshoot and the steady-state control error of the control under different visual delays and visual loss rates.
[0042] The step division of the above various methods is only for clear description. When implemented, they can be combined into one step or some steps can be split into multiple steps as long as the same logical relationship is included, and they are all within the protection scope of this application; adding insignificant modifications to the algorithm or process or introducing insignificant designs, but not changing the core design of its algorithm and process are all within the protection scope of this application.
[0043] Another embodiment of this application proposes an AUV vision dynamic docking PID parameter self-tuning device using fuzzy rules. The implementation details of an AUV vision dynamic docking PID parameter self-tuning device using fuzzy rules proposed in this embodiment are specifically described below. The following content is only implementation details provided for easy understanding and is not necessary for implementing this solution. The specific structure of an AUV vision dynamic docking PID parameter self-tuning device using fuzzy rules proposed in this embodiment can be as Figure 3 shown, including: A fuzzy rule establishment module 201, configured to establish fuzzy rules to fuzzily classify the visual delay into three categories: low, medium, and high, and fuzzily classify the visual loss rate into three categories: low, medium, and high, where the visual delay consists of a fixed delay and a variable delay, and the visual loss rate is the ratio of the number of images with parsing failures to the total number of images.
[0044] The control model construction module 202 is used to construct a PID parameter self-tuning control model 205.
[0045] The acquisition module 203 is used to acquire the pose information of the docking AUV relative to the target AUV at present, and is also used for the current visual delay and the current visual loss rate of the docking AUV.
[0046] The fuzzy classification module 204 is used to perform fuzzy classification on the current visual delay and the current visual loss rate of the docking AUV based on fuzzy rules to obtain a fuzzy classification result.
[0047] The PID parameter self-tuning control model 205 is used to generate initial PID parameters based on the pose information, and defuzzify the fuzzy classification result according to the maximum membership degree to obtain the corresponding PID parameter variation, and perform self-tuning on the initial PID parameters based on the PID parameter variation.
[0048] It should be noted that the control output of the PID parameter self-tuning control model 205 is the control quantity of the thruster 301, that is, the thruster 301 is used as the control output actuator of the PID parameter self-tuning control model 205.
[0049] It is worth mentioning that each module and module involved in this embodiment are all logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or can be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, units not closely related to solving the technical problems proposed in this application are not introduced in this embodiment, but this does not mean that there are no other units in this embodiment.
[0050] It is not difficult to find that this embodiment is a system embodiment corresponding to the above method embodiment. This embodiment can be implemented in cooperation with the above method embodiment. The relevant technical details and technical effects mentioned in the above method embodiment are still valid in this embodiment. To avoid repetition, they are not elaborated here. Correspondingly, the relevant technical details mentioned in this embodiment can also be applied to the above method embodiment.
[0051] Another embodiment of this application proposes an electronic device, as Figure 4 shown, including: at least one processor 401; and a memory 402 communicatively connected to the at least one processor 401; wherein, the memory 402 stores instructions executable by the at least one processor 401, and the instructions are executed by the at least one processor 401 to enable the at least one processor 401 to execute a method for self-tuning PID parameters for AUV visual dynamic docking using fuzzy rules as described in the above method embodiments.
[0052] Among them, the memory and the processor are connected in a bus manner. The bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and the memory together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and thus will not be further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single component or multiple components, such as multiple receivers and transmitters, and provides a unit for communicating with various other devices on the transmission medium.
[0053] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interface, voltage regulation, power management, and other control functions. The memory can be used to store data used by the processor when executing operations.
[0054] Another embodiment of the present application proposes a computer-readable storage medium in which a computer program is stored. When the computer program is executed by a processor, it can implement a method for self-tuning PID parameters of AUV vision dynamic docking using fuzzy rules as described in the above method embodiment.
[0055] That is, those skilled in the art can understand that all or part of the steps in the above method embodiment can be completed by instructing relevant hardware through a program. The program is stored in a storage medium and includes several instructions for causing a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the method for self-tuning PID parameters of AUV vision dynamic docking using fuzzy rules described in the above method embodiment. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories, random access memories, magnetic disks, or optical discs that can store program codes.
[0056] Those of ordinary skill in the art can understand that the above embodiments are all specific embodiments for implementing the present application, and in practical applications, various changes can be made in form and details without departing from the spirit and scope of the present application.
Claims
1. An AUV vision dynamic docking PID parameter self-tuning method using fuzzy rules, which is applied to the docking AUV, is characterized in that The method includes: Establishing fuzzy rules to fuzzily classify visual delay into three categories: low, medium, and high, and fuzzily classify visual loss rate into three categories: low, medium, and high; wherein, the visual delay consists of a fixed delay and a variable delay, and the visual loss rate is the ratio of the number of images with parsing failures to the total number of images; Inputting the current pose information of the docking AUV relative to the target AUV into a pre-constructed PID parameter self-tuning control model, and generating initial PID parameters by the control model based on the pose information; Obtaining the current visual delay and current visual loss rate of the docking AUV, and performing fuzzy classification based on the fuzzy rules to obtain a fuzzy classification result; Defuzzifying the fuzzy classification result according to the maximum membership degree to obtain the corresponding PID parameter variation amount, and self-tuning the initial PID parameters based on the PID parameter variation amount.
2. A method for self-tuning PID parameters of AUV vision dynamic docking using fuzzy rules according to claim 1, characterized in that, The PID parameter self-tuning control model is constructed through the following steps: Determining that the input of the PID parameter self-tuning control model is the pose information of the docking AUV relative to the target AUV, and the pose information of the docking AUV relative to the target AUV includes the relative position and relative distance between the docking AUV and the target AUV; Determining that the control output of the PID parameter self-tuning control model is the control amount of the thruster, that is, using the thruster as the control output actuator of the PID parameter self-tuning control model; wherein, the thruster includes a main thruster, an auxiliary side thruster, and an auxiliary vertical thruster.
3. A method for self-tuning PID parameters of AUV vision dynamic docking using fuzzy rules according to claim 1, characterized in that, The visual delay is calculated by the following formula: ； ； Among them, represents the visual delay, represents the fixed delay, represents the variable delay, represents the time required for the processing and transmission of the camera, represents the time consumed by the PNP image processing algorithm.
4. A method for self-tuning PID parameters of AUV vision dynamic docking using fuzzy rules according to claim 3, characterized in that The fuzzily classifying the visual delay into three categories: low, medium, and high is achieved through the following formula: ； Among them, represents low latency, represents medium latency, represents high latency, represents the control period.
5. A method for self-tuning of AUV vision dynamic docking PID parameters using fuzzy rules according to claim 1, characterized in that The visual loss rate is calculated by the following formula: ； ； ； Among them, represents the visual loss rate, represents the number of images with parsing failures, , , respectively represent the number of images with parsing failures in the th control period, the th control period, and the th control period, represents the total number of images, , , respectively represent the total number of images in the th control period, the th control period, and the th control period.
6. A method for self-tuning PID parameters of AUV vision dynamic docking using fuzzy rules according to claim 1, characterized in that The fuzzily classifying the visual loss rate into three categories: low, medium, and high is achieved through the following formula: ； Among them, represents a low loss rate, represents a medium loss rate, represents a high loss rate.
7. A method for self-tuning PID parameters for AUV visual dynamic docking using fuzzy rules according to any one of claims 1 to 6, characterized in that, The PID parameters include the P parameter , the I parameter and the D parameter , and obtaining the corresponding PID parameter variation according to the defuzzification of the fuzzy classification result based on the maximum membership degree includes: If the fuzzy classification result of visual latency is low latency and the fuzzy classification result of visual loss rate is low loss rate, then increase 、decrease 、increase ; If the fuzzy classification result of visual latency is low latency and the fuzzy classification result of visual loss rate is medium loss rate, then increase , keep unchanged, decrease ; If the fuzzy classification result of visual latency is low latency and the fuzzy classification result of visual loss rate is high loss rate, then reduce , increase , reduce ; If the fuzzy classification result of the visual delay is medium delay and the fuzzy classification result of the visual loss rate is low loss rate, then keep unchanged, increase , increase ; If the fuzzy classification result of visual latency is medium latency and the fuzzy classification result of visual loss rate is medium loss rate, then keep unchanged, keep unchanged, keep unchanged; If the fuzzy classification result of visual latency is medium latency and the fuzzy classification result of visual loss rate is high loss rate, then reduce 、reduce 、increase ; If the fuzzy classification result of visual latency is high latency and the fuzzy classification result of visual loss rate is low loss rate, then increase , decrease , increase ; If the fuzzy classification result of visual latency is high latency and the fuzzy classification result of visual loss rate is medium loss rate, then reduce , increase , reduce ; If the fuzzy classification result of visual latency is high latency and the fuzzy classification result of visual loss rate is high loss rate, then reduce 、reduce 、increase 。 8. An AUV vision dynamic docking PID parameter self-tuning device using fuzzy rules, characterized in that, The device includes: A fuzzy rule establishment module for establishing fuzzy rules to fuzzily classify visual delay into three categories: low, medium, and high, and fuzzily classify visual loss rate into three categories: low, medium, and high, wherein, the visual delay consists of a fixed delay and a variable delay, and the visual loss rate is the ratio of the number of images with parsing failures to the total number of images; A control model construction module for constructing a PID parameter self-tuning control model; An acquisition module for acquiring the current pose information of the docking AUV relative to the target AUV, and also for the current visual delay and current visual loss rate of the docking AUV; A fuzzy classification module for fuzzily classifying the current visual delay and current visual loss rate of the docking AUV based on the fuzzy rules to obtain a fuzzy classification result; A PID parameter self-tuning control model for generating initial PID parameters based on the pose information, defuzzifying the fuzzy classification result according to the maximum membership degree to obtain the corresponding PID parameter variation amount, and self-tuning the initial PID parameters based on the PID parameter variation amount.
9. An electronic device, characterized in that, Including: At least one processor; And, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute a method for self-tuning PID parameters for AUV vision dynamic docking using fuzzy rules according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements a method for self-tuning PID parameters for AUV vision dynamic docking using fuzzy rules according to any one of claims 1 to 7.