Robotic platform stability maintenance method, system, device, and storage medium

Abstract

The application relates to the technical field of robot control, and provides a robot platform stability maintaining method, system, device and storage medium, and solves the problem of low attitude stability of an aerial work robot caused by poor anti-interference capability of the aerial work robot in a complex dynamic environment. The method comprises the following steps: collecting acceleration, angular velocity and displacement data of a robot platform, and filtering and fusing the data to extract attitude deviation features; inputting the features into a joint mechanics model, combining hydraulic damping characteristics and joint motion constraints to generate real-time damping parameters; performing coupled operation on the attitude deviation features and the damping parameters through an adaptive sliding mode control algorithm to generate a compensation control instruction of a hydraulic drive joint; and applying the instruction to a deformable support mechanism to continuously adjust the hydraulic damping force and the joint motion trajectory so that the projection of the platform gravity center is kept within the stable boundary range of a discontinuous support surface. The application improves the anti-interference capability and the attitude stability of the aerial work robot in the complex dynamic environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robot control, and in particular to a robot platform stability maintaining method, system, device and storage medium. BACKGROUND

[0002] In high-altitude operation environment, the robot platform often faces the dual challenges of non-continuous support surface and wind disturbance, and needs to adjust the posture in real time to maintain stability, avoid imbalance or even overturning due to sudden change of support surface or strong wind disturbance, which puts high requirements on the response speed, environmental adaptability and anti-interference ability of the control system.

[0003] The existing scheme adopts data fusion technology based on inertial measurement unit and position sensor, combines proportional-integral-derivative control algorithm, and adjusts the output torque of the joint motor to realize dynamic balance of the platform posture; the scheme triggers the control instruction through the preset stability threshold to correct the inclination or deviation of the platform.

[0004] However, the scheme relies on a control model with fixed parameters, which is difficult to adapt to the dynamic changes of support surface mutation and wind disturbance in high-altitude environment, resulting in adjustment lag or overshoot phenomenon; at the same time, only relying on motor torque adjustment, lacking of collaborative optimization of hydraulic damping characteristics, the stability maintaining effect is limited under strong disturbance. SUMMARY

[0005] The present application provides a robot platform stability maintaining method, system, device and storage medium to solve the problem of low posture stability of high-altitude operation robot due to poor anti-interference ability in complex dynamic environment.

[0006] In the first aspect, the present application provides a robot platform stability maintaining method, comprising:

[0007] Obtaining real-time motion data of the robot platform;

[0008] Filtering and fusing the real-time motion data to generate a posture deviation feature;

[0009] Inputting the posture deviation feature into a pre-trained joint mechanics model, the joint mechanics model generating real-time damping parameters according to the posture deviation feature, hydraulic damping characteristics and joint motion constraints;

[0010] Based on the real-time damping parameters, combining an adaptive sliding mode control algorithm, operating the posture deviation feature to generate a compensation control instruction for the hydraulic driven joint, the compensation control instruction acting on the deformable support mechanism of the robot platform.

[0011] Optionally, the attitude deviation feature is calculated based on the real-time damping parameter and an adaptive sliding mode control algorithm to generate a compensation control instruction for the hydraulic drive joint, including:

[0012] According to the real-time damping parameter, the attenuation rate of the boundary layer thickness corresponding to the control instruction in the adaptive sliding mode control algorithm is dynamically adjusted;

[0013] The pitch rate in the attitude deviation feature is directionally weighted with the center of gravity offset value to generate a deviation correction vector matching the deformation direction of the deformable support mechanism;

[0014] The deviation correction vector is phase-lag compensated based on the adjusted attenuation rate to generate a compensation control instruction.

[0015] Optionally, the deviation correction vector is phase-lag compensated based on the adjusted attenuation rate to generate a compensation control instruction, including:

[0016] According to the correlation between the adjusted attenuation rate and the disturbance frequency, the time delay required for phase-lag compensation is determined;

[0017] The component in the deviation correction vector that is co-directional with the mutation direction of the non-continuous support surface is segmented and translated by the time delay to generate a correction component;

[0018] The extension acceleration of the hydraulic drive joint is nonlinearly scaled based on the correction component;

[0019] According to the nonlinearly scaled extension acceleration and the correction component, a compensation control instruction is generated.

[0020] Optionally, the extension acceleration of the hydraulic drive joint is nonlinearly scaled based on the correction component, including:

[0021] According to the mutation amplitude of the non-continuous support surface, a scaling range corresponding to the amplitude change rate of the correction component is determined;

[0022] Based on the proportion of the component in the correction component that is co-directional with the mutation direction of the non-continuous support surface, a dynamic adjustment coefficient of the amplitude change rate in the scaling range is calculated;

[0023] The product of the dynamic adjustment coefficient and the adjusted attenuation rate is taken as a scaling factor of the extension acceleration;

[0024] The extension acceleration is nonlinearly scaled according to the scaling factor.

[0025] Optionally, the joint mechanics model generates real-time damping parameters according to the attitude deviation feature, the hydraulic damping characteristic, and the joint motion constraint, including:

[0026] The joint mechanics model establishes a reverse correlation between the hydraulic damping characteristic and the joint extension rate through the establishing module.

[0027] The joint mechanics model calculates the target deformation angle of each hydraulic drive joint according to the pitch rate in the attitude deviation feature through the calculation module.

[0028] Based on the target deformation angle of each hydraulic drive joint, the allowed deformation range of each hydraulic drive joint is determined in combination with the target angle threshold in the joint motion constraint.

[0029] Within the allowed deformation range, the center of gravity offset value in the attitude deviation feature is mapped to the pressure regulation coefficient of the hydraulic circuit according to the reverse correlation to generate real-time damping parameters.

[0030] Optionally, the mapping of the center of gravity offset value in the attitude deviation feature to the pressure regulation coefficient of the hydraulic circuit according to the reverse correlation within the allowed deformation range to generate real-time damping parameters includes:

[0031] According to the proportional relationship between the mutation amplitude of the non-continuous support surface and the allowed deformation range, the adjustable interval of the pressure regulation coefficient is determined.

[0032] Based on the reverse correlation, the center of gravity acceleration of the center of gravity offset value is converted to the pressure growth gradient of the hydraulic circuit.

[0033] According to the distribution law of the pressure growth gradient in the adjustable interval, in combination with the pressure fluctuation of the hydraulic circuit, real-time damping parameters are generated.

[0034] Optionally, the real-time motion data includes acceleration, angular velocity, and visual positioning data.

[0035] The filtering and fusion processing of the real-time motion data to generate the attitude deviation feature includes:

[0036] Based on the displacement mutation feature of the non-continuous support surface, the acceleration and the angular velocity are respectively filtered.

[0037] The displacement offset in the visual positioning data is matched with the filtered acceleration, and the first deviation component corresponding to the vertical direction of the robot platform and the second deviation component corresponding to the horizontal direction are extracted from the matching result.

[0038] According to a synthetic vector direction of the first deviation component and the second deviation component, a posture deviation feature is generated in combination with a filtered angular velocity.

[0039] In a second aspect, the present application provides a robot platform stability maintaining system, comprising:

[0040] An acquisition module is configured to acquire real-time motion data of the robot platform.

[0041] A processing module is configured to perform filtering fusion processing on the real-time motion data to generate a posture deviation feature.

[0042] An input module is configured to input the posture deviation feature into a pre-trained joint mechanics model, and the joint mechanics model is configured to generate real-time damping parameters according to the posture deviation feature, hydraulic damping characteristics and joint motion constraints.

[0043] A generation module is configured to perform operation on the posture deviation feature based on the real-time damping parameters and in combination with an adaptive sliding mode control algorithm to generate a compensation control instruction for a hydraulic driving joint, and the compensation control instruction is configured to act on a deformable support mechanism of the robot platform.

[0044] In a third aspect, the present application provides a computing device comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the robot platform stability maintaining method of any one of the first aspect.

[0045] In a fourth aspect, the present application provides a computer storage medium storing computer program instructions, and the computer program instructions are executed by a processor to implement the robot platform stability maintaining method of any one of the first aspect.

[0046] The technical solution provided by the present application has the following beneficial effects:

[0047] The present application firstly comprehensively perceives the instantaneous motion state of the robot platform in the high-altitude dynamic environment through the multi-sensor cooperative acquisition mode, thereby providing accurate input data for the subsequent control link; on this basis, the sensor noise interference is effectively eliminated, the feature quantity reflecting the actual posture change of the platform is accurately extracted, and then a reliable basis is provided for the stability control of the platform; subsequently, the damping adjustment parameters matched with the current posture deviation are output in combination with the mechanics characteristics and the environmental constraint conditions, and the damping adjustment parameters are used as the adjustment reference with physical adaptation ability in the subsequent control algorithm; finally, the optimal control quantity is calculated in real time through the intelligent algorithm, and the corresponding action of the executing mechanism is accurately guided, so that the platform can always maintain a stable state in the complex high-altitude dynamic environment.

[0048] Further, the application also dynamically adjusts the boundary layer thickness decay rate of the control algorithm through the real-time damping parameter, simultaneously directionally weights the inclination rate and the gravity center offset value to generate a deviation correction vector, and compensates the phase lag of the vector based on the adjusted decay rate, and finally generates a compensation control instruction, which realizes the dynamic adaptation of the control parameter and the environmental disturbance, effectively solves the response lag problem of the hydraulic system, and ensures the synchronization of the control instruction and the actual demand through the accurate phase compensation, thereby improving the stability control precision of the aerial work robot in the complex dynamic environment.

[0049] These aspects or other aspects of the present application will be more apparent in the following description of the embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort.

[0051] Figure 1 A flow chart of a robot platform stability maintaining method provided by an embodiment of the present application;

[0052] Figure 2 A structural schematic diagram of a robot platform stability maintaining system provided by an embodiment of the present application;

[0053] Figure 3 A structural schematic diagram of a computing device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

[0055] In some processes described in the specification and claims of the present application and the above description, a plurality of operations appearing in a specific order are included, but it should be clearly understood that these operations can be executed or in parallel without the order appearing in the text. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes can include more or fewer operations, and the operations can be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in the text are used to distinguish different messages, devices, modules, etc., and do not represent the order of sequence, nor do "first" and "second" represent different types.

[0056] In the field of high-altitude operation robot stability control, the existing technology mainly adopts a scheme of PID control based on fixed parameters combined with motor torque adjustment, and the core defect is that the control model lacks adaptability to the dynamic characteristics of non-continuous support surface and wind disturbance: on the one hand, the preset stability threshold cannot match the mutation amplitude and direction change of the support surface in real time, resulting in adjustment lag or overshoot; on the other hand, simply relying on motor torque adjustment while ignoring the cooperative optimization of hydraulic system damping characteristics makes it difficult to achieve accurate phase compensation under strong wind disturbance, causing platform oscillation or response delay; these problems essentially result from the structural contradiction between static control architecture and dynamic environmental demand.

[0057] In view of the above limitations, the present application proposes a robot platform stability maintenance method, which is innovative in that it constructs a posture deviation feature through real-time motion data, quantifies the hydraulic damping characteristics as real-time parameters adapted to the environment in combination with the joint mechanics model, and finally generates a control instruction with phase compensation capability through an adaptive sliding mode algorithm; this method has broken through three levels of dynamic adaptation: online matching of support surface mutation characteristics and filtering parameters, real-time mapping of wind disturbance intensity and damping parameters, and cooperative optimization of hydraulic delay effect and control boundary, thereby fundamentally solving the stability defects caused by insufficient environmental dynamic identification and actuator response mismatch in the prior art.

[0058] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0059] Figure 1 A flowchart of a robot platform stability maintenance method provided by an embodiment of the present application is shown in Figure 1 The method comprises the following steps:

[0060] Step 101: Obtain real-time motion data of the robot platform.

[0061] In step 101, the robot platform is a robot platform of a contact net self-wheel operation and maintenance equipment vehicle group;

[0062] The real-time motion data mainly includes the following contents: acceleration and angular velocity collected by the six-axis inertial sensor of the contact net self-wheel operation and maintenance equipment vehicle group robot platform in real time, and visual positioning data of the platform relative to the contact net support structure obtained by the visual sensor;

[0063] And, the real-time motion data is obtained in a high-altitude dynamic environment in which the robot platform is on a non-continuous support surface and is disturbed by wind force, wherein the non-continuous support surface refers to a characteristic that a support surface contacted by the robot platform during high-altitude operation has discontinuous, abrupt or intermittent contact, such as a high-altitude scaffold gap, a joint of a temporarily built platform and the like, which causes the discontinuity of the support surface.

[0064] The wind disturbance represents a dynamic disturbance force generated by airflow movement in a high-altitude environment on the robot platform, which can cause unexpected displacement or inclination of the platform; the high-altitude dynamic environment refers to an operation environment with a height greater than or equal to 5 meters from the ground, in which the influence of wind disturbance and discontinuity of the support surface on the stability of the platform is enhanced.

[0065] Step 102: performing filtering and fusion processing on the real-time motion data to generate a posture deviation feature.

[0066] In step 102, the posture deviation feature represents a feature quantity obtained after processing and used to reflect the difference between the actual posture of the platform and the expected posture.

[0067] In the embodiments of the present application, the acceleration and the angular velocity are respectively subjected to dynamic balance filtering processing to eliminate high-frequency noise disturbance caused by wind disturbance; meanwhile, the platform displacement information in the visual positioning data is subjected to trajectory matching analysis with the filtered acceleration data, and then the first deviation component of the platform in the vertical direction and the second deviation component of the platform in the horizontal direction are extracted therefrom; finally, the posture deviation feature containing the inclination change rate of the platform and the center of gravity offset value is generated through vector composition operation in combination with the filtered angular velocity data.

[0068] For example, when the catenary self-wheel operation and maintenance equipment vehicle group robot platform performs catenary maintenance operation at a height of 5 meters, the six-axis inertial sensor detects that the platform has longitudinal acceleration change and angular velocity change around the horizontal axis, and the visual sensor identifies that the platform has lateral displacement relative to the catenary support structure; these data are collected and transmitted to the processing unit in real time, wherein the longitudinal acceleration change is the motion feature of the platform in the track direction, the angular velocity change around the horizontal axis reflects the possible inclination of the platform, and the lateral displacement indicates the relative position change of the platform and the support structure.

[0069] In the above high-altitude operation scenario, the processing unit first matches and analyzes the filtered longitudinal acceleration data and the visually positioned lateral displacement data, extracts the gravity projection deviation in the vertical direction, which indicates that the platform center of gravity has deviated from the predetermined position, and extracts the inertial deviation data in the horizontal direction, which further indicates that the platform has a risk of lateral sliding; finally, the attitude deviation characteristics are obtained by comprehensive analysis combined with the angular velocity data, which clearly show that the platform is tilting outward at a certain rate, and the center of gravity deviation is increasing continuously.

[0070] Step 103: inputting the attitude deviation characteristics into a pre-trained joint mechanics model, and generating real-time damping parameters according to the attitude deviation characteristics, hydraulic damping characteristics, and joint motion constraints.

[0071] In step 103, the hydraulic damping characteristics represent the relationship between the resistance generated by the hydraulic system during movement and the speed, and the joint motion constraints represent the motion range and mechanical characteristics of each joint under the mechanical structure restriction.

[0072] The real-time damping parameters are the hydraulic adjustment amounts calculated by the joint mechanics model and dynamically adapted to the current environment, and the values thereof are determined by the inclination change rate in the attitude deviation characteristics, the hydraulic system damping characteristic curve, and the joint motion constraint range, and are used to guide the hydraulic system to generate the accurate damping force required to suppress the attitude deviation of the platform.

[0073] In the embodiments of the present application, the attitude deviation characteristics are input into a pre-established joint mechanics model, which calculates the target deformation angle of each joint according to the current inclination change rate of the platform; at the same time, the damping characteristic curve of the hydraulic system at different speeds and the mechanical motion constraint range of each joint are combined to determine the optimal real-time damping parameters through mechanical balance calculation; these parameters reflect the hydraulic system adjustment amount required to maintain the stability of the platform under the current environmental conditions.

[0074] For example, for the case that the platform tilts outward, first, the mechanical model is used to calculate the extension amount of the four corner support joints of the platform to restore the balance state; then, according to the hydraulic system characteristic curve, it is determined that the damping force of the outer support joints needs to be increased to effectively suppress the tilting trend; at the same time, considering the constraint conditions such as the maximum allowable extension amount of each support joint, the real-time damping parameters are generated, which can clearly indicate that the damping force of the two outer support joints needs to be increased, while the damping force of the two inner support joints remains unchanged.

[0075] Step 104: based on the real-time damping parameter, combining an adaptive sliding mode control algorithm, operating the attitude deviation feature to generate a compensation control instruction for the hydraulic drive joint, which acts on the deformable support mechanism of the robot platform.

[0076] In step 104, the hydraulic drive joint is the power execution component of the robot platform, which drives the deformation and movement of the deformable support mechanism through the hydraulic circuit to adjust the attitude and position of the entire robot platform; the compensation control instruction represents the control signal for correcting the platform attitude deviation; the deformable support mechanism represents the mechanical structure that can adjust the platform attitude by deformation.

[0077] In the embodiments of the present application, first, the adaptive sliding mode control algorithm is used to adjust the thickness variation rate of the control boundary layer based on the real-time damping parameter, so that it matches the current environmental disturbance intensity; then the attitude deviation feature is directionally sensitive weighted to generate a deviation correction vector corresponding to the platform deformation direction; finally, the phase compensation algorithm is used to eliminate the influence of the response delay of the hydraulic system, and accurate hydraulic drive joint control instructions are generated; these instructions act on the deformable support mechanism of the platform, and by adjusting the hydraulic damping force and extension position of each support point, the platform center of gravity is returned to the stable range.

[0078] For example, in a 5-meter high-altitude operation scene, the control algorithm adjusts the control strategy according to the real-time damping parameter, generates instructions to increase the pressure of the outer side support hydraulic cylinder for the case of platform tilting on the outer side; considering the response delay characteristics of the hydraulic system, control signals can be sent in advance at a preset interval, such as 0.3 seconds; after the hydraulic system executes these instructions, the platform outer side support force gradually increases, effectively suppressing the tilting trend, and after a certain time adjustment, the platform center of gravity can be returned to the center area of the support surface, and then restored to a stable state.

[0079] The robot platform stability maintenance method provided by the present application accurately identifies the platform attitude change through multi-sensor data fusion, then calculates the optimal adjustment parameter based on the mechanical model, and generates accurate control instructions using an intelligent control algorithm, achieving rapid and stable control of the catenary self-wheel maintenance equipment vehicle set in a high-altitude complex environment. This method effectively overcomes the stability challenges brought by non-continuous support surfaces and wind disturbances, ensuring the safety and reliability of high-altitude operations.

[0080] In order to further improve the control accuracy of the operation robot platform in a complex dynamic environment, in some embodiments, step 104: based on the real-time damping parameter, combining an adaptive sliding mode control algorithm, operating the attitude deviation feature to generate a compensation control instruction for the hydraulic drive joint, includes:

[0081] Step 201: dynamically adjusting the decay rate of the boundary layer thickness corresponding to the control instruction in the adaptive sliding mode control algorithm according to the real-time damping parameter.

[0082] In step 201, the decay rate of the boundary layer thickness refers to the parameter adjustment rate for smoothing the change of the control instruction in the adaptive sliding mode control algorithm, which directly affects the balance between the system anti-interference ability and the response speed.

[0083] In the embodiments of the present application, the current environmental disturbance intensity is judged according to the size of the real-time damping parameter. When the damping parameter is larger, it corresponds to stronger wind disturbance or sudden change of the supporting surface. At this time, the decay rate of the boundary layer thickness is accelerated to improve the system response speed. Conversely, the decay rate is slowed down to ensure the control stability. Exemplarily, this adjustment process can be realized through a preset damping parameter-decay rate mapping relationship.

[0084] Step 202: directionally weighting the pitch rate of change in the attitude deviation feature and the center of gravity offset value to generate a deviation correction vector matched with the deformation direction of the deformable support mechanism.

[0085] In step 202, the pitch rate of change refers to the change amount of the tilt angle per unit time of the robot platform, which can be obtained by attitude deviation feature extraction. Specifically, it can be calculated by coordinate transformation of the filtered and fused angular velocity, and is used to reflect the fast or slow degree of platform attitude imbalance. The center of gravity offset value represents the deviation distance of the platform center of gravity from the ideal support position, which is calculated by vector composition of the first and second deviation components, and is used to reflect the severity of platform imbalance.

[0086] The deviation correction vector is a spatial vector composed of the direction of the pitch rate of change and the weighted center of gravity offset value. Its direction indicates the direction in which the deformable support mechanism needs to be deformed, and its amplitude represents the required adjustment intensity. The deviation correction vector is used to generate accurate compensation control instructions.

[0087] In the embodiments of the present application, the direction of the pitch rate of change is first analyzed to determine the main tilt direction of the platform, and then the adjustment intensity required in each direction is calculated in combination with the center of gravity offset value. Finally, a deviation correction vector completely matched with the deformation demand of the support mechanism is generated through vector composition. This vector not only contains the spatial direction information that needs to be adjusted, but also contains the specific adjustment amount in each direction.

[0088] Step 203: phase lag compensation is performed on the deviation correction vector based on the adjusted decay rate to generate a compensation control instruction.

[0089] In step 203, the adjusted decay rate reflects the optimal control rhythm under the current environment.

[0090] In the embodiments of the present application, the expected delay time of the hydraulic system is calculated according to the adjusted attenuation rate, and then the control quantity in the deviation correction vector is shifted forward by the time amount, while the control quantity amplitude is dynamically scaled according to the attenuation rate, and finally the generated compensation control instruction can accurately match the actual response characteristics of the hydraulic system.

[0091] The following is a specific example:

[0092] When the catenary self-wheel operation and maintenance equipment vehicle group robot platform is performing maintenance work at a height of 5 meters, when the system detects that the platform is tilting outward at a rate of 0.5 degrees per second and the center of gravity offset reaches 15 centimeters, first determine that the outer support joint needs to increase the damping force by 30% according to the real-time damping parameter, and use the adaptive sliding mode control algorithm to adjust the attenuation rate of the boundary layer thickness to 2 millimeters per second. The attenuation rate value of the boundary layer thickness can be obtained by querying the mapping relationship table of the damping parameter and the preset mapping relationship table.

[0093] Then, the 0.5-degree per second tilt rate and the 15-centimeter per second center of gravity offset value are directionally weighted according to a 1:2 ratio, and in the weighting process, the proportional coefficient is determined as the deformation sensitivity parameter of the support mechanism according to the platform structure characteristics, and a deviation correction vector pointing to the inside of the track with an amplitude of 35 centimeters is generated.

[0094] Finally, based on the adjusted attenuation rate, it is calculated that the hydraulic system has a response delay of 0.3 seconds, which is determined by the ratio of the length of the hydraulic pipeline and the flow rate of the oil, and accordingly the deviation correction vector is sent 0.3 seconds in advance, and the control quantity amplitude is enlarged by 1.2 times to compensate for the attenuation effect, to generate a compensation control instruction.

[0095] In the embodiments of the present application, the method realizes rapid and accurate control of the high-altitude operation robot in complex environment by dynamically adjusting the control parameters, accurately calculating the correction requirements, and intelligently compensating for the system delay, thereby improving the stability maintenance capability of the platform under the conditions of non-continuous support surface and wind disturbance.

[0096] In order to further improve the control accuracy of the operation robot platform in complex dynamic environment, in some embodiments, step 203: the phase lag compensation of the deviation correction vector based on the adjusted attenuation rate is performed to generate a compensation control instruction, comprising:

[0097] Step 301: according to the correlation between the adjusted attenuation rate and the disturbance frequency, determine the time delay required for phase lag compensation.

[0098] In step 301, the disturbance frequency can refer to the wind-induced disturbance frequency, which can be obtained by analyzing the periodic fluctuation component in the inertial sensor data; the time delay amount refers to the time length required to issue the control instruction in advance to compensate for the response lag of the hydraulic system, which is determined by the decay rate and the disturbance frequency, wherein the faster the decay rate or the higher the disturbance frequency, the smaller the required time delay amount.

[0099] In the embodiments of the present application, the system response requirement reflected by the adjusted decay rate is first analyzed, and then based on the system response requirement and in combination with the real-time monitored wind disturbance main frequency component, the optimal compensation time is determined through a preset delay amount calculation model, so as to ensure accurate matching of the control instruction and the hydraulic execution time.

[0100] Step 302: segmentally translating the component in the deviation correction vector that is in the same direction as the mutation direction of the non-continuous support surface according to the time delay amount to generate a correction component.

[0101] In step 302, the mutation direction can be obtained by analyzing the change trend of the displacement offset, which is the displacement of the robot platform relative to the non-continuous support surface, and the correction component is a control quantity vector that is adjusted by time shifting and has a time advance feature.

[0102] In the embodiments of the present application, the component in the deviation correction vector that is consistent with the mutation direction of the support surface is first identified, and then the component is translated forward according to the calculated time delay amount, while keeping other direction components unchanged, to generate a correction component that can compensate for the hydraulic delay and maintain spatial coordination.

[0103] Step 303: nonlinearly scaling the extension and retraction acceleration of the hydraulic drive joint based on the correction component.

[0104] In step 303, the extension and retraction acceleration can be determined by the control quantity amplitude change rate in the correction component, which can be obtained by calculating the change amount of the component in unit time, and the extension and retraction acceleration is used to reflect the speed change rate required by the hydraulic drive joint to match the platform posture adjustment requirement.

[0105] In the embodiments of the present application, the speed adjustment requirement of the hydraulic drive joint is first scaled dynamically according to the amplitude change trend of the control quantity in each direction of the correction component, and then the adjustment gradient is increased in the fast change direction and decreased in the slow change direction, thereby realizing accurate and efficient speed control.

[0106] Step 304: generating a compensation control instruction according to the nonlinearly scaled extension and retraction acceleration and the correction component.

[0107] In the embodiment of the present application, the adjusted gradient of the nonlinearly scaled velocity in each direction is fused with the spatial information of the correction component to generate a multi-dimensional control instruction that has both time accuracy and reasonable amplitude, which can ensure that each hydraulic drive joint cooperatively completes the stable adjustment of the platform.

[0108] The following is a specific example:

[0109] In the process of the catenary self-wheel operation and maintenance equipment vehicle group robot platform at 5 meters high altitude maintenance operation, when the system detects that the platform tilts outward at a rate of 0.5 degrees per second and the center of gravity deviates by 15 centimeters, first, according to the adjusted boundary layer thickness decay rate of 2 millimeters per second and the detected disturbance frequency of 0.4 hertz, the time delay amount is determined by the delay amount calculation formula T=K / (vxf), where T is the time delay amount, K is a system constant, v is the decay rate, and f is the wind frequency. In the example, when K is 0.24, v is 2 millimeters per second, and f is 0.4 hertz, the time delay amount is calculated to be 0.3 seconds.

[0110] Subsequently, the component in the deviation correction vector that is the same as the mutation direction of the track outer side support surface is processed 0.3 seconds in advance, while the components in other directions remain unchanged, to generate a correction component containing time compensation; then, according to the change trend of the outer side support control amount amplitude in the component from 0 to 35 centimeters in 0.5 seconds, the telescopic acceleration is calculated to be 70 centimeters per second, and the gradient value is nonlinearly amplified by 1.3 times according to the platform dynamic response requirement.

[0111] The finally generated compensation control instruction is used to control the outer side support hydraulic cylinder to act 0.3 seconds in advance at a regulation speed of 91 centimeters per second, so that the tilted platform is corrected to the safe range within 3.5 seconds, and the center of gravity deviation is controlled within 2 centimeters, wherein the stable time of 3.5 seconds is calculated by the platform mass of 10 tons, the maximum output of the hydraulic system of 50 kilonewtons, and other parameters.

[0112] In the embodiment of the present application, the method realizes effective compensation of the response delay of the hydraulic system by accurately calculating the compensation time, intelligently adjusting the control amount timing, and dynamically optimizing the regulation amplitude, thereby ensuring the fast, accurate and stable control of the high-altitude operation robot under the conditions of wind disturbance and non-continuous support surface.

[0113] In order to further improve the control accuracy of the operation robot platform in the non-continuous support surface environment, in some embodiments, step 303: based on the correction component, the telescopic acceleration of the hydraulic drive joint is nonlinearly scaled, comprising:

[0114] Step 401: according to the mutation amplitude of the non-continuous support surface, determine the scaling range corresponding to the amplitude change rate of the correction component.

[0115] In step 401, the amplitude change rate is calculated by the instantaneous amplitude differential of the correction component, reflecting the rate change of the robot platform center of gravity offset; the scaling range refers to the reasonable interval of the adjustment amplitude of the control quantity determined according to the mutation degree of the support surface, and the upper and lower threshold values thereof are positively correlated with the mutation amplitude of the support surface. The greater the mutation amplitude is, the wider the allowed adjustment range is.

[0116] In the embodiments of the present application, the minimum and maximum adjustment threshold values of the amplitude change rate of the correction component are determined based on the specific size characteristics of the current support surface mutation and in combination with the platform structure stability requirement, thereby providing a reference range for subsequent scaling.

[0117] For example, when the catenary self-wheel operation and maintenance equipment vehicle group robot platform is operating at a height of 5 meters, if it is detected that the right side of the track support surface suddenly sinks by 8 centimeters, firstly, the minimum stable adjustment threshold value corresponding to the size mutation is determined to be 0.6 and the maximum safe adjustment threshold value is determined to be 1.8 according to the platform structure stability analysis model; wherein the minimum threshold value 0.6 is calculated by the formula: minimum threshold value = 0.5 + 8 x 0.0125, wherein 0.5 is the base value, 8 is the mutation size (unit: centimeter), and 0.0125 is the preset coefficient; the maximum threshold value 1.8 is determined by the formula: maximum threshold value = 1.5 + mutation size 8 centimeters x coefficient 0.0375, wherein 1.5 is the base value, 8 is the mutation size (unit: centimeter), and 0.0375 is the preset coefficient. The above two base values and coefficients can be obtained from a preset database; meanwhile, considering that the current wind level is level 3, the maximum threshold value is corrected by a reduction coefficient of 0.9, and finally the allowed adjustment threshold value range of the amplitude change rate of the correction component is determined to be 0.6 to 1.62.

[0118] Step 402: based on the proportion of the component in the correction component that is in the same direction as the mutation direction of the discontinuous support surface, a dynamic adjustment coefficient of the amplitude change rate in the scaling range is calculated.

[0119] In step 402, the mutation direction is used to describe the spatial trend of the mutation, and the mutation amplitude is used to describe the mutation degree, so the two are used together to quantify the disturbance characteristics of the high-altitude dynamic environment; the component proportion refers to the proportion of the control quantity in the correction component that is consistent with the mutation direction of the support surface, which can reflect the demand intensity of the current main adjustment direction; the dynamic adjustment coefficient is an adjustment intensity parameter calculated according to the proportion in the threshold value range.

[0120] In the embodiments of the present application, the proportion of the module length of the vector in the same direction as the support surface mutation to the total module length in the correction component is calculated, and then the proportion is mapped into a preset threshold value range. In the mapping process, a dynamic adjustment coefficient reflecting the current environmental demand can be obtained by interpolation calculation.

[0121] Step 403: multiplying the dynamic adjustment coefficient and the adjusted attenuation rate to obtain a scaling factor of the expansion acceleration.

[0122] In step 403, the scaling factor is a comprehensive parameter finally used to adjust the expansion acceleration, which is determined by the dynamic adjustment coefficient and the attenuation rate, so that the environmental demand and the system response characteristics can be considered.

[0123] In the embodiments of the present application, the scaling factor considering the sudden change demand of the support surface and the system response ability can be obtained by multiplying the calculated dynamic adjustment coefficient and the adjusted attenuation rate.

[0124] Step 404: nonlinearly scaling the expansion acceleration according to the scaling factor.

[0125] In the embodiments of the present application, the original expansion acceleration is adjusted by using the scaling factor. For example, the scaling ratio in the gradient component corresponding to the sudden change direction is greater than that in other directions, so that accurate directional control is realized.

[0126] In the embodiments of the present application, the method realizes rapid and accurate stable control of the aerial work robot under the condition of non-continuous support surface by dynamically determining the adjustment range, accurately calculating the adjustment strength, and directionally optimizing the control gradient, thereby effectively overcoming the imbalance risk caused by the sudden change of the support surface.

[0127] In order to further improve the accuracy of the work robot platform in the multi-degree-of-freedom joint collaborative control, in some embodiments, step 103: the joint mechanical model generates real-time damping parameters according to the attitude deviation characteristics, the hydraulic damping characteristics, and the joint motion constraints, including:

[0128] Step 501: establishing, by the establishing module of the joint mechanical model, an inverse correlation relationship between the hydraulic damping characteristics and the joint expansion rate.

[0129] In step 501, the establishing module is a parameterized mathematical model obtained by fitting experimental data; the inverse correlation relationship refers to the negative correlation between the damping force of the hydraulic system and the joint motion speed, which is specifically manifested as that when the damping force increases, the joint expansion speed correspondingly decreases, and this relationship can be determined by the fluid mechanics characteristics of the hydraulic system.

[0130] In the embodiments of the present application, the quantitative relationship curve between the damping force and the joint speed is established by analyzing the pressure loss characteristics of the hydraulic oil at different flow rates, which reflects the inherent energy dissipation characteristics of the hydraulic system and provides a theoretical basis for subsequent parameter mapping.

[0131] Step 502: calculating, by a calculation module of the joint mechanics model, a target deformation angle of each hydraulic driving joint according to the inclination rate of change in the attitude deviation feature.

[0132] In step 502, the calculation module is a solver based on the robot kinematics model; the target deformation angle refers to an angle that each hydraulic driving joint needs to reach to compensate for the attitude deviation of the platform, which can be calculated by the inclination rate of change and the joint kinematics relationship.

[0133] In the embodiments of the present application, the angle that each hydraulic driving joint needs to adjust is calculated according to the inclination rate of change in the attitude deviation feature and the proportional relationship between each joint and the center of gravity of the platform, and these angle quantities constitute the control target of joint cooperative movement; for example, when the robot platform encounters lateral wind disturbance during operation at a height of 5 meters, the inclination rate of change is detected to be 5° / s based on the attitude deviation feature, and the target deformation angle of the robot hip joint is calculated to be 15° and the knee joint is 10° according to the movement constraint of the robot hip joint in the joint mechanics model, and the target deformation angle is used to generate matching real-time damping parameters to stabilize the platform attitude.

[0134] Step 503: determining an allowed deformation range of each hydraulic driving joint based on the target deformation angle of each hydraulic driving joint and the target angle threshold in the joint movement constraint.

[0135] In step 503, the target angle threshold is an important parameter to ensure mechanical safety; the allowed deformation range refers to the angle interval within which each hydraulic driving joint can safely work under the limitation of mechanical structure, and the upper and lower threshold values of the interval can be determined by the physical structure parameters of the joint.

[0136] In the embodiments of the present application, the calculated target deformation angle is compared with the maximum movement angle allowed by each joint design, and then the angle exceeding the safe range is limited to ensure that all joints work within the range allowed by the mechanical structure.

[0137] Step 504: within the allowed deformation range, mapping the center of gravity offset value in the attitude deviation feature to a pressure adjustment coefficient of a hydraulic circuit according to the reverse correlation relationship to generate real-time damping parameters, the hydraulic circuit being generated by the joint mechanics model according to the hydraulic damping characteristics.

[0138] In step 504, the pressure adjustment coefficient is a dimensionless parameter reflecting the size of the damping force required by the hydraulic system, and its value is positively correlated with the center of gravity offset degree and the joint movement demand.

[0139] In the embodiments of the present application, within the determined allowable deformation range, the center of gravity offset value is converted into the corresponding pressure demand of the hydraulic system according to the reverse correlation, and the damping parameters that can effectively stabilize the platform and will not cause overload of the hydraulic system are generated considering the real-time motion state of each joint.

[0140] In the embodiments of the present application, the method realizes rapid and accurate stabilization of the high-altitude operation robot platform under multi-degree-of-freedom cooperative control by establishing an accurate hydraulic-mechanical relationship model, reasonably calculating joint motion requirements, strictly guaranteeing the mechanical safety range, and intelligently generating damping parameters, effectively overcoming the attitude control problem under complex environment.

[0141] In order to further improve the accuracy of the damping parameter generation of the operation robot platform, in some embodiments, step 504: the center of gravity offset value in the attitude deviation feature is mapped into the pressure regulating coefficient of the hydraulic circuit within the allowable deformation range according to the reverse correlation to generate real-time damping parameters, comprising:

[0142] Step 601: determining the adjustable interval of the pressure regulating coefficient according to the proportional relationship between the mutation amplitude of the discontinuous support surface and the allowable deformation range.

[0143] In step 601, the proportional relationship reflects the dynamic balance between environmental disturbance and mechanical capability; for example, when the unilateral support surface of the robot platform suddenly subsides by 200 mm, the maximum deformation range allowed by the joint mechanical model is ± 150 mm, and the proportional relationship is 200: 150 = 4: 3, the upper limit of the adjustable interval of the pressure regulating coefficient needs to be compressed to 75% of the original design to avoid joint over-limit deformation.

[0144] And the above adjustable interval refers to the effective range of the allowable change of the pressure regulating coefficient, and the upper and lower threshold values thereof can be determined by the ratio of the support surface mutation degree to the joint allowable deformation capability, for example, the larger the mutation or the smaller the deformation capability, the narrower the corresponding interval range.

[0145] In the embodiments of the present application, the ratio of the support surface mutation size to the maximum allowable deformation angle of the joint is calculated first, and then the ratio is mapped onto the preset pressure regulating interval reference value to obtain an operable range that meets the stability requirement and does not exceed the mechanical limit.

[0146] Step 602: converting the center of gravity acceleration of the center of gravity offset value into the pressure growth gradient of the hydraulic circuit based on the reverse correlation.

[0147] In step 602, the center of gravity acceleration is a change trend index obtained by time-differentiating the center of gravity offset value; the pressure growth gradient represents the rate of change of the hydraulic circuit pressure with respect to time, and its value is positively correlated with the acceleration speed of the center of gravity offset.

[0148] In the embodiment of the present application, the instantaneous change speed of the center of gravity offset is converted into the equivalent pressure demand change speed of the hydraulic circuit according to the reverse correlation relationship, which can ensure that the adjustment process of the damping force matches the development speed of the platform imbalance.

[0149] Step 603: According to the distribution rule of the pressure growth gradient in the adjustable interval, and combining the pressure fluctuation of the hydraulic circuit, a real-time damping parameter is generated.

[0150] In step 603, the distribution rule describes a reasonable distribution method of the pressure gradient in the adjustable interval; the current wind disturbance intensity refers to the size of the lateral thrust generated by the instantaneous wind speed in the high-altitude environment on the robot platform, and the disturbance intensity can be measured in real time through the fluctuation amplitude of the lateral acceleration in the six-axis inertial sensor; the pressure fluctuation amount refers to the periodic fluctuation component of the hydraulic circuit pressure caused by wind disturbance, and the amplitude is positively correlated with the wind disturbance intensity, which can be obtained in real time through the mapping relationship table of wind grade and pressure fluctuation in historical data.

[0151] In the embodiment of the present application, first, the position distribution of the pressure growth gradient in the adjustable interval is analyzed, then the pressure fluctuation component corresponding to the current wind grade is superimposed, and finally the comprehensive damping parameter that can effectively suppress the mutation of the support surface and offset the wind disturbance is generated through a weighted fusion method.

[0152] For example, first, the pressure growth gradient of 0.5 MPa / s is determined based on the growth rate of the center of gravity offset value of 10 mm per second; then the distribution position of the pressure growth gradient in the adjustable interval [0.3, 0.8] MPa / s is calculated as 40%, and the specific calculation method is: (0.5-0.3) / (0.8-0.3)=40%; at the same time, according to the additional fluctuation amount of ±0.2 MPa corresponding to the current wind grade 2, a sine wave fluctuation synchronized with the wind disturbance is superimposed at the 40% distribution position; finally, a dynamic damping parameter with an amplitude of 0.5±0.12 MPa is generated.

[0153] In the embodiment of the present application, the method realizes the real-time adaptation of the damping parameter to the complex working conditions in the high altitude by dynamically determining the adjustment interval, accurately converting the change trend, and intelligently fusing the environmental disturbance, thereby ensuring the reliable stability of the robot platform under the non-continuous support surface and wind disturbance.

[0154] In the case where the real-time running data includes acceleration, angular velocity and visual positioning data, in order to further improve the accuracy of the attitude sensing of the working robot platform, in some embodiments, step 102: the real-time motion data is filtered and fused to generate an attitude deviation feature, including:

[0155] Step 701: filtering the acceleration and the angular velocity respectively based on a displacement mutation feature of the non-continuous support surface.

[0156] In step 701, the displacement mutation feature refers to the sudden change characteristics of the platform position caused by the non-continuous support surface, which is manifested as the step fluctuation of the acceleration and angular velocity data; the acceleration represents the linear acceleration data of the platform in three-dimensional space measured by the inertial sensor, reflecting the change rate of the platform motion state; the angular velocity represents the angular velocity data of the platform rotating around the three-dimensional coordinate axis measured by the inertial sensor, reflecting the speed of the platform attitude change.

[0157] In the embodiments of the present application, for the support surface mutation interference unique in the high-altitude environment, an adaptive filtering algorithm can be used to process the original acceleration and angular velocity signals, so as to effectively separate the effective signal generated by the real platform motion from the high-frequency noise caused by the environmental interference, and provide clean input data for subsequent analysis.

[0158] Step 702: trajectory matching the displacement offset in the visual positioning data with the filtered acceleration, and extracting a first deviation component corresponding to the robot platform in the vertical direction and a second deviation component corresponding to the robot platform in the horizontal direction from the matching result.

[0159] In step 702, the visual positioning data represents the displacement and orientation information of the platform relative to the surrounding environment obtained by the visual sensor, which is used to assist in positioning the spatial position of the platform; the first deviation component reflects the imbalance degree of the platform in the vertical direction, and the second deviation component represents the motion deviation in the horizontal direction.

[0160] In the embodiments of the present application, firstly, the trend of the overall displacement change of the platform detected by the visual system is analyzed in space-time correlation with the filtered acceleration data; then, the position deviation of the platform in the gravity direction and the inertial motion component on the horizontal plane are extracted through coordinate transformation and vector decomposition method, so as to comprehensively describe the imbalance state of the robot platform of the catenary self-wheel operation and maintenance equipment train set.

[0161] Step 703: generating a posture deviation feature according to the synthetic vector direction of the first deviation component and the second deviation component, and combining the filtered angular velocity.

[0162] In step 703, the synthetic vector direction is the overall imbalance trend of the vertical and horizontal direction deviations.

[0163] In the embodiments of the present application, the first deviation component and the second deviation component are vector synthesized to obtain the main direction of the overall deviation trend of the platform, and then the rotation motion feature reflected by the filtered angular velocity is combined to generate a complete posture deviation description containing displacement and rotation information, which provides a comprehensive basis for subsequent control.

[0164] The implementation process is as follows: first, the vector composition result of the first deviation component and the second deviation component is calculated to obtain the platform overall deviation trend direction, the composition vector direction is obtained through vector addition, specifically: the first deviation component is multiplied by the vertical unit vector and the second deviation component is multiplied by the horizontal unit vector, to obtain the composition vector direction, then the filtered angular velocity is converted into a rotation axis direction vector according to the right-hand rule, and finally the composition vector direction and the rotation axis direction vector are cross-multiplied to obtain the attitude deviation feature, wherein the length of the feature represents the attitude deviation degree and the direction represents the deviation correction direction.

[0165] The specific embodiment is as follows: when the aerial work robot is located at 5 meters and the height wind level is 4, the first deviation component is 0.3 m / s 2 , the direction is vertically downward, and the second deviation component is 0.2 m / s 2 , the direction is horizontally eastward, wherein m / s 2 is the unit of gravitational acceleration, the composition vector direction is arctan(0.2 / 0.3)=33.7°, wherein 33.7° represents east deviation downward, the angular velocity is 1.5 rad / s, and the rotation is around the north axis, and the attitude deviation feature is generated after cross multiplication, the size is 0.45 grad / s, and the direction is east deviation upward 57.3°, wherein 0.45 is calculated by 0.3*1.5, and 57.3° is obtained by subtracting 33.7° from 90°.

[0166] In the embodiment of the present application, the method realizes the accurate perception of the platform attitude of the aerial work robot by intelligent filtering to eliminate environmental interference, accurate matching of multi-source data, and comprehensive fusion of motion features, thereby providing reliable state input for stability control.

[0167] Figure 2 A structural schematic diagram of a robot platform stability maintaining system provided by the embodiment of the present application is shown in FIG. 1, and the system comprises: Figure 2

[0168] An acquisition module 21 is configured to acquire real-time motion data of a robot platform.

[0169] A processing module 22 is configured to perform filtering fusion processing on the real-time motion data to generate an attitude deviation feature.

[0170] An input module 23 is configured to input the attitude deviation feature into a pre-trained joint mechanics model, and the joint mechanics model generates real-time damping parameters according to the attitude deviation feature, hydraulic damping characteristics, and joint motion constraints.

[0171] ​The generating module 24 is configured to operate the attitude deviation feature based on the real-time damping parameter and an adaptive sliding mode control algorithm, and generate a compensation control instruction for the hydraulic drive joint, the compensation control instruction being used for the deformable support mechanism of the robot platform.

[0172] Figure 2 The robot platform stability maintaining system can perform Figure 1 The robot platform stability maintaining method of the embodiments has the same implementation principles and technical effects as the robot platform stability maintaining system. The specific operation modes of each module and unit of the robot platform stability maintaining system have been described in the embodiments of the method, and thus will not be described here.

[0173] In one possible design, Figure 2 The robot platform stability maintaining system of the embodiments can be implemented as a computing device, such as a computer. Figure 3 As shown in the figure, the computing device can include a storage component 31 and a processing component 32.

[0174] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32.

[0175] The processing component 32 is configured to perform the above Figure 1 The robot platform stability maintaining method of the embodiments.

[0176] The processing component 32 can include one or more processors to execute the computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, for executing the above method.

[0177] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or nonvolatile storage devices or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0178] Of course, the computing device can also include other components, such as an input / output interface, a display component, a communication component, etc.

[0179] The input / output interface provides an interface between the processing component and peripheral interface modules, which can be output devices, input devices, etc.

[0180] The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, etc.

[0181] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform, and the computing device can be a cloud server, and the processing component, the storage component, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0182] The embodiment of the present application also provides a computer storage medium, which stores a computer program, and the computer program can implement the above-mentioned Figure 1 A robot platform stability maintaining method of the embodiment shown.

[0183] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-mentioned system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be described here.

[0184] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0185] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, and the computer software products can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0186] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for maintaining the stability of a robot platform, characterized in that, include: Acquire real-time motion data from the robot platform; The real-time motion data is filtered and fused to generate attitude deviation features; The posture deviation features are input into a pre-trained joint mechanics model, which generates real-time damping parameters based on the posture deviation features, hydraulic damping characteristics, and joint motion constraints. Based on the real-time damping parameters and combined with the adaptive sliding mode control algorithm, the posture deviation characteristics are calculated to generate compensation control commands for the hydraulically driven joints. The compensation control commands are applied to the deformable support mechanism of the robot platform. Based on the real-time damping parameters and combined with the adaptive sliding mode control algorithm, the attitude deviation characteristics are calculated to generate compensation control commands for the hydraulically driven joint, including: Based on the real-time damping parameters, the decay rate of the boundary layer thickness corresponding to the control command in the adaptive sliding mode control algorithm is dynamically adjusted. The tilt angle change rate and the center of gravity offset value in the attitude deviation characteristics are directionally weighted to generate a deviation correction vector that matches the deformation direction of the deformable support mechanism. Phase lag compensation is performed on the deviation correction vector based on the adjusted attenuation rate to generate compensation control commands; The step of performing phase lag compensation on the deviation correction vector based on the adjusted attenuation rate to generate a compensation control command includes: Based on the correlation between the adjusted attenuation rate and the disturbance frequency, determine the time delay required for phase lag compensation; The component in the deviation correction vector that is in the same direction as the abrupt change direction of the discontinuous support surface is segmented and translated according to the time delay amount to generate the correction component. Based on the correction component, the extension and retraction acceleration of the hydraulically driven joint is nonlinearly scaled; Compensation control commands are generated based on the nonlinearly scaled scaling acceleration and the correction component.

2. The method for maintaining the stability of a robot platform according to claim 1, characterized in that, The nonlinear scaling of the extension and retraction acceleration of the hydraulically driven joint based on the correction component includes: Based on the abrupt change amplitude of the discontinuous support surface, determine the scaling range corresponding to the amplitude change rate of the correction component; Based on the proportion of the component in the correction component that is in the same direction as the abrupt change direction of the discontinuous support surface, the dynamic adjustment coefficient of the amplitude change rate within the scaling range is calculated. The product of the dynamic adjustment coefficient and the adjusted decay rate is used as the scaling factor of the stretching acceleration. The stretching acceleration is nonlinearly scaled according to the scaling factor.

3. The method for maintaining the stability of a robot platform according to claim 2, characterized in that, The joint mechanics model generates real-time damping parameters based on the posture deviation characteristics, hydraulic damping characteristics, and joint motion constraints, including: The inverse correlation between the hydraulic damping characteristics and the joint extension / retraction rate is established through the joint mechanics model building module. The target deformation angle of each hydraulically driven joint is calculated using the calculation module of the joint mechanics model based on the tilt angle change rate in the posture deviation characteristics. Based on the target deformation angle of each hydraulically driven joint, and combined with the target angle threshold in the joint motion constraint, the allowable deformation range of each hydraulically driven joint is determined. Within the allowable deformation range, the center of gravity offset value in the attitude deviation feature is mapped to the pressure adjustment coefficient of the hydraulic circuit according to the reverse correlation to generate real-time damping parameters.

4. The method for maintaining the stability of a robot platform according to claim 3, characterized in that, Within the allowable deformation range, mapping the center of gravity offset value in the attitude deviation feature to the pressure adjustment coefficient of the hydraulic circuit according to the reverse correlation to generate real-time damping parameters includes: The adjustable range of the pressure adjustment coefficient is determined based on the proportional relationship between the abrupt change amplitude of the discontinuous support surface and the allowable deformation range. Based on the reverse correlation, the center of gravity acceleration of the center of gravity offset value is converted into the pressure growth gradient of the hydraulic circuit; Based on the distribution pattern of the pressure growth gradient within the adjustable range, and combined with the pressure fluctuation of the hydraulic circuit, real-time damping parameters are generated.

5. The method for maintaining the stability of a robot platform according to claim 4, characterized in that, The real-time motion data includes acceleration, angular velocity, and visual positioning data; The real-time motion data is filtered and fused to generate attitude deviation features, including: Based on the abrupt displacement characteristics of the discontinuous support surface, the acceleration and the angular velocity are filtered respectively. The displacement offset in the visual positioning data is matched with the filtered acceleration to determine the trajectory. From the matching result, the first deviation component corresponding to the robot platform in the vertical direction and the second deviation component corresponding to the robot platform in the horizontal direction are extracted. Based on the combined vector direction of the first deviation component and the second deviation component, and combined with the filtered angular velocity, attitude deviation features are generated.

6. A robot platform stability maintenance system, characterized in that, include: The acquisition module is used to acquire real-time motion data of the robot platform; The processing module is used to filter and fuse the real-time motion data to generate attitude deviation features; The input module is used to input the posture deviation features into a pre-trained joint mechanics model, which generates real-time damping parameters based on the posture deviation features, hydraulic damping characteristics, and joint motion constraints. The generation module is used to calculate the attitude deviation characteristics based on the real-time damping parameters and combined with the adaptive sliding mode control algorithm, and generate compensation control commands for the hydraulically driven joints. The compensation control commands are applied to the deformable support mechanism of the robot platform. Based on the real-time damping parameters and combined with the adaptive sliding mode control algorithm, the attitude deviation characteristics are calculated to generate compensation control commands for the hydraulically driven joint, including: Based on the real-time damping parameters, the decay rate of the boundary layer thickness corresponding to the control command in the adaptive sliding mode control algorithm is dynamically adjusted. The tilt angle change rate and the center of gravity offset value in the attitude deviation characteristics are directionally weighted to generate a deviation correction vector that matches the deformation direction of the deformable support mechanism. Phase lag compensation is performed on the deviation correction vector based on the adjusted attenuation rate to generate compensation control commands; The step of performing phase lag compensation on the deviation correction vector based on the adjusted attenuation rate to generate a compensation control command includes: Based on the correlation between the adjusted attenuation rate and the disturbance frequency, determine the time delay required for phase lag compensation; The component in the deviation correction vector that is in the same direction as the abrupt change direction of the discontinuous support surface is segmented and translated according to the time delay amount to generate the correction component. Based on the correction component, the extension and retraction acceleration of the hydraulically driven joint is nonlinearly scaled; Compensation control commands are generated based on the nonlinearly scaled scaling acceleration and the correction component.

7. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a robot platform stability maintenance method as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that, The system contains a computer program that, when executed by a computer, implements a method for maintaining the stability of a robot platform as described in any one of claims 1 to 5.

Images