A balance car disturbance identification method and related device

Abstract

The application provides a balance car disturbance identification method and related equipment, and relates to the balance car control technical field. In the case of obtaining the driving generalized force data output by the motion controller of the target balance car in the current control period and the actual dynamic system parameters of the target balance car in the current control period, the historical dynamic system estimation parameter set corresponding to the current control period, the actual dynamic system parameters and the driving generalized force data are used to obtain the target dynamic system estimation parameter set of the target balance car in the target control period through dynamic system open-loop estimation. Then, the actual state parameter of the dynamic system of the target balance car in the target control period is compared with the target dynamic system estimation parameter set, and the pre-stored disturbance type identification model is called to identify the disturbance type of the obtained parameter comparison result, so that the actual disturbance type of the target balance car in the target control period is identified in time and accurately.

Description

Technical Field

[0001] This application relates to the field of self-balancing scooter control technology, and more specifically, to a self-balancing scooter disturbance identification method and related equipment. Background Technology

[0002] With the continuous development of science and technology, electric self-balancing scooters have experienced rapid growth due to their ability to serve as a means of transportation and recreational equipment. However, in actual use, various disturbances often occur due to factors such as terrain and user needs (e.g., the scooter being picked up, the scooter hitting an obstacle, short-term body disturbance, and the scooter bouncing on uneven surfaces). It is worth noting that currently, the industry lacks a disturbance detection solution that can promptly detect the type of disturbance. This results in the scooter failing to identify the specific disturbance type during actual operation, causing it to continue operating at its original motor speed even when encountering disturbances. Consequently, when the scooter hits an obstacle or gets stuck in a corner, the motor may stall, leading to spin-up after a rollover. This also prevents the scooter from slowing down in time on uneven surfaces, resulting in rollovers and spin-up after a rollover. Furthermore, even when picked up by the user, the scooter may continue to spin-up and fail to regain balance when placed back on the ground, severely impacting the user experience. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide a method and device for identifying disturbances in a self-balancing scooter, a control device for the self-balancing scooter, and a readable storage medium, which can identify the actual disturbance type of the electric self-balancing scooter during its movement in a timely and accurate manner, so that the electric self-balancing scooter can adjust its movement status in a timely manner based on the identified disturbance type, thereby improving the user experience.

[0004] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows:

[0005] In a first aspect, this application provides a method for identifying disturbances in a self-balancing scooter, the method comprising:

[0006] Acquire the driving generalized force data output by the motion controller of the target self-balancing vehicle in the current control cycle, as well as the actual dynamic system parameters of the target self-balancing vehicle in the current control cycle;

[0007] Based on the historical dynamic system estimation parameter set corresponding to the current control cycle, the actual dynamic system parameters, and the driving generalized force data, an open-loop estimation of the dynamic system is performed for the target control cycle to obtain the target dynamic system prediction parameter set of the target balance vehicle in the target control cycle, wherein the target control cycle is the next control cycle of the current control cycle;

[0008] The actual dynamic system state parameters are obtained by the target self-balancing vehicle moving according to the driving generalized force data within the target control cycle.

[0009] The actual state parameters of the dynamic system are compared with the estimated parameter set of the target dynamic system, and the pre-stored disturbance type identification model is called to identify the disturbance type of the obtained parameter comparison results, so as to obtain the actual disturbance type of the target balance vehicle in the target control cycle.

[0010] In an optional implementation, the step of acquiring the driving generalized force data output by the motion controller of the target self-balancing vehicle in the current control cycle includes:

[0011] Detect whether the motion controller is a model-free controller;

[0012] If the motion controller is not a model-free controller, extract the driving generalized force data that conforms to the kinematic principle from the balance vehicle motion control parameters output by the motion controller in the current control cycle.

[0013] When it is detected that the motion controller is a model-free controller, the motion control parameters of the balance vehicle output by the motion controller in the current control cycle are converted according to the parameter conversion relationship between the preset generalized force data and the control parameters of the motion controller, so as to obtain the driving generalized force data.

[0014] In an optional implementation, the historical dynamic system estimation parameter set corresponding to the current control cycle includes historical dynamic system prediction parameters for the current control cycle from multiple historical control cycles that are continuously distributed before the current control cycle. The step of performing open-loop estimation of the dynamic system for the target control cycle based on the historical dynamic system estimation parameter set corresponding to the current control cycle, the actual dynamic system parameters, and the driving generalized force data to obtain the target dynamic system prediction parameter set for the target self-balancing vehicle in the target control cycle includes:

[0015] The historical dynamic system prediction parameters corresponding to each of the multiple historical control cycles and the actual dynamic system parameters of the current control cycle are respectively used as open-loop prediction parameters, and the dynamic system state change rate equation of the open-loop prediction parameter is constructed based on the driving generalized force data.

[0016] Based on the dynamic system state change rate equation, calculate the dynamic system parameter prediction increment from the current control period to the target control period for the parameter to be predicted in the open loop.

[0017] The parameter to be predicted in the open loop is superimposed with the predicted increment of the dynamic system parameter to obtain a target dynamic system predicted parameter for the target control period from the target dynamic system predicted parameter set.

[0018] In an optional implementation, the open-loop prediction parameters include the position and velocity information of the target self-balancing vehicle body in the forward direction, and the tilt angle and tilt angular velocity of the target self-balancing vehicle's swing arm relative to the vertical direction. The step of constructing the dynamic system state change velocity equation based on the driving generalized force data includes:

[0019] Based on the inverted pendulum model of the target self-balancing vehicle, the forward kinematic equations of the target self-balancing vehicle under the action of the driving generalized force data are constructed according to the tilt angle and tilt angular velocity in the open-loop prediction parameters.

[0020] The velocity information and tilt angular velocity in the open-loop prediction parameters are integrated with the forward kinematic equations to obtain the velocity equations for the state changes of the dynamic system.

[0021] In an optional implementation, the forward kinematic equations of the target self-balancing vehicle under the action of the generalized driving force data, corresponding to the open-loop prediction parameters, are expressed as follows:

[0022]

[0023] At this point, the dynamic system state change rate equation for the parameters to be predicted in the open loop is expressed as follows:

[0024]

[0025] in, Used to represent the forward acceleration corresponding to the open-loop prediction parameter. This represents the acceleration of the target self-balancing vehicle body in the forward direction under the action of the open-loop prediction parameters and the generalized driving force data. The following parameters represent the tilt angular acceleration of the target self-balancing scooter's swing arm relative to the vertical direction under the influence of the open-loop estimated parameters and the generalized driving force data: l represents the distance between the center of mass of the target self-balancing scooter's swing arm and the rotational joint on the scooter body; m2 represents the mass of the target self-balancing scooter's swing arm; m1 represents the mass of the target self-balancing scooter's scooter body; q represents the tilt angular acceleration of the target self-balancing scooter's swing arm relative to the vertical direction; l represents the distance between the center of mass of the target self-balancing scooter's swing arm and the rotational joint on the scooter body; m2 represents the mass of the target self-balancing scooter's swing arm; m1 represents the mass of the target self-balancing scooter's scooter body; q represents the tilt angular acceleration of the target self-balancing scooter's swing arm D2 This is used to represent the tilt angle of the target self-balancing vehicle's swing arm relative to the vertical direction in the open-loop prediction parameters. The parameter 'g' represents the tilt angular velocity of the target self-balancing vehicle's swing arm relative to the vertical direction in the open-loop prediction parameters, while 'g' represents the acceleration due to gravity. Used to represent the driving generalized force data This is used to represent the rate of change of the dynamic system state of the parameter to be predicted in the open loop under the influence of the driving generalized force data. This is used to represent the speed information of the target self-balancing vehicle body in the forward direction in the open-loop prediction parameters.

[0026] In an optional implementation, the step of comparing the actual state parameters of the dynamic system with the estimated parameter set of the target dynamic system includes:

[0027] Extract the actual tilt angular velocity of the target balance vehicle's swing arm relative to the vertical direction during the target control cycle from the actual state parameters of the dynamic system;

[0028] For the target dynamic system prediction parameter set, which includes the target control cycle and the corresponding target dynamic system prediction parameters for each historical control cycle prior to the target control cycle, extract the predicted tilt angular velocity of the pendulum relative to the vertical direction in the target control cycle, which is included in the target dynamic system prediction parameters.

[0029] The actual tilt angular velocity is compared with each extracted estimated tilt angular velocity to obtain the angular velocity comparison result of each historical control cycle before the target control cycle in the parameter comparison result.

[0030] In an optional implementation, the method further includes:

[0031] Obtain dynamic system parameter comparison sample sets corresponding to different disturbance types. Each dynamic system parameter comparison sample set includes multiple dynamic system parameter comparison samples corresponding to the same disturbance type. Each dynamic system parameter comparison sample is used to describe the relative numerical distribution of the actual dynamic system state parameters and the estimated dynamic system state parameters under the corresponding disturbance type.

[0032] The model is trained by comparing the dynamic system parameters corresponding to different disturbance types with the sample set to obtain the disturbance type identification model.

[0033] Secondly, this application provides a self-balancing scooter disturbance identification device, the device comprising:

[0034] The motion data acquisition module is used to acquire the driving generalized force data output by the motion controller of the target self-balancing vehicle in the current control cycle, as well as the actual dynamic system parameters of the target self-balancing vehicle in the current control cycle.

[0035] The system open-loop estimation module is used to perform dynamic system open-loop estimation for the target control cycle based on the historical dynamic system estimation parameter set corresponding to the current control cycle, the actual dynamic system parameters, and the driving generalized force data, to obtain the target dynamic system prediction parameter set of the target balance vehicle in the target control cycle, wherein the target control cycle is the next control cycle of the current control cycle;

[0036] The motion data acquisition module is also used to acquire the actual dynamic system state parameters obtained by the target balance vehicle moving according to the driving generalized force data within the target control cycle;

[0037] The disturbance type identification module is used to compare the actual state parameters of the dynamic system with the estimated parameter set of the target dynamic system, and call the pre-stored disturbance type identification model to identify the disturbance type of the obtained parameter comparison result, so as to obtain the actual disturbance type of the target balance vehicle in the target control cycle.

[0038] In an optional embodiment, the apparatus further includes:

[0039] The disturbance sample acquisition module is used to acquire dynamic system parameter comparison sample sets corresponding to different disturbance types. Each dynamic system parameter comparison sample set includes multiple dynamic system parameter comparison samples corresponding to the same disturbance type. Each dynamic system parameter comparison sample is used to describe the relative numerical distribution of the actual dynamic system state parameters and the estimated dynamic system state parameters under the corresponding disturbance type.

[0040] The identification model training module is used to train the model based on the dynamic system parameter comparison sample set corresponding to different disturbance types, so as to obtain the disturbance type identification model.

[0041] Thirdly, this application provides a self-balancing scooter control device, including a processor and a memory, wherein the memory stores a computer program that can be executed by the processor, and the processor can execute the computer program to implement the self-balancing scooter disturbance identification method described in any of the foregoing embodiments.

[0042] Fourthly, this application provides a readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the self-balancing scooter disturbance identification method described in any of the foregoing embodiments.

[0043] In this case, the beneficial effects of the embodiments of this application may include the following:

[0044] This application, upon obtaining the driving generalized force data output by the motion controller of the target self-balancing vehicle in the current control cycle, and the actual dynamic system parameters of the target self-balancing vehicle in the current control cycle, will obtain the target dynamic system prediction parameter set of the target self-balancing vehicle in the target control cycle through open-loop estimation of the dynamic system based on the historical dynamic system estimation parameter set corresponding to the current control cycle, the actual dynamic system parameters, and the driving generalized force data. Then, the actual state parameters of the dynamic system obtained by the target self-balancing vehicle moving according to the driving generalized force data in the target control cycle will be compared with the target dynamic system prediction parameter set. A pre-stored disturbance type identification model will be called to identify the disturbance type of the obtained parameter comparison results, thereby timely and accurately identifying the actual disturbance type of the target self-balancing vehicle in the target control cycle. This allows the electric self-balancing vehicle to adjust its own movement status in a timely manner based on the identified disturbance type, improving the user experience.

[0045] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a schematic diagram of the composition of the self-balancing scooter control device provided in the embodiments of this application;

[0048] Figure 2 This is one of the flowcharts illustrating the self-balancing scooter disturbance identification method provided in this application embodiment;

[0049] Figure 3 for Figure 2 A flowchart illustrating the sub-steps included in step S220;

[0050] Figure 4 A schematic diagram of the inverted pendulum model of the electric balance vehicle provided in the embodiments of this application;

[0051] Figure 5 A second schematic flowchart illustrating the self-balancing scooter disturbance identification method provided in this application embodiment;

[0052] Figure 6 This is one of the schematic diagrams of the composition of the self-balancing scooter disturbance identification device provided in the embodiments of this application;

[0053] Figure 7 This is a second schematic diagram of the composition of the self-balancing scooter disturbance identification device provided in the embodiments of this application.

[0054] Icons: 10-Side scooter control device; 11-Memory; 12-Processor; 13-Communication unit; 100-Side scooter disturbance identification device; 110-Motion data acquisition module; 120-System open-loop estimation module; 130-Disturbance type identification module; 140-Disturbance sample acquisition module; 150-Identification model training module. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0056] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0057] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0058] In the description of this application, it should be understood that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product is in use, or the orientation or positional relationship commonly understood by those skilled in the art. They are used only for the convenience of describing this application and simplifying the description, and are not intended to indicate or imply that the equipment or component referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0059] In the description of this application, it should also be understood that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. Those skilled in the art will understand the specific meaning of the above terms in this application based on the specific circumstances.

[0060] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0061] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the composition of the self-balancing scooter control device 10 provided in this application embodiment. In this application embodiment, the self-balancing scooter control device 10 can be communicatively connected to the electric self-balancing scooter and used to control the movement state of the electric self-balancing scooter, enabling the electric self-balancing scooter to achieve the desired movement effect under the user's control. Specifically, the self-balancing scooter control device 10 can timely and accurately identify the actual disturbance type during the actual movement of the electric self-balancing scooter, so as to drive the electric self-balancing scooter to adjust its own movement status in a timely manner based on the identified disturbance type (for example, reducing the motor speed of the electric self-balancing scooter according to different disturbance types by different adjustment ranges) to ensure the user experience.

[0062] In this embodiment, the self-balancing scooter control device 10 may be a computer device independent of the electric self-balancing scooter, wherein the computer device may be a personal computer, cloud server, laptop, tablet computer, etc.; the self-balancing scooter control device 10 may also be a hardware module device integrated with the electric self-balancing scooter; the electric self-balancing scooter may be a unicycle or a two-wheeled self-balancing scooter with position control, force control, or force-position hybrid control.

[0063] In this embodiment, the self-balancing scooter control device 10 may include a memory 11, a processor 12, a communication unit 13, and a self-balancing scooter disturbance identification device 100. The memory 11, processor 12, and communication unit 13 are electrically connected directly or indirectly to each other to achieve data transmission or interaction. For example, these components can be electrically connected via one or more communication buses or signal lines.

[0064] In this embodiment, the memory 11 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc. The memory 11 is used to store computer programs, and the processor 12 can execute the computer programs accordingly after receiving execution instructions.

[0065] In this embodiment, the processor 12 can be an integrated circuit chip with signal processing capabilities. The processor 12 can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0066] In this embodiment, the communication unit 13 is used to establish a communication connection between the self-balancing scooter control device 10 and other electronic devices via a network, and to send and receive data through the network, wherein the network includes wired communication networks and wireless communication networks. For example, the self-balancing scooter control device 10 can obtain the motion control strategy of the electric self-balancing scooter under different disturbance types through the communication unit 13, wherein the different disturbance types may include the self-balancing scooter being picked up, the self-balancing scooter hitting an obstacle, short-term disturbance of the body, the self-balancing scooter bumping along an uneven road surface, etc., and the motion control strategy is used to describe the motor speed adjustment scheme of the corresponding electric self-balancing scooter under the corresponding disturbance type.

[0067] In this embodiment, the self-balancing scooter disturbance identification device 100 includes at least one software function module that can be stored in the memory 11 in the form of software or firmware or embedded in the operating system of the self-balancing scooter control device 10. The processor 12 can be used to execute the executable modules stored in the memory 11, such as the software function modules and computer programs included in the self-balancing scooter disturbance identification device 100. The self-balancing scooter control device 100 can timely and accurately identify the actual disturbance type of the electric self-balancing scooter during its movement, so that the electric self-balancing scooter can subsequently adjust its movement status in a timely manner based on the identified disturbance type, thereby improving the user experience.

[0068] Understandable, Figure 1 The block diagram shown is only a schematic diagram of one composition of the self-balancing scooter control device 10. The self-balancing scooter control device 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0069] In this application, to ensure that the self-balancing scooter control device 10 can promptly and accurately identify the actual disturbance type of the electric self-balancing scooter during its movement, so that the electric self-balancing scooter can subsequently adjust its movement status in a timely manner based on the identified disturbance type and improve the user experience, this application provides a self-balancing scooter disturbance identification method to achieve the aforementioned objective. The self-balancing scooter disturbance identification method provided in this application will be described in detail below.

[0070] Please refer to Figure 2 , Figure 2 This is one of the flowcharts illustrating the self-balancing scooter disturbance identification method provided in this application embodiment. In this application embodiment, the self-balancing scooter disturbance identification method may include steps S210 to S240.

[0071] Step S210: Obtain the driving generalized force data output by the motion controller of the target self-balancing vehicle in the current control cycle, as well as the actual dynamic system parameters of the target self-balancing vehicle in the current control cycle.

[0072] In this embodiment, the driving generalized force data is matched with the motion control command output by the motion controller in the current control cycle. The self-balancing vehicle control device 10 processes the motion control command according to the controller type of the motion controller of the target self-balancing vehicle to obtain the driving generalized force data output by the motion controller of the target self-balancing vehicle in the current control cycle.

[0073] The actual dynamic system parameters are the kinematic parameters that the target balance vehicle actually exhibits in the current control cycle, which may include the position and speed information of the target balance vehicle body in the forward direction in the current control cycle, and the tilt angle and tilt angular velocity of the target balance vehicle's swing arm relative to the vertical direction in the current control cycle.

[0074] In one embodiment of this invention, the step of acquiring the driving generalized force data output by the motion controller of the target self-balancing vehicle in the current control cycle may include:

[0075] Detect whether the motion controller is a model-free controller;

[0076] If the motion controller is not a model-free controller, extract the driving generalized force data that conforms to the kinematic principle from the balance vehicle motion control parameters output by the motion controller in the current control cycle.

[0077] When it is detected that the motion controller is a model-free controller, the motion control parameters of the balance vehicle output by the motion controller in the current control cycle are converted according to the parameter conversion relationship between the preset generalized force data and the control parameters of the motion controller, so as to obtain the driving generalized force data.

[0078] If the motion controller is not a model-free controller, it means that the motion controller is actually involved in the kinematic model of the target balance vehicle. The motion control parameters output by the motion controller usually include the generalized force vectors (including desired force / desired torque) of the target balance vehicle at each generalized coordinate. Thus, the balance vehicle control device 10 can directly extract the corresponding driving generalized force data from the balance vehicle motion control parameters output by the motion controller in the current control cycle.

[0079] If the motion controller is a model-free controller, it means that the motion controller does not actually involve the kinematic model of the target self-balancing vehicle. The motion control parameters output by the motion controller may not necessarily include the generalized force vectors corresponding to the target self-balancing vehicle at each generalized coordinate. They may involve speed control or position control quantities. In this case, parameter transformation is required to obtain the corresponding driving generalized force data. Specifically, when the motion control parameters output by the motion controller are speed control quantities, the parameter transformation relationship between the generalized force data and the control parameters of the motion controller can be represented by the correlation between the speed increment of the electric self-balancing vehicle motor and the motor output torque within a single control cycle.

[0080]

[0081] Wherein, Δv represents the speed increment of the electric self-balancing scooter motor within a single control cycle, ΔT represents the cycle length of a single control cycle, u represents the motor output torque of the electric self-balancing scooter motor, f represents the time-varying nonlinear motor friction force of the electric self-balancing scooter motor, J represents the motor rotor inertia of the electric self-balancing scooter motor, and J represents the reduction ratio of the reducer of the electric self-balancing scooter motor. The generalized force data can be represented using the motor output torque of the electric self-balancing scooter motor.

[0082] Therefore, this application can ensure that the balance vehicle control device 10 obtains the generalized force vector content that is compatible with the motion control command of the motion controller by following the specific steps of step S210 above, namely, "obtaining the driving generalized force data output by the motion controller of the target balance vehicle in the current control cycle".

[0083] Step S220: Based on the historical dynamic system estimated parameter set, actual dynamic system parameters and driving generalized force data corresponding to the current control cycle, perform open-loop estimation of the dynamic system for the target control cycle to obtain the target dynamic system predicted parameter set of the target balance vehicle in the target control cycle.

[0084] In this embodiment, the self-balancing vehicle control device 10 can construct a corresponding dynamic system for the target self-balancing vehicle based on kinematic principles, so as to predict the theoretical value of the motion status of the target self-balancing vehicle in a future control cycle through the dynamic system, wherein the target control cycle is the next control cycle after the current control cycle.

[0085] Meanwhile, to ensure that the self-balancing scooter control device 10 can predict more comprehensive target dynamic system parameters of the target self-balancing scooter during the target control cycle based on the constructed dynamic system (including the theoretical position and speed information of the scooter body in the forward direction during the target control cycle, and the theoretical tilt angle and tilt angular velocity of the scooter's swing arm relative to the vertical direction during the target control cycle), the self-balancing scooter control device 10 in this application can predict the dynamic system parameters of the current control cycle by using the actual dynamic system parameters of the corresponding historical control cycles for multiple historical control cycles consecutively distributed before the current control cycle. This yields the historical dynamic system prediction parameters (including target balance) corresponding to the historical dynamic system estimation parameter set of the historical control cycle in relation to the current control cycle. The theoretical movement position and theoretical speed information of the vehicle body in the forward direction estimated by the vehicle body in the corresponding historical control cycle for the current control cycle, and the theoretical tilt angle and theoretical tilt angular velocity of the target balance vehicle's swing arm relative to the vertical direction estimated by the target balance vehicle in the corresponding historical control cycle for the current control cycle, are then used as open-loop prediction parameters for the historical dynamic system prediction parameters corresponding to the aforementioned multiple historical control cycles and the actual dynamic system parameters of the current control cycle. Based on the open-loop prediction parameters, a target dynamic system prediction parameter that matches the driving generalized force data is predicted, thereby obtaining a target dynamic system prediction parameter set composed of the target dynamic system prediction parameters estimated by the vehicle body in the previous multiple historical control cycles (including the current control cycle) for the target control cycle.

[0086] Alternatively, please refer to Figure 3 , Figure 3 yes Figure 2 The flowchart illustrates the sub-steps included in step S220. In this embodiment, step S220 may include sub-steps S221 to S223 to improve the comprehensiveness of data prediction for dynamic system parameters of the target control cycle.

[0087] Sub-step S221: Take the historical dynamic system prediction parameters corresponding to each of the multiple historical control cycles and the actual dynamic system parameters of the current control cycle as open-loop prediction parameters respectively, and construct the dynamic system state change rate equation of the open-loop prediction parameter based on the driving generalized force data.

[0088] In this embodiment, a single open-loop prediction parameter may include the position and speed information of the target scooter's body in the forward direction, and the tilt angle and tilt angular velocity of the target scooter's swing arm relative to the vertical direction. When a historical dynamic system prediction parameter of a certain historical control cycle is used as an open-loop prediction parameter, the open-loop prediction parameter may be expressed as the theoretical moving position and theoretical moving speed information of the target scooter's body in the forward direction predicted by the corresponding historical control cycle for the current control cycle, and the theoretical tilt angle and theoretical tilt angular velocity of the target scooter's swing arm relative to the vertical direction predicted by the corresponding historical control cycle for the current control cycle. When the actual dynamic system parameter of the current control cycle is used as an open-loop prediction parameter, the actual dynamic system parameter may be expressed as the actual moving position and actual moving speed information of the target scooter's body in the forward direction in the current control cycle, and the actual tilt angle and actual tilt angular velocity of the target scooter's swing arm relative to the vertical direction in the current control cycle.

[0089] After determining a parameter to be estimated in an open-loop manner, the self-balancing vehicle control device 10 can construct a dynamic system state change rate equation for the target self-balancing vehicle under the action of the parameter to be estimated in an open-loop manner and the driving generalized force data based on kinematic principles. This dynamic system state change rate equation can characterize the dynamic system parameter change rate of the corresponding parameter to be estimated in the current control cycle.

[0090] It is understandable that since most disturbances experienced by an electric self-balancing scooter act in its forward and backward movement direction, this can be mitigated by establishing... Figure 4 The inverted pendulum model of the vehicle shown is used to describe the forward kinematics model of the electric self-balancing vehicle. In this case, the step of constructing the dynamic system state change rate equation of the open-loop prediction parameter based on the driving generalized force data may include:

[0091] Based on the inverted pendulum model of the target self-balancing vehicle, the forward kinematic equations of the target self-balancing vehicle under the action of the driving generalized force data are constructed according to the tilt angle and tilt angular velocity in the open-loop prediction parameters.

[0092] The velocity information and tilt angular velocity in the open-loop prediction parameters are integrated with the forward kinematic equations to obtain the velocity equations for the state changes of the dynamic system.

[0093] The forward kinematic equations of the target self-balancing vehicle under the influence of the generalized driving force data and corresponding to the open-loop prediction parameters are expressed as follows:

[0094]

[0095] At this point, the dynamic system state change rate equation for the parameters to be predicted in the open loop is expressed as follows:

[0096]

[0097] in, Used to represent the forward acceleration corresponding to the open-loop prediction parameter. This represents the acceleration of the target self-balancing vehicle body in the forward direction under the action of the open-loop prediction parameters and the generalized driving force data. The following parameters represent the tilt angular acceleration of the target self-balancing scooter's swing arm relative to the vertical direction under the influence of the open-loop estimated parameters and the generalized driving force data: l represents the distance between the center of mass of the target self-balancing scooter's swing arm and the rotational joint on the scooter body; m2 represents the mass of the target self-balancing scooter's swing arm; m1 represents the mass of the target self-balancing scooter's scooter body; q represents the tilt angular acceleration of the target self-balancing scooter's swing arm relative to the vertical direction; l represents the distance between the center of mass of the target self-balancing scooter's swing arm and the rotational joint on the scooter body; m2 represents the mass of the target self-balancing scooter's swing arm; m1 represents the mass of the target self-balancing scooter's scooter body; q represents the tilt angular acceleration of the target self-balancing scooter's swing arm D2 This is used to represent the tilt angle of the target self-balancing vehicle's swing arm relative to the vertical direction in the open-loop prediction parameters. The parameter 'g' represents the tilt angular velocity of the target self-balancing vehicle's swing arm relative to the vertical direction in the open-loop prediction parameters, while 'g' represents the acceleration due to gravity. Used to represent the driving generalized force data This is used to represent the rate of change of the dynamic system state of the parameter to be predicted in the open loop under the influence of the driving generalized force data. This is used to represent the speed information of the target self-balancing vehicle body in the forward direction in the open-loop prediction parameters.

[0098] Sub-step S222: Based on the dynamic system state change rate equation, calculate the dynamic system parameter prediction increment from the current control period to the target control period for the parameter to be predicted in the open loop.

[0099] In this embodiment, the predicted increment of the dynamic system parameters can be obtained by multiplying the dynamic system state change rate equation corresponding to the open-loop predicted parameter by the period duration of a single control cycle.

[0100] Sub-step S223 involves superimposing the open-loop prediction parameter to be obtained with the dynamic system parameter prediction increment to obtain a target dynamic system prediction parameter for the target control cycle from the target dynamic system prediction parameter set.

[0101] In this embodiment, the correlation between a single open-loop prediction parameter and the corresponding target dynamic system prediction parameter is expressed by the following formula:

[0102]

[0103] Where ΔT represents the duration of a single control cycle. This is used to represent the open-loop prediction parameters of the target self-balancing vehicle in the current control cycle. The parameters used to represent the target dynamic system prediction parameters of the target self-balancing vehicle during the target control cycle. This is used to represent the rate of change of the dynamic system state of the open-loop prediction parameter to be estimated in the current control cycle under the action of the corresponding driving generalized force data.

[0104] In this case, if the historical dynamic system estimation parameter set records N historical control cycles that predict the historical dynamic system parameters for the current control cycle, then the target dynamic system estimation parameter set will record N+1 historical control cycles (including the current control cycle) that predict the target dynamic system parameters for the target control cycle.

[0105] Therefore, by executing the above sub-steps S221 to S223, this application can improve the comprehensiveness of data prediction for dynamic system parameters of the target control cycle.

[0106] Step S230: Obtain the actual state parameters of the dynamic system obtained by the target self-balancing vehicle moving according to the driving generalized force data within the target control cycle.

[0107] In this embodiment, the actual state parameters of the dynamic system may include the actual position and speed information of the target scooter body in the forward direction during the target control cycle, and the actual tilt angle and actual tilt angular velocity of the target scooter's swing arm relative to the vertical direction during the target control cycle. The actual tilt angular velocity of the target scooter's swing arm relative to the vertical direction during the target control cycle can be directly detected by a gyroscope mounted on the target scooter.

[0108] Step S240: Compare the actual state parameters of the dynamic system with the estimated parameter set of the target dynamic system, and call the pre-stored disturbance type identification model to identify the disturbance type of the obtained parameter comparison results, so as to obtain the actual disturbance type of the target balance vehicle in the target control cycle.

[0109] In this embodiment, the self-balancing scooter control device 10 can compare the actual state parameters of the dynamic system with the estimated parameters of each target dynamic system in the target dynamic system estimated parameter set according to parameter type to obtain the corresponding parameter comparison results. Then, the parameter comparison results with strong data comprehensiveness are substituted into the disturbance type identification model for feature identification to obtain the actual disturbance type of the target self-balancing scooter in the target control cycle. This improves the timeliness and accuracy of identifying the actual disturbance type of the target self-balancing scooter in the actual movement process, so as to adjust the movement status of the target self-balancing scooter in a timely manner based on the identified disturbance type and improve the user experience.

[0110] In one embodiment of this invention, to improve the efficiency of disturbance type identification, the self-balancing vehicle control device 10 can directly select the tilt angular velocity as the parameter comparison focus between the actual state parameter of the dynamic system and the estimated parameter set of the target dynamic system, avoiding secondary integration calculations. In this case, the disturbance type identification model is directly strongly correlated with the tilt angular velocity. The step of comparing the actual state parameter of the dynamic system with the estimated parameter set of the target dynamic system may include:

[0111] Extract the actual tilt angular velocity of the target balance vehicle's swing arm relative to the vertical direction during the target control cycle from the actual state parameters of the dynamic system;

[0112] For the target dynamic system prediction parameter set, which includes the target control cycle and the corresponding target dynamic system prediction parameters for each historical control cycle prior to the target control cycle, extract the predicted tilt angular velocity of the pendulum relative to the vertical direction in the target control cycle, which is included in the target dynamic system prediction parameters.

[0113] The actual tilt angular velocity is compared with each extracted estimated tilt angular velocity to obtain the angular velocity comparison result of each historical control cycle before the target control cycle in the parameter comparison result.

[0114] Therefore, by executing the above steps S210 to S240, this application can ensure that the balance vehicle control device 10 can identify the actual disturbance type of the electric balance vehicle during the movement process in a timely and accurate manner, so that the electric balance vehicle can adjust its own movement status in a timely manner based on the identified disturbance type, thereby improving the user experience.

[0115] Alternatively, please refer to Figure 5 , Figure 5 This is the second schematic flowchart of the self-balancing scooter disturbance identification method provided in this application embodiment. In this application embodiment, with Figure 2 Compared to the self-balancing scooter disturbance identification method shown, Figure 5The self-balancing scooter disturbance identification method shown may also include steps S250 and S260 to train a disturbance type identification model that achieves high-accuracy disturbance type identification.

[0116] Step S250: Obtain the dynamic system parameter comparison sample set corresponding to each of the different disturbance types, wherein a single dynamic system parameter comparison sample set includes multiple dynamic system parameter comparison samples corresponding to the same disturbance type.

[0117] In this embodiment, the single dynamic system parameter comparison sample is used to describe the relative numerical distribution of the actual dynamic system state parameters and the estimated dynamic system state parameters under the corresponding disturbance type.

[0118] In one embodiment of this example, in order to improve the recognition efficiency of the finally trained disturbance type recognition model, each dynamic system parameter comparison sample can directly select the tilt angular velocity as the parameter value distribution focus, so as to ensure that the finally trained disturbance type recognition model is directly strongly correlated with the tilt angular velocity. At this time, a single dynamic system parameter comparison sample is essentially used to describe the relative value distribution of the actual tilt angular velocity and the estimated tilt angular velocity under the corresponding disturbance type.

[0119] Step S260: Train the model based on the dynamic system parameter comparison sample set corresponding to different disturbance types to obtain the disturbance type identification model.

[0120] In this embodiment, the self-balancing vehicle control device 10 can train a model by substituting the dynamic system parameter comparison sample set corresponding to different disturbance types into a low-computing-power classifier, thereby obtaining a disturbance type identification model with high accuracy in disturbance type identification. The low-computing-power classifier can be, but is not limited to, a support vector machine classifier, a decision tree classifier, etc.

[0121] Therefore, by performing the above steps S250 to S260, this application can train a disturbance type recognition model that achieves high-accuracy disturbance type recognition.

[0122] In this application, to ensure that the self-balancing scooter control device 10 can execute the aforementioned self-balancing scooter disturbance identification method through the self-balancing scooter disturbance identification device 100, this application implements the aforementioned function by dividing the self-balancing scooter disturbance identification device 100 into functional modules. The specific composition of the self-balancing scooter disturbance identification device 100 provided in this application will be described below.

[0123] Please refer to Figure 6 , Figure 7This is one of the schematic diagrams of the components of the self-balancing scooter disturbance identification device 100 provided in this application embodiment. In this application embodiment, the self-balancing scooter disturbance identification device 100 may include a motion data acquisition module 110, a system open-loop estimation module 120, and a disturbance type identification module 130.

[0124] The motion data acquisition module 110 is used to acquire the driving generalized force data output by the motion controller of the target self-balancing vehicle in the current control cycle, as well as the actual dynamic system parameters of the target self-balancing vehicle in the current control cycle.

[0125] The system open-loop estimation module 120 is used to perform dynamic system open-loop estimation for the target control period based on the historical dynamic system estimation parameter set, actual dynamic system parameters and driving generalized force data corresponding to the current control period, to obtain the target dynamic system prediction parameter set of the target balance vehicle in the target control period, where the target control period is the next control period after the current control period.

[0126] The motion data acquisition module 110 is also used to acquire the actual state parameters of the dynamic system obtained by the target balance vehicle moving according to the driving generalized force data within the target control cycle.

[0127] The disturbance type identification module 130 is used to compare the actual state parameters of the dynamic system with the estimated parameter set of the target dynamic system, and call the pre-stored disturbance type identification model to identify the disturbance type of the obtained parameter comparison results, so as to obtain the actual disturbance type of the target balance vehicle in the target control cycle.

[0128] Alternatively, please refer to Figure 7 , Figure 7 This is a second schematic diagram of the composition of the self-balancing scooter disturbance identification device 100 provided in this application embodiment. In this application embodiment, the self-balancing scooter disturbance identification device 100 may further include a disturbance sample acquisition module 140 and a recognition model training module 150.

[0129] The disturbance sample acquisition module 140 is used to acquire dynamic system parameter comparison sample sets corresponding to different disturbance types. Each dynamic system parameter comparison sample set includes multiple dynamic system parameter comparison samples corresponding to the same disturbance type. Each dynamic system parameter comparison sample is used to describe the relative numerical distribution of the actual dynamic system state parameters and the estimated dynamic system state parameters under the corresponding disturbance type.

[0130] The identification model training module 150 is used to train the model based on the dynamic system parameter comparison sample set corresponding to different disturbance types, so as to obtain the disturbance type identification model.

[0131] It should be noted that the basic principle and technical effects of the self-balancing scooter disturbance identification device 100 provided in this embodiment are the same as those of the aforementioned self-balancing scooter disturbance identification method. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the above description of the self-balancing scooter disturbance identification method.

[0132] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of the apparatus, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0133] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part. If the function is implemented as a software functional module and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned readable storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0134] In summary, in the self-balancing scooter disturbance identification method and device, self-balancing scooter control equipment, and readable storage medium provided in this application embodiment, when obtaining the driving generalized force data output by the motion controller of the target self-balancing scooter in the current control cycle, and the actual dynamic system parameters of the target self-balancing scooter in the current control cycle, this application will obtain the target dynamic system estimated parameter set of the target self-balancing scooter in the target control cycle through open-loop estimation of the dynamic system based on the historical dynamic system estimated parameter set corresponding to the current control cycle, the actual dynamic system parameters, and the driving generalized force data. Then, the actual state parameters of the dynamic system obtained by the target self-balancing scooter moving according to the driving generalized force data in the target control cycle will be compared with the target dynamic system estimated parameter set, and a pre-stored disturbance type identification model will be called to identify the disturbance type of the obtained parameter comparison results. This allows for timely and accurate identification of the actual disturbance type of the target self-balancing scooter in the target control cycle, so that the electric self-balancing scooter can adjust its own movement status in a timely manner based on the identified disturbance type, thereby improving the user experience.

[0135] The above descriptions are merely various embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for identifying disturbances in a self-balancing scooter, characterized in that, The method includes: Acquire the driving generalized force data output by the motion controller of the target self-balancing vehicle in the current control cycle, as well as the actual dynamic system parameters of the target self-balancing vehicle in the current control cycle; Based on the historical dynamic system estimation parameter set corresponding to the current control cycle, the actual dynamic system parameters, and the driving generalized force data, an open-loop estimation of the dynamic system is performed for the target control cycle to obtain the target dynamic system prediction parameter set of the target balance vehicle in the target control cycle. The target control cycle is the next control cycle after the current control cycle. The historical dynamic system estimation parameter set includes the historical dynamic system prediction parameters of multiple historical control cycles that are continuously distributed before the current control cycle for the current control cycle. The target dynamic system prediction parameter set includes the target dynamic system prediction parameters of multiple historical control cycles that are continuously distributed before the target control cycle and include the current control cycle for the target control cycle. The actual dynamic system state parameters are obtained by the target self-balancing vehicle moving according to the driving generalized force data within the target control cycle. The actual state parameters of the dynamic system are compared with the estimated parameter set of the target dynamic system, and the pre-stored disturbance type identification model is called to identify the disturbance type of the obtained parameter comparison results, so as to obtain the actual disturbance type of the target balance vehicle in the target control cycle.

2. The method according to claim 1, characterized in that, The step of acquiring the driving generalized force data output by the motion controller of the target self-balancing vehicle in the current control cycle includes: Detect whether the motion controller is a model-free controller; If the motion controller is not a model-free controller, extract the driving generalized force data that conforms to the kinematic principle from the balance vehicle motion control parameters output by the motion controller in the current control cycle. When it is detected that the motion controller is a model-free controller, the motion control parameters of the balance vehicle output by the motion controller in the current control cycle are converted according to the parameter conversion relationship between the preset generalized force data and the control parameters of the motion controller, so as to obtain the driving generalized force data.

3. The method according to claim 1, characterized in that, The step of performing open-loop estimation of the dynamic system for the target control period based on the historical dynamic system estimation parameter set corresponding to the current control period, the actual dynamic system parameters, and the driving generalized force data, to obtain the target dynamic system prediction parameter set of the target self-balancing vehicle in the target control period, includes: The historical dynamic system prediction parameters corresponding to each of the multiple historical control cycles and the actual dynamic system parameters of the current control cycle are respectively used as open-loop prediction parameters, and the dynamic system state change rate equation of the open-loop prediction parameter is constructed based on the driving generalized force data. Based on the dynamic system state change rate equation, calculate the dynamic system parameter prediction increment from the current control period to the target control period for the parameter to be predicted in the open loop. The parameter to be opened-loop predicted is superimposed with the predicted increment of the dynamic system parameter to obtain a target dynamic system predicted parameter for the target control period from the target dynamic system predicted parameter set.

4. The method according to claim 3, characterized in that, The parameters to be predicted in the open-loop system include the position and velocity information of the target self-balancing vehicle body in the forward direction, and the tilt angle and tilt angular velocity of the target self-balancing vehicle's swing arm relative to the vertical direction. The step of constructing the dynamic system state change velocity equation based on the driving generalized force data includes: Based on the inverted pendulum model of the target self-balancing vehicle, the forward kinematic equations of the target self-balancing vehicle under the action of the driving generalized force data are constructed according to the tilt angle and tilt angular velocity in the open-loop prediction parameters. The velocity information and tilt angular velocity in the open-loop prediction parameters are integrated with the forward kinematic equations to obtain the velocity equations for the state changes of the dynamic system.

5. The method according to claim 4, characterized in that, The forward kinematic equations of the target self-balancing vehicle under the action of the generalized driving force data, corresponding to the open-loop predicted parameters, are expressed as follows: ； At this point, the dynamic system state change rate equation for the parameters to be predicted in the open loop is expressed as follows: ； in, Used to represent the forward acceleration corresponding to the open-loop prediction parameter. This represents the acceleration of the target self-balancing vehicle body in the forward direction under the action of the open-loop prediction parameters and the generalized driving force data. This represents the tilt angular acceleration of the target self-balancing vehicle's swing arm relative to the vertical direction under the action of the open-loop estimated parameters and the generalized driving force data. This is used to represent the distance between the center of mass of the pendulum of the target self-balancing scooter and the rotating joint on the scooter body. Used to represent the mass of the swing arm of the target self-balancing scooter. Used to represent the mass of the target self-balancing scooter. This is used to represent the tilt angle of the target self-balancing vehicle's swing arm relative to the vertical direction in the open-loop prediction parameters. This is used to represent the tilt angular velocity of the target self-balancing vehicle's swing arm relative to the vertical direction in the open-loop prediction parameters. Used to represent gravitational acceleration Used to represent the driving generalized force data This is used to represent the rate of change of the dynamic system state of the parameter to be predicted in the open-loop manner under the influence of the driving generalized force data. This is used to represent the speed information of the target self-balancing vehicle body in the forward direction in the open-loop prediction parameters.

6. The method according to any one of claims 1-5, characterized in that, The step of comparing the actual state parameters of the dynamic system with the estimated parameter set of the target dynamic system includes: Extract the actual tilt angular velocity of the target balance vehicle's swing arm relative to the vertical direction during the target control cycle from the actual state parameters of the dynamic system; For the target dynamic system prediction parameter set, which includes the target control cycle and the corresponding target dynamic system prediction parameters for each historical control cycle prior to the target control cycle, extract the predicted tilt angular velocity of the pendulum relative to the vertical direction in the target control cycle, which is included in the target dynamic system prediction parameters. The actual tilt angular velocity is compared with each extracted estimated tilt angular velocity to obtain the angular velocity comparison result of each historical control cycle before the target control cycle in the parameter comparison result.

7. The method according to claim 6, characterized in that, The method further includes: Obtain dynamic system parameter comparison sample sets corresponding to different disturbance types. Each dynamic system parameter comparison sample set includes multiple dynamic system parameter comparison samples corresponding to the same disturbance type. Each dynamic system parameter comparison sample is used to describe the relative numerical distribution of the actual dynamic system state parameters and the estimated dynamic system state parameters under the corresponding disturbance type. The model is trained by comparing the dynamic system parameters corresponding to different disturbance types with the sample set to obtain the disturbance type identification model.

8. A disturbance detection device for a self-balancing scooter, characterized in that, The device includes: The motion data acquisition module is used to acquire the driving generalized force data output by the motion controller of the target self-balancing vehicle in the current control cycle, as well as the actual dynamic system parameters of the target self-balancing vehicle in the current control cycle. The system open-loop estimation module is used to perform dynamic system open-loop estimation for the target control period based on the historical dynamic system estimation parameter set corresponding to the current control period, the actual dynamic system parameters, and the driving generalized force data, to obtain the target dynamic system prediction parameter set of the target balance vehicle in the target control period. The target control period is the next control period after the current control period. The historical dynamic system estimation parameter set includes the historical dynamic system prediction parameters of multiple historical control periods that are continuously distributed before the current control period for the current control period. The target dynamic system prediction parameter set includes the target dynamic system prediction parameters of multiple historical control periods that are continuously distributed before the target control period and include the current control period for the target control period. The motion data acquisition module is also used to acquire the actual dynamic system state parameters obtained by the target balance vehicle moving according to the driving generalized force data within the target control cycle; The disturbance type identification module is used to compare the actual state parameters of the dynamic system with the estimated parameter set of the target dynamic system, and call the pre-stored disturbance type identification model to identify the disturbance type of the obtained parameter comparison result, so as to obtain the actual disturbance type of the target balance vehicle in the target control cycle.

9. The apparatus according to claim 8, characterized in that, The device further includes: The disturbance sample acquisition module is used to acquire dynamic system parameter comparison sample sets corresponding to different disturbance types. Each dynamic system parameter comparison sample set includes multiple dynamic system parameter comparison samples corresponding to the same disturbance type. Each dynamic system parameter comparison sample is used to describe the relative numerical distribution of the actual dynamic system state parameters and the estimated dynamic system state parameters under the corresponding disturbance type. The identification model training module is used to train the model based on the dynamic system parameter comparison sample set corresponding to different disturbance types, so as to obtain the disturbance type identification model.

10. A self-balancing scooter control device, characterized in that, It includes a processor and a memory, the memory storing a computer program that can be executed by the processor, the processor being able to execute the computer program to implement the self-balancing scooter disturbance identification method according to any one of claims 1-7.

11. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the self-balancing scooter disturbance identification method according to any one of claims 1-7.

Images