CN113642103A - Method and device for adjusting parameters of dynamic model, medium and electronic equipment - Google Patents
Method and device for adjusting parameters of dynamic model, medium and electronic equipment Download PDFInfo
- Publication number
- CN113642103A CN113642103A CN202110839480.0A CN202110839480A CN113642103A CN 113642103 A CN113642103 A CN 113642103A CN 202110839480 A CN202110839480 A CN 202110839480A CN 113642103 A CN113642103 A CN 113642103A
- Authority
- CN
- China
- Prior art keywords
- error
- target
- information
- fuzzy
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The disclosure relates to a method, a device, a medium and an electronic device for adjusting kinetic model parameters, wherein the method comprises the following steps: acquiring simulation running state information of a dynamic model of the unmanned aerial vehicle when the dynamic model runs according to at least one target parameter, and equipment running state information of the unmanned aerial vehicle when the dynamic model runs according to the at least one target parameter; determining target error information between the simulation running state information and the equipment running state information; fuzzifying the target error information to determine a model parameter adjustment fuzzy matrix corresponding to the target error information; and adjusting the fuzzy matrix according to the model parameters, and adjusting the parameters of the dynamic model. By the scheme, the target error information is fuzzified, so that the parameters of the dynamic model can be automatically and adaptively adjusted, technicians do not need to manually adjust the parameters, the simulation degree of the dynamic model is improved, and the accuracy and the efficiency of constructing the dynamic model are improved.
Description
Technical Field
The present disclosure relates to the field of unmanned driving, and in particular, to a method, an apparatus, a medium, and an electronic device for adjusting parameters of a dynamic model.
Background
At present, unmanned equipment is more and more widely applied, such as unmanned vehicles and unmanned aerial vehicles, and the unmanned equipment senses the surrounding environment and the self state by using a sensor and decides the next operation track through a path planning algorithm, so that automatic driving is realized.
The external environment of the unmanned equipment in an actual scene is complex and variable, the performance of the unmanned equipment needs to be tested before the unmanned equipment really operates autonomously, so that the safety of the equipment in the operation process is ensured, and because the real vehicle test has high cost, long period and low efficiency, a dynamic model of the unmanned equipment can be built, the sensing and decision algorithm of the unmanned equipment in different scenes is trained and verified through an unmanned simulation platform, the performance of the unmanned equipment is tested in a simulation mode, wherein whether the built dynamic model can truly reflect the motion characteristic of the unmanned equipment or not has great influence on the accuracy of the simulation test.
Disclosure of Invention
The invention aims to provide a method, a device, a medium and electronic equipment for adjusting parameters of a dynamic model, which can automatically and adaptively adjust the parameters of the dynamic model and improve the accuracy and efficiency of dynamic model construction.
In order to achieve the above object, in a first aspect, the present disclosure provides a method for adjusting parameters of a dynamical model, the method including:
acquiring simulation running state information of a dynamic model of the unmanned aerial vehicle when the dynamic model runs according to at least one target parameter, and equipment running state information of the unmanned aerial vehicle when the dynamic model runs according to the at least one target parameter;
determining target error information between the simulation running state information and the equipment running state information;
fuzzifying the target error information to determine a model parameter adjustment fuzzy matrix corresponding to the target error information;
and adjusting the fuzzy matrix according to the model parameters, and adjusting the parameters of the dynamic model.
Optionally, the blurring the target error information to determine a model parameter adjustment blurring matrix corresponding to the target error information includes:
determining at least one target fuzzy set corresponding to target error information according to the target error information and a first preset membership function, wherein the first preset membership function is used for representing the membership of a plurality of preset error information to each preset fuzzy set respectively;
determining an error fuzzy matrix corresponding to the target error information according to the fuzzy vector of the target fuzzy set in the first preset membership function, wherein the fuzzy vector of the target fuzzy set is formed by the membership of a plurality of preset error information to the target fuzzy set respectively;
and determining the model parameter adjustment fuzzy matrix according to the error fuzzy matrix.
Optionally, the determining the model parameter adjustment fuzzy matrix according to the error fuzzy matrix includes:
determining a fuzzy relation matrix between the error information and the model parameter adjustment information according to a fuzzy rule between the error information and the model parameter adjustment information, the first preset membership function and a second preset membership function, wherein the second preset membership function is used for representing the membership of a plurality of preset model parameter adjustment information to each preset fuzzy set respectively;
and determining the model parameter adjustment fuzzy matrix according to the error fuzzy matrix and the fuzzy relation matrix.
Optionally, the preset fuzzy set includes: negative large, negative small, zero, positive small, positive large;
the fuzzy rule comprises: if the error information is under the condition of negative large, the model parameter adjustment information is under the condition of negative large, if the error information is under the condition of negative small, the model parameter adjustment information is under the condition of negative small, if the error information is under the condition of zero, the model parameter adjustment information is under the condition of zero, if the error information is under the condition of positive small, the model parameter adjustment information is under the condition of positive small, and if the error information is under the condition of positive large, the model parameter adjustment information is under the condition of positive large.
Optionally, the adjusting the fuzzy matrix according to the model parameter, and adjusting the parameter of the dynamic model includes;
defuzzification is carried out on the model parameter adjustment fuzzy matrix to obtain target model parameter adjustment information;
and adjusting the parameters of the dynamic model according to the parameter adjustment information of the target model.
Optionally, the target model parameter adjustment information comprises at least one of: transmission system transmission ratio, steering system transmission ratio, brake pressure of a brake system, power system transmission ratio and power system throttle valve parameters.
Optionally, the target error information comprises at least one of: velocity error, acceleration error, angular velocity error, jerk error, angular acceleration error, trajectory error, steering error, rate of change of velocity error, rate of change of acceleration error, rate of change of angular velocity error, rate of change of jerk error, rate of change of angular acceleration error, rate of change of trajectory error, rate of change of steering error.
In a second aspect, the present disclosure provides an apparatus for adjusting parameters of a kinetic model, the apparatus comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is configured to acquire simulation running state information of a dynamic model of the unmanned aerial vehicle when the dynamic model runs according to at least one target parameter, and equipment running state information of the unmanned aerial vehicle when the unmanned aerial vehicle runs according to the at least one target parameter;
an error information determination module configured to determine target error information between the simulated operational state information and the device operational state information;
a processing module configured to perform fuzzification processing on the target error information to determine a model parameter adjustment fuzzy matrix corresponding to the target error information;
an adjusting module configured to adjust a fuzzy matrix according to the model parameters, and adjust parameters of the dynamic model.
Optionally, the processing module includes:
the first determining submodule is configured to determine at least one target fuzzy set corresponding to target error information according to the target error information and a first preset membership function, wherein the first preset membership function is used for representing membership of a plurality of preset error information to each preset fuzzy set respectively;
a second determining submodule configured to determine an error fuzzy matrix corresponding to the target error information according to a fuzzy vector of the target fuzzy set in the first preset membership function, wherein the fuzzy vector of the target fuzzy set is formed by membership degrees of a plurality of preset error information to the target fuzzy set respectively;
a third determination submodule configured to determine the model parameter adjustment blur matrix from the error blur matrix.
Optionally, the third determining sub-module includes:
a fourth determining submodule configured to determine a fuzzy relation matrix between the error information and the model parameter adjustment information according to a fuzzy rule between the error information and the model parameter adjustment information, the first preset membership function, and a second preset membership function, wherein the second preset membership function is used for representing the membership of a plurality of preset model parameter adjustment information to each preset fuzzy set respectively;
a fifth determining submodule configured to determine the model parameter adjustment fuzzy matrix according to the error fuzzy matrix and the fuzzy relation matrix.
Optionally, the preset fuzzy set includes: negative large, negative small, zero, positive small, positive large;
the fuzzy rule comprises: if the error information is under the condition of negative large, the model parameter adjustment information is under the condition of negative large, if the error information is under the condition of negative small, the model parameter adjustment information is under the condition of negative small, if the error information is under the condition of zero, the model parameter adjustment information is under the condition of zero, if the error information is under the condition of positive small, the model parameter adjustment information is under the condition of positive small, and if the error information is under the condition of positive large, the model parameter adjustment information is under the condition of positive large.
Optionally, the adjusting module comprises;
a processing submodule configured to defuzzify the model parameter adjustment fuzzy matrix to obtain target model parameter adjustment information;
an adjusting submodule configured to adjust parameters of the dynamic model according to the target model parameter adjustment information.
Optionally, the target model parameter adjustment information comprises at least one of: transmission system transmission ratio, steering system transmission ratio, brake pressure of a brake system, power system transmission ratio and power system throttle valve parameters.
Optionally, the target error information comprises at least one of: velocity error, acceleration error, angular velocity error, jerk error, angular acceleration error, trajectory error, steering error, rate of change of velocity error, rate of change of acceleration error, rate of change of angular velocity error, rate of change of jerk error, rate of change of angular acceleration error, rate of change of trajectory error, rate of change of steering error.
In a third aspect, the present disclosure provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method provided by the first aspect of the present disclosure.
In a fourth aspect, the present disclosure provides an electronic device comprising: a memory having a computer program stored thereon; a processor for executing the computer program in the memory to implement the steps of the method provided by the first aspect of the present disclosure.
By the technical scheme, the simulation running state information of the dynamic model of the unmanned equipment when running according to at least one target parameter, the equipment running state information of the unmanned equipment when running according to at least one target parameter, the target error information between the simulation running state information and the equipment running state information are obtained, the difference between the dynamic model and the unmanned equipment can be reflected, the target error information is fuzzified, the target error information can be converted into a fuzzy vector, a model parameter adjustment fuzzy matrix corresponding to the target error information is determined, the fuzzy matrix is adjusted according to the model parameter, and the parameter of the dynamic model can be adjusted. Therefore, by fuzzifying the target error information, various parameters of the dynamic model can be automatically and adaptively adjusted, the parameters do not need to be manually adjusted by technicians, the parameter fitting efficiency is improved, the simulation degree of the dynamic model can be improved by adaptively adjusting the parameters of the dynamic model, the dynamic model is closer to the motion characteristic of the unmanned equipment, and the accuracy and the efficiency of constructing the dynamic model are improved.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
FIG. 1 is a flow chart illustrating a method of tuning kinetic model parameters according to an exemplary embodiment.
FIG. 2 is a flow diagram illustrating a method of blurring target error information to determine a corresponding model parameter adjustment blur matrix according to an example embodiment.
FIG. 3 is a flow diagram illustrating a method for adjusting a blur matrix based on error blur matrix determination model parameters, according to an example embodiment.
Fig. 4 is a block diagram illustrating an apparatus for adjusting parameters of a kinetic model according to an exemplary embodiment.
FIG. 5 is a block diagram illustrating an electronic device in accordance with an example embodiment.
FIG. 6 is a block diagram illustrating an electronic device in accordance with an example embodiment.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
The application scenario of the method is introduced firstly, the method can be applied to the process of building a dynamic model of the unmanned equipment, and parameters of the dynamic model need to be adjusted in the process of building the dynamic model of the unmanned equipment so as to improve the simulation degree of the dynamic model, namely improve the consistency of the dynamic model and the motion characteristics of the unmanned equipment.
Fig. 1 is a flowchart illustrating a method for adjusting parameters of a dynamical model, which may be applied to a dynamical model building platform, according to an exemplary embodiment, and as shown in fig. 1, the method may include S101 to S104.
In S101, simulation operating state information of the dynamical model of the unmanned aerial vehicle when operating according to the at least one target parameter and device operating state information of the unmanned aerial vehicle when operating according to the at least one target parameter are obtained.
The target parameter may be a parameter required for driving the unmanned device to operate, and may include, for example, an accelerator opening degree, a steering direction of a steering wheel, and the like. The number of target parameters in the present disclosure is not particularly limited, and may be one or more. For example, the dynamic model building platform may generate an operation control instruction according to the at least one target parameter, and send the operation control instruction to the unmanned aerial vehicle and the dynamic model respectively, so that the unmanned aerial vehicle and the dynamic model operate according to the at least one target parameter. It should be noted that the operation control command may be sent to the unmanned device and the dynamic model at the same time, or may be sent to the unmanned device and the dynamic model at different times, and the disclosure is not limited thereto.
The operation environment of the dynamic model can be set to be the same as the external environment of the unmanned equipment, and the environment such as the road friction coefficient, the wind resistance and the like is the same as the environment of the unmanned equipment. The unmanned aerial vehicle may transmit the device operation state information while operating according to the at least one target parameter to the dynamics model construction platform, and the device operation state information may include, for example, a real-time speed, a real-time acceleration, a real-time angular speed, a real-time jerk, a real-time angular acceleration, a real-time trajectory information, and a real-time steering information of the unmanned aerial vehicle. Moreover, because the actual device operation state information of the unmanned device has a data jitter phenomenon, the device operation state information can be firstly filtered. The dynamic model may send simulated operating state information while operating according to the at least one target parameter to the dynamic model building platform, which may include, for example, real-time velocity, real-time acceleration, real-time angular velocity, real-time jerk, real-time angular acceleration, real-time trajectory information, and real-time steering information of the dynamic model.
In S102, target error information between the simulation operation state information and the device operation state information is determined.
Illustratively, the target error information may include at least one of: velocity error, acceleration error, angular velocity error, jerk error, angular acceleration error, trajectory error, steering error, rate of change of velocity error, rate of change of acceleration error, rate of change of angular velocity error, rate of change of jerk error, rate of change of angular acceleration error, rate of change of trajectory error, rate of change of steering error.
In S103, the target error information is fuzzified to determine a model parameter adjustment fuzzy matrix corresponding to the target error information.
In S104, the fuzzy matrix is adjusted according to the model parameters, and the parameters of the dynamic model are adjusted.
The dynamic model and the unmanned equipment operate according to the same parameters, target error information between the generated simulation operation state information and the equipment operation state information can reflect the difference between the dynamic model and the unmanned equipment, fuzzification processing is carried out on the target error information, the target error information can be converted into a fuzzy vector, and a model parameter adjustment fuzzy matrix corresponding to the target error information is determined based on fuzzy reasoning. And adjusting the fuzzy matrix according to the model parameters to determine the parameter adjustment information of the target model, and adjusting the parameters of the dynamic model by taking the parameter adjustment information of the target model as a control quantity. In the process of constructing the dynamic model, the parameters of the dynamic model can be adjusted for multiple times until the error between the simulation running state information of the dynamic model and the equipment running state information of the unmanned equipment is smaller than a certain threshold value. Therefore, by fuzzifying the target error information, various parameters of the dynamic model can be automatically and adaptively adjusted, technicians do not need to manually adjust the parameters, the parameter fitting efficiency is improved, and the accuracy and efficiency of dynamic model construction are improved.
By the technical scheme, the simulation running state information of the dynamic model of the unmanned equipment when running according to at least one target parameter, the equipment running state information of the unmanned equipment when running according to at least one target parameter, the target error information between the simulation running state information and the equipment running state information are obtained, the difference between the dynamic model and the unmanned equipment can be reflected, the target error information is fuzzified, the target error information can be converted into a fuzzy vector, a model parameter adjustment fuzzy matrix corresponding to the target error information is determined, the fuzzy matrix is adjusted according to the model parameter, and the parameter of the dynamic model can be adjusted. Therefore, by fuzzifying the target error information, various parameters of the dynamic model can be automatically and adaptively adjusted, the parameters do not need to be manually adjusted by technicians, the parameter fitting efficiency is improved, the simulation degree of the dynamic model can be improved by adaptively adjusting the parameters of the dynamic model, the dynamic model is closer to the motion characteristic of the unmanned equipment, and the accuracy and the efficiency of constructing the dynamic model are improved.
Fig. 2 is a flowchart illustrating a method of blurring target error information to determine a corresponding model parameter adjustment blurring matrix according to an exemplary embodiment, which may include S201 to S203, as shown in fig. 2.
In S201, at least one target fuzzy set corresponding to the target error information is determined according to the target error information and the first preset membership function.
The first preset membership function is used for representing the membership of a plurality of preset error information to each preset fuzzy set respectively. For example, the preset fuzzy set may include: negative large (NB), Negative Small (NS), Zero (ZO), Positive Small (PS), positive large (PB). Table 1 shows an example of a first preset membership function in an exemplary embodiment, where a value range of preset error information is [ -1.5, 1.5], and a target error information is taken as a speed error, the target error information is positive, a speed representing a dynamic model is higher than a speed of the unmanned device, the target error information is negative, and the speed representing the dynamic model is lower than the speed of the unmanned device. It should be noted that the plurality of preset error information in table 1 are discrete points, which are only for illustration and explanation, and the first preset membership function may be a continuous function.
TABLE 1
For example, taking target error information as a speed error as an example, the target error information is 1.5, the membership degree of the target error information to the positive large (PB) of the fuzzy set is 1, and the target fuzzy set corresponding to the target error information can be determined to be the positive large (PB). Illustratively, for example, if the target error information is 1, and the degree of membership of the target error information to the positive large (PB) and the degree of membership of the target error information to the Positive Small (PS) of the fuzzy set is 0.5, it may be determined that the target fuzzy set corresponding to the target error information includes the positive large (PB) and the Positive Small (PS).
In S202, an error fuzzy matrix corresponding to the target error information is determined according to the fuzzy vector of the target fuzzy set in the first preset membership function.
The fuzzy vector of the target fuzzy set is composed of membership degrees of a plurality of preset error information to the target fuzzy set respectively. Illustratively, taking table 1 as an example, the blur vector for the positive large (PB) blur set is [0,0,0,0,0,0.5,1], and the blur vector for the Positive Small (PS) blur set is [0,0,0,0.5,0,0.5,0 ].
Taking the target error information as 1.5 as an example, the target fuzzy set corresponding to the target error information is Positive (PB), and the corresponding error fuzzy matrix can be a fuzzy vector [0,0,0,0,0,0.5,1] of which the fuzzy set is Positive (PB). Taking the target error information as 1 as an example, the target fuzzy set corresponding to the target error information includes positive large (PB) and Positive Small (PS), and the corresponding error fuzzy matrix may be composed of fuzzy vectors of the positive large (PB) fuzzy set and fuzzy vectors of the Positive Small (PS) fuzzy set.
In S203, a model parameter adjustment fuzzy matrix is determined according to the error fuzzy matrix.
An exemplary embodiment of this step S203 may be as shown in fig. 3, including S301 and S302.
In S301, a fuzzy relation matrix between the error information and the model parameter adjustment information is determined according to a fuzzy rule, a first preset membership function, and a second preset membership function between the error information and the model parameter adjustment information.
And the second preset membership function is used for representing the membership of the parameter adjustment information of the plurality of preset models to each preset fuzzy set respectively. Table 2 shows an example of a second preset membership function in an exemplary embodiment, where the value range of the preset model parameter adjustment information is [ -2, 2], the model parameter adjustment information is taken as an example of a transmission ratio of the power system, the model parameter adjustment information is negative and indicates that the transmission ratio of the power system of the dynamic model needs to be increased, and the model parameter adjustment information is positive and indicates that the transmission ratio of the power system of the dynamic model needs to be decreased. It should be noted that the plurality of preset model parameter adjustment information in table 2 are discrete points, which are only for illustration and explanation, and the second preset membership function may be a continuous function.
TABLE 2
The fuzzy rule between the error information and the model parameter adjustment information may be: if the error information is under the condition of negative large, the model parameter adjustment information is under the condition of negative large, if the error information is under the condition of negative small, the model parameter adjustment information is under the condition of negative small, if the error information is under the condition of zero, the model parameter adjustment information is under the condition of zero, if the error information is under the condition of positive small, the model parameter adjustment information is under the condition of positive small, and if the error information is under the condition of positive large, the model parameter adjustment information is under the condition of positive large.
The fuzzy relation matrix between the error information and the model parameter adjustment information can be determined by taking intersection through fuzzy set operation in the rules and taking union through fuzzy set operation in the rules, and the fuzzy relation matrix R can be determined through the following formula:
R=(NBe×NBu)∪(NSe×NSu)∪(ZOe×ZOu)∪(PSe×PSu)∪(PBe×PBu)
wherein NBe represents a fuzzy vector with a negative fuzzy set in the first preset membership function, and in table 1 as an example, NBe is [1,0.5,0,0,0,0,0 ]. NBu represents a fuzzy vector with a large negative value of the fuzzy set in the second preset membership function, and the fuzzy vector of the fuzzy set in the second preset membership function is composed of membership degrees of the plurality of preset model parameter adjustment information to the fuzzy set, and NBu is [1,0.5,0,0,0,0,0,0,0] taking table 2 as an example. NSe denotes the fuzzy vector with the smallest fuzzy set in the first preset membership function, for example, NSe ═ 0,0.5,1,0.5,0,0,0 in table 1. NSu denotes the fuzzy vector with small negative set in the second preset membership function, for example, NSu ═ 0,0.5,1,0.5,0,0,0,0 in table 2. ZOe denotes the fuzzy vector of the fuzzy set zero in the first preset membership function, for example, table 1, ZOe ═ 0,0,0.5,1,0.5,0, 0. ZOu denotes the fuzzy vector of the fuzzy set zero in the second preset membership function, for example, in table 2, ZOu ═ 0,0,0,0.5,1,0.5,0, 0. PSe represents a fuzzy vector with a positive small fuzzy set in the first preset membership function, and for example, in table 1, PSe is [0,0,0,0.5,0,0.5,0 ]. PSu represents a fuzzy vector with a just small fuzzy set in the second preset membership function, and for example, in table 2, PSu is [0,0,0,0,0,0.5,1,0.5,0 ]. PBe denotes the fuzzy vector with the largest fuzzy set in the first preset membership function, for example, table 1, PBe ═ 0,0,0,0,0.5, 1. PBu represents a fuzzy vector with a large fuzzy set in the second preset membership function, and for example, PBu is [0,0,0,0,0,0,0,0.5,1] in table 2.
In S302, a model parameter adjustment fuzzy matrix is determined according to the error fuzzy matrix and the fuzzy relation matrix.
For example, the fuzzy matrix may be adjusted using the product of the error fuzzy matrix and the fuzzy relation matrix as the model parameter.
By the technical scheme, the target error information is subjected to fuzzy processing, an error fuzzy matrix corresponding to the target error information can be determined, the model parameter adjustment fuzzy matrix can be determined according to the fuzzy relation matrix and the error fuzzy matrix between the error information and the model parameter adjustment information, and the parameters of the dynamic model can be adjusted according to the model parameter adjustment fuzzy matrix. Therefore, by fuzzifying the target error information, various parameters of the dynamic model can be automatically and adaptively adjusted, and the accuracy and efficiency of constructing the dynamic model are improved.
Optionally, adjusting the fuzzy matrix according to the model parameters in S104, and adjusting the parameters of the dynamic model may include;
defuzzification is carried out on the model parameter adjustment fuzzy matrix to obtain target model parameter adjustment information; and adjusting the parameters of the dynamic model according to the parameter adjustment information of the target model.
Illustratively, the model parameter adjustment fuzzy matrix can be defuzzified by adopting the maximum membership principle to obtain the target model parameter adjustment information. The target model parameter adjustment information may include at least one of: transmission system transmission ratio, steering system transmission ratio, brake pressure of a brake system, power system transmission ratio and power system throttle valve parameters. For example, a powertrain transmission ratio may be obtained from a speed error and a rate of change of the speed error between the dynamic model and the unmanned device, and a steering transmission ratio may be obtained from a steering error and a rate of change of the steering error between the dynamic model and the unmanned device.
For example, taking the target model parameter adjustment information as the power system transmission ratio as an example, if the target model parameter adjustment information is negative, it indicates that the power system transmission ratio of the dynamic model needs to be increased, and if the target model parameter adjustment information is positive, it indicates that the power system transmission ratio of the dynamic model needs to be decreased. Therefore, the parameters of the dynamic model can be automatically and adaptively adjusted, and the simulation degree and the accuracy of the dynamic model are continuously improved.
Based on the same inventive concept, the present disclosure further provides an apparatus for adjusting dynamic model parameters, and fig. 4 is a block diagram of an apparatus for adjusting dynamic model parameters according to an exemplary embodiment, as shown in fig. 4, the apparatus 400 may include:
an obtaining module 401 configured to obtain simulated operation state information of a dynamic model of an unmanned aerial vehicle when the dynamic model operates according to at least one target parameter, and equipment operation state information of the unmanned aerial vehicle when the unmanned aerial vehicle operates according to the at least one target parameter;
an error information determination module 402 configured to determine target error information between the simulated operational state information and the device operational state information;
a processing module 403, configured to perform blurring processing on the target error information to determine a model parameter adjustment blurring matrix corresponding to the target error information;
an adjusting module 404 configured to adjust a fuzzy matrix according to the model parameters, and adjust parameters of the dynamical model.
By adopting the device, the simulation running state information of the dynamic model of the unmanned equipment when running according to at least one target parameter, the equipment running state information of the unmanned equipment when running according to at least one target parameter, and the target error information between the simulation running state information and the equipment running state information are obtained, the difference between the dynamic model and the unmanned equipment can be reflected, the target error information is fuzzified, the target error information can be converted into a fuzzy vector, so that a model parameter adjustment fuzzy matrix corresponding to the target error information is determined, the fuzzy matrix is adjusted according to the model parameter, and the parameter of the dynamic model can be adjusted. Therefore, by fuzzifying the target error information, various parameters of the dynamic model can be automatically and adaptively adjusted, the parameters do not need to be manually adjusted by technicians, the parameter fitting efficiency is improved, the simulation degree of the dynamic model can be improved by adaptively adjusting the parameters of the dynamic model, the dynamic model is closer to the motion characteristic of the unmanned equipment, and the accuracy and the efficiency of constructing the dynamic model are improved.
Optionally, the processing module 403 includes:
the first determining submodule is configured to determine at least one target fuzzy set corresponding to target error information according to the target error information and a first preset membership function, wherein the first preset membership function is used for representing membership of a plurality of preset error information to each preset fuzzy set respectively;
a second determining submodule configured to determine an error fuzzy matrix corresponding to the target error information according to a fuzzy vector of the target fuzzy set in the first preset membership function, wherein the fuzzy vector of the target fuzzy set is formed by membership degrees of a plurality of preset error information to the target fuzzy set respectively;
a third determination submodule configured to determine the model parameter adjustment blur matrix from the error blur matrix.
Optionally, the third determining sub-module includes:
a fourth determining submodule configured to determine a fuzzy relation matrix between the error information and the model parameter adjustment information according to a fuzzy rule between the error information and the model parameter adjustment information, the first preset membership function, and a second preset membership function, wherein the second preset membership function is used for representing the membership of a plurality of preset model parameter adjustment information to each preset fuzzy set respectively;
a fifth determining submodule configured to determine the model parameter adjustment fuzzy matrix according to the error fuzzy matrix and the fuzzy relation matrix.
Optionally, the preset fuzzy set includes: negative large, negative small, zero, positive small, positive large;
the fuzzy rule comprises: if the error information is under the condition of negative large, the model parameter adjustment information is under the condition of negative large, if the error information is under the condition of negative small, the model parameter adjustment information is under the condition of negative small, if the error information is under the condition of zero, the model parameter adjustment information is under the condition of zero, if the error information is under the condition of positive small, the model parameter adjustment information is under the condition of positive small, and if the error information is under the condition of positive large, the model parameter adjustment information is under the condition of positive large.
Optionally, the adjusting module 404 includes;
a processing submodule configured to defuzzify the model parameter adjustment fuzzy matrix to obtain target model parameter adjustment information;
an adjusting submodule configured to adjust parameters of the dynamic model according to the target model parameter adjustment information.
Optionally, the target model parameter adjustment information comprises at least one of: transmission system transmission ratio, steering system transmission ratio, brake pressure of a brake system, power system transmission ratio and power system throttle valve parameters.
Optionally, the target error information comprises at least one of: velocity error, acceleration error, angular velocity error, jerk error, angular acceleration error, trajectory error, steering error, rate of change of velocity error, rate of change of acceleration error, rate of change of angular velocity error, rate of change of jerk error, rate of change of angular acceleration error, rate of change of trajectory error, rate of change of steering error.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 5 is a block diagram illustrating an electronic device 700 according to an example embodiment. As shown in fig. 5, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input/output (I/O) interface 704, and a communication component 705.
The processor 701 is configured to control the overall operation of the electronic device 700, so as to complete all or part of the steps in the above-mentioned method for adjusting the kinetic model parameters. The memory 702 is used to store various types of data to support operation at the electronic device 700, such as instructions for any application or method operating on the electronic device 700 and application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and the like. The Memory 702 may be implemented by any type of volatile or non-volatile Memory device or 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 Memory, flash Memory, magnetic disk, or optical disk. The multimedia components 703 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 702 or transmitted through the communication component 705. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 704 provides an interface between the processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, which is not limited herein. The corresponding communication component 705 may thus include: Wi-Fi module, Bluetooth module, NFC module, etc.
In an exemplary embodiment, the electronic Device 700 may be implemented by 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 performing the above-mentioned method for adjusting kinetic model parameters.
In another exemplary embodiment, a computer readable storage medium is also provided, which comprises program instructions, which when executed by a processor, implement the steps of the above-described method of tuning kinetic model parameters. For example, the computer readable storage medium may be the memory 702 comprising program instructions executable by the processor 701 of the electronic device 700 to perform the above-described method for adjusting the kinetic model parameters.
Fig. 6 is a block diagram illustrating an electronic device 1900 according to an example embodiment. For example, the electronic device 1900 may be provided as a server. Referring to fig. 6, an electronic device 1900 includes a processor 1922, which may be one or more in number, and a memory 1932 for storing computer programs executable by the processor 1922. The computer program stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processor 1922 may be configured to execute the computer program to perform the above-described method of adjusting the kinetic model parameters.
Additionally, electronic device 1900 may also include a power component 1926 and a communication component 1950, the power component 1926 may be configured to perform power management of the electronic device 1900, and the communication component 1950 may be configured to enable communication, e.g., wired or wireless communication, of the electronic device 1900. In addition, the electronic device 1900 may also include input/output (I/O) interfaces 1958. The electronic device 1900 may operate based on an operating system, such as Windows Server, stored in memory 1932TM,Mac OS XTM,UnixTM,LinuxTMAnd so on.
In another exemplary embodiment, a computer readable storage medium is also provided, which comprises program instructions, which when executed by a processor, implement the steps of the above-described method of tuning kinetic model parameters. For example, the computer readable storage medium may be the memory 1932 comprising program instructions executable by the processor 1922 of the electronic device 1900 to perform the method for tuning kinetic model parameters described above.
In another exemplary embodiment, a computer program product is also provided, which comprises a computer program executable by a programmable apparatus, the computer program having code portions for performing the above-described method of tuning kinetic model parameters when executed by the programmable apparatus.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that, in the foregoing embodiments, various features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various combinations that are possible in the present disclosure are not described again.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.
Claims (10)
1. A method for adjusting parameters of a kinetic model, the method comprising:
acquiring simulation running state information of a dynamic model of the unmanned aerial vehicle when the dynamic model runs according to at least one target parameter, and equipment running state information of the unmanned aerial vehicle when the dynamic model runs according to the at least one target parameter;
determining target error information between the simulation running state information and the equipment running state information;
fuzzifying the target error information to determine a model parameter adjustment fuzzy matrix corresponding to the target error information;
and adjusting the fuzzy matrix according to the model parameters, and adjusting the parameters of the dynamic model.
2. The method of claim 1, wherein the blurring the target error information to determine a model parameter adjustment blurring matrix corresponding to the target error information comprises:
determining at least one target fuzzy set corresponding to target error information according to the target error information and a first preset membership function, wherein the first preset membership function is used for representing the membership of a plurality of preset error information to each preset fuzzy set respectively;
determining an error fuzzy matrix corresponding to the target error information according to the fuzzy vector of the target fuzzy set in the first preset membership function, wherein the fuzzy vector of the target fuzzy set is formed by the membership of a plurality of preset error information to the target fuzzy set respectively;
and determining the model parameter adjustment fuzzy matrix according to the error fuzzy matrix.
3. The method of claim 2, wherein determining the model parameter adjustment blur matrix from the error blur matrix comprises:
determining a fuzzy relation matrix between the error information and the model parameter adjustment information according to a fuzzy rule between the error information and the model parameter adjustment information, the first preset membership function and a second preset membership function, wherein the second preset membership function is used for representing the membership of a plurality of preset model parameter adjustment information to each preset fuzzy set respectively;
and determining the model parameter adjustment fuzzy matrix according to the error fuzzy matrix and the fuzzy relation matrix.
4. The method of claim 3, wherein the preset fuzzy set comprises: negative large, negative small, zero, positive small, positive large;
the fuzzy rule comprises: if the error information is under the condition of negative large, the model parameter adjustment information is under the condition of negative large, if the error information is under the condition of negative small, the model parameter adjustment information is under the condition of negative small, if the error information is under the condition of zero, the model parameter adjustment information is under the condition of zero, if the error information is under the condition of positive small, the model parameter adjustment information is under the condition of positive small, and if the error information is under the condition of positive large, the model parameter adjustment information is under the condition of positive large.
5. The method of claim 1, wherein said adjusting a blur matrix according to said model parameters, adjusting parameters of said dynamical model, comprises;
defuzzification is carried out on the model parameter adjustment fuzzy matrix to obtain target model parameter adjustment information;
and adjusting the parameters of the dynamic model according to the parameter adjustment information of the target model.
6. The method of claim 5, wherein the target model parameter adjustment information comprises at least one of: transmission system transmission ratio, steering system transmission ratio, brake pressure of a brake system, power system transmission ratio and power system throttle valve parameters.
7. The method according to any of claims 1-6, wherein the target error information comprises at least one of: velocity error, acceleration error, angular velocity error, jerk error, angular acceleration error, trajectory error, steering error, rate of change of velocity error, rate of change of acceleration error, rate of change of angular velocity error, rate of change of jerk error, rate of change of angular acceleration error, rate of change of trajectory error, rate of change of steering error.
8. An apparatus for adjusting parameters of a kinetic model, the apparatus comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is configured to acquire simulation running state information of a dynamic model of the unmanned aerial vehicle when the dynamic model runs according to at least one target parameter, and equipment running state information of the unmanned aerial vehicle when the unmanned aerial vehicle runs according to the at least one target parameter;
an error information determination module configured to determine target error information between the simulated operational state information and the device operational state information;
a processing module configured to perform fuzzification processing on the target error information to determine a model parameter adjustment fuzzy matrix corresponding to the target error information;
an adjusting module configured to adjust a fuzzy matrix according to the model parameters, and adjust parameters of the dynamic model.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
10. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110839480.0A CN113642103B (en) | 2021-07-23 | 2021-07-23 | Method and device for adjusting parameters of dynamic model, medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110839480.0A CN113642103B (en) | 2021-07-23 | 2021-07-23 | Method and device for adjusting parameters of dynamic model, medium and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113642103A true CN113642103A (en) | 2021-11-12 |
CN113642103B CN113642103B (en) | 2022-08-02 |
Family
ID=78418222
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110839480.0A Active CN113642103B (en) | 2021-07-23 | 2021-07-23 | Method and device for adjusting parameters of dynamic model, medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113642103B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117648216A (en) * | 2024-01-30 | 2024-03-05 | 苏州元脑智能科技有限公司 | Method, device, server and medium for adjusting memory correctable error threshold |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106527129A (en) * | 2016-10-18 | 2017-03-22 | 长安大学 | Parallel robot indirect self-adaptive fuzzy control parameter determining method |
CN107037820A (en) * | 2016-12-13 | 2017-08-11 | 中国科学院沈阳自动化研究所 | The control method of aircraft in a kind of cabin |
US20180261082A1 (en) * | 2015-09-11 | 2018-09-13 | Hangzhou Hikvision Digital Technology Co., Ltd. | Method and device for processing traffic road information |
CN109709799A (en) * | 2018-12-29 | 2019-05-03 | 西安西驰电气股份有限公司 | A kind of PID Optimization Method of Fuzzy Control for power retractable volume |
CN111428382A (en) * | 2020-04-17 | 2020-07-17 | 福瑞泰克智能***有限公司 | Method, system, computer device and readable storage medium for vehicle trajectory control |
WO2021007985A1 (en) * | 2019-07-18 | 2021-01-21 | 深圳大学 | Particle filtering method and device based on tsk fuzzy model, and storage medium |
CN112733359A (en) * | 2021-01-05 | 2021-04-30 | 北京三快在线科技有限公司 | Kinetic model verification method, device, medium, electronic equipment and unmanned equipment |
-
2021
- 2021-07-23 CN CN202110839480.0A patent/CN113642103B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180261082A1 (en) * | 2015-09-11 | 2018-09-13 | Hangzhou Hikvision Digital Technology Co., Ltd. | Method and device for processing traffic road information |
CN106527129A (en) * | 2016-10-18 | 2017-03-22 | 长安大学 | Parallel robot indirect self-adaptive fuzzy control parameter determining method |
CN107037820A (en) * | 2016-12-13 | 2017-08-11 | 中国科学院沈阳自动化研究所 | The control method of aircraft in a kind of cabin |
CN109709799A (en) * | 2018-12-29 | 2019-05-03 | 西安西驰电气股份有限公司 | A kind of PID Optimization Method of Fuzzy Control for power retractable volume |
WO2021007985A1 (en) * | 2019-07-18 | 2021-01-21 | 深圳大学 | Particle filtering method and device based on tsk fuzzy model, and storage medium |
CN111428382A (en) * | 2020-04-17 | 2020-07-17 | 福瑞泰克智能***有限公司 | Method, system, computer device and readable storage medium for vehicle trajectory control |
CN112733359A (en) * | 2021-01-05 | 2021-04-30 | 北京三快在线科技有限公司 | Kinetic model verification method, device, medium, electronic equipment and unmanned equipment |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117648216A (en) * | 2024-01-30 | 2024-03-05 | 苏州元脑智能科技有限公司 | Method, device, server and medium for adjusting memory correctable error threshold |
CN117648216B (en) * | 2024-01-30 | 2024-04-23 | 苏州元脑智能科技有限公司 | Method, device, server and medium for adjusting memory correctable error threshold |
Also Published As
Publication number | Publication date |
---|---|
CN113642103B (en) | 2022-08-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sakhdari et al. | Adaptive tube-based nonlinear MPC for economic autonomous cruise control of plug-in hybrid electric vehicles | |
US10259468B2 (en) | Active vehicle performance tuning based on driver behavior | |
CN111931286B (en) | Training method, device and equipment for longitudinal dynamics model | |
US11242050B2 (en) | Reinforcement learning with scene decomposition for navigating complex environments | |
CN109799699B (en) | Automatic driving system control parameter processing method, device, equipment and storage medium | |
CN112947492B (en) | Vehicle control method and device, storage medium, electronic equipment and vehicle | |
Vegamoor et al. | String stability of connected vehicle platoons under lossy V2V communication | |
CN113642103B (en) | Method and device for adjusting parameters of dynamic model, medium and electronic equipment | |
CN112382165B (en) | Driving strategy generation method, device, medium, equipment and simulation system | |
CN113253612B (en) | Automatic driving control method, device, equipment and readable storage medium | |
CN112733359B (en) | Dynamics model verification method and device, medium, electronic equipment and unmanned equipment | |
CN111508253A (en) | Method for providing automatic driving service platform and server using the same | |
CN113625753B (en) | Method for guiding neural network to learn unmanned aerial vehicle maneuver flight by expert rules | |
CN109543225B (en) | Vehicle control scheme generation method and device, storage medium and electronic equipment | |
CN116461507A (en) | Vehicle driving decision method, device, equipment and storage medium | |
CN116795720A (en) | Unmanned driving system credibility evaluation method and device based on scene | |
CN113799772B (en) | Control method, device and control system of vehicle | |
US20220358316A1 (en) | Vehicle lidar system with neural network-based dual density point cloud generator | |
CN115047769A (en) | Unmanned combat platform obstacle avoidance-arrival control method based on constraint following | |
CN111634356A (en) | Self-balancing robot control method and system, self-balancing robot and medium | |
CN113596780B (en) | Vehicle interaction information generation method, device, equipment and computer readable medium | |
Matusi et al. | FPGA implementation of a interval type-2 fuzzy inference for quadrotor attitude control | |
CN113593241B (en) | Vehicle interaction information verification method and device, electronic equipment and readable medium | |
CN112289023B (en) | Parking simulation test method and device for automatic driving and related equipment | |
Rebling et al. | Development and testing of driver assistance systems with unity |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |