CN117970810B - Self-adaptive fault tolerance control method, system and electronic equipment - Google Patents
Self-adaptive fault tolerance control method, system and electronic equipment Download PDFInfo
- Publication number
- CN117970810B CN117970810B CN202410361924.8A CN202410361924A CN117970810B CN 117970810 B CN117970810 B CN 117970810B CN 202410361924 A CN202410361924 A CN 202410361924A CN 117970810 B CN117970810 B CN 117970810B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- model
- state
- adaptive
- control
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 230000008569 process Effects 0.000 claims abstract description 27
- 230000003044 adaptive effect Effects 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 13
- 238000005259 measurement Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 230000006399 behavior Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- MZWGYEJOZNRLQE-KXQOOQHDSA-N 1-stearoyl-2-myristoyl-sn-glycero-3-phosphocholine Chemical compound CCCCCCCCCCCCCCCCCC(=O)OC[C@H](COP([O-])(=O)OCC[N+](C)(C)C)OC(=O)CCCCCCCCCCCCC MZWGYEJOZNRLQE-KXQOOQHDSA-N 0.000 description 7
- 230000001133 acceleration Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention discloses a self-adaptive fault tolerance control method, a system and electronic equipment, and relates to the field of vehicle fault tolerance control, wherein the method comprises the steps of obtaining the state of a vehicle key component, and when a fault signal is detected according to the state of the vehicle key component, obtaining real-time data of a vehicle in the running process, and triggering the online update of a model; according to the real-time data, the GP-based model is updated online to obtain an online learning model; obtaining a self-adaptive model according to the online learning model and a nominal model of the vehicle; and controlling the vehicle to track the expected path to run after the failure based on the random model predictive control method according to the self-adaptive model. The invention can realize accurate track tracking and reliable fault-tolerant control.
Description
Technical Field
The present invention relates to the field of fault-tolerant control of vehicles, and in particular, to a method, a system, and an electronic device for adaptive fault-tolerant control.
Background
With the popularity of autopilot, ensuring the driving safety of fully autopilot vehicles is a complex challenge. It is counted that the number of safety accidents involving intelligent driving of test vehicles per year is quite large. With the increasing number of components and increasing complexity of the system, the probability of failure of an autonomous car increases significantly. In the event of a malfunction of an actuator or sensor, the stability of the autonomous car may be affected, resulting in deviation from a predetermined path, and even possibly causing serious traffic accidents. Therefore, research on the application of fault tolerant control in automatic driving automobiles to improve driving safety has become a urgent problem to be solved. However, in the prior art, the fault-tolerant control method only focuses on the problem of robust control, and does not consider the optimal path tracking control of the automatic driving automobile under various fault conditions.
Therefore, in order to ensure optimal path tracking control of an autopilot under various fault conditions, and further realize safe driving, it is highly desirable to provide an optimal adaptive fault-tolerant control method or system.
Disclosure of Invention
The invention aims to provide a self-adaptive fault tolerance control method, a self-adaptive fault tolerance control system and electronic equipment, which can realize accurate track tracking and reliable fault tolerance control.
In order to achieve the above object, the present invention provides the following solutions: an adaptive fault tolerance control method, comprising: acquiring the state of a vehicle key component, and acquiring real-time data of the vehicle in the running process when a fault signal is detected according to the state of the vehicle key component, and triggering the online update of a model; the vehicle key components include: a sensor and an actuator; the real-time data during driving includes: the vehicle state without failure, the vehicle state with failure, and the control command.
According to the real-time data, online updating is carried out on the basis of a Gaussian Process (GP) model, and an online learning model is obtained; and obtaining an adaptive model according to the online learning model and a nominal model of the vehicle.
According to the adaptive model, the vehicle is controlled to track a desired path to run after a fault based on a random model predictive control method (SMPC).
Optionally, when the automatically driven vehicle is not malfunctioning, the nonlinear state space equation of the actual running behavior of the vehicle is:。
Wherein, Is/>State quantity of time,/>For/>State quantity at time-1,/>Is/>The control quantity at the moment-1,Is/>Measurement of time of day,/>Is/>Process noise at time-1,/>Is/>Measurement noise of time,/>Is a measurement equation of the system,/>Is a nominal model of the vehicle.
Optionally, the adaptive model is:；
Wherein, Is based on GP model,/>Is an adaptive model obtained by combining a nominal model and a GP-based learned model, and is a matrix/>Is a member of/>The coefficient matrix to be determined is a matrix of coefficients,，/>Is to data set/>Unmodeled function obtained after training,/>Is system noise,/>And selected state quantity/>And control amount/>Related,/>AndAre all matrices.
Optionally, the data setBy input/>And output/>Composition is prepared.
。
Wherein,And/>Respectively represent/>Time of day and/>Vehicle state quantity under failure at time-1,/>Representative/>Vehicle state without failure at time,/>For/>-Control quantity at time 1, which is a control command, represents a training data pair.
Optionally, the method for controlling the vehicle to track the expected path to run based on the random model prediction control method SMPC after the fault occurs according to the adaptive model specifically includes: cost function:。
constraint conditions: 。
。
。
。
。
。
。
=/>。
Wherein, Is the average value of the state quantity of the vehicle at the moment k,/>To predict the FOV,/>As a weighting matrix,/>AndIs the minimum value and the maximum value of the state quantity at the moment k,/>And/>Is the minimum value and the maximum value of the control quantity at the moment k,/>And/>Boundary probabilities,/>, respectivelyFor the reference state quantity of the vehicle at time k,/>And/>Weights corresponding to the state quantity and the control quantity respectively,/>For the control variable change at time k/(And/>Respectively, the minimum value and the maximum value of the control quantity change at the moment k,/>To control the volume constraint,/>For state quantity constraint,/>For the reference state quantity of the final moment,/>As the state quantity at the final time,/>For the state quantity of the system at the k moment,/>Representation ofObeying the mean value to be/>Variance is/>Is of the normal distribution,/>() Representing probability,/>Is the state quantity at the initial time.
An adaptive fault tolerant control system comprising: the triggering module is used for acquiring the state of the vehicle key component, acquiring real-time data of the vehicle in the running process when detecting a fault signal according to the state of the vehicle key component, and triggering the online updating of the model; the vehicle key components include: a sensor and an actuator; the real-time data during driving includes: the vehicle state without failure, the vehicle state with failure, and the control command.
The self-adaptive model determining module is used for carrying out online updating on the basis of the GP model according to the real-time data to obtain an online learning model; and obtaining an adaptive model according to the online learning model and a nominal model of the vehicle.
And the path tracking control module is used for controlling the vehicle to track the expected path to run after the fault based on the SMPC according to the self-adaptive model.
An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform the one adaptive fault tolerance control method.
Optionally, the memory is a computer readable storage medium.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: according to the self-adaptive fault tolerance control method, the self-adaptive fault tolerance control system and the electronic equipment, the GP-based model online learning can be flexibly adapted to a complex and changeable system through the non-parameter modeling and online learning capacity of a Gaussian process, and the prediction performance is dynamically and continuously improved through a real-time learning system. The uncertainty estimation capability enables the controller to be adaptively adjusted when facing system faults or anomalies, selects optimal control quantity at each time step, adapts to dynamic changes of the system, improves the robustness and reliability of the control system, and accordingly better meets control requirements of actual complex systems. For the problem of path tracking of an autonomous vehicle in the event of a position failure, the SMPC is used for controlling the path tracking problem. The SMPC uses the probability constraints of the state quantity and the control variable to effectively process the uncertainty of the system, including faults and noise, thereby improving the robustness of the controller. The adaptive control characteristic enables the system to adjust the control strategy in real time to adapt to dynamic environment and system change, and compared with the traditional method, the method can achieve accurate track tracking and reliable fault-tolerant control.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a self-adaptive fault tolerance control method provided by the invention.
Fig. 2 is a schematic diagram of an overall control process of a self-adaptive fault tolerance control method according to the present invention.
Fig. 3 is a schematic diagram of a GP-based model online learning process.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a self-adaptive fault tolerance control method, a self-adaptive fault tolerance control system and electronic equipment, which can realize accurate track tracking and reliable fault tolerance control.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
As shown in fig. 1 and fig. 2, the adaptive fault tolerance control method provided by the present invention includes S101 to S103.
S101, acquiring the state of a vehicle key component, acquiring real-time data of the vehicle in the running process when a fault signal is detected according to the state of the vehicle key component, and triggering the online update of the model. The vehicle key components include: a sensor and an actuator. The real-time data during driving includes: the vehicle state without failure, the vehicle state with failure, and the control command.
The in-vehicle detection module is responsible for checking the status of sensors, actuators, or other critical components. If the detection module detects an anomaly, such as a sensor failure, an actuator failure, or a system performance degradation, the system will recognize that a fault may exist.
Once a fault is found, the detection module generates an exception report and sends a fault signal to the control system. The control system will start the online learning module after receiving the fault signal. Notably, the online learning module functions to improve the adaptivity of the system dynamics model through learning and adaptation processes.
After the online learning module begins to operate, it will acquire real-time data generated by the autonomous vehicle during its travel, which may include sensor data, environmental information, and various status information within the vehicle. These data will be the training data pairs for the online learning process.
The key of the whole process is timely response of the online learning module and effective acquisition of real-time data after the vehicle encounters a fault.
S102, online updating is carried out on the model based on GP according to real-time data, and an online learning model is obtained; and obtaining an adaptive model according to the online learning model and a nominal model of the vehicle.
When the automatically driven vehicle is not malfunctioning, the nonlinear state space equation of the actual running behavior of the vehicle can be expressed as follows.
（1）。
Wherein,Is/>State quantity of time,/>For/>State quantity at time-1,/>Is/>The control quantity at the moment-1,Is/>Measurement of time of day,/>Is/>Process noise at time-1,/>Is/>Measurement noise of time,/>Is a measurement equation of the system,/>Is a nominal model of the vehicle to approximate the actual dynamic behavior of the vehicle.
The nominal model of the vehicle can be described by the following formula.
（2）。
（3）。
（4）。
Wherein,，/>，/>Longitudinal position, lateral position and heading angle of the vehicle, respectively; /(I)Represents independent acceleration in the longitudinal direction and is influenced by various forces; /(I)Is the longitudinal speed; /(I)And/>Representing the rigidity of the front and rear wheels, respectively; m is the mass of the whole vehicle; /(I)And/>Respectively representing the distances from the front and rear axles to the Center of Gravity (CG) of the vehicle; /(I)Represents the front wheel rotation angle; /(I)Is yaw moment of inertia; /(I)Is the longitudinal acceleration; /(I)Is course angular velocity,/>Is course angular acceleration; /(I)For transverse velocity,/>Is the lateral acceleration.
The following error model is defined to better achieve tracking of the autonomous vehicle.
（5）。
（6）。
（7）。
（8）。
（9）。
（10）。
Wherein,And/>Respectively a lateral error and a heading error,/>And/>Representing the respective corresponding rates of change; /(I)And/>Longitudinal distance error and longitudinal velocity error with respect to the reference trajectory, respectively; /(I)、/>And/>Representing a reference yaw angle, a reference speed and a reference acceleration, respectively. The state quantity of the system is/>，Is the control quantity of the system, the superscript T is the transposition, and the parameter/>=/>。
When an autonomous vehicle fails, there is a large deviation of the actual dynamic behavior of the vehicle from normal. In this case, accurate motion control would not be possible if the controller continued to use the nominal model. To capture the difference between the nominal model and the actual state of the vehicle under fault, a GP-based approach is used to learn this difference online. The GP based model online learning system is shown in fig. 3.
GP is a non-parameterized machine learning method for modeling the relationship between input and output. It predicts by learning the probability distribution of the training data and provides an estimate of the uncertainty. In online learning, the application GP can flexibly update the model to accommodate new failure scenarios. By continuously acquiring new data and incorporating it into the training process of the model, the gaussian process can dynamically adjust the parameters and structure of the model for online updating of the system dynamics model.
The dynamics of the vehicle under fault are approximated by a combination of nominal model and GP-based learning model components, described by the following equation.
（11）。
Wherein,Is a nominal model of the vehicle,/>Is based on GP model,/>Is an adaptive model obtained by combining a nominal model and a GP-based model, and is a matrix/>Is a model/>, which is learned by onlineAnd (5) a coefficient matrix determined. /(I)Can be described by the following formula: /(I)（12）。
Wherein the method comprises the steps ofIs to data set/>Unmodeled function obtained after training,/>Is the noise of the system, which is the noise of the system,And selected state quantity/>And control amount/>In relation, by introducing matrix/>AndTo reduce the dimension of training. Training data set/>By input/>And output/>The composition is as follows:（13）。
Wherein, And/>Respectively represent/>Time of day and/>Vehicle state quantity under failure at time-1,/>Representative/>Vehicle state without failure at time,/>For/>-Control quantity at time 1, which is a control command, represents a training data pair.
Matrix-basedThe inputs contained in (1) propose an a priori GP model, which can be defined by the following equation:（14）。
Wherein the method comprises the steps of Is GP model,/>Representing a Gaussian process,/>For another input variable, it is usually used to calculate covariance matrix, mean/>, of GP modelSum covariance matrix/>Can be described by the following formula: /(I)（15）。
（16）。
Wherein,() Is the expected value.
At a given data point [ ],/>) The posterior distribution of the unknown function is mean/>Variance is/>Specifically, formula (17) and formula (18).
（17）。
（18）。
Using zero-mean functionAnd a square index kernel (SE) to determine covariance function/>. The expression that results in the covariance function can be described as formula (19) by the following formula.
（19）。
Wherein the method comprises the steps ofRepresenting the output variance,/>= diag（/>）/>Is a length scale covariance diagonal matrix,/>Is a unitary matrix,/>=/>，/>Is the noise of the gaussian process model.
By using training data setsTraining the GP model by applying formulas (12) - (19) to obtain/>. This enables the dynamics model of the vehicle to be updated online by equation (11). The updated vehicle dynamics model more accurately reflects vehicle dynamics under the fault, thereby being used for an optimal control process to better realize control and adjustment of the automatic driving vehicle.
S103, controlling the vehicle to track the expected path to run after the failure based on the random model prediction control method according to the self-adaptive model.
To ensure that the vehicle can travel according to a baseline on the road, the cost function may be defined as:（20）。
Wherein the method comprises the steps of For the reference state, related information from the reference track,/>And/>The weights corresponding to the states and inputs, respectively.
In path tracking, the vehicle should follow the reference path as much as possible, and the distance between the vehicle and the reference path should be constrained. While also taking into account the longitudinal and transverse movements of the vehicle. Further, the range of the control amount is also limited due to the limitation of steering and acceleration. In addition, to avoid overly aggressive driving behavior, the speed of acceleration and steering should also be limited. Thus, constraints on states and inputs, and constraints on input rates, can be described by the formula:（21）。
（22）。
（23）。
Due to state quantity Including uncertainties caused by potential variations in severity of the fault at different times and environmental conditions, inequality constraints need to be introduced to account for the likelihood of faults during automatic driving path tracking. These inequality constraints include information related to the state quantity and the control quantity. Constraint on state using opportunistic constraint formulas/>And input constraints/>Modeling was performed as follows: /(I)（24）。
（25）。
Wherein,And/>Is the boundary probability.
The probability constraints in equations (24) and (25) after being converted to linear constraints can be described by the following equation:（26）。
（27）。
Wherein the symbols are Quantile function/>, representing a standard normal distributionWhile kernel function/>Average value/>The parameters representing the gaussian distribution.
In summary, the optimal adaptive control for vehicle path tracking under a SMPC control failure can be described by the following formula:（28）。
s. t.（29）。
（30）。
（31）。
（32）。
（33）。
（34）。
（35）。
=/>（36）。
Wherein, Is the average value of the state quantity of the vehicle at the moment k,/>To predict the FOV,/>For the weighting matrix, the first control quantity in the control sequence obtained by the optimization solution is applied to the vehicle motion control, so that the vehicle can accurately track the path even if the vehicle has a fault. /(I)And/>Respectively, minimum value and maximum value of state quantity at k time,/>AndRespectively, minimum value and maximum value of control quantity at k time,/>For the reference state quantity of the vehicle at time k,/>For the control variable change at time k/(And/>Respectively, the minimum value and the maximum value of the control quantity change at the moment k,/>To control the volume constraint,/>For state quantity constraint,/>For the reference state quantity of the final moment,/>As the state quantity at the final time,/>The state quantity of the system at the moment k; /(I)Representation/>Obeying the mean value to be/>Variance is/>Is a positive too much distribution; /(I)() Representing probability,/>Is the state quantity at the initial time.
Corresponding to the method, the invention also provides a self-adaptive fault tolerance control system, which comprises the following steps: the triggering module is used for acquiring the state of the vehicle key component, acquiring real-time data of the vehicle in the running process when detecting a fault signal according to the state of the vehicle key component, and triggering the online learning of the model; the vehicle key components include: a sensor and an actuator; the real-time data during driving includes: the vehicle state without failure, the vehicle state with failure, and the control command.
The self-adaptive model determining module is used for carrying out online updating on the basis of the GP model according to the real-time data to obtain an online learning model; and obtaining an adaptive model according to the online learning model and a nominal model of the vehicle.
And the path tracking control module is used for controlling the vehicle to track the expected path to run after the fault based on the SMPC according to the self-adaptive model.
In order to execute the method corresponding to the embodiment to realize the corresponding functions and technical effects, the invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic equipment to execute the adaptive fault tolerance control method.
The memory is a computer-readable storage medium.
Based on the above description, the technical solution of the present invention may be embodied in essence or a part contributing to the prior art or a part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned computer storage medium includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (4)
1. An adaptive fault tolerance control method, comprising:
Acquiring the state of a vehicle key component, and acquiring real-time data of the vehicle in the running process when a fault signal is detected according to the state of the vehicle key component, and triggering the online update of a model; the vehicle key components include: a sensor and an actuator; the real-time data during driving includes: the vehicle state under no fault, the vehicle state under fault and the control instruction;
According to the real-time data, online updating is carried out on the model based on the Gaussian process, and an online learning model is obtained; obtaining a self-adaptive model according to the online learning model and a nominal model of the vehicle;
according to the self-adaptive model, controlling the vehicle to track the expected path to run after the vehicle fails based on a random model prediction control method;
When the automatically driven vehicle does not fail, the nonlinear state space equation of the actual running behavior of the vehicle is:
Wherein χ k is the state quantity at time k, χ k-1 is the state quantity at time k-1, u k-1 is the control quantity at time k-1, Γ k is the measurement value at time k, ω k-1 is the process noise at time k-1, v k is the measurement noise at time k, h is the measurement equation of the system, and f nom is the nominal model of the vehicle;
The self-adaptive model is as follows:
Wherein, Is a model based on a Gaussian process, and f ada is an adaptive model obtained by combining a nominal model and a learned model based on the Gaussian process, and is a matrix/>Is a member of/>The coefficient matrix to be determined is a matrix of coefficients, Is an unmodeled function obtained after training the dataset E, ω GP is the system noise,/>Related to the selected state quantity χ k and the control quantity u k,/>AndAre all matrixes;
the data set E consists of an input G and an output Y;
Wherein, And/>Representing the vehicle state quantity under the faults at the moment k and the moment k-1 respectively,/>Representing the state of the vehicle without faults at the moment k; u k-1 is the control quantity at time k-1 and is a control instruction; representing training data pairs;
the method for controlling the vehicle to track the expected path to run after the failure based on the random model prediction control method according to the self-adaptive model specifically comprises the following steps:
Cost function:
constraint conditions:
Wherein, Is the average value of the state quantity of the vehicle at the moment k, N is the prediction vision, P is the weighting matrix,/>And/>Respectively, minimum value and maximum value of state quantity at k time,/>And/>Respectively, minimum value and maximum value of control quantity at k time,/>And/>Boundary probabilities,/>, respectivelyFor the reference state quantity of the vehicle at the moment k, Q and R are weights corresponding to the state quantity and the control quantity respectively, deltau k is the control quantity change at the moment k, and/ >And/>Respectively, the minimum value and the maximum value of the control quantity change at the moment k,/>To control the volume constraint,/>For state quantity constraint,/>For the reference state quantity of the final moment,/>As the state quantity at the final time,/>The state quantity of the system at the moment k; /(I)Meaning χ k obeys the mean value/>Variance is/>Is a positive too much distribution; pr () represents probability,/>Is the state quantity at the initial time.
2. An adaptive fault-tolerant control system for implementing an adaptive fault-tolerant control method according to claim 1, characterized in that the control system comprises:
The triggering module is used for acquiring the state of the vehicle key component, acquiring real-time data of the vehicle in the running process when detecting a fault signal according to the state of the vehicle key component, and triggering the online updating of the model; the vehicle key components include: a sensor and an actuator; the real-time data during driving includes: the vehicle state under no fault, the vehicle state under fault and the control instruction;
The self-adaptive model determining module is used for carrying out online updating on the basis of the Gaussian process model according to the real-time data to obtain an online learning model; obtaining a self-adaptive model according to the online learning model and a nominal model of the vehicle;
And the path tracking control module is used for controlling the vehicle to track the expected path to run after the failure based on the random model prediction control method according to the self-adaptive model.
3. An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform an adaptive fault tolerance control method according to claim 1.
4. An electronic device as claimed in claim 3, characterized in that the memory is a computer readable storage medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410361924.8A CN117970810B (en) | 2024-03-28 | 2024-03-28 | Self-adaptive fault tolerance control method, system and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410361924.8A CN117970810B (en) | 2024-03-28 | 2024-03-28 | Self-adaptive fault tolerance control method, system and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117970810A CN117970810A (en) | 2024-05-03 |
| CN117970810B true CN117970810B (en) | 2024-06-21 |
Family
ID=90862894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410361924.8A Active CN117970810B (en) | 2024-03-28 | 2024-03-28 | Self-adaptive fault tolerance control method, system and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117970810B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111007722A (en) * | 2019-12-18 | 2020-04-14 | 厦门大学 | Transverse robust fault-tolerant control system and method for four-wheel steering automatic driving automobile |
| CN117360544A (en) * | 2023-11-14 | 2024-01-09 | 海南大学 | DRL-MPC-based automatic driving vehicle transverse control method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112904838B (en) * | 2021-01-06 | 2021-11-26 | 北京科技大学 | Two-dimensional plane intelligent vehicle queue control method |
| CN114348026B (en) * | 2022-01-30 | 2023-11-28 | 中国第一汽车股份有限公司 | Vehicle control method, device, equipment and storage medium |
-
2024
- 2024-03-28 CN CN202410361924.8A patent/CN117970810B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111007722A (en) * | 2019-12-18 | 2020-04-14 | 厦门大学 | Transverse robust fault-tolerant control system and method for four-wheel steering automatic driving automobile |
| CN117360544A (en) * | 2023-11-14 | 2024-01-09 | 海南大学 | DRL-MPC-based automatic driving vehicle transverse control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117970810A (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107862346B (en) | Method and equipment for training driving strategy model | |
| CN111775949B (en) | Personalized driver steering behavior auxiliary method of man-machine co-driving control system | |
| CN113120001A (en) | Transverse control method and device for automatic driving vehicle and vehicle | |
| KR102024986B1 (en) | Apparatus and method for lane Keeping control | |
| CN116108717B (en) | Traffic transportation equipment operation prediction method and device based on digital twin | |
| US20090105900A1 (en) | Reconfigurable Structure Method of Estimating Vehicle Lateral Velocity | |
| US11827293B2 (en) | Real-time estimation of achievable angle, velocity, and acceleration capabilities of steering actuator | |
| EP3751465A1 (en) | Methods, apparatuses and computer programs for generating a reinforcement learning-based machine-learning model and for generating a control signal for operating a vehicle | |
| Blume et al. | Neural roll angle estimation in a model predictive control system | |
| Sieberg et al. | Hybrid state estimation–a contribution towards reliability enhancement of artificial neural network estimators | |
| JP4069481B2 (en) | Vehicle behavior estimation device | |
| CN117389276B (en) | Unmanned vehicle driving path tracking control method based on driving risk prediction | |
| Lee et al. | Adaptive fault detection and emergency control of autonomous vehicles for fail-safe systems using a sliding mode approach | |
| Satouri et al. | Trajectory tracking of an autonomous vehicle using immersion and invariance control | |
| US10235818B2 (en) | Adaptive vehicle control | |
| US11679759B2 (en) | System and method for adaptive control of vehicle dynamics | |
| CN117970810B (en) | Self-adaptive fault tolerance control method, system and electronic equipment | |
| CN117584996A (en) | New energy automobile control method | |
| US20230001940A1 (en) | Method and Device for Optimum Parameterization of a Driving Dynamics Control System for Vehicles | |
| KR101930163B1 (en) | Apparatus and method for lane Keeping control | |
| Lüdemann | Heterogeneous and hybrid control with application in automotive systems | |
| Das | Vehicle Dynamics Modelling: Lateral and Longitudinal | |
| CN110789521A (en) | Wheel collision detection | |
| CN115284809B (en) | Intelligent internet fleet active suspension control method and system and computer equipment | |
| Yamauchi et al. | Adaptive identification method of vehicle modeling according to the fluctuation of road and running situation in autonomous driving |
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 |