CN115755683A - Vehicle state control method and system - Google Patents
Vehicle state control method and system Download PDFInfo
- Publication number
- CN115755683A CN115755683A CN202211392759.XA CN202211392759A CN115755683A CN 115755683 A CN115755683 A CN 115755683A CN 202211392759 A CN202211392759 A CN 202211392759A CN 115755683 A CN115755683 A CN 115755683A
- Authority
- CN
- China
- Prior art keywords
- information
- monitoring
- module
- prediction
- 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.)
- Pending
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The embodiment of the application discloses a vehicle state control method and a system, wherein the method comprises the following steps: monitoring bus data to obtain third monitoring information and fourth monitoring information, wherein the time corresponding to the fourth monitoring information is the next time of the time corresponding to the third monitoring information; acquiring a reference motion state, wherein the reference motion state is a motion state of the vehicle at a moment corresponding to the fourth monitoring information; determining a target monitoring difference value according to the third monitoring information and the fourth monitoring information; inputting map environment information into a map information processing module to obtain the output of the map information processing module; inputting the output of the map information processing module, the target monitoring difference value and the reference motion state into a control prediction first module to obtain a target prediction control action; and controlling the vehicle according to the target prediction control action. The method and the device can independently perform full-automatic vehicle control and judge whether the vehicle control is in place or not under the condition of no need of human intervention.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a vehicle state control method and system.
Background
With the development of computer technology and electric control vehicle technology, people can be served for more intelligent vehicle control, unmanned automatic control is also the main development direction of intelligent vehicle driving, but the automatic control capability of the current related technology is insufficient, end-to-end full-automatic control without manual intervention cannot be realized, and an effective evaluation method is also lacked for the control effect of the full-automatic control.
Disclosure of Invention
In order to solve at least one technical problem, embodiments of the present application provide a vehicle state control method and system.
In one aspect, an embodiment of the present application provides a method for training a vehicle state model, where the vehicle state model includes a monitoring data processing module, a map information processing module, a control information input module, a control prediction first module, an operation prediction second module, a first evaluator group, and a second evaluator group, the monitoring data processing module is connected to the control information input module, the monitoring data processing module and the map information processing module are connected to the control prediction first module, the monitoring data processing module and the map information processing module are connected to the control prediction second module, the control prediction first module is connected to the first evaluator group, the control prediction second module is connected to the second evaluator group, and the first evaluator group and the second evaluator group respectively include at least two evaluators, where the method includes:
acquiring training information, wherein the training information comprises a sample control action, map environment information, first monitoring information, second monitoring information, a first motion state and a second motion state, the first monitoring information is bus data monitored before the sample control action is implemented, the second monitoring information is bus data monitored after the sample control action is implemented, the first motion state is a motion state of a vehicle when the sample control action is implemented, and the second motion state is a motion state of the vehicle at the next moment corresponding to the first motion state;
inputting the sample manipulation action into the manipulation information input module;
inputting the map environment information into the map information processing module;
inputting the output of the control information input module, the first monitoring information and the second monitoring information into the monitoring data processing module;
inputting the output of the map information processing module, the output of the monitoring data processing module and the first motion state into the control prediction first module to obtain a first control prediction result;
inputting the output of the map information processing module and the second motion state into the control prediction second module to obtain a second control prediction result;
adjusting a parameter of a correlation module based on the first and second maneuver predictors.
In another aspect, an embodiment of the present application provides a vehicle state control method, including:
monitoring bus data to obtain third monitoring information and fourth monitoring information, wherein the time corresponding to the fourth monitoring information is the next time of the time corresponding to the third monitoring information;
acquiring a reference motion state, wherein the reference motion state is the motion state of the vehicle at the moment corresponding to the fourth monitoring information;
determining a target monitoring difference value according to the third monitoring information and the fourth monitoring information;
inputting map environment information into a map information processing module to obtain the output of the map information processing module;
inputting the output of the map information processing module, the target monitoring difference value and the reference motion state into a first control prediction module to obtain a target prediction control action;
controlling the vehicle according to the target predicted control action;
the map information processing module and the control prediction first module both belong to a vehicle state model, and the vehicle state model is obtained by training through the method.
On the other hand, an embodiment of the present application provides a vehicle state model training apparatus, the vehicle state model includes a monitoring data processing module, a map information processing module, a control information input module, a control prediction first module, an operation prediction second module, a first evaluator group, and a second evaluator group, the monitoring data processing module is connected to the control information input module, the monitoring data processing module and the map information processing module are connected to the control prediction first module, the monitoring data processing module and the map information processing module are connected to the control prediction second module, the control prediction first module is connected to the first evaluator group, the control prediction second module is connected to the second evaluator group, and the first evaluator group and the second evaluator group respectively include at least two evaluators, the apparatus includes:
the training information acquisition module is used for acquiring training information, wherein the training information comprises a sample control action, map environment information, first monitoring information, second monitoring information, a first motion state and a second motion state, the first monitoring information is bus data monitored before the sample control action is implemented, the second monitoring information is bus data monitored after the sample control action is implemented, the first motion state is a motion state of a vehicle when the sample control action is implemented, and the second motion state is a motion state of the vehicle at the next moment corresponding to the first motion state;
the data processing module is used for inputting the sample manipulation action into the manipulation information input module; inputting the map environment information into the map information processing module; inputting the output of the control information input module, the first monitoring information and the second monitoring information into the monitoring data processing module; inputting the output of the map information processing module, the output of the monitoring data processing module and the first motion state into the control prediction first module to obtain a first control prediction result; inputting the output of the map information processing module and the second motion state into the control prediction second module to obtain a second control prediction result;
and the parameter adjusting module is used for adjusting parameters of the related module based on the first manipulation prediction result and the second manipulation prediction result.
In another aspect, an embodiment of the present application provides a vehicle state control system, including:
the monitoring module is used for monitoring bus data to obtain third monitoring information and fourth monitoring information, wherein the moment corresponding to the fourth monitoring information is the next moment of the moment corresponding to the third monitoring information;
a reference motion state obtaining module, configured to obtain a reference motion state, where the reference motion state is a motion state of the vehicle at a time corresponding to the fourth monitoring information;
a monitoring difference value obtaining module, configured to determine a target monitoring difference value according to the third monitoring information and the fourth monitoring information;
the environment map processing module is used for inputting map environment information into the map information processing module to obtain the output of the map information processing module;
the control information prediction module is used for inputting the output of the map information processing module, the target monitoring difference value and the reference motion state into the control prediction first module to obtain a target prediction control action;
the control module is used for controlling the vehicle according to the target prediction control action;
the map information processing module and the control prediction first module both belong to a vehicle state model, and the vehicle state model is obtained by training through the method.
The embodiment of the application provides a vehicle state control method and a vehicle state control system, firstly, a vehicle state model is trained, the vehicle state model mainly has two functions, one function is that the module for predicting the operation and control information has the capability of independently predicting the operation and control action by arranging two modules for predicting the operation and control information and respective evaluator groups and adjusting parameters of the modules for predicting the operation and control information and the respective evaluator groups, and the operation and control action is information required for vehicle control. The other is that the vehicle state model can also finally obtain monitoring difference data corresponding to each single control action, the monitoring difference data represents the inevitable difference of data on the bus before and after each control action, and whether the combination of the single control action and the control action is executed in place can be known by actually monitoring the change of the data in the bus and comparing the monitoring difference data corresponding to each single control action, so that the self-evaluation effect is achieved, namely, whether the vehicle control is in place can be independently evaluated by the embodiment of the application, and human intervention is still not needed. In conclusion, the embodiment of the application can independently perform full-automatic vehicle control and judge whether the vehicle control is in place or not under the condition that human intervention is not needed.
Furthermore, the embodiment of the application needs to use the map information, the information monitored in the bus and the motion state of the vehicle for predicting the control information, that is, the available information is effectively utilized, so that the predicted control action is accurate and reasonable, the correct control decision is made, and the decision correctness enables the implementation effect of the application not to be inferior to the vehicle control implementation effect under manual intervention.
Drawings
In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the related art, the drawings used in the description of the embodiments or the related art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without inventive efforts.
FIG. 1 is a schematic diagram of a vehicle state model provided by an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a training method provided in an embodiment of the present application;
fig. 3 is a schematic flowchart of a vehicle state control method according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some, not all, of the embodiments of the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without any creative effort belong to the protection scope of the embodiments in the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the embodiments of the present application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or otherwise described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In order to make the objects, technical solutions and advantages disclosed in the embodiments of the present application more clearly understood, the embodiments of the present application are described in further detail below with reference to the accompanying drawings and the embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the embodiments of the application and are not intended to limit the embodiments of the application.
In the following, the terms "first", "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present embodiment, the meaning of "a plurality" is two or more unless otherwise specified.
An embodiment of the present application provides a vehicle state model training method, please refer to fig. 1, where the vehicle state model includes a monitoring data processing module, a map information processing module, a control information input module, a control prediction first module, an operation prediction second module, a first evaluator group, and a second evaluator group, the monitoring data processing module is connected to the control information input module, the monitoring data processing module and the map information processing module are both connected to the control prediction first module, the monitoring data processing module and the map information processing module are both connected to the control prediction second module, the control prediction first module is connected to the first evaluator group, the control prediction second module is connected to the second evaluator group, and the first evaluator group and the second evaluator group respectively include at least two evaluators.
Referring to fig. 2, the method includes:
s101, training information is obtained, wherein the training information comprises a sample control action, map environment information, first monitoring information, second monitoring information, a first motion state and a second motion state, the first monitoring information is bus data monitored before the sample control action is implemented, the second monitoring information is bus data monitored after the sample control action is implemented, the first motion state is a motion state of a vehicle when the sample control action is implemented, and the second motion state is a motion state of the vehicle at the next moment corresponding to the first motion state.
The present application is not limited to the sample manipulation motion, and it may be a single control motion or a combination thereof for the vehicle, such as turning left and decelerating, turning right and decelerating, moving straight and accelerating, etc. The map environment information is high-precision map information of a road section where the vehicle runs.
And S102, inputting the sample control action into the control information input module.
Specifically, the sample manipulation action may be extracted based on the manipulation information input module to obtain a corresponding output, specifically, the sample manipulation action is extracted as information that can be processed by other related modules.
And S103, inputting the map environment information into the map information processing module.
Specifically, vectorization processing may be performed on the map environment information based on the map information processing module to obtain a corresponding output. Vectorization processing is not described in detail in the embodiments of the present application, and reference may be made to the prior art.
And S104, inputting the output of the control information input module, the first monitoring information and the second monitoring information into the monitoring data processing module.
And determining monitoring difference information based on the difference between the first monitoring information and the second monitoring information, wherein the information can be used as the output of the monitoring data processing module.
Meanwhile, the monitoring data processing module can also obtain mapping information according to the output of the control information input module and the monitoring difference information, and the mapping information represents the corresponding relation between the sample operation action and the monitoring difference information. For example, the snoop difference information indicates that 1, 3, 5, 8, and 9 bits of the bus data have respectively generated corresponding changes, which are likely to be related to the sample operation, thereby constructing the mapping information.
Of course, there may be cases where individual changes are not related to the sample manipulation action, for example, only 1, 3, 5 are related to the sample manipulation action, that is, as long as the sample manipulation action is performed, 1, 3, 5 necessarily produce corresponding changes. And 8-bit and 9-bit variations are also present in the mapping information, i.e. the mapping information is noisy, which can be excluded by performing autocorrelation analysis on a large amount of mapping information. The embodiment of the present application uses the listening difference information including noise as an output of the listening data processing module, and this noise should be regarded as "noise" only because it is not related to the sample manipulation motion, but this noise also reflects the state of the vehicle and is effective data for performing the prediction of the maneuver information, and therefore, is also output by the listening data processing module.
And S105, inputting the output of the map information processing module, the output of the monitoring data processing module and the first motion state into the control prediction first module to obtain a first control prediction result.
The structure of the first control and prediction module is not limited, and a first control and prediction result can be output only based on the output of the map information processing module, the output of the monitoring data processing module and the first motion state, and a mainstream neural network with prediction capability can be selected, so that the structure is not limited. It should be noted that, the specific structure of each single module in the embodiments of the present application may refer to the prior art, but the vehicle state model formed by the organic combination of the modules and the training method for the vehicle state model are original designs of the present application.
The first manipulation prediction result is a single manipulation action or a combination thereof.
And S106, inputting the output of the map information processing module and the second motion state into the control prediction second module to obtain a second control prediction result.
And S107, adjusting parameters of the relevant modules based on the first control prediction result and the second control prediction result.
Specifically, the second maneuver prediction result may be input to each evaluator of the second evaluator group, and first evaluation prediction information output by each evaluator according to a preset noise signal is obtained, where the first evaluation prediction information represents an expected reward value under the assumption that the second maneuver prediction result is continuously executed for a preset time. The embodiment of the present application does not limit the specific structure of each evaluator used, and the evaluator can be obtained by a modeling method using a correlation technique. Therefore, the method has the capability of outputting the reward expectation value, the specific steps of using the reward expectation value for parameter adjustment and performing model parameter adjustment based on the reward expectation value are highlighted, and the modeling process of the evaluator is not repeated.
And determining the reward prediction target based on the product of the minimum value in each piece of the first evaluation prediction information and a preset attenuation coefficient. In some embodiments, the reward prediction target may be obtained by adding a reward preset coefficient to a product of the minimum value in each of the first evaluation prediction information and a preset attenuation coefficient, but both the attenuation coefficient and the reward preset coefficient may be set according to actual conditions.
And inputting the first control prediction result into each evaluator in the first evaluator group to obtain second evaluation prediction information output by each evaluator according to a preset noise signal. The second evaluation prediction information and the first evaluation prediction information are based on the same inventive concept, and are not described in detail herein.
An evaluation prediction target is obtained based on a weighted square sum of the second evaluation prediction information. The weight may be set according to circumstances, and in some scenarios, may be set to 1, that is, the sum of squares of each of the above-mentioned second evaluation prediction information is directly used as an evaluation prediction target.
Updating parameters of the first module of maneuver prediction and the first set of evaluators based on a difference between the reward prediction objective and the evaluation prediction objective.
Specifically, the parameters of the first evaluator group are adjusted in a gradient descending manner; and adjusting the parameters of the first module predicted by the control in a gradient ascending mode. And updating the parameters of the maneuver predicting second module based on the parameters of the maneuver predicting first module; and updating the parameters of the second evaluator group based on the parameters of the first evaluator group. Updating one module based on another module may also be considered as parameter update passing, which is not limited herein and may refer to the prior art. Of course, the parameters of other modules not mentioned need not be adjusted.
In the process of training the model, a large amount of mapping information can be generated, autocorrelation analysis is carried out on all the mapping information to obtain a target mapping record table, and each record in the target mapping record table represents the corresponding relation between a single control action and the change bit of the corresponding monitoring data. For example, the acceleration operation corresponds to the 1 st and 4 th bit changes in the bus data, and the steering operation corresponds to the 14 th and 63 th bit changes.
An embodiment of the present application further provides a vehicle state control method, as shown in fig. 3, where the method includes:
s201, monitoring bus data to obtain third monitoring information and fourth monitoring information, wherein the time corresponding to the fourth monitoring information is the next time of the time corresponding to the third monitoring information.
The time corresponding to the third monitoring information may be any time when the vehicle state control method is put into use.
And S202, acquiring a reference motion state, wherein the reference motion state is the motion state of the vehicle at the moment corresponding to the fourth monitoring information.
And S203, determining a target monitoring difference value according to the third monitoring information and the fourth monitoring information.
Specifically, the target listening difference value refers to a difference value between the third listening information and the fourth listening information.
And S204, inputting the map environment information into a map information processing module to obtain the output of the map information processing module.
Please refer to the above description for the operation of this step.
And S205, inputting the output of the map information processing module, the target monitoring difference value and the reference motion state into a first control and prediction module to obtain a target prediction control action.
And S206, controlling the vehicle according to the target prediction control action. The modules used in the vehicle state control method belong to vehicle state models, and the vehicle state models are obtained by training through the method.
Obviously, the vehicle control method can fully automatically influence the vehicle state without manual intervention. In addition, the target prediction control action can be input into a monitoring data processing module in the vehicle state model to obtain target monitoring difference data; acquiring actually measured monitoring difference data based on monitoring data before the target prediction control action is executed and monitoring data after the target prediction control action is executed; and evaluating the control result according to the difference between the target monitoring difference data and the actual measurement monitoring difference data. For example, based on a known target mapping record table and the target prediction control action, the difference of the monitoring data under the condition that the target prediction control action is completely implemented in place, that is, target monitoring difference data, can be obtained, and the difference between the target monitoring difference data and the actually measured monitoring difference data can be used for judging whether the target prediction control action is implemented in place or not, if not, which link is not in place can be directly obtained according to the analysis of the difference between the target monitoring difference data and the actually measured monitoring difference data without manual intervention.
In one embodiment, there is further provided a vehicle state model training device, wherein the vehicle state model includes a monitoring data processing module, a map information processing module, a manipulation information input module, a manipulation prediction first module, an operation prediction second module, a first evaluator group and a second evaluator group, the monitoring data processing module is connected to the manipulation information input module, the monitoring data processing module and the map information processing module are both connected to the manipulation prediction first module, the monitoring data processing module and the map information processing module are both connected to the manipulation prediction second module, the manipulation prediction first module is connected to the first evaluator group, the manipulation prediction second module is connected to the second evaluator group, and the first evaluator group and the second evaluator group respectively include at least two evaluators, the device includes:
a training information obtaining module, configured to obtain training information, where the training information includes a sample manipulation action, map environment information, first monitoring information, second monitoring information, a first motion state, and a second motion state, the first monitoring information is bus data that is monitored before the sample manipulation action is performed, the second monitoring information is bus data that is monitored after the sample manipulation action is performed, the first motion state is a motion state of a vehicle when the sample manipulation action is performed, and the second motion state is a motion state of the vehicle at a next time corresponding to the first motion state;
the data processing module is used for inputting the sample control action into the control information input module; inputting the map environment information into the map information processing module; inputting the output of the control information input module, the first monitoring information and the second monitoring information into the monitoring data processing module; inputting the output of the map information processing module, the output of the monitoring data processing module and the first motion state into the control prediction first module to obtain a first control prediction result; inputting the output of the map information processing module and the second motion state into the control prediction second module to obtain a second control prediction result;
and the parameter adjusting module is used for adjusting parameters of the relevant module based on the first control prediction result and the second control prediction result.
In one embodiment, there is also provided a vehicle state control system, the system comprising:
the monitoring module is used for monitoring bus data to obtain third monitoring information and fourth monitoring information, wherein the moment corresponding to the fourth monitoring information is the next moment of the moment corresponding to the third monitoring information;
a reference motion state obtaining module, configured to obtain a reference motion state, where the reference motion state is a motion state of the vehicle at a time corresponding to the fourth monitoring information;
a monitoring difference value obtaining module, configured to determine a target monitoring difference value according to the third monitoring information and the fourth monitoring information;
the environment map processing module is used for inputting map environment information into the map information processing module to obtain the output of the map information processing module;
the control information prediction module is used for inputting the output of the map information processing module, the target monitoring difference value and the reference motion state into the control prediction first module to obtain a target prediction control action;
the control module is used for controlling the vehicle according to the target prediction control action;
the map information processing module and the control prediction first module both belong to a vehicle state model, and the vehicle state model is obtained by training through the method.
The device part and the system part in the embodiment of the present application are based on the same inventive concept as the respective method embodiments, and are not described herein again.
The above description is only a preferred embodiment of the present application, and is not intended to limit the present application, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A vehicle state model training method is characterized in that a vehicle state model comprises a monitoring data processing module, a map information processing module, an operation information input module, an operation prediction first module, an operation prediction second module, a first evaluator group and a second evaluator group, the monitoring data processing module is connected with the operation information input module, the monitoring data processing module and the map information processing module are both connected with the operation prediction first module, the monitoring data processing module and the map information processing module are both connected with the operation prediction second module, the operation prediction first module is connected with the first evaluator group, the operation prediction second module is connected with the second evaluator group, and the first evaluator group and the second evaluator group respectively comprise at least two evaluators, and the method comprises the following steps:
acquiring training information, wherein the training information comprises a sample control action, map environment information, first monitoring information, second monitoring information, a first motion state and a second motion state, the first monitoring information is bus data monitored before the sample control action is implemented, the second monitoring information is bus data monitored after the sample control action is implemented, the first motion state is a motion state of a vehicle when the sample control action is implemented, and the second motion state is a motion state of the vehicle at the next moment corresponding to the first motion state;
inputting the sample manipulation action into the manipulation information input module;
inputting the map environment information into the map information processing module;
inputting the output of the control information input module, the first monitoring information and the second monitoring information into the monitoring data processing module;
inputting the output of the map information processing module, the output of the monitoring data processing module and the first motion state into the control prediction first module to obtain a first control prediction result;
inputting the output of the map information processing module and the second motion state into the control prediction second module to obtain a second control prediction result;
adjusting a parameter of a correlation module based on the first and second maneuver predictors.
2. The method of claim 1, wherein adjusting parameters of a correlation module based on the first and second steering predictors comprises:
inputting the second control prediction result into each evaluator in the second evaluator group to obtain first evaluation prediction information output by each evaluator according to a preset noise signal, wherein the evaluation prediction information represents an reward expected value under the assumption of continuously executing the second control prediction result for a preset time;
determining a reward prediction target based on the product of the minimum value in each piece of first evaluation prediction information and a preset attenuation coefficient;
inputting the first control prediction result into each evaluator in the first evaluator group to obtain second evaluation prediction information output by each evaluator according to a preset noise signal;
obtaining an evaluation prediction target based on the weighted square sum of the second evaluation prediction information;
updating parameters of the first module of maneuver predictions and the first set of evaluators based on a difference between the reward prediction objective and the evaluation prediction objective.
3. The method of claim 2, wherein updating the parameters of the maneuver prediction first module and the first set of evaluators based on the difference between the reward prediction objective and the evaluation prediction objective comprises:
adjusting parameters of the first evaluator set in a gradient decreasing manner;
adjusting a parameter of the steering prediction first module in a gradient ascending manner.
4. The method of claim 3, wherein adjusting parameters of a correlation module based on the first and second maneuver predictors further comprises:
updating a parameter of the maneuver prediction second module based on a parameter of the maneuver prediction first module;
updating the parameters of the second evaluator set based on the parameters of the first evaluator set.
5. The method of claim 1, wherein the inputting the sample manipulation action into the manipulation information input module comprises: extracting information of the sample control action based on the control information input module to obtain corresponding output;
the inputting the map environment information into the map information processing module includes: vectorizing the map environment information based on the map information processing module to obtain corresponding output;
the inputting the output of the control information input module, the first monitoring information and the second monitoring information into the monitoring data processing module includes:
acquiring monitoring difference value information based on the first monitoring information and the second monitoring information;
obtaining mapping information according to the output of the control information input module and the monitoring difference information, wherein the mapping information represents the corresponding relation between the sample operation action and the monitoring difference information;
and taking the monitoring difference value information as the output of the monitoring data processing module.
6. The method of claim 5, further comprising:
and performing autocorrelation analysis on all mapping information to obtain a target mapping record table, wherein each record in the target mapping record table represents the corresponding relation between a single control action and the change bit of the corresponding monitored data.
7. A vehicle state control method, characterized by comprising:
monitoring bus data to obtain third monitoring information and fourth monitoring information, wherein the moment corresponding to the fourth monitoring information is the next moment of the moment corresponding to the third monitoring information;
acquiring a reference motion state, wherein the reference motion state is a motion state of the vehicle at a moment corresponding to the fourth monitoring information;
determining a target monitoring difference value according to the third monitoring information and the fourth monitoring information;
inputting map environment information into a map information processing module to obtain the output of the map information processing module;
inputting the output of the map information processing module, the target monitoring difference value and the reference motion state into a first control prediction module to obtain a target prediction control action;
controlling the vehicle according to the target predicted control action;
wherein the map information processing module and the maneuver prediction first module both belong to a vehicle state model, which is trained using the method of any one of claims 1 to 6.
8. The method of claim 7, further comprising:
inputting the target prediction control action into a monitoring data processing module in the vehicle state model to obtain target monitoring difference data;
acquiring actually-measured monitoring difference data based on monitoring data before the target prediction control action is executed and monitoring data after the target prediction control action is executed;
and evaluating a control result according to the difference between the target monitoring difference data and the actual measurement monitoring difference data.
9. A vehicle state model training device is characterized in that a vehicle state model comprises a monitoring data processing module, a map information processing module, a control information input module, a control prediction first module, an operation prediction second module, a first evaluator group and a second evaluator group, wherein the monitoring data processing module is connected with the control information input module, the monitoring data processing module and the map information processing module are connected with the control prediction first module, the monitoring data processing module and the map information processing module are connected with the control prediction second module, the control prediction first module is connected with the first evaluator group, the control prediction second module is connected with the second evaluator group, and the first evaluator group and the second evaluator group respectively comprise at least two evaluators, the device comprises:
the training information acquisition module is used for acquiring training information, wherein the training information comprises a sample control action, map environment information, first monitoring information, second monitoring information, a first motion state and a second motion state, the first monitoring information is bus data monitored before the sample control action is implemented, the second monitoring information is bus data monitored after the sample control action is implemented, the first motion state is a motion state of a vehicle when the sample control action is implemented, and the second motion state is a motion state of the vehicle at the next moment corresponding to the first motion state;
the data processing module is used for inputting the sample manipulation action into the manipulation information input module; inputting the map environment information into the map information processing module; inputting the output of the control information input module, the first monitoring information and the second monitoring information into the monitoring data processing module; inputting the output of the map information processing module, the output of the monitoring data processing module and the first motion state into the control prediction first module to obtain a first control prediction result; inputting the output of the map information processing module and the second motion state into the control prediction second module to obtain a second control prediction result;
and the parameter adjusting module is used for adjusting parameters of the related module based on the first manipulation prediction result and the second manipulation prediction result.
10. A vehicle state control system, characterized in that the system comprises:
the monitoring module is used for monitoring bus data to obtain third monitoring information and fourth monitoring information, wherein the time corresponding to the fourth monitoring information is the next time of the time corresponding to the third monitoring information;
a reference motion state obtaining module, configured to obtain a reference motion state, where the reference motion state is a motion state of the vehicle at a time corresponding to the fourth monitoring information;
a monitoring difference value obtaining module, configured to determine a target monitoring difference value according to the third monitoring information and the fourth monitoring information;
the environment map processing module is used for inputting map environment information into the map information processing module to obtain the output of the map information processing module;
the control information prediction module is used for inputting the output of the map information processing module, the target monitoring difference value and the reference motion state into the control prediction first module to obtain a target prediction control action;
the control module is used for controlling the vehicle according to the target prediction control action;
wherein the map information processing module and the maneuver prediction first module both belong to a vehicle state model, which is trained using the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211392759.XA CN115755683A (en) | 2022-11-08 | 2022-11-08 | Vehicle state control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211392759.XA CN115755683A (en) | 2022-11-08 | 2022-11-08 | Vehicle state control method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115755683A true CN115755683A (en) | 2023-03-07 |
Family
ID=85368154
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211392759.XA Pending CN115755683A (en) | 2022-11-08 | 2022-11-08 | Vehicle state control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115755683A (en) |
-
2022
- 2022-11-08 CN CN202211392759.XA patent/CN115755683A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114357594B (en) | Bridge abnormity monitoring method, system, equipment and storage medium based on SCA-GRU | |
| CN110706213B (en) | Bridge cluster structure damage judgment method based on strain response cumulative distribution function difference | |
| KR102057066B1 (en) | Traffic System Modeling Method Built-in Machine Learning using Traffic Big data | |
| KR102038703B1 (en) | Method for estimation on online multivariate time series using ensemble dynamic transfer models and system thereof | |
| CN108415884B (en) | Real-time tracking method for structural modal parameters | |
| CN112308281A (en) | Temperature information prediction method and device | |
| CN116610092A (en) | Method and system for vehicle analysis | |
| KR20220009058A (en) | Learning method of artificial intelligence part for monitoring system of cable-supported bridge and the artificial intelligence part | |
| CN113988210A (en) | Method and device for restoring distorted data of structure monitoring sensor network and storage medium | |
| CN114707632A (en) | Sensor network sensor fault positioning method, system, equipment and medium | |
| CN112613617A (en) | Uncertainty estimation method and device based on regression model | |
| CN113744888B (en) | Regional epidemic trend prediction and early warning method and system | |
| CN100582722C (en) | Apparatus and methods for evaluating a dynamic system | |
| CN114298270A (en) | Pollutant concentration prediction method fusing domain knowledge and related equipment thereof | |
| CN117951636A (en) | Soil pollution detection method, device and medium based on data fusion of Internet of things | |
| CN115755683A (en) | Vehicle state control method and system | |
| CN116960962A (en) | Mid-long term area load prediction method for cross-area data fusion | |
| CN111738878A (en) | Bridge stress detection system | |
| CN116502496A (en) | Simple bridge damage detection method based on mobile load and convolutional neural network | |
| CN116166642A (en) | Spatio-temporal data filling method, system, equipment and medium based on guide information | |
| CN113780356B (en) | Water quality prediction method and system based on integrated learning model | |
| CN112787882A (en) | Internet of things edge traffic prediction method, device and equipment | |
| Ištoka Otković et al. | Analysis of neural network responses in calibration of microsimulation traffic model | |
| CN117131465B (en) | Single-pipe tower damage identification method and device, electronic equipment and readable storage medium | |
| KR20230140743A (en) | Battery malfunction detection method and system through artificial intelligence neural network battery model based on field data |
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 |