CN115158352A

CN115158352A - Target vehicle control method, device, vehicle-mounted terminal and medium

Info

Publication number: CN115158352A
Application number: CN202210799081.0A
Authority: CN
Inventors: 朱珩; 郭晋文; 韩坪良; 王磊
Original assignee: Suzhou Zhijia Technology Co Ltd
Current assignee: Suzhou Zhijia Technology Co Ltd
Priority date: 2022-07-06
Filing date: 2022-07-06
Publication date: 2022-10-11

Abstract

The application provides a control method and device of a target vehicle, a vehicle-mounted terminal and a medium, and belongs to the technical field of vehicles. The method comprises the following steps: acquiring target state data of a target vehicle, wherein the target state data represents a target state which the target vehicle needs to reach; acquiring multiple groups of historical data of a target vehicle, and determining target control data corresponding to the target state data based on the multiple groups of historical data and the target state data, wherein each group of historical data comprises historical state data and historical control data of the target vehicle at one moment, the historical state data represents the state of the target vehicle at the moment, and the historical control data is data used for controlling the target vehicle at the moment; the control target vehicle transitions from the current state to the target state based on the target control data. The target control data determined by the method is high in accuracy, and the effect of controlling the target vehicle based on the target control data is good.

Description

Target vehicle control method, device, vehicle-mounted terminal and medium

Technical Field

The present disclosure relates to the field of vehicle technologies, and in particular, to a method and an apparatus for controlling a target vehicle, a vehicle-mounted terminal, and a medium.

Background

With the development of vehicle technology, the application of automatic driving vehicles is increasingly wide. During the travel of an autonomous vehicle, it is generally necessary to control the autonomous vehicle based on control data.

In the related art, an autonomous vehicle determines control data in a PID (proportional integral derivative) control manner. However, in this way, a fixed formula is used to determine the control data, and the parameters in the formula need to be set by the user according to experience and are not accurate enough, which results in low accuracy of the determined control data.

Disclosure of Invention

The embodiment of the application provides a control method and device of a target vehicle, a vehicle-mounted terminal and a medium, which can improve the accuracy of determining control data so as to improve the control effect of the target vehicle. The technical scheme is as follows:

in one aspect, there is provided a control method of a target vehicle, the method including:

acquiring target state data of a target vehicle, wherein the target state data represents a target state which the target vehicle needs to reach;

acquiring multiple groups of historical data of the target vehicle, and determining target control data corresponding to the target state data based on the multiple groups of historical data and the target state data, wherein each group of historical data comprises historical state data and historical control data of the target vehicle at a moment, the historical state data represents the state of the target vehicle at the moment, and the historical control data is data used for controlling the target vehicle at the moment;

controlling the target vehicle to transition from a current state to the target state based on the target control data.

In a possible implementation manner, the determining, based on the multiple sets of historical data and the target state data, target control data corresponding to the target state data includes:

determining at least two sets of proximity history data corresponding to the target state data from a plurality of sets of history data of the target vehicle, the proximity history data including a history state data closest in distance to the target state data;

and determining the target control data corresponding to the target state data based on historical control data included in the at least two groups of adjacent historical data.

In a possible implementation manner, the determining, based on historical control data included in the at least two sets of adjacent historical data, target control data corresponding to the target state data includes any one of:

weighting historical control data included in at least two groups of adjacent historical data based on weights of the historical control data included in the at least two groups of adjacent historical data to obtain target control data corresponding to the target state data, wherein the weights of the historical control data included in the adjacent historical data are inversely related to the distance between the historical state data included in the adjacent historical data and the target state data;

and determining the average value of historical control data included by the at least two groups of adjacent historical data as target control data corresponding to the target state data.

In one possible implementation, the dynamical model comprises the plurality of sets of historical data and a function for determining the target control data;

the acquiring multiple sets of historical data of the target vehicle, and determining target control data corresponding to the target state data based on the multiple sets of historical data and the target state data includes:

and calling the dynamic model, acquiring multiple groups of historical data of the target vehicle, and inputting the multiple groups of historical data and the target state data into the function to obtain the target control data.

In one possible implementation, the function includes a plurality of parameters; the process of training the kinetic model includes:

in the iteration process, a parameter value set is determined based on the value ranges corresponding to the parameters, the parameter value set comprises the value of each parameter, the value of each parameter belongs to the value range of each parameter, and each parameter in the dynamic model is configured according to the value of each parameter;

calling the configured dynamic model to respectively determine predictive control data corresponding to a plurality of historical state data, and determining the error of the parameter value set based on the plurality of historical control data and the plurality of predictive control data;

and continuously determining the error of the next parameter value set in the next iteration process until the error of the last parameter value set is determined, and configuring each parameter in the dynamic model according to the value of each parameter in the parameter value set with the error meeting the error condition to obtain the trained dynamic model.

In one possible implementation, the method further includes:

acquiring test data of the target vehicle, wherein the test data comprises test state data and test control data of the target vehicle;

calling the dynamic model, and determining the predictive control data corresponding to the test data;

determining a test error corresponding to the test data based on the prediction control data and the test control data included in the test data;

if the test error does not accord with the test condition, adjusting the value range corresponding to at least one parameter in the function, and retraining the dynamic model based on the adjusted value ranges corresponding to the parameters until the test error corresponding to the test data determined by calling the trained dynamic model accords with the test condition.

In one possible implementation, the method further includes:

calling the trained dynamic model, and determining control data corresponding to a plurality of preset state data respectively;

constructing a look-up table based on each preset state data and corresponding control data;

and querying the control data corresponding to any state data from the query table.

In one possible implementation, the historical state data includes acceleration, and the method further includes:

acquiring the acceleration of the target vehicle at the moment and the gradient of a road surface on which the target vehicle runs;

and adjusting the acceleration based on the gradient to obtain the adjusted acceleration.

In another aspect, there is provided a control apparatus of a target vehicle, the apparatus including:

the data acquisition module is used for acquiring target state data of a target vehicle, wherein the target state data represents a target state which the target vehicle needs to reach;

the data determining module is used for acquiring multiple sets of historical data of the target vehicle, and determining target control data corresponding to the target state data based on the multiple sets of historical data and the target state data, wherein each set of historical data comprises historical state data and historical control data of the target vehicle at one moment, the historical state data represents the state of the target vehicle at the moment, and the historical control data is data used for controlling the target vehicle at the moment;

a vehicle control module to control the target vehicle to transition from a current state to the target state based on the target control data.

In one possible implementation manner, the data determining module is configured to:

In a possible implementation manner, the data determining module is configured to:

the data determination module is used for calling the dynamic model, acquiring multiple groups of historical data of the target vehicle, and inputting the multiple groups of historical data and the target state data into the function to obtain the target control data.

In one possible implementation, the function includes a plurality of parameters; the apparatus further comprises a training module configured to:

In a possible implementation manner, the apparatus further includes a testing module, where the testing module is configured to:

and if the test error does not accord with the test condition, adjusting the value range corresponding to at least one parameter in the function, and the training module is further used for retraining the dynamic model based on the adjusted value ranges corresponding to the parameters until the test error corresponding to the test data determined by calling the trained dynamic model accords with the test condition.

In one possible implementation, the apparatus further includes:

the query table construction module is used for calling the trained dynamic model and determining control data corresponding to a plurality of preset state data respectively; constructing a lookup table based on each preset state data and corresponding control data;

and the query module is used for querying the control data corresponding to any state data from the query table.

In one possible implementation, the historical state data includes acceleration, and the apparatus further includes:

the data acquisition module is used for acquiring the acceleration of the target vehicle at the moment and the gradient of a road surface on which the target vehicle runs;

and the acceleration adjusting module is used for adjusting the acceleration based on the gradient to obtain the adjusted acceleration.

In another aspect, a vehicle-mounted terminal is provided, which includes a processor and a memory, where at least one program code is stored in the memory, and the at least one program code is loaded and executed by the processor to implement the control method of the target vehicle described above.

In another aspect, a computer-readable storage medium having at least one program code stored therein is provided, the at least one program code being loaded and executed by a processor to implement the control method of the target vehicle described above.

In another aspect, a computer program product is provided, which comprises a computer program for being loaded and executed by a processor to implement the above-mentioned control method of a target vehicle.

The embodiment of the application provides a control scheme of a target vehicle, aiming at a target state which needs to be achieved by the target vehicle, multiple groups of historical data of the target vehicle are obtained, so that the target control data are determined by combining the multiple groups of historical data and the target state data representing the target state, and the determined target control data can refer to the historical state data and the historical control data at one moment in the historical driving process and can refer to the corresponding relation between the historical state data and the historical control data, so that the determined target control data are high in accuracy, and the target vehicle is controlled based on the target control data with a good effect.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a control method for a target vehicle according to an embodiment of the present application;

FIG. 2 is a flowchart of another control method for a target vehicle according to an embodiment of the present application;

FIG. 3 is a flow chart of a training process for a kinetic model provided by an embodiment of the present application;

FIG. 4 is a schematic diagram of a training process of a kinetic model provided by an embodiment of the present application;

fig. 5 is a block diagram of a control device of a target vehicle according to an embodiment of the present application;

fig. 6 is a block diagram of a structure of a vehicle-mounted terminal according to an embodiment of the present disclosure.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, the following detailed description of the embodiments of the present application will be made with reference to the accompanying drawings.

The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different elements and not for describing a particular sequential order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The control method of the target vehicle provided by the embodiment of the application is executed by the vehicle-mounted terminal. The vehicle-mounted terminal is arranged on a vehicle and used for controlling the vehicle. Optionally, the vehicle-mounted terminal is a vehicle-mounted computer or a vehicle-mounted computer. The vehicle is an autonomous vehicle, such as a passenger car, a truck and a trailer towed thereby.

The control method of the target vehicle can be applied to a vehicle control scene. For example, during the running of the vehicle, the vehicle-mounted terminal provided on the vehicle determines control data for controlling the vehicle by the control method of the target vehicle provided in the embodiment of the present application, so as to control the vehicle based on the control data.

It should be noted that the above application scenarios are only exemplary, and do not limit the vehicle control scenario, and the present application can be applied to any other vehicle control scenario besides the above scenarios.

Fig. 1 is a flowchart of a control method for a target vehicle according to an embodiment of the present disclosure. Referring to fig. 1, the method is performed by a vehicle-mounted terminal, and includes:

101. target state data of the target vehicle is obtained, and the target state data represents a target state which the target vehicle needs to reach.

The target vehicle is a vehicle controlled by a vehicle-mounted terminal, and the vehicle-mounted terminal is arranged on the target vehicle. The state data of the target vehicle at a certain time point represents the state of the target vehicle at that time point. The status data comprises at least one of weight, speed or acceleration of the vehicle, for example the status data comprises a weight of 5t (tons), a speed of 80km/h (kilometers per hour), an acceleration of 1m/s2 (meters per second squared). The target state data indicates a target state that the target vehicle needs to reach, which is a state that the target vehicle is about to reach.

102. The method comprises the steps of obtaining multiple sets of historical data of a target vehicle, determining target control data corresponding to the target state data based on the multiple sets of historical data and the target state data, wherein each set of historical data comprises historical state data and historical control data of the target vehicle at one moment, the historical state data represents the state of the target vehicle at the moment, and the historical control data is data used for controlling the target vehicle at the moment.

The historical state data and the historical control data are respectively state data and control data collected at a historical moment before the current moment. The control data of the vehicle includes at least one of driving data and braking data of the vehicle. The driving data is a command value of a driving command, and the braking data is a command value of a braking command. In the embodiment of the application, after the vehicle-mounted terminal determines the control data, the vehicle-mounted terminal issues a control command containing the control data to an execution mechanism of the vehicle through an execution mechanism interface, so that the execution mechanism is controlled to execute the control command, and the vehicle is controlled. For example, the actuator interface of the vehicle is an engine torque control interface, the control data is drive command data, and the drive data is a torque value output by the engine torque control interface. For another example, the actuator interface of the vehicle is a brake torque control interface, the control data is brake data, and the brake data is a torque value output by the brake torque control interface.

In the embodiment of the application, the historical state data and the historical control data at the same time are corresponding, and the target control data corresponding to the target state data can be determined based on multiple sets of historical data and target state data of the target vehicle. Alternatively, the in-vehicle terminal stores a plurality of sets of history data of the target vehicle, and after determining the target state data, acquires the stored plurality of sets of history data. The number of the multiple sets of historical data may be set as needed, which is not limited in the embodiment of the present application.

103. Based on the target control data, the control-target vehicle transitions from the current state to the target state.

After determining the target control data, the in-vehicle terminal controls the target vehicle based on the target control data. Optionally, the vehicle-mounted terminal issues a control command including the target control data to an execution mechanism of the vehicle, and the control execution mechanism executes the control command, so as to control the target vehicle to transition from the current state to the target state. For example, if the current state of the target vehicle is a speed of 40km/h and the target state is 80km/h, the vehicle-mounted terminal controls the target vehicle to accelerate based on the target control data until the speed reaches 80km/h.

Fig. 2 is a flowchart of a control method of a target vehicle according to an embodiment of the present application. Referring to fig. 2, the method is performed by a vehicle-mounted terminal, and includes:

201. target state data of the target vehicle is acquired, and the target state data represents a target state which the target vehicle needs to reach.

The target vehicle is a vehicle controlled by a vehicle-mounted terminal, and the vehicle-mounted terminal is arranged on the target vehicle. The state data of the target vehicle at a certain time point indicates the state of the target vehicle at that time point. The status data includes at least one of weight, speed or acceleration of the vehicle, for example the status data includes a weight of 5t (tons), a speed of 80km/h (kilometers per hour), an acceleration of 1m/s2 (meters per second squared). The target state data indicates a target state that the target vehicle needs to reach, which is a state that the target vehicle is about to reach.

202. The method comprises the steps of obtaining multiple sets of historical data of a target vehicle, wherein each set of historical data comprises historical state data and historical control data of the target vehicle at one moment, the historical state data represents the state of the target vehicle at the moment, and the historical control data is data used for controlling the target vehicle at the moment.

The historical state data and the historical control data are respectively state data and control data collected in the historical driving process of the target vehicle. The control data of the vehicle includes at least one of driving data and braking data of the vehicle. The driving data is a command value of a driving command, and the braking data is a command value of a braking command. In the embodiment of the application, after the vehicle-mounted terminal determines the control data, the vehicle-mounted terminal issues a control command containing the control data to an execution mechanism of the vehicle through an execution mechanism interface, so that the execution mechanism is controlled to execute the control command, and the vehicle is controlled. For example, the actuator interface of the vehicle is an engine torque control interface, the control data is drive command data, and the drive data is a torque value output by the engine torque control interface. For another example, the actuator interface of the vehicle is a brake torque control interface, the control data is brake data, and the brake data is a torque value output by the brake torque control interface.

Alternatively, the in-vehicle terminal stores a plurality of sets of history data of the target vehicle, and after determining the target state data, acquires the stored plurality of sets of history data. The number of the multiple sets of historical data may be set as needed, which is not limited in the embodiment of the present application.

In the embodiment of the application, the historical state data and the historical control data at the same time are corresponding, and after the vehicle-mounted terminal acquires multiple sets of historical data of the target vehicle, the vehicle-mounted terminal determines the target control data corresponding to the target state data based on the multiple sets of historical data and the target state data.

203. At least two sets of proximity history data corresponding to the target state data are determined from the plurality of sets of history data of the target vehicle, the proximity history data including a closest distance between the history state data and the target state data.

The distance between the data represents the similarity degree between the data, the closer the distance is, the more similar the data is represented, and the farther the distance between the data is, the more dissimilar the data is represented. In one possible implementation, determining at least two sets of proximate history data corresponding to the target state data from the plurality of sets of history data of the target vehicle includes: determining the distance between the target state data and the historical state data included in each group of historical data, and determining the historical data to which at least two pieces of historical state data closest to each other belong as the adjacent historical data corresponding to the target state data. The nearest historical state data refers to: historical state data to which a closest distance of the determined plurality of distances belongs. The distance between at least two nearest historical state data and the target state data is smaller than the distance between the historical state data and the target state data included in the historical data except the at least two groups of adjacent historical data.

The distance between the data may be an euclidean distance, a manhattan distance, or the like, which is not limited in the embodiment of the present application. The number of the at least two adjacent historical data may be set according to needs, and is not limited in the embodiment of the present application. E.g. a number of 2,3 or 4 etc.

204. And determining target control data corresponding to the target state data based on historical control data included by the at least two adjacent historical data.

When the distance between the historical state data and the target state data is close, the control data of the historical data is likely to be similar to the target control data corresponding to the target state data, and the target control data can be determined based on the historical control data included in the adjacent historical data.

In one possible implementation manner, the determining, based on the historical control data included in the at least two pieces of adjacent historical data, an implementation manner of the target control data corresponding to the target state data includes: and weighting historical control data included by the at least two groups of adjacent historical data based on the weights of the historical control data included by the at least two groups of adjacent historical data to obtain target control data corresponding to the target state data, wherein the weights of the historical control data included by the adjacent historical data are in negative correlation with the distance between the historical state data included by the adjacent historical data and the target state data.

The more the distance between the historical state data and the target state data included in the proximity historical data is, the more similar the historical state data and the target state data are, the more likely the historical control data and the target control data included in the proximity historical data are also similar, the closer the distance between the historical state data and the target state data included in the proximity historical data is, the greater the weight corresponding to the historical control data included in the proximity historical data is, and the farther the distance is, the smaller the weight is.

Since the historical control data and the target control data included in at least two sets of adjacent historical data are similar to each other, and the distances between the historical state data and the target state data included in different sets of adjacent historical data are different, the importance degrees of the historical control data included in different sets of adjacent historical data to the determination of the target control data are also different, and the weighting processing is performed on at least two sets of historical control data by allocating a weight to the historical control data included in each set of adjacent historical data, so that the determined target control data are more accurate.

The weighting process includes a weighted average processing manner, which is not limited in the embodiment of the present application.

In another possible implementation manner, the determining, based on the historical control data included in the at least two pieces of adjacent historical data, the target control data corresponding to the target state data includes: and determining the average value of the historical control data included by the at least two groups of adjacent historical data as the target control data corresponding to the target state data. Because the historical control data included by the at least two groups of adjacent historical data are similar to the target control data, the average value of the historical control data included by the at least two groups of adjacent historical data can be directly determined as the target control data, and the calculation speed and the efficiency are high.

In the embodiment of the present application, steps 203 to 204 are an implementation manner of determining target control data corresponding to target state data based on multiple sets of historical data and the target state data. Since each set of history data includes the history state data and the history control data of the target vehicle at a history time and is the real data of the target vehicle, reference can be provided for determining the target control data, the closer the distance between the history state data and the target state data included in the proximity history data is, the more similar the history state data and the target state data are, the more likely the history control data included in the proximity history data is to be similar to the target control data, and the higher the accuracy of the target control data determined by the history control data included in at least two proximity history data is.

In one possible implementation manner, a dynamic model is deployed in the vehicle-mounted terminal, and the dynamic model is used for determining control data corresponding to any state data. The input data of the dynamic model is state data, and the output data is control data corresponding to the state data. The dynamic model training process is described in the following embodiment shown in fig. 3, and will not be described in detail herein. Wherein the dynamical model comprises a plurality of sets of historical data and functions for determining target control data; correspondingly, the implementation mode of acquiring multiple groups of historical data of the target vehicle and determining the target control data corresponding to the target state data on the basis of the multiple groups of historical data and the target state data comprises the following steps: and calling a dynamic model, acquiring multiple groups of historical data of the target vehicle, and inputting the multiple groups of historical data and the target state data into a function to obtain target control data.

Optionally, the dynamic model includes a function for determining at least two sets of neighboring historical data corresponding to the target state data from a plurality of sets of historical data of the target vehicle, and determining the target control data corresponding to the target state data based on historical control data included in the at least two sets of neighboring historical data. The implementation manner of determining the target control data by calling the dynamic model is shown in step 202-step 204, and is not described herein again. The dynamic model can be regarded as a model obtained by packaging multiple groups of historical data and functions, the vehicle-mounted terminal can directly determine target control data by calling the dynamic model, and the determination efficiency is high.

205. Based on the target control data, the control-target vehicle transitions from the current state to the target state.

After determining the target control data, the in-vehicle terminal controls the target vehicle based on the target control data. Optionally, the vehicle-mounted terminal issues a control command including the target control data to an execution mechanism of the vehicle, and the control execution mechanism executes the control command, so as to control the target vehicle to transition from the current state to the target state.

In the embodiment of the application, the server trains the dynamic model, and after the trained dynamic model is obtained, the dynamic model is deployed on the vehicle-mounted terminal, so that the vehicle-mounted terminal calls the dynamic model to determine the target control data corresponding to the target state data. The following describes the training process of the kinetic model.

Fig. 3 is a flowchart of a method for training a dynamical model according to an embodiment of the present application. Referring to fig. 3, the method is performed by a server, the method comprising:

301. and acquiring a dynamic model, wherein the dynamic model comprises a plurality of groups of historical data of the target vehicle and a function, the function is used for determining target control data corresponding to target state data of the target vehicle, and the function comprises a plurality of parameters.

Optionally, the server obtains multiple sets of historical data of the target vehicle, and the multiple sets of historical data and a preset function form a dynamic model. The plurality of sets of historical data of the target vehicle may be data collected during testing of the target vehicle. The parameter is a parameter with an undetermined value or a parameter with a preset value, which is not limited in the embodiment of the application, and the preset value can be set as required.

Wherein the function is used to determine the target control data. For example, if the function in the dynamic model includes a function for determining at least two sets of proximity history data corresponding to the target state data from among a plurality of sets of history data of the target vehicle, and a function for determining target control data corresponding to the target state data based on the history control data included in the at least two sets of proximity history data, the parameter included in the function may be the number of the at least two sets of proximity history data.

302. In the iteration process, a parameter value set is determined based on value ranges corresponding to a plurality of parameters, the parameter value set comprises the value of each parameter, the value of each parameter belongs to the value range of each parameter, and each parameter in the dynamic model is configured according to the value of each parameter.

The value range of each parameter can be set as required, for example, the parameter is the number of at least two sets of neighboring historical data, and the value range is {2,3,4}. In each iteration process, a value is selected from the value range corresponding to each parameter to obtain a parameter value set, and each parameter in the dynamic model is configured according to the value of each parameter, so that the parameter in the configured dynamic model is determined.

303. And calling the configured dynamic model to respectively determine predictive control data corresponding to the plurality of historical state data, and determining the error of the parameter value set based on the plurality of historical control data and the plurality of predictive control data.

And calling the configured dynamic model to respectively determine the predictive control data corresponding to each historical state data, so as to realize prediction of the control data corresponding to the historical state data. The implementation mode of calling the configured dynamic model to respectively determine the predictive control data corresponding to the plurality of historical state data comprises the following steps: and calling the configured dynamic model, determining at least two groups of predicted adjacent historical data corresponding to the historical state data from the plurality of groups of historical data for each historical state data, and determining the predicted control data corresponding to the historical state data based on the historical control data included in the at least two groups of predicted adjacent historical data. The implementation manner is referred to the implementation manner of step 203-step 204, and is not described herein.

Because each historical state data has the historical control data corresponding to each historical state data, and the difference between the historical control data and the predictive control data corresponding to the same historical state data can represent the prediction error of the dynamic model, optionally, the implementation manner of determining the error of the parameter value set based on a plurality of historical control data and a plurality of predictive control data includes: and determining a difference value between the historical control data and the prediction control data corresponding to each historical state data, and determining an error of the parameter value set based on the difference values corresponding to the plurality of historical state data. The error of the parameter value set is a mean square error, a root mean square error or an average absolute value error of differences of a plurality of historical state data.

304. And continuously determining the error of the next parameter value set in the next iteration process until the error of the last parameter value set is determined, and configuring each parameter in the dynamic model according to the value of each parameter in the parameter value set with the error meeting the error condition to obtain the trained dynamic model.

If each parameter has a value range corresponding to each parameter, a plurality of possible parameter value sets can be determined based on the value ranges corresponding to the plurality of parameters, each iteration process corresponds to one parameter value set, and the error of each parameter value set is determined by repeatedly performing step 303. Optionally, the error condition is that an error of the parameter value set is a minimum error of the determined errors of the parameter value set. The smaller the error of the parameter value set is, the higher the prediction accuracy of the dynamic model configured according to the parameter value set is, and then the dynamic model can be configured according to the parameter value set corresponding to the minimum error, so that a model with higher accuracy is obtained.

In the embodiment of the application, the accuracy of the trained dynamic model is high enough, and the trained dynamic model can be deployed in the vehicle-mounted terminal, so that the vehicle-mounted terminal calls the dynamic model to determine the target control data corresponding to the target state data. Or, in other embodiments, after the dynamic model is trained, the dynamic model may also be tested, and accordingly, after step 304, the server obtains test data of the target vehicle, where the test data includes test state data and test control data of the target vehicle; calling a dynamic model, and determining predictive control data corresponding to the test data; determining a test error corresponding to the test data based on the test control data included in the prediction control data and the test data; if the test error does not accord with the test condition, adjusting the value range corresponding to at least one parameter in the function, and retraining the dynamic model based on the adjusted value ranges corresponding to the parameters until the test error corresponding to the test data determined by calling the trained dynamic model accords with the test condition.

The test data of the target vehicle are historical data of the target vehicle, and the test data are different from the historical data included in the dynamic model. The test data may be data collected during a test of the target vehicle. It should be noted that the test data is data for testing a dynamic model, and the test process of the target vehicle refers to a test on the target vehicle.

The number of the test data may be one or more, which is not limited in the embodiment of the present application. And if the number of the test data is one, the test error corresponding to the test data is the difference value between the prediction control data and the test control data. If the number of the test data is multiple, determining a difference value between the test control data included in each test data and the prediction control data corresponding to the test data, and determining a test error based on the difference values corresponding to the multiple test data. The test error is a mean square error, a root mean square error or a mean absolute value error of a difference value of the plurality of test data.

The test condition is that the test error is smaller than the error threshold, and the error threshold can be set as required, which is not limited in the embodiment of the present application. If the test error does not accord with the test condition, the test error is larger, and the test accuracy of the dynamic model is not high. If the value ranges of the parameters in the function are unreasonable, the test accuracy of the dynamic model may be affected, and the value ranges corresponding to the parameters may be adjusted, so that the dynamic model is retrained based on the adjusted value ranges corresponding to the multiple parameters. If the test error meets the condition, the test error is smaller, the test accuracy of the dynamic model is higher, and retraining is not needed.

In the embodiment of the application, the dynamic model is called to determine the predictive control data corresponding to the test data, and whether the dynamic model is retrained or not can be determined according to the test error corresponding to the test data, so that the accuracy of the dynamic model is improved.

When the number of the test data is large, if the test error does not accord with the error condition, new historical data corresponding to the data range can be obtained according to the data range to which the test data with a large difference value between the test control data and the prediction control data in the plurality of test data belongs, the obtained new historical data is supplemented into the plurality of historical data included in the dynamic model to obtain a plurality of supplemented historical data, and the dynamic model is retrained based on the plurality of supplemented historical data until the test error corresponding to the test data determined by the trained dynamic model is called to accord with the test condition. The data range to which the test data belongs refers to a data range to which the test state data included in the test data belongs, for example, the test state data includes weight, speed, and acceleration, and the data range includes a weight range, a speed range, and an acceleration range. The data range can be set as desired.

The difference between the test control data included in the test data and the corresponding predictive control data is large, and the test data in the data range to which the test data belongs is possibly small or not accurate enough, new historical data corresponding to the data range can be acquired, so that a plurality of historical data included in the dynamic model are supplemented, and the dynamic model is retrained based on the supplemented plurality of historical data, so that the dynamic model can learn the corresponding relation between more historical control data included in the historical data and historical state data, and the accuracy of the dynamic model is improved.

In the embodiment of the application, a technician can deploy the trained dynamic model to the vehicle-mounted terminal so that the vehicle-mounted terminal calls the dynamic model to determine the target control data corresponding to the target state data, and can construct the query table by the server so that the technician deploys the query table to the vehicle-mounted terminal. Correspondingly, after the dynamic model is trained, the server calls the trained dynamic model to determine control data corresponding to a plurality of preset state data respectively; and constructing a query table based on each preset state data and the corresponding control data, wherein the query table is used for the vehicle-mounted terminal to query the control data corresponding to any state data from the query table. Wherein the preset state data can be set as required. See, for example, the look-up table shown in table 1.

TABLE 1

The group of data comprises preset state data and corresponding control data, the preset state data comprises weight, speed and acceleration, and the control data comprises command values. The first set of data comprises a weight 1, a velocity value 1, an acceleration value 1 and a command value 1, the second set of data comprises a weight 2, a velocity value 2, an acceleration value 2 and a command value 2, and the third set of data comprises a weight 3, a velocity value 3, an acceleration value 3 and a command value 3.

After the query table is constructed, the query table is deployed into the vehicle-mounted terminal, and accordingly, after the vehicle-mounted terminal acquires the target state data, the target control data corresponding to the target state data is queried from the query table, and then the vehicle is controlled based on the target control data.

In the embodiment of the application, the vehicle-mounted terminal can directly query based on the query table by constructing the query table, and the efficiency of determining the target control data is high.

In the embodiment of the application, the dynamic model can support off-line simulation analysis, and can also be deployed in a vehicle-mounted terminal for on-line control of a vehicle. The building and the deployment of the dynamic model do not depend on simulation tools in the related technology, so that the cost of the dynamic model is low, and the dynamic model can be more flexibly applied to large-scale simulation analysis.

The following describes the acquisition process of a plurality of historical data included in the kinetic model.

The first step is as follows: and selecting a target vehicle, and configuring a test tool and a data acquisition tool for controlling an execution mechanism according to an execution mechanism interface of the target vehicle.

The actuating mechanism interface for vehicle driving can be an engine torque interface or an accelerator opening and closing control interface, and the actuating mechanism interface for vehicle braking can be a braking torque control interface or a braking air pressure control interface. And configuring a corresponding test tool for controlling the actuator according to the type of the actuator interface, for example, configuring a test tool corresponding to the engine torque interface if the actuator interface is the engine torque interface. The data acquisition tool is used for acquiring control data included in a control command output by the execution mechanism interface and acquiring state data of the target vehicle such as weight, speed, acceleration and the like.

The second step is that: and respectively testing the target vehicle on an open road and a closed field, acquiring data and recording the acquired data.

Prior to the test, the data range of the control data, the data range of the state data, the gradient range of the road surface, and the like are determined. And testing each data range, and acquiring data belonging to the data range. The data acquisition tool acquires state data, control data and road surface gradient of a target vehicle, and transmits the acquired data to the data recording equipment, and the data recording equipment receives the data and stores the received data so as to train a dynamic model by the server. The data transmission frequency can be set as desired.

For example, when a target vehicle is tested on an open road, the target vehicle travels along a long straight road at speeds of 80km/h, 85km/h and 90km/h, respectively. When the target vehicle is tested in the closed field, the target vehicle is tested according to the test mode of the table 2.

TABLE 2

The number of data sampling sets, the target speed, the maximum torque, and the maximum braking torque may be set as required, and table 2 illustrates the data sampling sets as 19, and the target speed as 90km/h, respectively.

The third step: and extracting the weight, the speed, the driving data, the braking data, the acceleration and the gradient of the road surface of the target vehicle at the same moment from the acquired data. Optionally, the extracted data is composed into structured data as shown in table 3 below. In table 3, 3 sets of data are taken as an example.

TABLE 3

Speed of rotation	Drive data	Brake data	Acceleration of a vehicle	Slope of slope	Weight(s)
						Speed 1	Drive data 1	Brake data 1	Acceleration 1	Slope 1	Weight 1
Speed 2	Drive data 2	Brake data 2	Acceleration 2	Slope 2	Weight 2
						Speed 3	Drive data 3	Brake data 3	Acceleration 2	Slope 3	Weight 3

In addition, it can also be determined whether the extracted data already covers the data range and is complete and not lost. If data loss, damage or insufficient data range coverage occurs, the second step can be performed again to perform a supplementary test.

The fourth step: and training a dynamic model by adopting a non-generalized machine learning method based on an example based on the extracted data, wherein the dynamic model can represent the corresponding relation between the state data and the control data of the target vehicle.

The dynamic model provided in the embodiment of the present application is a longitudinal dynamic model for a target vehicle, and accordingly, before training the dynamic model, the collected acceleration may be adjusted based on the collected gradient, and optionally, the process of adjusting the acceleration includes: acquiring the acceleration of a target vehicle at the current moment and the gradient of a road surface on which the target vehicle runs; and adjusting the acceleration based on the gradient to obtain the adjusted acceleration. Optionally, an implementation of the gradient-based adjustment of the acceleration includes: based on the gradient, an acceleration component of the gravitational acceleration in a direction parallel to the road surface is determined, and the acceleration is adjusted based on the acceleration component. For example, the sum of the acceleration and the acceleration component or the difference between the acceleration and the acceleration component is determined as the adjusted acceleration. When the target vehicle runs on a road surface with a certain gradient, the gravity acceleration influences the running of the target vehicle, so that the acceleration is adjusted based on the gradient, and the accuracy of the adjusted acceleration is higher.

It should be noted that the dynamic model represents the corresponding relationship between the immediate state data and the control data of the vehicle, and does not depend on the time information.

The fifth step: and testing the dynamic model based on the test data, and stopping training if the test error corresponding to the test data meets the test condition. And if the test error corresponding to the test data does not meet the condition, the fourth step is carried out again until the test error corresponding to the test data meets the test condition.

The dynamic model is tested, so that the quality evaluation of the dynamic model is realized, if the test error meets the test condition, the quality is up to the standard, and if the test error does not meet the test condition, the quality is not up to the standard.

And a sixth step: and (6) deriving a dynamic model.

The dynamic model can be used for off-line simulation analysis and can also be used for on-line vehicle control.

For example, referring to fig. 4, a target vehicle is selected first, static data is collected, then the target vehicle is tested on an open road and a closed field respectively, dynamic data is collected, whether the collected inspection data range covers or not is determined, if the data range does not cover the dynamic data range, the inspection data is determined to be complete or not if the data range does not cover the dynamic data range, the inspection data is determined to be complete or not, if the data range does not cover the dynamic data range, the data range is determined to be incomplete or not, the data range is determined to be supplementary, if the data range does not cover the dynamic data range, the data range is determined to be complete or not, the data range is determined to be supplementary, if the data range is determined to be complete, the data range is determined to be supplementary, the data range is determined to be complete, the dynamic data range is used for online control of the vehicle, state data and control data generated when the dynamic model is collected, and the data is regarded as part of the data required for the dynamic model to be updated and used for training.

The method provided by the embodiment of the application can be adapted to different execution mechanisms in the truck, can support an accelerator opening and closing amount control interface, an engine torque control interface, a brake torque control interface and a brake air pressure control interface, and improves the adaptation degree of a dynamic model and the target vehicle. And, through regard as whole with truck and the trailer that pulls, can be according to different weight, different truck and trailer combination, build the dynamics model in a flexible way. In addition, the longitudinal state and the transverse state are decoupled, the conditions of transverse turning and the like of the target vehicle are not considered, the influence of the transverse state of the vehicle on the modeling process in the longitudinal state is eliminated, the data acquisition, data processing and modeling processes are simplified, a dynamic model for predicting control data in the longitudinal state of the vehicle is established, and the modeling mode is fast and efficient.

All the above optional technical solutions may be combined arbitrarily to form optional embodiments of the present application, and are not described herein again.

Fig. 5 is a block diagram of a control device of a target vehicle according to an embodiment of the present application. Referring to fig. 5, the apparatus includes:

a data obtaining module 501, configured to obtain target state data of a target vehicle, where the target state data represents a target state that the target vehicle needs to reach;

the data determining module 502 is configured to obtain multiple sets of historical data of the target vehicle, and determine target control data corresponding to the target state data based on the multiple sets of historical data and the target state data, where each set of historical data includes historical state data and historical control data of the target vehicle at a time, the historical state data represents a state of the target vehicle at the time, and the historical control data is data used for controlling the target vehicle at the time;

a vehicle control module 503 for controlling the target vehicle to transition from the current state to the target state based on the target control data.

In one possible implementation, the data determining module 502 is configured to:

determining at least two sets of adjacent historical data corresponding to the target state data from a plurality of sets of historical data of the target vehicle, wherein the adjacent historical data comprises the historical state data which is closest to the target state data;

and determining target control data corresponding to the target state data based on historical control data included in at least two groups of adjacent historical data.

weighting historical control data included by at least two groups of adjacent historical data based on the weights of the historical control data included by at least two groups of adjacent historical data to obtain target control data corresponding to the target state data, wherein the weights of the historical control data included by the adjacent historical data are in negative correlation with the distance between the historical state data included by the adjacent historical data and the target state data;

and determining the average value of the historical control data included by the at least two groups of adjacent historical data as the target control data corresponding to the target state data.

In one possible implementation, the dynamical model includes a plurality of sets of historical data and a function for determining target control data;

the data determining module 502 is configured to invoke a dynamic model, obtain multiple sets of historical data of the target vehicle, and input the multiple sets of historical data and the target state data into a function to obtain target control data.

In one possible implementation, the function includes a plurality of parameters; the device further comprises a training module for:

in the iteration process, a parameter value set is determined based on value ranges corresponding to a plurality of parameters, the parameter value set comprises the value of each parameter, the value of each parameter belongs to the value range of each parameter, and each parameter in the dynamic model is configured according to the value of each parameter;

calling the configured dynamic model to respectively determine predictive control data corresponding to a plurality of historical state data, and determining errors of a parameter value set based on the plurality of historical control data and the plurality of predictive control data;

In one possible implementation, the apparatus further includes a testing module, configured to:

acquiring test data of a target vehicle, wherein the test data comprises test state data and test control data of the target vehicle;

calling a dynamic model, and determining predictive control data corresponding to the test data;

determining a test error corresponding to the test data based on the test control data included in the prediction control data and the test data;

and the training module is also used for retraining the dynamic model based on the adjusted value ranges corresponding to the plurality of parameters until the test error corresponding to the test data determined by calling the trained dynamic model meets the test condition.

In one possible implementation, the apparatus further includes:

It should be noted that: the control device of the target vehicle provided in the above embodiment is only exemplified by the division of the above functional modules when controlling the target vehicle, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the vehicle-mounted terminal is divided into different functional modules to complete all or part of the above described functions. In addition, the control device of the target vehicle and the control method of the target vehicle provided in the above embodiments belong to the same concept, and the specific implementation process thereof is described in detail in the method embodiments, and will not be described again.

Fig. 6 shows a block diagram of a vehicle-mounted terminal 600 according to an exemplary embodiment of the present application.

Generally, the in-vehicle terminal 600 includes: a processor 601 and a memory 602.

The processor 601 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor 601 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 601 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 601 may be integrated with a GPU (Graphics Processing Unit) that is responsible for rendering and drawing content that the display screen needs to display. In some embodiments, processor 601 may also include an AI (Artificial Intelligence) processor for processing computational operations related to machine learning.

The memory 602 may include one or more computer-readable storage media, which may be non-transitory. The memory 602 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in the memory 602 is used to store at least one program code for execution by the processor 601 to implement the control method of the target vehicle provided by the method embodiments herein.

In some embodiments, the vehicle-mounted terminal 600 may further include: a peripheral interface 603 and at least one peripheral. The processor 601, memory 602, and peripheral interface 603 may be connected by buses or signal lines. Various peripheral devices may be connected to the peripheral interface 603 via a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 604, a display 605, a camera assembly 606, an audio circuit 607, a positioning component 608, and a power supply 609.

The peripheral interface 603 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 601 and the memory 602. In some embodiments, the processor 601, memory 602, and peripheral interface 603 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 601, the memory 602, and the peripheral interface 603 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

The Radio Frequency circuit 604 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 604 communicates with communication networks and other communication devices via electromagnetic signals. The rf circuit 604 converts an electrical signal into an electromagnetic signal to transmit, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 604 comprises: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuit 604 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: the world wide web, metropolitan area networks, intranets, generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the rf circuit 604 may further include NFC (Near Field Communication) related circuits, which are not limited in this application.

The display 605 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 605 is a touch display screen, the display screen 605 also has the ability to capture touch signals on or over the surface of the display screen 605. The touch signal may be input to the processor 601 as a control signal for processing. At this point, the display 605 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display 605 may be one, and is disposed on the front panel of the in-vehicle terminal 600; in other embodiments, the number of the display screens 605 may be at least two, and the display screens are respectively disposed on different surfaces of the vehicle-mounted terminal 600 or are in a folding design; in other embodiments, the display 605 may be a flexible display disposed on a curved surface or a folding surface of the in-vehicle terminal 600. Even more, the display 605 may be arranged in a non-rectangular irregular pattern, i.e., a shaped screen. The Display 605 may be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), and the like.

The camera assembly 606 is used to capture images or video. Optionally, camera assembly 606 includes a front camera and a rear camera. Generally, a front camera is disposed at a front panel of the terminal, and a rear camera is disposed at a rear surface of the terminal. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 606 may also include a flash. The flash lamp can be a single-color temperature flash lamp or a double-color temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp and can be used for light compensation under different color temperatures.

Audio circuitry 607 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 601 for processing or inputting the electric signals to the radio frequency circuit 604 to realize voice communication. For the purpose of stereo sound collection or noise reduction, a plurality of microphones may be provided at different portions of the in-vehicle terminal 600. The microphone may also be an array microphone or an omni-directional acquisition microphone. The speaker is used to convert electrical signals from the processor 601 or the radio frequency circuit 604 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, audio circuitry 607 may also include a headphone jack.

The positioning component 608 is used for positioning the current geographic Location of the in-vehicle terminal 600 to implement navigation or LBS (Location Based Service). The Positioning component 608 can be a Positioning component based on the united states GPS (Global Positioning System), the chinese beidou System, the russian graves System, or the european union's galileo System.

The power supply 609 is used to supply power to each component in the in-vehicle terminal 600. The power supply 609 may be ac, dc, disposable or rechargeable. When the power supply 609 includes a rechargeable battery, the rechargeable battery may be a wired rechargeable battery or a wireless rechargeable battery. The wired rechargeable battery is a battery charged through a wired line, and the wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery may also be used to support fast charge technology.

Those skilled in the art will appreciate that the configuration shown in fig. 6 is not limiting of the in-vehicle terminal 600, and may include more or fewer components than those shown, or combine some components, or employ a different arrangement of components.

Embodiments of the present application also provide a computer-readable storage medium, which stores at least one program code, and the at least one program code is loaded and executed by a processor to implement the control method of a target vehicle as shown in the above embodiments.

The embodiments of the present application also provide a computer program product, wherein when the program codes in the computer program product are executed by a processor, the control method of the target vehicle as shown in the above embodiments is realized.

In some embodiments, the computer program according to the embodiments of the present application may be deployed to be executed on one computer device, or executed on a plurality of in-vehicle terminals located at one site, or executed on a plurality of in-vehicle terminals distributed at a plurality of sites and interconnected through a communication network, and the plurality of in-vehicle terminals distributed at the plurality of sites and interconnected through the communication network may constitute a block chain system.

It should be noted that information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data for analysis, stored data, presented data, etc.), and signals referred to in this application are authorized by the user or sufficiently authorized by various parties, and the collection, use, and processing of the relevant data is required to comply with relevant laws and regulations and standards in relevant countries and regions. For example, the control data and status data referred to in this application are obtained with sufficient authorization.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A control method of a target vehicle, characterized by comprising:

2. The method of claim 1, wherein determining target control data corresponding to the target state data based on the plurality of sets of historical data and the target state data comprises:

3. The method according to claim 2, wherein the determining the target control data corresponding to the target state data based on the historical control data included in the at least two sets of adjacent historical data includes any one of:

weighting historical control data included by the at least two groups of adjacent historical data based on weights of the historical control data included by the at least two groups of adjacent historical data to obtain target control data corresponding to the target state data, wherein the weights of the historical control data included by the adjacent historical data are in negative correlation with the distance between the historical state data included by the adjacent historical data and the target state data;

4. The method of claim 1, wherein a kinetic model includes the plurality of sets of historical data and a function used to determine the target control data;

5. The method of claim 4, wherein the function comprises a plurality of parameters; the process of training the kinetic model includes:

in the iteration process, a parameter value set is determined based on value ranges corresponding to the parameters, the parameter value set comprises the value of each parameter, the value of each parameter belongs to the value range of each parameter, and each parameter in the dynamic model is configured according to the value of each parameter;

6. The method of claim 5, further comprising:

7. The method of claim 5, further comprising:

constructing a lookup table based on each preset state data and corresponding control data;

and inquiring the control data corresponding to any state data from the lookup table.

8. The method of claim 1, wherein the historical state data comprises acceleration, the method further comprising:

9. A control apparatus of a target vehicle, characterized in that the apparatus comprises:

10. The apparatus of claim 9, wherein the data determination module is configured to:

11. The apparatus of claim 10, wherein the data determination module is configured to either:

12. The apparatus of claim 9, wherein a kinetic model comprises the plurality of sets of historical data and a function for determining the target control data;

13. The apparatus of claim 12, wherein the function comprises a plurality of parameters; the apparatus further comprises a training module to:

14. The apparatus of claim 13, further comprising a testing module configured to:

and if the test error does not accord with the test condition, adjusting the value range corresponding to at least one parameter in the function, wherein the training module is further used for retraining the dynamic model based on the adjusted value ranges corresponding to the parameters until the test error corresponding to the test data determined by calling the trained dynamic model accords with the test condition.

15. The apparatus of claim 13, further comprising:

the query table construction module is used for calling the trained dynamic model and determining control data corresponding to a plurality of preset state data respectively; constructing a look-up table based on each preset state data and corresponding control data;

16. The apparatus of claim 9, wherein the historical state data comprises acceleration, the apparatus further comprising:

17. A vehicle-mounted terminal characterized by comprising a processor and a memory, wherein at least one program code is stored in the memory, and the at least one program code is loaded and executed by the processor to implement the control method of a target vehicle according to any one of claims 1 to 8.

18. A computer-readable storage medium, characterized in that at least one program code is stored therein, which is loaded and executed by a processor, to implement the control method of a target vehicle according to any one of claims 1 to 8.

19. A computer program product comprising a computer program for being loaded and executed by a processor to carry out a method of controlling a target vehicle according to any one of claims 1 to 8.