CN112572458A - Performance estimation method and device of vehicle speed controller - Google Patents
Performance estimation method and device of vehicle speed controller Download PDFInfo
- Publication number
- CN112572458A CN112572458A CN202011521277.0A CN202011521277A CN112572458A CN 112572458 A CN112572458 A CN 112572458A CN 202011521277 A CN202011521277 A CN 202011521277A CN 112572458 A CN112572458 A CN 112572458A
- Authority
- CN
- China
- Prior art keywords
- target
- vehicle
- moment
- speed
- expected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/105—Speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/107—Longitudinal acceleration
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
- B60W2520/105—Longitudinal acceleration
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The application discloses a method and a device for estimating the performance of a vehicle speed controller, wherein the method comprises the following steps: and acquiring target input parameters. And inputting the target input parameters into the K neighbor regression model to obtain the predicted speed of the vehicle at the target moment. The performance of the vehicle speed controller is estimated in conjunction with the predicted speed of the vehicle at the target time and the desired speed of the vehicle at the target time. According to the performance estimation method of the vehicle speed controller, the predicted speed of the vehicle at the target moment is obtained through the K neighbor regression model, whether the vehicle speed controller can reach the expected speed of the vehicle at the target moment is determined by combining the obtained predicted speed of the vehicle at the target moment and the expected speed of the vehicle at the target moment, and the performance of the vehicle speed controller is estimated. The accuracy of the K nearest neighbor regression model is high, so that the accuracy of the finally obtained performance estimation result of the vehicle speed controller is improved.
Description
Technical Field
The present application relates to the field of vehicle control, and in particular, to a method and an apparatus for estimating a performance of a vehicle speed controller.
Background
The vehicle speed controller is used to control the speed of the vehicle during travel of the vehicle. The vehicle speed controller is commanded to a desired speed to be achieved by the vehicle so that the vehicle speed controller controls the vehicle to achieve the desired speed in accordance with the command. It is important to estimate the performance of the vehicle speed controller, determine whether the vehicle speed controller can achieve a desired speed, and estimate the driving state of the vehicle accordingly.
The currently adopted linear regression algorithm is inaccurate in estimation result obtained by estimating the vehicle speed controller.
Disclosure of Invention
In order to solve the technical problem, the application provides a performance estimation method and device of a vehicle speed controller, which are used for improving the accuracy of performance estimation of the vehicle speed controller.
In order to achieve the above purpose, the technical solutions provided in the embodiments of the present application are as follows:
the embodiment of the application provides a performance estimation method of a vehicle speed controller, which comprises the following steps:
acquiring target input parameters; the target input parameters comprise the actual speed of the target vehicle at the current moment, the actual acceleration of the target vehicle at the current moment, the expected speed of the target vehicle at the target moment and the expected acceleration of the target vehicle at the target moment; the target time is any time after the current time;
inputting the target input parameters into a K nearest neighbor regression model to obtain the predicted speed of the vehicle at the target moment; the K-neighbor regression model is obtained by training according to vehicle historical data, and the vehicle historical data comprises the vehicle historical actual speed at a first moment, the vehicle historical actual acceleration at the first moment, the vehicle historical expected speed at a second moment, the vehicle historical expected acceleration at the second moment and the vehicle historical actual speed at the second moment; the second moment is any moment after the first moment;
estimating the performance of the vehicle speed controller in combination with the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time.
Optionally, the training process of the K-nearest neighbor regression model includes:
dividing the vehicle history data into training data and verification data;
performing data preprocessing on the training data and the verification data to obtain target training data and target verification data;
determining a target model hyperparameter of a K nearest neighbor regression model by using a cross validation method based on the target training data and the target validation data;
and training according to the target model hyperparameter and the target training data to obtain the K nearest neighbor regression model.
Optionally, the estimating the vehicle speed controller by combining the predicted vehicle speed at the target time and the desired target vehicle speed at the target time includes:
calculating the difference value between the predicted speed of the vehicle at the target moment and the expected speed of the target vehicle at the target moment;
judging whether the difference value exceeds a preset threshold value or not;
when the difference value exceeds the preset threshold value, judging whether the expected speed of the target vehicle at the target moment meets a first preset range or not and whether the expected acceleration of the target vehicle at the target moment meets a second preset range or not;
and when the expected speed of the target vehicle at the target moment meets the first preset range and the expected acceleration of the target vehicle at the target moment meets the second preset range, determining that the performance of the vehicle speed controller does not meet the requirement.
Optionally, the estimating the vehicle speed controller by combining the predicted vehicle speed at the target time and the desired target vehicle speed at the target time includes:
calculating the difference value between the predicted speed of the vehicle at the target moment and the expected speed of the target vehicle at the target moment;
judging whether the difference value exceeds a preset threshold value or not;
and when the difference value does not exceed the preset threshold value, determining that the performance of the vehicle speed controller meets the requirement.
Optionally, before the obtaining the target input parameter, the method further includes:
acquiring an input parameter; the input parameters comprise the actual speed and the actual acceleration of the vehicle at the current moment, the expected speed of the vehicle at the target moment and the expected acceleration of the vehicle at the target moment;
and carrying out data preprocessing on the input parameters to obtain target input parameters.
An embodiment of the present application also provides a performance estimation apparatus of a vehicle speed controller, the apparatus including:
a first acquisition unit configured to acquire a target input parameter; the target input parameters comprise the actual speed of the target vehicle at the current moment, the actual acceleration of the target vehicle at the current moment, the expected speed of the target vehicle at the target moment and the expected acceleration of the target vehicle at the target moment; the target time is any time after the current time;
the second acquisition unit is used for inputting the target input parameters into a K neighbor regression model to acquire the predicted speed of the vehicle at the target moment; the K-neighbor regression model is obtained by training according to vehicle historical data, and the vehicle historical data comprises the vehicle historical actual speed at a first moment, the vehicle historical actual acceleration at the first moment, the vehicle historical expected speed at a second moment, the vehicle historical expected acceleration at the second moment and the vehicle historical actual speed at the second moment; the second moment is any moment after the first moment;
an estimating unit for estimating the performance of the vehicle speed controller in combination with the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time.
Optionally, the apparatus further comprises:
the training unit is used for training the K nearest neighbor regression model;
the training unit includes:
a dividing subunit, configured to divide the vehicle history data into training data and verification data;
the first acquisition subunit is used for carrying out data preprocessing on the training data and the verification data to obtain target training data and target verification data;
a first determining subunit, configured to determine, based on the target training data and the target verification data, a target model hyperparameter of the K-nearest neighbor regression model by using a cross-validation method;
and the second obtaining subunit is used for training and obtaining the K nearest neighbor regression model according to the target model hyperparameter and the target training data.
Optionally, the estimating unit includes:
a calculation subunit configured to calculate a difference between the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time;
the first judgment subunit judges whether the difference value exceeds a preset threshold value;
the second judgment subunit is configured to, when the difference exceeds the preset threshold, judge whether the target vehicle expected speed at the target time meets a first preset range, and judge whether the target vehicle expected acceleration at the target time meets a second preset range;
and the second determining subunit is used for determining that the performance of the vehicle speed controller does not meet the requirement when the expected speed of the target vehicle at the target moment meets the first preset range and the expected acceleration of the target vehicle at the target moment meets the second preset range.
An embodiment of the present application also provides a performance estimation apparatus of a vehicle speed controller, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, when executing the computer program, implementing the method of estimating a performance of a vehicle speed controller.
The embodiment of the application also provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium and is used for executing the performance estimation method of the vehicle speed controller.
According to the technical scheme, the method has the following beneficial effects:
the embodiment of the application provides a method and a device for estimating the performance of a vehicle speed controller, wherein the method comprises the following steps: and acquiring target input parameters, wherein the target input parameters comprise the actual speed of the target vehicle at the current moment, the actual acceleration of the target vehicle at the current moment, the expected speed of the target vehicle at the target moment and the expected acceleration of the target vehicle at the target moment. And inputting the target input parameters into the K neighbor regression model to obtain the predicted speed of the vehicle at the target moment. The K-nearest neighbor regression model is obtained by training according to vehicle historical data. The vehicle history data includes a vehicle history actual speed at a first time and a vehicle history actual acceleration at the first time, a vehicle history expected speed at a second time and a vehicle history expected acceleration at the second time, and a vehicle history actual speed at the second time; the second time is any time after the first time. The performance of the vehicle speed controller is estimated in conjunction with the predicted speed of the vehicle at the target time and the desired speed of the vehicle at the target time. According to the performance estimation method of the vehicle speed controller, the predicted speed of the vehicle at the target moment is obtained through the K neighbor regression model, whether the vehicle speed controller can reach the expected speed of the vehicle at the target moment is determined by combining the obtained predicted speed of the vehicle at the target moment and the expected speed of the vehicle at the target moment, and the performance of the vehicle speed controller is estimated. The accuracy of the K nearest neighbor regression model is high, so that the accuracy of the finally obtained performance estimation result of the vehicle speed controller is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are 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 flow chart of a method for estimating performance of a vehicle speed controller according to an embodiment of the present application;
FIG. 2 is a flowchart of a K-nearest neighbor regression model training process provided by an embodiment of the present application;
fig. 3 is a schematic diagram of a performance estimation device of a vehicle speed controller according to an embodiment of the present application.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, embodiments accompanying the drawings are described in detail below.
As shown in fig. 1, fig. 1 is a flowchart of a performance estimation method of a vehicle speed controller according to an embodiment of the present application. As shown, the method includes S101-S103:
s101: acquiring target input parameters; the target input parameters comprise the actual speed of the target vehicle at the current moment, the actual acceleration of the target vehicle at the current moment, the expected speed of the target vehicle at the target moment and the expected acceleration of the target vehicle at the target moment; the target time is any time after the current time.
And acquiring target input parameters, wherein the target input parameters specifically comprise the actual speed of the target vehicle at the current moment, the actual acceleration of the target vehicle at the current moment, the expected speed of the target vehicle at the target moment and the expected acceleration of the target vehicle at the target moment. The target time is any time after the current time.
The target vehicle desired speed at the target time and the target vehicle desired acceleration at the target time are specifically: the speed and acceleration that the vehicle can reach at the target moment is desired at the present moment.
It will be appreciated that at the present time, the vehicle speed controller will receive speed commands for a target vehicle desired speed to be achieved by the vehicle at any time after the present time and a target vehicle desired acceleration required to achieve the desired speed. Wherein any time after the current time is the target time. When the vehicle speed controller receives the speed command, the vehicle speed controller controls the vehicle to adopt the expected acceleration of the target vehicle on the basis of the actual speed and the actual acceleration of the target vehicle at the current moment so that the vehicle reaches the expected speed of the target vehicle at the target moment.
In specific implementation, before obtaining the target input parameter, the method for estimating the performance of the vehicle speed controller provided by the embodiment of the application further includes:
acquiring an input parameter; the input parameters comprise the actual speed and the actual acceleration of the vehicle at the current moment, the expected speed of the vehicle at the target moment and the expected acceleration of the vehicle at the target moment;
and carrying out data preprocessing on the input parameters to obtain target input parameters.
It will be appreciated that the input parameters are vehicle related speed data that can be collected in real time. To facilitate the use of the acquired speed data, data pre-processing is performed on each of the input parameters. The pretreatment comprises treatment modes such as normalization treatment and the like.
S102: inputting the target input parameters into a K nearest neighbor regression model to obtain the predicted speed of the vehicle at the target moment; the K neighbor regression model is obtained by training according to vehicle historical data, and the vehicle historical data comprises the vehicle historical actual speed at a first moment, the vehicle historical actual acceleration at the first moment, the vehicle historical expected speed at a second moment, the vehicle historical expected acceleration at the second moment and the vehicle historical actual speed at the second moment; the second time is any time after the first time.
And inputting the obtained target input parameters into the K-nearest neighbor regression model, and obtaining the vehicle predicted speed at the target moment output by the K-nearest neighbor regression model. The predicted speed of the vehicle at the target moment is specifically as follows: after the vehicle receives the target vehicle expected speed at the target moment and the target vehicle expected acceleration at the target moment at the current moment, the vehicle is predicted to adopt the target vehicle expected acceleration and obtain the speed at the target moment.
In specific implementation, the K-nearest neighbor regression model is obtained by training according to vehicle historical data, and the vehicle historical data comprises the vehicle historical actual speed at a first moment, the vehicle historical actual acceleration at the first moment, the vehicle historical expected speed at a second moment, the vehicle historical expected acceleration at the second moment and the vehicle historical actual speed at the second moment; the second time is any time after the first time.
It can be understood that, since the K-nearest neighbor regression model is a highly accurate regression model, the output quantity obtained by the K-nearest neighbor regression model, that is, the predicted speed of the vehicle at the target time, is highly accurate.
S103: the performance of the vehicle speed controller is estimated in conjunction with the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time.
And after the predicted speed of the vehicle at the target moment is obtained, comparing the predicted speed of the vehicle at the target moment with the expected speed of the vehicle at the target moment, and estimating the performance of the vehicle speed controller according to the comparison result.
In particular implementation, the estimating the vehicle speed controller by combining the predicted vehicle speed at the target time and the expected target vehicle speed at the target time comprises:
calculating a difference between the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time;
judging whether the difference value exceeds a preset threshold value or not;
when the difference value exceeds a preset threshold value, judging whether the expected speed of the target vehicle at the target moment meets a first preset range or not and whether the expected acceleration of the target vehicle at the target moment meets a second preset range or not;
and when the expected speed of the target vehicle at the target moment meets a first preset range and the expected acceleration of the target vehicle at the target moment meets a second preset range, determining that the performance of the vehicle speed controller does not meet the requirement.
It is to be noted that, when the difference between the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time exceeds a preset threshold, it is determined that the vehicle cannot reach the desired speed of the vehicle at the target time. For the case where the vehicle cannot reach the vehicle desired speed at the target time, it may be that the target vehicle desired speed at the target time and the target vehicle desired acceleration at the target time are set unreasonably, or that the vehicle speed controller cannot reach the target vehicle desired speed and the target vehicle desired acceleration.
In order to know whether the reason for the fact that the vehicle cannot reach the desired speed of the vehicle at the target moment is that the vehicle speed controller cannot reach the desired speed and the desired acceleration of the target vehicle, it is necessary to first determine whether the desired speed and the desired acceleration of the target vehicle at the target moment are set reasonably, that is, first determine whether the desired speed and the desired acceleration of the target vehicle at the target moment satisfy a first preset range and whether the desired acceleration of the target vehicle at the target moment satisfy a second preset range. When the target vehicle desired speed at the target time and the target vehicle desired acceleration at the target time are both set to be reasonable, it is determined that the cause of the vehicle failing to reach the vehicle desired speed at the target time is that the performance of the vehicle speed controller fails to reach the target vehicle desired speed and the target vehicle desired acceleration.
It should be noted that, on the one hand, the first preset range related to the desired speed of the target vehicle at the target time is specifically an empirical value of the desired speed of the target vehicle at the target time, the empirical value is obtained through experiments, and the empirical value is related to the speed of the vehicle at the last time. On the other hand, the second preset range relating to the target vehicle desired acceleration at the target time is an empirical value of the target vehicle desired acceleration at the target time, which is obtained experimentally and which is related to the acceleration at the previous time. It will be appreciated that the previous time is specifically the previous time of the target time.
In addition, when the difference between the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time does not exceed the preset threshold, it is determined that the performance of the vehicle speed controller satisfies the requirement.
It should be noted that the preset threshold, the first preset range and the second preset range may be selected according to actual situations, and the preset threshold, the first preset range and the second preset range are not limited at all.
It is understood that the target vehicle desired speed and the target vehicle desired acceleration need to be readjusted when it is determined that the target vehicle desired speed at the target time does not satisfy the first preset range or the target vehicle desired acceleration at the target time does not satisfy the second preset range.
The embodiment of the application provides a method and a device for estimating the performance of a vehicle speed controller, wherein the method comprises the following steps: and acquiring target input parameters. And inputting the target input parameters into the K neighbor regression model to obtain the predicted speed of the vehicle at the target moment. The performance of the vehicle speed controller is estimated in conjunction with the predicted speed of the vehicle at the target time and the desired speed of the vehicle at the target time. According to the performance estimation method of the vehicle speed controller, the predicted speed of the vehicle at the target moment is obtained through the K neighbor regression model, whether the vehicle speed controller can reach the expected speed of the vehicle at the target moment is determined by combining the obtained predicted speed of the vehicle at the target moment and the expected speed of the vehicle at the target moment, and the performance of the vehicle speed controller is estimated. On the basis of high accuracy of the K nearest neighbor regression model obtained through training, the accuracy of the finally obtained performance estimation result of the vehicle speed controller is improved.
The embodiment of the present application further provides a method for training a K-nearest neighbor regression model, referring to fig. 2, and fig. 2 is a flowchart of a training process of the K-nearest neighbor regression model provided in the embodiment of the present application. As shown in fig. 2, the training process of the K-nearest neighbor regression model may include S201-S204:
s201: the vehicle history data is divided into training data and validation data.
The method includes the steps of obtaining vehicle history data, and dividing the obtained vehicle history data into training data and verification data. The training data is used for training the K nearest neighbor regression model, specifically, used for training the K nearest neighbor regression model when the hyper-parameters of the K nearest neighbor regression model are confirmed, and also used for training the K nearest neighbor regression model after the hyper-parameters are acquired. The validation data was used to validate the accuracy of the K-nearest neighbor regression model.
It is understood that the ratio of the training data and the test data is selected according to the actual situation, and is not limited herein.
S202: and performing data preprocessing on the training data and the verification data to obtain target training data and target verification data.
And performing data preprocessing on the training data and the verification data to obtain preprocessed target training data and target verification data. Wherein the data preprocessing facilitates the comparison and weighting of data of different units or magnitudes.
It should be noted that both the target training data and the target verification data can be divided into model input data and model output data, wherein the model input data are the vehicle historical actual speed at the first moment, the vehicle historical actual acceleration at the first moment, the vehicle historical expected speed at the second moment and the vehicle historical expected acceleration at the second moment; the model output data is the historical actual speed of the vehicle at the second time. It will be appreciated that both the model input data and the model output data are actual data.
S203: and determining the target model hyperparameters of the K nearest neighbor regression model by using a cross validation method based on the target training data and the target validation data.
And determining the target model hyperparameters of the K nearest neighbor regression model by using a cross validation method based on the target training data and the target validation data. And the target model hyper-parameter of the K neighbor regression model is the optimal neighbor number K value in the K neighbor regression model.
It can be understood that before the training set is used to construct the K-nearest neighbor regression model, an optimal K-nearest neighbor number is specified.
In specific implementation, the accuracy of the K nearest neighbor regression model is measured by using the mean square error. Selecting different K values, determining the K value which enables the mean square error of the K nearest neighbor regression model to be minimum by using a cross validation method based on target training data and target validation data, and determining the minimum K value as the optimal K value, namely the target model hyperparameter of the K nearest neighbor regression model.
S204: and training according to the hyper-parameters of the target model and the target training data to obtain a K nearest neighbor regression model.
And after determining a target model hyperparameter (K value) of the K nearest neighbor regression model, training according to target training data to obtain the K nearest neighbor regression model.
It should be noted that, after the K-nearest neighbor regression model is obtained, the accuracy of the K-nearest neighbor regression model can be verified by using the target verification data. In specific implementation, model input data in the target verification data is input into the K neighbor regression model to obtain verification output. And calculating a mean square error through the verification output and the model output data in the target verification data, and when the mean square error value is smaller than a preset error, determining that the verification output on the verification data is close to the model output data in the target verification data, and determining that the fitting effect of the K nearest neighbor regression model meets the requirement. The preset error is selected according to the actual situation, and is not limited here.
It is understood that the performance estimation method of the vehicle speed controller provided by the embodiment of the application can be executed by the vehicle-mounted terminal, and can also be executed by a device which has a prediction requirement on the speed of the vehicle at any moment and can acquire vehicle information.
By the K nearest neighbor regression model training method provided by the embodiment of the application, the K nearest neighbor regression model with high accuracy can be obtained. Further, the predicted speed of the vehicle at the target moment is obtained through a K neighbor regression model with high accuracy, whether the vehicle speed controller can reach the expected speed of the vehicle at the target moment is determined by combining the obtained predicted speed of the vehicle at the target moment and the expected speed of the vehicle at the target moment, the performance of the vehicle speed controller is estimated, and the accuracy of the performance estimation result of the vehicle speed controller is finally improved.
An embodiment of the present application further provides a performance estimation apparatus for a vehicle speed controller, as shown in fig. 3, fig. 3 is a schematic diagram of the performance estimation apparatus for a vehicle speed controller provided in the embodiment of the present application, and the apparatus includes:
a first acquisition unit 301 configured to acquire a target input parameter; the target input parameters comprise the actual speed of the target vehicle at the current moment, the actual acceleration of the target vehicle at the current moment, the expected speed of the target vehicle at the target moment and the expected acceleration of the target vehicle at the target moment; the target moment is any moment after the current moment;
a second obtaining unit 302, configured to input the target input parameter into the K-nearest neighbor regression model, and obtain a predicted speed of the vehicle at the target time; the K neighbor regression model is obtained by training according to vehicle historical data, and the vehicle historical data comprises the vehicle historical actual speed at a first moment, the vehicle historical actual acceleration at the first moment, the vehicle historical expected speed at a second moment, the vehicle historical expected acceleration at the second moment and the vehicle historical actual speed at the second moment; the second moment is any moment after the first moment;
an estimation unit 303 for estimating the performance of the vehicle speed controller in combination with the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time.
Optionally, in some implementations of this embodiment, the apparatus further includes:
the training unit is used for training the K nearest neighbor regression model;
the training unit comprises:
the dividing subunit is used for dividing the vehicle historical data into training data and verification data;
the first acquisition subunit is used for carrying out data preprocessing on the training data and the verification data to acquire target training data and target verification data;
the first determining subunit is used for determining a target model hyperparameter of the K nearest neighbor regression model by using a cross validation method based on target training data and target validation data;
and the second obtaining subunit is used for training and obtaining the K nearest neighbor regression model according to the target model hyperparameter and the target training data.
Optionally, in some implementations of this embodiment, the estimating unit 303 includes:
a calculation subunit configured to calculate a difference between the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time;
the first judging subunit judges whether the difference value exceeds a preset threshold value;
the second judgment subunit is used for judging whether the expected speed of the target vehicle at the target moment meets a first preset range or not and whether the expected acceleration of the target vehicle at the target moment meets a second preset range or not when the difference value exceeds a preset threshold value;
and the second determining subunit is used for determining that the performance of the vehicle speed controller does not meet the requirement when the expected speed of the target vehicle at the target moment meets a first preset range and the expected acceleration of the target vehicle at the target moment meets a second preset range.
Optionally, in some implementations of this embodiment, the estimating unit 303 includes:
a calculation subunit configured to calculate a difference between the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time;
the first judgment subunit is used for judging whether the difference value exceeds a preset threshold value or not;
and a third determining subunit, configured to determine that the performance of the vehicle speed controller satisfies the requirement when the difference does not exceed the preset threshold.
Optionally, in some implementations of this embodiment, the apparatus further includes:
a third acquisition unit configured to acquire the input parameter before acquiring the target input parameter; the input parameters comprise the actual speed and the actual acceleration of the vehicle at the current moment, the expected speed of the vehicle at the target moment and the expected acceleration of the vehicle at the target moment;
and the fourth acquisition unit is used for carrying out data preprocessing on the input parameters to acquire target input parameters.
According to the performance estimation device of the vehicle speed controller, the predicted speed of the vehicle at the target moment is obtained through the K-neighbor regression model, whether the vehicle speed controller can reach the expected speed of the vehicle at the target moment is determined by combining the obtained predicted speed of the vehicle at the target moment and the expected speed of the vehicle at the target moment, and the performance of the vehicle speed controller is estimated. On the basis of high accuracy of the K nearest neighbor regression model obtained through training, the accuracy of the finally obtained performance estimation result of the vehicle speed controller is improved.
An embodiment of the present application also provides a performance estimation apparatus of a vehicle speed controller, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, when executing the computer program, implementing the method of estimating a performance of a vehicle speed controller as described in the above embodiments.
Embodiments of the present application also provide a computer-readable storage medium, in which a computer program is stored, the computer program being used for executing the performance estimation method of the vehicle speed controller according to the above embodiments.
It should be noted that, in the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. The method disclosed by the embodiment corresponds to the system disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the system part for description.
It should also be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of estimating performance of a vehicle speed controller, the method comprising:
acquiring target input parameters; the target input parameters comprise the actual speed of the target vehicle at the current moment, the actual acceleration of the target vehicle at the current moment, the expected speed of the target vehicle at the target moment and the expected acceleration of the target vehicle at the target moment; the target time is any time after the current time;
inputting the target input parameters into a K nearest neighbor regression model to obtain the predicted speed of the vehicle at the target moment; the K-neighbor regression model is obtained by training according to vehicle historical data, and the vehicle historical data comprises the vehicle historical actual speed at a first moment, the vehicle historical actual acceleration at the first moment, the vehicle historical expected speed at a second moment, the vehicle historical expected acceleration at the second moment and the vehicle historical actual speed at the second moment; the second moment is any moment after the first moment;
estimating the performance of the vehicle speed controller in combination with the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time.
2. The method of claim 1, wherein the training process of the K-nearest neighbor regression model comprises:
dividing the vehicle history data into training data and verification data;
performing data preprocessing on the training data and the verification data to obtain target training data and target verification data;
determining a target model hyperparameter of a K nearest neighbor regression model by using a cross validation method based on the target training data and the target validation data;
and training according to the target model hyperparameter and the target training data to obtain the K nearest neighbor regression model.
3. The method of claim 1, wherein said estimating the vehicle speed controller in combination with the predicted vehicle speed at the target time and the desired target vehicle speed at the target time comprises:
calculating the difference value between the predicted speed of the vehicle at the target moment and the expected speed of the target vehicle at the target moment;
judging whether the difference value exceeds a preset threshold value or not;
when the difference value exceeds the preset threshold value, judging whether the expected speed of the target vehicle at the target moment meets a first preset range or not and whether the expected acceleration of the target vehicle at the target moment meets a second preset range or not;
and when the expected speed of the target vehicle at the target moment meets the first preset range and the expected acceleration of the target vehicle at the target moment meets the second preset range, determining that the performance of the vehicle speed controller does not meet the requirement.
4. The method of claim 1, wherein said estimating the vehicle speed controller in combination with the predicted vehicle speed at the target time and the desired target vehicle speed at the target time comprises:
calculating the difference value between the predicted speed of the vehicle at the target moment and the expected speed of the target vehicle at the target moment;
judging whether the difference value exceeds a preset threshold value or not;
and when the difference value does not exceed the preset threshold value, determining that the performance of the vehicle speed controller meets the requirement.
5. The method of claim 1, wherein prior to said obtaining target input parameters, the method further comprises:
acquiring an input parameter; the input parameters comprise the actual speed and the actual acceleration of the vehicle at the current moment, the expected speed of the vehicle at the target moment and the expected acceleration of the vehicle at the target moment;
and carrying out data preprocessing on the input parameters to obtain target input parameters.
6. A performance estimation apparatus of a vehicle speed controller, characterized by comprising:
a first acquisition unit configured to acquire a target input parameter; the target input parameters comprise the actual speed of the target vehicle at the current moment, the actual acceleration of the target vehicle at the current moment, the expected speed of the target vehicle at the target moment and the expected acceleration of the target vehicle at the target moment; the target time is any time after the current time;
the second acquisition unit is used for inputting the target input parameters into a K neighbor regression model to acquire the predicted speed of the vehicle at the target moment; the K-neighbor regression model is obtained by training according to vehicle historical data, and the vehicle historical data comprises the vehicle historical actual speed at a first moment, the vehicle historical actual acceleration at the first moment, the vehicle historical expected speed at a second moment, the vehicle historical expected acceleration at the second moment and the vehicle historical actual speed at the second moment; the second moment is any moment after the first moment;
an estimating unit for estimating the performance of the vehicle speed controller in combination with the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time.
7. The apparatus of claim 6, further comprising:
the training unit is used for training the K nearest neighbor regression model;
the training unit includes:
a dividing subunit, configured to divide the vehicle history data into training data and verification data;
the first acquisition subunit is used for carrying out data preprocessing on the training data and the verification data to obtain target training data and target verification data;
a first determining subunit, configured to determine, based on the target training data and the target verification data, a target model hyperparameter of the K-nearest neighbor regression model by using a cross-validation method;
and the second obtaining subunit is used for training and obtaining the K nearest neighbor regression model according to the target model hyperparameter and the target training data.
8. The apparatus of claim 6, wherein the estimation unit comprises:
a calculation subunit configured to calculate a difference between the predicted speed of the vehicle at the target time and the desired speed of the target vehicle at the target time;
the first judgment subunit judges whether the difference value exceeds a preset threshold value;
the second judgment subunit is configured to, when the difference exceeds the preset threshold, judge whether the target vehicle expected speed at the target time meets a first preset range, and judge whether the target vehicle expected acceleration at the target time meets a second preset range;
and the second determining subunit is used for determining that the performance of the vehicle speed controller does not meet the requirement when the expected speed of the target vehicle at the target moment meets the first preset range and the expected acceleration of the target vehicle at the target moment meets the second preset range.
9. A performance estimation device of a vehicle speed controller, characterized by comprising: memory, a processor, and a computer program stored on the memory and executable on the processor, when executing the computer program, implementing a method of estimating a performance of a vehicle speed controller according to any one of claims 1-5.
10. A computer-readable storage medium, characterized in that a computer program for executing the performance estimation method of a vehicle speed controller according to any one of claims 1 to 5 is stored in the computer-readable storage medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011521277.0A CN112572458B (en) | 2020-12-21 | 2020-12-21 | Performance estimation method and device of vehicle speed controller |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011521277.0A CN112572458B (en) | 2020-12-21 | 2020-12-21 | Performance estimation method and device of vehicle speed controller |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112572458A true CN112572458A (en) | 2021-03-30 |
| CN112572458B CN112572458B (en) | 2022-06-10 |
Family
ID=75136475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011521277.0A Active CN112572458B (en) | 2020-12-21 | 2020-12-21 | Performance estimation method and device of vehicle speed controller |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112572458B (en) |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1191399A (en) * | 1997-09-25 | 1999-04-06 | Fujitsu Ten Ltd | Travel control method for vehicle |
| EP1637718A1 (en) * | 2003-06-25 | 2006-03-22 | Hitachi Construction Machinery Co., Ltd. | Engine control device for construction machine |
| JP2010083402A (en) * | 2008-10-01 | 2010-04-15 | Toyota Motor Corp | Vehicle speed controller |
| US20140005916A1 (en) * | 2012-06-29 | 2014-01-02 | International Business Machines Corporation | Real-time traffic prediction and/or estimation using gps data with low sampling rates |
| US20140257665A1 (en) * | 2013-03-05 | 2014-09-11 | Bayerische Motoren Werke Aktiengesellschaft | Method for the Cruise and/or Range Control of Motor Vehicles |
| EP2847053A1 (en) * | 2012-04-05 | 2015-03-18 | Scania CV AB | Method and system for control of at least a speed regulator |
| CN104464304A (en) * | 2014-12-25 | 2015-03-25 | 北京航空航天大学 | Urban road vehicle running speed forecasting method based on road network characteristics |
| CN105612091A (en) * | 2013-10-10 | 2016-05-25 | 日立汽车***株式会社 | Vehicle motion control device |
| US20160288781A1 (en) * | 2015-03-30 | 2016-10-06 | Hyundai Motor Company | Motor speed control method and system for improving performance of running resistance evaluation |
| CN106218715A (en) * | 2016-07-20 | 2016-12-14 | 广西科技大学 | A kind of control method of four-wheel independent steering vehicle |
| CN109664880A (en) * | 2019-02-15 | 2019-04-23 | 东软睿驰汽车技术（沈阳）有限公司 | Whether a kind of verification vehicle occurs the method and device of disconnected inspection |
| CN109747651A (en) * | 2018-12-27 | 2019-05-14 | 东软睿驰汽车技术（沈阳）有限公司 | A kind of control method for vehicle, apparatus and system |
| CN109747652A (en) * | 2018-12-27 | 2019-05-14 | 东软睿驰汽车技术（沈阳）有限公司 | A kind of control method for vehicle, apparatus and system |
| US20190168732A1 (en) * | 2016-09-28 | 2019-06-06 | Hitachi Automotive Systems, Ltd. | Vehicle control unit |
| AT520781A2 (en) * | 2017-12-22 | 2019-07-15 | Avl List Gmbh | Behavior model of an environmental sensor |
| US20190283765A1 (en) * | 2016-12-05 | 2019-09-19 | Cummins Inc. | Multi-vehicle load delivery management systems and methods |
| CN111216713A (en) * | 2020-02-17 | 2020-06-02 | 哈尔滨工业大学 | Automatic driving vehicle speed pre-aiming control method |
| US20200209402A1 (en) * | 2018-12-31 | 2020-07-02 | Lyft, Inc. | Systems and methods for estimating vehicle speed based on radar |
| US20200231179A1 (en) * | 2019-01-22 | 2020-07-23 | Honda Motor Co., Ltd. | Guidance system, guidance method, and storage medium |
| US20200339115A1 (en) * | 2019-04-26 | 2020-10-29 | Toyota Jidosha Kabushiki Kaisha | Vehicle control device |
| CN111845768A (en) * | 2020-06-19 | 2020-10-30 | 腾讯科技（深圳）有限公司 | Vehicle running parameter prediction method and device |
| CN112009499A (en) * | 2020-09-14 | 2020-12-01 | 北京罗克维尔斯科技有限公司 | Automatic vehicle driving control method and device |
-
2020
- 2020-12-21 CN CN202011521277.0A patent/CN112572458B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1191399A (en) * | 1997-09-25 | 1999-04-06 | Fujitsu Ten Ltd | Travel control method for vehicle |
| EP1637718A1 (en) * | 2003-06-25 | 2006-03-22 | Hitachi Construction Machinery Co., Ltd. | Engine control device for construction machine |
| JP2010083402A (en) * | 2008-10-01 | 2010-04-15 | Toyota Motor Corp | Vehicle speed controller |
| EP2847053A1 (en) * | 2012-04-05 | 2015-03-18 | Scania CV AB | Method and system for control of at least a speed regulator |
| US20140005916A1 (en) * | 2012-06-29 | 2014-01-02 | International Business Machines Corporation | Real-time traffic prediction and/or estimation using gps data with low sampling rates |
| US20140257665A1 (en) * | 2013-03-05 | 2014-09-11 | Bayerische Motoren Werke Aktiengesellschaft | Method for the Cruise and/or Range Control of Motor Vehicles |
| CN105612091A (en) * | 2013-10-10 | 2016-05-25 | 日立汽车***株式会社 | Vehicle motion control device |
| CN104464304A (en) * | 2014-12-25 | 2015-03-25 | 北京航空航天大学 | Urban road vehicle running speed forecasting method based on road network characteristics |
| US20160288781A1 (en) * | 2015-03-30 | 2016-10-06 | Hyundai Motor Company | Motor speed control method and system for improving performance of running resistance evaluation |
| CN106218715A (en) * | 2016-07-20 | 2016-12-14 | 广西科技大学 | A kind of control method of four-wheel independent steering vehicle |
| US20190168732A1 (en) * | 2016-09-28 | 2019-06-06 | Hitachi Automotive Systems, Ltd. | Vehicle control unit |
| US20190283765A1 (en) * | 2016-12-05 | 2019-09-19 | Cummins Inc. | Multi-vehicle load delivery management systems and methods |
| AT520781A2 (en) * | 2017-12-22 | 2019-07-15 | Avl List Gmbh | Behavior model of an environmental sensor |
| CN109747652A (en) * | 2018-12-27 | 2019-05-14 | 东软睿驰汽车技术（沈阳）有限公司 | A kind of control method for vehicle, apparatus and system |
| CN109747651A (en) * | 2018-12-27 | 2019-05-14 | 东软睿驰汽车技术（沈阳）有限公司 | A kind of control method for vehicle, apparatus and system |
| US20200209402A1 (en) * | 2018-12-31 | 2020-07-02 | Lyft, Inc. | Systems and methods for estimating vehicle speed based on radar |
| US20200231179A1 (en) * | 2019-01-22 | 2020-07-23 | Honda Motor Co., Ltd. | Guidance system, guidance method, and storage medium |
| CN109664880A (en) * | 2019-02-15 | 2019-04-23 | 东软睿驰汽车技术（沈阳）有限公司 | Whether a kind of verification vehicle occurs the method and device of disconnected inspection |
| US20200339115A1 (en) * | 2019-04-26 | 2020-10-29 | Toyota Jidosha Kabushiki Kaisha | Vehicle control device |
| CN111216713A (en) * | 2020-02-17 | 2020-06-02 | 哈尔滨工业大学 | Automatic driving vehicle speed pre-aiming control method |
| CN111845768A (en) * | 2020-06-19 | 2020-10-30 | 腾讯科技（深圳）有限公司 | Vehicle running parameter prediction method and device |
| CN112009499A (en) * | 2020-09-14 | 2020-12-01 | 北京罗克维尔斯科技有限公司 | Automatic vehicle driving control method and device |
Non-Patent Citations (4)
| Title |
|---|
| 朱敏等: "无人驾驶越野车辆纵向速度跟踪控制试验", 《机械工程学报》 * |
| 朱敏等: "无人驾驶越野车辆纵向速度跟踪控制试验", 《机械工程学报》, 31 December 2018 (2018-12-31), pages 112 - 115 * |
| 赵伟等: "基于模糊自整定PID的履带车辆自动驾驶***纵向车速控制", 《计算机应用》, 30 June 2018 (2018-06-30), pages 68 - 71 * |
| 郭躬德等: "《近邻分类方法及其应用-下册》", 30 April 2014, pages: 352 - 355 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112572458B (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110126807B (en) | Vehicle speed control method, vehicle speed control system and vehicle | |
| JP5810116B2 (en) | Secondary battery state detection device and secondary battery state detection method | |
| KR102142745B1 (en) | Method for determining a control observer for the soc | |
| US20190212391A1 (en) | Method for monitoring a battery | |
| US11675016B2 (en) | Diagnostic device and diagnostic method for battery | |
| CN110549005B (en) | Machining condition adjustment device and machine learning device | |
| JP4956476B2 (en) | Battery discharge duration prediction method, battery state detection method, battery state detection device, and battery power supply system | |
| KR102109583B1 (en) | Method and Apparatus for pricing based on machine learning | |
| US20190219641A1 (en) | Secondary battery state detection device and secondary battery state detection method | |
| JP2007179968A (en) | Battery status control device | |
| US20170330458A1 (en) | Server, System, and Method for Determining a Position of an End of a Traffic Jam | |
| CN112117892A (en) | Electric power converter | |
| US20180043531A1 (en) | Control device, control method, and non-transitory recording medium | |
| CN112784482A (en) | Thermal runaway prediction method and device | |
| CN112572458B (en) | Performance estimation method and device of vehicle speed controller | |
| JP6119554B2 (en) | Charge state calculation device | |
| US11573542B2 (en) | Method and apparatus for adjusting process control prediction model and process controller | |
| JP5405252B2 (en) | Learning control system and learning control method | |
| CN111098743B (en) | Charging time prediction method and device and electronic equipment | |
| KR20210138498A (en) | Device and method for operating a test bench | |
| CN111856303B (en) | Battery resistance measuring device | |
| JP2017146194A (en) | Secondary battery diagnosis device | |
| KR20220020885A (en) | Method and apparatus for predictive vehicle control | |
| JP2012078360A (en) | Method and device for detecting battery state, and battery power system | |
| CN112542621B (en) | Battery temperature vector generation method and related equipment thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |