CN112406873A - Longitudinal control model parameter confirmation method, vehicle control method, storage medium, and electronic device - Google Patents

Longitudinal control model parameter confirmation method, vehicle control method, storage medium, and electronic device Download PDF

Info

Publication number
CN112406873A
CN112406873A CN202011304374.4A CN202011304374A CN112406873A CN 112406873 A CN112406873 A CN 112406873A CN 202011304374 A CN202011304374 A CN 202011304374A CN 112406873 A CN112406873 A CN 112406873A
Authority
CN
China
Prior art keywords
control
model
parameters
vehicle
distance
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
Application number
CN202011304374.4A
Other languages
Chinese (zh)
Other versions
CN112406873B (en
Inventor
张昭
冯成浩
汪留辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dongfeng Motor Co Ltd
Original Assignee
Dongfeng Motor Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Dongfeng Motor Co Ltd filed Critical Dongfeng Motor Co Ltd
Priority to CN202011304374.4A priority Critical patent/CN112406873B/en
Publication of CN112406873A publication Critical patent/CN112406873A/en
Application granted granted Critical
Publication of CN112406873B publication Critical patent/CN112406873B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • B60W2050/0019—Control system elements or transfer functions
    • B60W2050/0028—Mathematical models, e.g. for simulation
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/802—Longitudinal distance
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/804—Relative longitudinal speed

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 longitudinal control model parameter confirmation method, a vehicle control method, a storage medium and electronic equipment, which comprise the steps of obtaining the state characteristics of road test data; clustering the state features and dividing control intervals; determining a time distance model of each control interval; calculating integral fitting acceleration deviations of all control intervals according to the time distance model; and taking the model parameters of the time distance model of each control interval corresponding to the integral fitting acceleration deviation meeting the preset conditions as the longitudinal control model parameters. By the aid of the method and the device, interference of subjective factors can be reduced, the division of control intervals and the objectivity of determination of longitudinal control model parameters are increased, time can be saved, efficiency is improved, cost is reduced, setting of the longitudinal control model parameters can be more in line with actual driving, driving habits of drivers are more closely attached to control of an automatic driving system, smoothness of logic switching of the control intervals is improved, and experience effects of automatic driving are improved.

Description

Longitudinal control model parameter confirmation method, vehicle control method, storage medium, and electronic device
Technical Field
The application relates to the technical field of automobiles, in particular to a longitudinal control model parameter confirmation method, a vehicle control method, a storage medium and electronic equipment.
Background
An ACC (Adaptive Cruise Control) system can not only keep a vehicle speed preset by a driver, but also reduce the vehicle speed as required at any time under specific driving conditions, even automatically brake, so as to adapt to traffic conditions. At present, the existing ACC system divides control modes according to human experience and then confirms corresponding model parameters in each control mode, so that subjective factors are large, the control modes cannot be objectively divided and the model parameters cannot be determined, and manual division is long in time consumption, low in efficiency and high in cost.
Disclosure of Invention
In view of the above, the present application provides a longitudinal control model parameter confirmation method, a vehicle control method, a storage medium and an electronic device to solve the above technical problems.
The application provides a method for confirming parameters of a longitudinal control model, which comprises the following steps: acquiring state characteristics of road test data; clustering the state features and dividing control intervals; determining a time distance model of each control interval; calculating integral fitting acceleration deviations of all control intervals according to the time distance model; and taking the model parameters of the time distance model of each control interval corresponding to the integral fitting acceleration deviation meeting the preset conditions as the longitudinal control model parameters.
Optionally, for the state feature clustering, dividing the control interval includes: determining a clustering algorithm; determining a weight parameter with a weight distance D between the road test data and the clustering center; taking an input value N and a weight parameter of a clustering algorithm as division parameters for dividing a control interval; determining the selection range of the division parameters according to the value ranges of the weight parameters and the input values; selecting a division parameter in the selection range of the division parameter; and clustering the state characteristics according to the selected division parameters by using a clustering algorithm, and dividing the control interval.
Optionally, determining a weight parameter of the weighted distance D between the road test data and the cluster center includes: selecting one or more feature quantities in the state features; acquiring a characteristic quantity difference value of each characteristic quantity of the road test data and the characteristic quantity corresponding to the clustering center; and determining the weight parameters corresponding to the characteristic quantity difference values one by one according to the influence proportion of each characteristic quantity difference value in the calculation of the weighted distance D.
Optionally, using the model parameters of the time distance model of each control interval corresponding to the overall fitting acceleration deviation meeting the predetermined condition as the longitudinal control model parameters, includes: comparing the overall fitted acceleration deviation with a predetermined acceleration deviation; if the integral fitting acceleration deviation is smaller than the preset acceleration deviation, taking the model parameters of the time interval model of each control interval corresponding to the integral fitting acceleration deviation smaller than the preset acceleration deviation as the parameters of the longitudinal control model; if the integral fitting acceleration deviation is larger than the preset acceleration deviation, selecting new division parameters, clustering the state characteristics again according to the new division parameters, dividing the control intervals again, re-determining the time-distance model of each control interval, and calculating the integral fitting acceleration deviation of all the control intervals according to the new time-distance model until the integral fitting acceleration deviation is smaller than the preset acceleration deviation or all the division parameters are traversed; and if the obtained integral fitting acceleration deviation is larger than the preset acceleration deviation after traversing all the division parameters, taking the model parameter of the time distance model of each control interval corresponding to the integral fitting acceleration deviation with the minimum difference value with the preset acceleration deviation as the longitudinal control model parameter.
Optionally, the characteristic quantity of the state characteristic includes a host vehicle speed VeRelative velocity V of the main vehicle and the front vehiclerRelative distance DrAnd the longitudinal acceleration a of the vehicleRoad surfaceWherein the front vehicle and the main vehicle share the same lane and are closest to the main vehicle.
Optionally, a time-distance original model a ═ k is obtained1(Dh-Dr)-k2VrWherein k is1、k2Is a constant number, DhThe expected distance between the vehicle and the front vehicle; determination of DhIs calculated by the formula Dh＝Ve*th+D0，thFor a fixed time interval, D0The distance between the vehicle and the front vehicle after parking; according to the time distance original model and the expected distance DhThe calculation formula is obtained by fitting road test data based on a constraint linear least square methodA time distance model of each control section, wherein the time distance model is a ═ c1*vr+c2*dr+c3*ve+c4Where a is the desired acceleration, c1、c2、c3、c4Are model parameters.
The present application also provides a vehicle control method based on the longitudinal control model parameter confirmation method as described above, which includes: acquiring the state characteristics of the current vehicle in real time; calculating a desired longitudinal acceleration of the vehicle using the state feature and a longitudinal control model; the vehicle is controlled according to a desired longitudinal acceleration of the vehicle.
Optionally, calculating a desired longitudinal acceleration of the vehicle using the status signature and the longitudinal control model comprises: calculating weighted distance D between state feature and cluster center of each control intervaliI is 1,2,3 … … N; will be weighted by a distance DiAscending order, selecting the first n control intervals with the minimum distance, and calculating the corresponding expected acceleration a according to the time distance model of the first n control intervalsiN is less than or equal to N; distance D with weighting of the first n smallest distancesiInto a weighted weight Pi(ii) a According to
Figure BDA0002787875800000031
Calculating the expected longitudinal acceleration a of the vehicleControl。
The present application further provides a non-transitory computer storage medium storing computer-executable instructions configured as the longitudinal control model parameter validation method described above or the vehicle control method described above.
The present application further provides an electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a longitudinal control model parameter validation method as described above or a vehicle control method as described above.
The longitudinal control model parameter confirmation method, the vehicle control method, the storage medium and the electronic equipment provided by the application divide the control interval by clustering the state characteristics of the road test data, calculating integral fitting acceleration deviation according to the determined time distance model of each control interval, taking the model parameters of the time distance model of each control interval corresponding to the integral fitting acceleration deviation meeting the preset conditions as longitudinal control model parameters, not only reducing the interference of subjective factors, increasing the division of the control intervals and the objectivity of the determination of the longitudinal control model parameters, but also saving time, improving efficiency, reducing cost, and enabling the setting of the longitudinal control model parameters to be more in line with actual driving, and then make the control of autopilot system more close to driver's driving habit, avoid the smoothness of each control interval logic switching, improve autopilot's experience effect.
Drawings
Fig. 1 is a flowchart of a method for identifying parameters of a vertical control model according to the present application.
Fig. 2 is a flowchart of S200 of the present application.
Fig. 3 is a flowchart of a vehicle control method of the present application.
Fig. 4 is a hardware configuration diagram of the electronic device of the present application.
Detailed Description
The technical solutions of the present application are described in detail below with reference to the accompanying drawings and specific embodiments. In which like parts are designated by like reference numerals. It should be noted that the terms "front," "back," "left," "right," "upper" and "lower" used in the following description refer to directions in the drawings, and the terms "inner" and "outer" refer to directions toward and away from, respectively, the geometric center of a particular component.
Fig. 1 is a flowchart illustrating a method for confirming parameters of a longitudinal control model according to the present application, and as shown in fig. 1, the method for confirming parameters of a longitudinal control model according to the present application includes:
s100, acquiring state characteristics of road test data;
in one embodiment, the status characteristics may includeSpeed V of tractoreRelative velocity V of the main vehicle and the front vehiclerAnd a relative distance DrAnd the longitudinal acceleration a of the vehicleRoad surfaceAnd the front vehicle and the main vehicle share the same lane and are closest to the main vehicle.
S200, clustering the state characteristics and dividing control intervals;
in this embodiment, a K-means clustering algorithm may be used to cluster the state features, and the state features are divided into N control intervals according to the input value N.
S300, determining a time distance model of each control interval;
each control interval corresponds to a time distance model. The desired acceleration for each control interval may be calculated from a time-distance model.
S400, calculating integral fitting acceleration deviations of all control intervals according to the time distance model;
each time the control interval is divided, an integral fitting acceleration deviation can be obtained based on all the control intervals according to the time-distance model.
In one embodiment, calculating the global fitting acceleration deviation of all control intervals according to the time-distance model comprises:
calculating interval fitting acceleration a of each control interval according to the time-distance modelZone(s)；
Fitting acceleration a with intervals of all control intervalsZone(s)Weighted calculation of integral fitting acceleration aMachine for finishing；
From the global fitting acceleration aMachine for finishingAcceleration a of vehicle in road test dataRoad surfaceAnd obtaining the integral fitting acceleration deviation by difference.
And S500, taking the model parameters of the time distance model of each control interval corresponding to the integral fitting acceleration deviation meeting the preset conditions as the longitudinal control model parameters.
According to the method for confirming the longitudinal control model parameters, the control intervals are divided through clustering the state characteristics of the road test data, the integral fitting acceleration deviation is calculated according to the determined time models of the control intervals, the model parameters of the time distance models of the control intervals corresponding to the integral fitting acceleration deviation meeting the preset conditions are used as the longitudinal control model parameters, the interference of subjective factors can be reduced, the objectivity of division of the control intervals and determination of the longitudinal control model parameters is improved, time can be saved, the efficiency is improved, the cost is reduced, the setting of the longitudinal control model parameters can be more consistent with the human driving style, the control of an automatic driving system is closer to the driving of a driver, the smoothness of logic switching of the control intervals is improved, and the experience effect of automatic driving is improved.
Further, in step S200, for clustering the state features, dividing the control interval includes:
s210, determining a clustering algorithm;
in the present embodiment, the clustering algorithm may employ a K-Means clustering algorithm (K-Means clustering algorithm).
S220, determining a weight parameter with a weight distance D between the road test data and the clustering center;
in one embodiment, the weighted distance D may be a weighted euclidean distance or a weighted mahalanobis distance.
S230, taking the input value N and the weight parameter of the clustering algorithm as the division parameters for dividing the control interval;
for example, the weighting parameters W1, W2, and W3 are divided into [ N, W1, W2, and W3 ]. The input value N is a preset number of cluster centers, i.e., a preset number of control intervals. The control intervals with different numbers can be divided by a clustering algorithm according to different division parameters.
S240, determining a selection range of the division parameters according to the value ranges of the weight parameters and the input values;
for example, in [ N, W1, W2, W3], N may be between 3 and 15, and W1, W2, W3 may be between [0 and 3 ].
S250, selecting the division parameters in the selection range of the division parameters;
for example, the selected partitioning parameter [ N, W1, W2, W3] is [12,1,1,2 ].
And S260, clustering the state characteristics according to the selected division parameters by using a clustering algorithm, and dividing the control interval.
And dividing N-12 control intervals according to [12,1,1,2] by adopting a K-Means clustering algorithm. Each control interval contains all road test data with the distance between the control interval and the cluster center less than or equal to the weighted distance D. And (3) iterating N times by using a K-Means clustering algorithm, and calculating weighted distances D between all road test data and all clustering centers in each iteration.
The input value of the K-Means clustering algorithm and the weight parameter with the weight Euclidean distance D are used as parameters for dividing the control interval, so that the control interval can be divided better, the division time is saved, and the division efficiency is improved. Moreover, the weight parameters are set, the influence proportion of the road test data with different dimensionalities on the clustering result can be adjusted, and simultaneously the data dimension can be balanced.
Further, in S220, determining the weight parameter of the weighted distance D between the road test data and the cluster center includes:
s2201, selecting one or more feature quantities in the state features;
the number of weight parameters is the same as the number of selected feature quantities. For example, there are three characteristic quantities Vr、Dr、VeCorresponding to three weight parameters W1, W2, W3. Two or more feature values may be selected as the number of feature values.
S2202, acquiring a characteristic quantity difference value of each characteristic quantity of the road test data and a characteristic quantity corresponding to a clustering center;
each control interval has a cluster center. For example,
Figure BDA0002787875800000061
is a VrThe difference in relative velocity corresponding to the cluster center,
Figure BDA0002787875800000062
is DrThe difference in relative distance from the center of the cluster,
Figure BDA0002787875800000063
is a VeA difference in host vehicle velocity corresponding to a cluster center.
S2203, determining the weight parameters corresponding to the feature quantity differences one-to-one according to the influence ratio of each feature quantity difference in the calculation of the weighted distance D.
In a specific embodiment of the present application, the weighted distance D using three characteristic quantities is calculated as
Figure BDA0002787875800000064
By selecting the characteristic quantity of the state characteristic and determining the weight parameter according to the characteristic quantity difference value of each characteristic quantity, the data dimension can be balanced, and the weight parameter can be adjusted according to the influence proportion of different characteristic quantities on the clustering result, so that the control interval can be better divided.
In a specific embodiment, S500, using the model parameters of the time distance model of each control interval corresponding to the global fitting acceleration deviation meeting the predetermined condition as the longitudinal control model parameters includes:
s510, comparing the integral fitting acceleration deviation with a preset acceleration deviation;
s520, if the integral fitting acceleration deviation is smaller than the preset acceleration deviation, taking the model parameters of the time interval model of each control interval corresponding to the integral fitting acceleration deviation smaller than the preset acceleration deviation as the parameters of the longitudinal control model;
for example, the global fitting acceleration deviation is 10m/s2The predetermined acceleration deviation is 12m/s2Then the integrated fit acceleration deviation is 10m/s2And taking the model parameters of the time distance model of each corresponding control interval as the parameters of the longitudinal control model.
S530, if the integral fitting acceleration deviation is larger than the preset acceleration deviation, selecting new division parameters, re-clustering the state characteristics according to the new division parameters, re-dividing the control intervals, re-determining the time distance model of each control interval, and calculating the integral fitting acceleration deviation of all the control intervals according to the new time distance model until the integral fitting acceleration deviation is smaller than the preset acceleration deviation or all the division parameters are traversed;
wherein, the division parameters correspond to the integral fitting acceleration deviation one by one. And when the integral fitting acceleration deviation is larger than the preset acceleration deviation, selecting a new division parameter, and repeating the operations S200-S400.
And S540, if the obtained overall fitting acceleration deviation is larger than the preset acceleration deviation after traversing all the division parameters, taking the model parameter of the time distance model of each control interval corresponding to the overall fitting acceleration deviation with the minimum difference value with the preset acceleration deviation as the longitudinal control model parameter.
Through the operation, the parameters of the longitudinal control model can be acquired, the driving habit of a driver can be fitted as much as possible, and the driving performance of the automatic driving system is improved.
Further, in S300, determining the time distance model of each control interval includes:
s310, acquiring a time distance original model a ═ k1(Dh-Dr)-k2(Vq-Ve)＝-k1(Dh-Dr)-k2VrWherein k is1、k2Is a constant number, DhIs the desired distance, V, between the host vehicle and the preceding vehicleqIs the speed of the leading vehicle;
s320, determining DhIs calculated by the formula Dh＝Ve*th+D0，thFor a fixed time interval, D0The distance between the vehicle and the front vehicle after parking;
s330, according to the time distance original model and the expected distance D between the vehicle and the front vehiclehThe calculation formula is that a time distance model of each control interval is obtained by fitting road test data based on a constraint linear least square method, and the time distance model is that a is c1*vr+c2*dr+c3*ve+c4Where a is the desired acceleration, C1，c2，c3，c4Are model parameters.
On the basis of the time interval original model, the time interval model of each control interval is obtained by fitting the road test data, so that the calculation steps of the time interval model can be simplified, the calculation time is saved, and the confirmation efficiency is improved.
The present application also provides a vehicle control method based on the longitudinal control model parameter confirmation method as described above, as shown in fig. 3, including:
s600, acquiring the state characteristics of the current vehicle in real time;
as described above, the state characteristic may be the host vehicle speed VeRelative velocity V of the main vehicle and the front vehiclerAnd a relative distance Dr。
S610, calculating the expected longitudinal acceleration of the vehicle by using the state characteristics and the longitudinal control model;
using a as c1*vr+c2*dr+c3*ve+c4And calculating to obtain the expected longitudinal acceleration a control of the vehicle according to the state characteristics acquired in real time.
And S620, controlling the vehicle according to the expected longitudinal acceleration of the vehicle.
The vehicle control method provided by the application calculates the expected longitudinal acceleration of the vehicle according to the obtained longitudinal control model, so that driving is more practical, the gap between the driving and manual driving is better reduced, and the comfort of automatic driving is better improved.
Optionally, S620, calculating the desired longitudinal acceleration of the vehicle using the state feature and the longitudinal control model comprises:
s6201, calculating weighted distance D between the state characteristics and the clustering center of each control intervali，i＝1，2，3……N；
For example, the control section is divided into 12 control sections according to the division parameter. Calculating weighted distance D between the input state feature and the cluster center of each control intervaliTo obtain D1To D12。
S6202, weighting distance DiAscending order, selecting the first n control intervals with the minimum distance, and calculating the corresponding expected acceleration a according to the time distance model of the first n control intervalsi，n≤N；
Will take weight of the European styleDistance DiIn ascending order, selecting model parameters C of time-distance model with the first n (for example, n is 3) control intervals with the smallest distance1，c2，c3，c4Calculating the expected acceleration a1，a2，a3The calculation amount can be reduced, and the calculation rate can be improved.
S6203, the distance D with the smallest top n weighted distancesiInto a weighted weight Pi；
Weighted Euclidean distance D can be obtained by utilizing Softmax functioniInto a weighted weight Pi. Wherein the Softmax function is
Figure BDA0002787875800000091
For example, [ P1, P2, P3] ═ Softmax (K/D1, K/D2, K/D3), where K is the function control output acceleration weighted average degree, the smaller the value of K, the more uniformly the accounting function considers each desired acceleration.
S6204, according to
Figure BDA0002787875800000092
Calculating the integral fitting acceleration aControl；
Take n as an example 3, aControl＝P1*a1+P2*a2+P3*a3。
The first n control intervals with the smallest distance are selected through weighted Euclidean distance ascending sequence arrangement, and then the expected longitudinal acceleration of the vehicle is calculated by utilizing the expected acceleration of the first n control intervals and the weighted weight converted by the weighted Euclidean distance, so that the speed is smoother when each control interval is switched, and the vehicle is driven more stably.
The present application further provides a non-transitory computer storage medium storing computer-executable instructions configured as the longitudinal control model parameter validation method described above or the vehicle control method described above.
The present application also provides an electronic device, as shown in fig. 4, including:
at least one processor 701; and the number of the first and second groups,
a memory 702 communicatively coupled to the at least one processor 701; wherein the content of the first and second substances,
the memory 702 stores instructions executable by the at least one processor 701 to enable the at least one processor 701 to perform a longitudinal control model parameter validation method as described above or a vehicle control method as described above.
The apparatus for performing the longitudinal control model parameter validation method as described above may further include: an input device 703 and an output device 704. The processor 701, memory 702, input device 703, and output device 704 may be connected by a bus or other means.
Memory 702, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 701 executes various functional applications and data processing of the server by running the nonvolatile software programs, instructions and modules stored in the memory 702, that is, implements the vertical control model parameter confirmation method in the above method embodiment.
The memory 702 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the longitudinal control model parameter confirmation method, and the like. Further, the memory 702 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device.
The input device 703 may receive input numeric or character information and generate key signal inputs related to user settings and function control related to the vertical control model parameter confirmation method. The output device 704 may include a display device such as a display screen.
The one or more modules are stored in the memory 702 and, when executed by the one or more processors, perform the method for vertical control model parameter validation in any of the method embodiments described above.
The product can execute the method provided by the embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.
The electronic device of embodiments of the present invention exists in a variety of forms, including but not limited to:
(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include: smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) Ultra mobile personal computer device: the equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as ipads.
(3) A portable entertainment device: such devices can display and play multimedia content. This type of device comprises: audio, video players (e.g., ipods), handheld game consoles, electronic books, and smart toys and portable car navigation devices.
(4) A server: the device for providing the computing service comprises a processor, a hard disk, a memory, a system bus and the like, and the server is similar to a general computer architecture, but has higher requirements on processing capacity, stability, reliability, safety, expandability, manageability and the like because of the need of providing high-reliability service.
(5) And other electronic devices with data interaction functions.
Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a mobile terminal (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, and not to limit the same; although embodiments of the present invention have been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A method for confirming parameters of a longitudinal control model is characterized by comprising the following steps:
acquiring state characteristics of road test data;
clustering the state features and dividing control intervals;
determining a time distance model of each control interval;
calculating integral fitting acceleration deviations of all control intervals according to the time distance model;
and taking the model parameters of the time distance model of each control interval corresponding to the integral fitting acceleration deviation meeting the preset conditions as the longitudinal control model parameters.
2. The method for validating parameters of a longitudinal control model according to claim 1, wherein for the clustering of the status features, dividing the control interval comprises:
determining a clustering algorithm;
determining a weight parameter with a weight distance D between the road test data and the clustering center;
taking an input value N and a weight parameter of a clustering algorithm as division parameters for dividing a control interval;
determining the selection range of the division parameters according to the value ranges of the weight parameters and the input values;
selecting a division parameter in the selection range of the division parameter;
and clustering the state characteristics according to the selected division parameters by using a clustering algorithm, and dividing the control interval.
3. The method for identifying parameters of a longitudinal control model according to claim 2, wherein determining the weighting parameters with the weighted distance D between the road test data and the cluster center comprises:
selecting one or more feature quantities in the state features;
acquiring a characteristic quantity difference value of each characteristic quantity of the road test data and the characteristic quantity corresponding to the clustering center;
and determining the weight parameters corresponding to the characteristic quantity difference values one by one according to the influence proportion of each characteristic quantity difference value in the calculation of the weighted distance D.
4. The method for confirming longitudinal control model parameters according to claim 3, wherein the step of using model parameters of the time distance model of each control interval corresponding to the global fitting acceleration deviation meeting the predetermined condition as the longitudinal control model parameters comprises:
comparing the overall fitted acceleration deviation with a predetermined acceleration deviation;
if the integral fitting acceleration deviation is smaller than the preset acceleration deviation, taking the model parameters of the time interval model of each control interval corresponding to the integral fitting acceleration deviation smaller than the preset acceleration deviation as the parameters of the longitudinal control model;
if the integral fitting acceleration deviation is larger than the preset acceleration deviation, selecting new division parameters, clustering the state characteristics again according to the new division parameters, dividing the control intervals again, re-determining the time-distance model of each control interval, and calculating the integral fitting acceleration deviation of all the control intervals according to the new time-distance model until the integral fitting acceleration deviation is smaller than the preset acceleration deviation or all the division parameters are traversed;
and if the obtained integral fitting acceleration deviation is larger than the preset acceleration deviation after traversing all the division parameters, taking the model parameter of the time distance model of each control interval corresponding to the integral fitting acceleration deviation with the minimum difference value with the preset acceleration deviation as the longitudinal control model parameter.
5. The longitudinal control model parameter validation method of claim 4, wherein the characteristic quantity of the status characteristic includes a host vehicle speed VeRelative velocity V of the main vehicle and the front vehiclerRelative distance DrAnd the longitudinal acceleration a of the vehicleRoad surfaceWherein the front vehicle and the main vehicle share the same lane and are closest to the main vehicle.
6. The method for identifying parameters of a longitudinal control model according to claim 5, wherein determining the time distance model for each control interval comprises:
acquiring a time distance original model a ═ k1(Dh-Dr)-k2VrWherein k is1、k2Is a constant number, DhThe expected distance between the vehicle and the front vehicle;
determination of DhIs calculated by the formula Dh＝Ve*th+D0，thFor a fixed time interval, D0The distance between the vehicle and the front vehicle after parking;
according to the time distance original model and the expected distance DhThe calculation formula is obtained by fitting road test data based on a constrained linear least square method to obtain a time distance model of each control interval, wherein the time distance model is a-c1*vr+c2*dr+c3*ve+c4Where a is the desired acceleration, c1、c2、c3、c4Are model parameters.
7. A vehicle control method based on the longitudinal control model parameter confirmation method according to any one of claims 1 to 6, characterized by comprising:
acquiring the state characteristics of the current vehicle in real time;
calculating a desired longitudinal acceleration of the vehicle using the state feature and a longitudinal control model;
the vehicle is controlled according to a desired longitudinal acceleration of the vehicle.
8. The vehicle control method of claim 7, wherein calculating a desired longitudinal acceleration of the vehicle using the state characteristic and a longitudinal control model comprises:
calculating weighted distance D between state feature and cluster center of each control intervali，i＝1,2,3……N；
Will be weighted by a distance DiAscending order, selecting the first n control intervals with the minimum distance, and calculating the corresponding expected acceleration a according to the time distance model of the first n control intervalsi，n≤N；
The first n bands with the smallest distanceWeighted distance DiInto a weighted weight Pi；
According to
Figure FDA0002787875790000031
Calculating the expected longitudinal acceleration a of the vehicleControl。
9. A non-transitory computer storage medium storing computer-executable instructions configured as the longitudinal control model parameter validation method of any of claims 1-6 or the vehicle control method of any of claims 7-8.
10. An electronic device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a longitudinal control model parameter validation method as claimed in any one of claims 1 to 6 or a vehicle control method as claimed in any one of claims 7 to 8.
CN202011304374.4A 2020-11-19 2020-11-19 Longitudinal control model parameter confirmation method, vehicle control method, storage medium, and electronic device Active CN112406873B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011304374.4A CN112406873B (en) 2020-11-19 2020-11-19 Longitudinal control model parameter confirmation method, vehicle control method, storage medium, and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011304374.4A CN112406873B (en) 2020-11-19 2020-11-19 Longitudinal control model parameter confirmation method, vehicle control method, storage medium, and electronic device

Publications (2)

Publication Number Publication Date
CN112406873A true CN112406873A (en) 2021-02-26
CN112406873B CN112406873B (en) 2022-03-08

Family

ID=74774617

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011304374.4A Active CN112406873B (en) 2020-11-19 2020-11-19 Longitudinal control model parameter confirmation method, vehicle control method, storage medium, and electronic device

Country Status (1)

Country Link
CN (1) CN112406873B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140012479A1 (en) * 2010-12-30 2014-01-09 Institute Of Automation, Chinese Academy Of Sciences Adaptive cruise control system and method for vehicle
US20170088128A1 (en) * 2015-09-29 2017-03-30 Honda Motor Co., Ltd. Driving support device that performs driving support in accordance with characteristics and skills of driver
CN109435952A (en) * 2018-10-31 2019-03-08 北京新能源汽车股份有限公司 Vehicle longitudinal control scaling method, device, system and automobile
CN109859465A (en) * 2019-01-09 2019-06-07 吉林大学 The longitudinally controlled parameter adjustment system of automatic Pilot based on traffic flow step response
CN110962848A (en) * 2019-07-31 2020-04-07 重庆长安汽车股份有限公司 Method and system for controlling automatic driving longitudinal motion
US20200172093A1 (en) * 2018-11-29 2020-06-04 291, Daehak-ro Lane-based probabilistic motion prediction of surrounding vehicles and predictive longitudinal control method and apparatus
CN111409455A (en) * 2020-03-26 2020-07-14 北京汽车集团有限公司 Vehicle speed control method and device, electronic device and storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140012479A1 (en) * 2010-12-30 2014-01-09 Institute Of Automation, Chinese Academy Of Sciences Adaptive cruise control system and method for vehicle
US20170088128A1 (en) * 2015-09-29 2017-03-30 Honda Motor Co., Ltd. Driving support device that performs driving support in accordance with characteristics and skills of driver
CN109435952A (en) * 2018-10-31 2019-03-08 北京新能源汽车股份有限公司 Vehicle longitudinal control scaling method, device, system and automobile
US20200172093A1 (en) * 2018-11-29 2020-06-04 291, Daehak-ro Lane-based probabilistic motion prediction of surrounding vehicles and predictive longitudinal control method and apparatus
CN109859465A (en) * 2019-01-09 2019-06-07 吉林大学 The longitudinally controlled parameter adjustment system of automatic Pilot based on traffic flow step response
CN110962848A (en) * 2019-07-31 2020-04-07 重庆长安汽车股份有限公司 Method and system for controlling automatic driving longitudinal motion
CN111409455A (en) * 2020-03-26 2020-07-14 北京汽车集团有限公司 Vehicle speed control method and device, electronic device and storage medium

Also Published As

Publication number Publication date
CN112406873B (en) 2022-03-08

Similar Documents

Publication Publication Date Title
US20210334420A1 (en) Driving simulation method and apparatus, electronic device, and computer storage medium
EP3730370A1 (en) Method and device for acquiring automatic driving track
US20190165750A1 (en) Controlling a volume level based on a user profile
CN109976901B (en) Resource scheduling method, device, server and readable storage medium
US9630627B2 (en) Method and apparatus for adaptive drive control including fuel-economic mode engagement
CN114684152A (en) Method, device, vehicle and medium for processing driving experience data
CN112406873B (en) Longitudinal control model parameter confirmation method, vehicle control method, storage medium, and electronic device
CN109887293B (en) Intersection signal control time interval dividing method
CN113947948A (en) Vehicle passing control method and device
CN109448211B (en) License plate issuing method, device, medium and equipment based on big data
CN111123729A (en) Method and device for vehicle driving simulation optimization, storage medium and terminal equipment
CN111625927B (en) Control method of simulation vehicle and related equipment
CN109803209B (en) Volume adjusting method of automobile central control system, storage medium and automobile central control system
CN116238517A (en) Road condition presenting method and device
CN113602267B (en) Lane keeping control method, storage medium, and electronic apparatus
CN114376811B (en) Wheelchair, control method and device thereof and computer readable storage medium
WO2023060586A1 (en) Automatic driving instruction generation model optimization method and apparatus, device, and storage medium
CN115366891A (en) Driving style recognition method, system and storage medium
CN115195728A (en) Vehicle following control method, system, equipment and storage medium
CN115168642A (en) Vehicle-mounted music recommendation method, device, equipment, storage medium and vehicle
CN117284302A (en) User-specific driving mode generation method, system, vehicle, electronic equipment and storage medium
CN113525356A (en) Automatic parking system, automatic parking method, storage medium, and electronic device
CN108734956B (en) Road condition data acquisition method and device of electronic map
CN116828041A (en) Push method and device for vehicle-mounted application, vehicle and storage medium
KR20120061697A (en) System and method for discriminating adaptive eco-driving

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant